Objective:Circulating tumor DNA(ctDNA)is increasingly being used as a potential biomarker in colorectal cancer(CRC)patients.However,the role of ctDNA in CRC prognosis prediction remains unclear.The objective is to sys...Objective:Circulating tumor DNA(ctDNA)is increasingly being used as a potential biomarker in colorectal cancer(CRC)patients.However,the role of ctDNA in CRC prognosis prediction remains unclear.The objective is to systematically assess the clinical value of ctDNA in colorectal cancer prognosis prediction throughout the treatment cycle.Methods:PubMed,Web of Science,Embase,Cochrane Library,Scopus,and clinical trials.gov database was searched from January 2016 to April 2023.Observational studies and randomized clinical trials reporting on ctDNA and prognostic outcomes in CRC patients were included.Pooled hazard risk ratios(HRs)were calculated for the primary outcomes,relapse-free survival(RFS),and overall survival(OS).Random-effects models were preferred considering the potential heterogeneity.Results:Sixty-five cohort studies were included.Association between ctDNA and shorter RFS or OS was significant,especially after the full-course treatment recommended by the guidelines(HR=8.92[95%CI:6.02-13.22],P<0.001,I^(2)=73%;HR=3.05[95%CI:1.72-5.41],P<0.001,I^(2)=48%)for all types of CRC patients.Despite the presence of heterogeneity,subgroup analyses showed that the cancer type and ctDNA detection assays may be the underlying cause.Besides,ctDNA may detect recurrence earlier than radiographic progression,but no uniform sampling time point between studies might bring bias.However,ctDNA detection did not appear to correlate with pathological complete response achievement in patients with locally advanced rectal cancer.Conclusion:ctDNA detection was significantly associated with poorer prognosis.The potential applications in prognostic prediction are promising and remain to be evaluated in other fields.展开更多
BACKGROUND Patients with colorectal cancer(CRC)undergo surgery,as well as perioperative chemoradiation or adjuvant chemotherapy primarily based on the tumor–node–metastasis(TNM)cancer staging system.However,treatmen...BACKGROUND Patients with colorectal cancer(CRC)undergo surgery,as well as perioperative chemoradiation or adjuvant chemotherapy primarily based on the tumor–node–metastasis(TNM)cancer staging system.However,treatment responses and prognostic outcomes of patients within the same stage vary markedly.The potential use of novel biomarkers can improve prognostication and shared decision making before implementation into certain therapies.AIM To investigate whether SUMF2,ADAMTS5,and PXDN methylation status could be associated with CRC prognosis.METHODS We conducted a Taiwan region cohort study involving 208 patients with CRC recruited from TriService General Hospital and applied the candidate gene approach to identify three genes involved in oncogenesis pathways.A methylation-specific polymerase chain reaction(MS-PCR)and Epi TYPER DNA methylation analysis were employed to detect methylation status and to quantify the methylation level of candidate genes in tumor tissue and adjacent normal tissue from participants.We evaluated SUMF2,ADAMTS5,and PXDN methylation as predictors of prognosis,including recurrence-free survival(RFS),progression-free survival(PFS),and overall survival(OS),using a Cox regression model and Kaplan–Meier analysis.RESULTS We revealed various outcomes related to methylation and prognosis.Significantly shorter PFS and OS were associated with the CpG_3+CpG_7 hypermethylation of SUMF2 from tumor tissue compared with CpG_3+CpG_7 hypomethylation[hazard ratio(HR)=2.24,95%confidence interval(CI)=1.03-4.85 for PFS,HR=2.56 and 95%CI=1.08-6.04 for OS].By contrast,a significantly longer RFS was associated with CpG_2 and CpG_13 hypermethylation of ADAMTS5 from normal tissue compared with CpG_2 and CpG_13 hypomethylation[HR(95%CI)=0.15(0.03-0.71)for CpG_2 and 0.20(0.04-0.97)for CpG_13].The relationship between the methylation status of PXDN and the prognosis of CRC did not reach statistical significance.CONCLUSION Our study found that CpG_3+CpG_7 hypermethylation of SUMF2 from tumor tissue was associated with significantly shorter PFS and OS compared with CpG_3+CpG_7 hypomethylation.CpG_2 and CpG_13 hypermethylation of ADAMTS5 from normal tissue was associated with a significantly longer RFS compared with CpG_2 and CpG_13 hypomethylation.These methylationrelated biomarkers which have implications for CRC prognosis prediction may aid physicians in clinical decision-making.展开更多
Objective:Through integrated bioinformatics analysis,the goal of this work was to find new,characterised N7-methylguanosine modification-related long non-coding RNAs(m7G-lncRNAs)that might be used to predict the progn...Objective:Through integrated bioinformatics analysis,the goal of this work was to find new,characterised N7-methylguanosine modification-related long non-coding RNAs(m7G-lncRNAs)that might be used to predict the prognosis of laryngeal squamous cell carcinoma(LSCC).Methods:The clinical data and LSCC gene expression data for the current investigation were initially retrieved from the TCGA database&sanitised.Then,using co-expression analysis of m7G-associated mRNAs&lncRNAs&differential expression analysis(DEA)among LSCC&normal sample categories,we discovered lncRNAs that were connected to m7G.The prognosis prediction model was built for the training category using univariate&multivariate COX regression&LASSO regression analyses,&the model’s efficacy was checked against the test category data.In addition,we conducted DEA of prognostic m7G-lncRNAs among LSCC&normal sample categories&compiled a list of co-expression networks&the structure of prognosis m7G-lncRNAs.To compare the prognoses for individuals with LSCC in the high-&low-risk categories in the prognosis prediction model,survival and risk assessments were also carried out.Finally,we created a nomogram to accurately forecast the outcomes of LSCC patients&created receiver operating characteristic(ROC)curves to assess the prognosis prediction model’s predictive capability.Results:Using co-expression network analysis&differential expression analysis,we discovered 774 m7G-lncRNAs and 551 DEm7G-lncRNAs,respectively.We then constructed a prognosis prediction model for six m7G-lncRNAs(FLG−AS1,RHOA−IT1,AC020913.3,AC027307.2,AC010973.2 and AC010789.1),identified 32 DEPm7G-lncRNAs,analyzed the correlation between 32 DEPm7G-lncRNAs and 13 DEPm7G-mRNAs,and performed survival analyses and risk analyses of the prognosis prediction model to assess the prognostic performance of LSCC patients.By displaying ROC curves and a nomogram,we finally checked the prognosis prediction model's accuracy.Conclusion:By creating novel predictive lncRNA signatures for clinical diagnosis&therapy,our findings will contribute to understanding the pathogenetic process of LSCC.展开更多
BACKGROUND The ubiquitin-proteasome pathway(UPP)has been proven to play important roles in cancer.AIM To investigate the prognostic significance of genes involved in the UPP and develop a predictive model for liver ca...BACKGROUND The ubiquitin-proteasome pathway(UPP)has been proven to play important roles in cancer.AIM To investigate the prognostic significance of genes involved in the UPP and develop a predictive model for liver cancer based on the expression of these genes.METHODS In this study,UPP-related E1,E2,E3,deubiquitylating enzyme,and proteasome gene sets were obtained from the Kyoto Encyclopedia of Genes and Genomes(KEGG)database,aiming to screen the prognostic genes using univariate and multivariate regression analysis and develop a prognosis predictive model based RESULTS Five genes(including autophagy related 10,proteasome 20S subunit alpha 8,proteasome 20S subunit beta 2,ubiquitin specific peptidase 17 like family member 2,and ubiquitin specific peptidase 8)were proven significantly correlated with prognosis and used to develop a prognosis predictive model for liver cancer.Among training,validation,and Gene Expression Omnibus sets,the overall survival differed significantly between the high-risk and low-risk groups.The expression of the five genes was significantly associated with immunocyte infiltration,tumor stage,and postoperative recurrence.A total of 111 differentially expressed genes(DEGs)were identified between the high-risk and low-risk groups and they were enriched in 20 and 5 gene ontology and KEGG pathways.Cell division cycle 20,Kelch repeat and BTB domain containing 11,and DDB1 and CUL4 associated factor 4 like 2 were the DEGs in the E3 gene set that correlated with survival.CONCLUSION We have constructed a prognosis predictive model in patients with liver cancer,which contains five genes that associate with immunocyte infiltration,tumor stage,and postoperative recurrence.展开更多
In order to develop precision or personalized medicine,identifying new quantitative imaging markers and building machine learning models to predict cancer risk and prognosis has been attracting broad research interest...In order to develop precision or personalized medicine,identifying new quantitative imaging markers and building machine learning models to predict cancer risk and prognosis has been attracting broad research interest recently.Most of these research approaches use the similar concepts of the conventional computer-aided detection schemes of medical images,which include steps in detecting and segmenting suspicious regions or tumors,followed by training machine learning models based on the fusion of multiple image features computed from the segmented regions or tumors.However,due to the heterogeneity and boundary fuzziness of the suspicious regions or tumors,segmenting subtle regions is often difficult and unreliable.Additionally,ignoring global and/or background parenchymal tissue characteristics may also be a limitation of the conventional approaches.In our recent studies,we investigated the feasibility of developing new computer-aided schemes implemented with the machine learning models that are trained by global image features to predict cancer risk and prognosis.We trained and tested several models using images obtained from full-field digital mammography,magnetic resonance imaging,and computed tomography of breast,lung,and ovarian cancers.Study results showed that many of these new models yielded higher performance than other approaches used in current clinical practice.Furthermore,the computed global image features also contain complementary information from the features computed from the segmented regions or tumors in predicting cancer prognosis.Therefore,the global image features can be used alone to develop new case-based prediction models or can be added to current tumor-based models to increase their discriminatory power.展开更多
Accurate cancer staging is the foundation of precision oncology and guides prognosis prediction and therapeutic decision-making. The conjoint TNM System by the American Joint Committee on Cancer (AJCC) and the Interna...Accurate cancer staging is the foundation of precision oncology and guides prognosis prediction and therapeutic decision-making. The conjoint TNM System by the American Joint Committee on Cancer (AJCC) and the International Union Against Cancer (UICC) has served as the global standard for tumor classification since inception.展开更多
Objective:To evaluate the predictive value of Modified Early Warning Score(MEWS)for neurological disease prognosis and identify prognostic factors.Methods:This retrospective study analyzed 768 neurological patients wi...Objective:To evaluate the predictive value of Modified Early Warning Score(MEWS)for neurological disease prognosis and identify prognostic factors.Methods:This retrospective study analyzed 768 neurological patients with MEWS≥4(June 2022–June 2024).Patients were stratified by outcomes(favorable/unfavorable).Multivariable logistic regression and ROC analysis were performed.Results:108 cases(13.1%)had unfavorable outcomes.Significant prognostic factors included:age,TBI history,onset-to-admission time,PT,MEWS score,and MEWS≥4 frequency(all P<0.05).MEWS showed AUC=0.749(sensitivity 62.0%,specificity 77.4%).Conclusion:MEWS demonstrates moderate predictive value(AUC=0.749)for neurological outcomes.Consciousness assessment limitations(56.5%impaired cases)may affect sensitivity.A specialized model incorporating pupillary reflexes and GCS is recommended for improved early warning.展开更多
BACKGROUND Circulating tumor DNA(ctDNA)-based liquid biopsy has been found to be effective for the detection of minimal residual disease and the evaluation of prognostic risk in various solid tumors,with good sensitiv...BACKGROUND Circulating tumor DNA(ctDNA)-based liquid biopsy has been found to be effective for the detection of minimal residual disease and the evaluation of prognostic risk in various solid tumors,with good sensitivity and specificity for identifying patients at high risk of recurrence.However,use of its results as a biomarker for guiding the treatment and predicting the prognosis of naso-pharyngeal carcinoma(NPC)has not been reported.CASE SUMMARY In this case study of a patient with stage IVb NPC,we utilized ctDNA as an independent biomarker to guide treatment.Chemotherapy was administered in the early stages of the disease,and local intensity-modulated radiation therapy was added when the patient tested positive for ctDNA,while radiation therapy was stopped and the patient was observed when the ctDNA test was negative.During the follow-up period,ctDNA signals became positive before tumor progression and became negative again at the end of treatment.We also explored the potential of ctDNA in combination with Epstein-Barr virus(EBV)DNA status to predict the prognosis of NPC patients,as well as the criteria for selecting genetic mutations and the testing cycle for ctDNA analysis.CONCLUSION The results of ctDNA-based liquid biopsy can serve as an independent biomarker,either independently or in conjunction with EBV DNA status,to guide the treatment and predict the prognosis of NPC.展开更多
Objective This study aimed to develop an effective predictive tool that combines radiomics and clinical information to predict the survival outcomes of patients with advanced non-small cell lung cancer(NSCLC)undergoin...Objective This study aimed to develop an effective predictive tool that combines radiomics and clinical information to predict the survival outcomes of patients with advanced non-small cell lung cancer(NSCLC)undergoing chemoimmunotherapy.Methods Data were collected from 201 patients with advanced NSCLC who received first-line chemoimmunotherapy across three institutions:those from Centers I&II(n=164)were randomly split in a 7:3 ratio into training(n=115)and validation(n=49)cohorts,and those form Center III(n=37)were designated as the external test cohort.The analysis was conducted using CT images and clinical data obtained before and after induction chemoimmunotherapy.We developed multiple intratumoral and peritumoral radiomics-based models,along with clinical prediction model that integrated patients’baseline clinicopathological characteristics with plasma biomarker profiles,to predict progression-free survival(PFS).Based on expectations derived from prior established models,a stepwise backward elimination approach was utilized to select candidate submodels for the combined model construction.This combined model was internally validated using time-dependent ROC curves in training and validation sets and externally validated in the external test set.Results The combined model was constructed by integrating four candidate sub-models(DeltaSub,Clinical,P4mm,and Habitat)selected through the stepwise regression analysis.The combined model demonstrated superior performance compared to conventional models that utilized only clinical features,as well as Classical-Pre,Classical-Post,delta intratumor feature-based,and peritumor feature-based models.The combined model demonstrated satisfactory predictive performance across all three datasets,achieving a C-index of 0.849(95%CI:0.812–0.885)in the training set,0.744(95%CI:0.664–0.842)in the validation set,and 0.731(95%CI:0.639–0.824)in the external test set for PFS.Conclusions We developed a novel radiomic-clinical model to predict PFS for advanced NSCLC patients treated with first-line chemoimmunotherapy.This model enhanced survival assessment through comprehensive feature integration.展开更多
Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in t...Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in the gastric cancer field based on its efficient computational power and learning capacities,such as imagebased diagnosis and prognosis prediction.AI-assisted diagnosis includes pathology,endoscopy,and computerized tomography,while researchers in the prognosis circle focus on recurrence,metastasis,and survival prediction.In this review,a comprehensive literature search was performed on articles published up to April 2020 from the databases of PubMed,Embase,Web of Science,and the Cochrane Library.Thereby the current status of AI-applications was systematically summarized in gastric cancer.Moreover,future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.展开更多
The small intestine is located in the middle of the gastrointestinal tract,so small intestinal diseases are more difficult to diagnose than other gastrointestinal diseases.However,with the extensive application of art...The small intestine is located in the middle of the gastrointestinal tract,so small intestinal diseases are more difficult to diagnose than other gastrointestinal diseases.However,with the extensive application of artificial intelligence in the field of small intestinal diseases,with its efficient learning capacities and computational power,artificial intelligence plays an important role in the auxiliary diagnosis and prognosis prediction based on the capsule endoscopy and other examination methods,which improves the accuracy of diagnosis and prediction and reduces the workload of doctors.In this review,a comprehensive retrieval was performed on articles published up to October 2020 from PubMed and other databases.Thereby the application status of artificial intelligence in small intestinal diseases was systematically introduced,and the challenges and prospects in this field were also analyzed.展开更多
Objective： To compare the feasibility and applicability of predicting the prognosis of patients using the Early Warning Score（MEWS） system and the Acute Physiology and Chronic Health Evaluation（APACHE Ⅱ） system ...Objective： To compare the feasibility and applicability of predicting the prognosis of patients using the Early Warning Score（MEWS） system and the Acute Physiology and Chronic Health Evaluation（APACHE Ⅱ） system in the Emergency Department.Methods： Using a prospective study method, the APACHE Ⅱ and MEWS data for 640 patients hospitalized in the Emergency Internal Medicine Department were collected. The prognoses, two scores to predict the corresponding prediction index of sensitivity, specificity and positive predictive value for the prognosis,the negative predictive value and the ROC curve for predicting the prognosis were analyzed for all patients.Results： In the prediction of the risk of mortality, the MEWS system had a high resolution. The MEWS area under the ROC curve was 0.93. The area under the ROC curve for the APACHE score was 0.79, and the difference was statistically significant（Z =4.348, P 〈 0.01）.Conclusions： Both the MEWS and APACHE Ⅱ systems can be used to determine the severity of emergency patients and have a certain predictive value for the patient＇s mortality risk. However, the MEWS system is simple and quick to operate, making it a useful supplement for APACHE Ⅱ score.展开更多
BACKGROUND Upper gastrointestinal bleeding(UGIB)is a common medical emergency and early assessment of its outcomes is vital for treatment decisions.AIM To develop a new scoring system to predict its prognosis.METHODS ...BACKGROUND Upper gastrointestinal bleeding(UGIB)is a common medical emergency and early assessment of its outcomes is vital for treatment decisions.AIM To develop a new scoring system to predict its prognosis.METHODS In this retrospective study,692 patients with UGIB were enrolled from two cen-ters and divided into a training(n=591)and a validation cohort(n=101).The clinical data were collected to develop new prognostic prediction models.The en-dpoint was compound outcome defined as(1)demand for emergency surgery or vascular intervention,(2)being transferred to the intensive care unit,or(3)death during hos-pitalization.The models’predictive ability was compared with previously esta-blished scores by receiver operating characteristic(ROC)curves.RESULTS Totally 22.2%(131/591)patients in the training cohort and 22.8%(23/101)in the validation cohort presented poor outcomes.Based on the stepwise-forward Lo-gistic regression analysis,eight predictors were integrated to determine a new post-endoscopic prognostic scoring system(MH-STRALP);a nomogram was de-termined to present the model.Compared with the previous scores(GBS,Rock-all,ABC,AIMS65,and PNED score),MH-STRALP showed the best prognostic prediction ability with area under the ROC curves(AUROCs)of 0.899 and 0.826 in the training and validation cohorts,respectively.According to the calibration cur-ve,decision curve analysis,and internal cross-validation,the nomogram showed good calibration ability and net clinical benefit in both cohorts.After removing the endoscopic indicators,the pre-endoscopic model(pre-MH-STRALP score)was conducted.Similarly,the pre-MHSTRALP score showed better predictive value(AUROCs of 0.868 and 0.767 in the training and validation cohorts,respectively)than the other pre-endoscopic scores.CONCLUSION The MH-STRALP score and pre-MH-STRALP score are simple,convenient,and accurate tools for prognosis prediction of UGIB,and may be applied for early decision on its management strategies.展开更多
Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of...Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of spread through air space(STAS),a distinct mode of lung cancer infiltration,has rarely been reported.Therefore,this study aimed to explore the relationship between STAS tumor cells and the clinical and molecular characteristics of patients with lung adenocarcinoma,as well as their impact on prognosis.Methods:This study included 147 patients who were diagnosed with lung adenocarcinoma at the Inner Mongolia Autonomous Region Cancer Institute between January 2014 and December 2017.Surgical resection specimens were retrospectively analyzed.Using univariate and multivariate Cox analyses,we assessed the association between STAS and the clinicopathological features and molecular characteristics of patients with lung adenocarcinoma.Furthermore,we investigated the effects on patient prognosis.In addition,we developed a column–line plot prediction model and performed internal validation.Results:Patients with positive STAS had a significantly higher proportion of tumors with a diameter≥2 cm,with infiltration around the pleura,blood vessels,and nerves,and a pathological stage>IIB than in STAS-negative patients(P<0.05).Cox multivariate survival analysis revealed that clinical stage,STAS status,tumor size,and visceral pleural invasion were independent prognostic factors influencing the 5-year progression-free survival in patients with lung adenocarcinoma.The predictive values and P values from the Hosmer-Lemeshow test were 0.8 and 0.2,respectively,indicating no statistical difference.Receiver operating characteristic curve analysis demonstrated areas under the curve of 0.884 and 0.872 for the training and validation groups,respectively.The nomogram model exhibited the best fit with a value of 192.09.Conclusions:Clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis are independent prognostic factors for patients with STAS-positive lung adenocarcinoma.The nomogrambased on the clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis showed good accuracy,differentiation,and clinical practicality.展开更多
Background:The 8th edition of the American Joint Committee on Cancer/Union for International Cancer Control(AJCC/UICC)pathological tumor-node-metastasis(pTNM)staging system may have increased accuracy in predicting pr...Background:The 8th edition of the American Joint Committee on Cancer/Union for International Cancer Control(AJCC/UICC)pathological tumor-node-metastasis(pTNM)staging system may have increased accuracy in predicting prognosis of gastric cancer due to its important modifications from previous editions.However,the homogeneity in prognosis within each subgroup classified according to the 8th edition may still exist.This study aimed to compare and analyze the prognosis prediction abilities of the 8th and 7th editions of AJCC/UICC pTNM staging system for gastric cancer and propose a modified pTNM staging system with external validation.Methods:In total,clinical data of 7911 patients from three high-capacity institutions in China and 10,208 cases from the Surveillance,Epidemiology,and End Results(SEER)Program Registry were analyzed.The homogeneity,discrimina-tory ability,and monotonicity of the gradient assessments of the 8th and 7th editions of AJCC/UICC pTNM staging system were compared using log-rank χ^(2),linear-trend χ^(2),likelihood-ratioχ2 statistics and Akaike information criterion(AIC)calculations,on which a modified pTNM classification with external validation using the SEER database was proposed.Results:Considerable stage migration,mainly for stage III,between the 8th and 7th editions was observed in both cohorts.The survival rates of subgroups of patients within stage IIIA,IIIB,or IIIC classified according to both editions were significantly different,demonstrating poor homogeneity for patient stratification.A modified pTNM staging system using data from the Chinese cohort was then formulated and demonstrated an improved homogeneity in these abovementioned subgroups.This staging system was further validated using data from the SEER cohort,and similar promising results were obtained.Compared with the 8th and 7th editions,the modified pTNM staging system displayed the highest log-rank χ^(2),linear-trend χ^(2),likelihood-ratio χ^(2),and lowest AIC values,indicating its superior discriminatory ability,monotonicity,homogeneity and prognosis prediction ability in both populations.Conclusions:The 8th edition of AJCC/UICC pTNM staging system is superior to the 7th edition,but still results in homogeneity in prognosis prediction.Our modified pTNM staging system demonstrated the optimal stratification and prognosis prediction ability in two large cohorts of different gastric cancer populations.展开更多
Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new...Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new insights into the development and use of artificial intelligence(AI)predictive models in clinical decision-making for COVID-19 and other diseases.Materials and Methods:We compared two proposed prediction models for COVID-19 prognosis that use a decision tree and logistic regression modeling.We evaluated the effectiveness of different model-building strategies using laboratory tests and/or clinical record data,their sensitivity and robustness to the timings of records used and the presence of missing data,and their predictive performance and capabilities in single-site and multicenter settings.Results:The predictive accuracies of the two models after retraining were improved to 93.2% and 93.9%,compared with that of the models directly used,with accuracies of 84.3% and 87.9%,indicating that the prediction models could not be used directly and require retraining based on actual data.In addition,based on the prediction model,new features obtained by model comparison and literature evidence were transferred to integrate the new models with better performance.Conclusions:Comparing the characteristics and differences of datasets used in model training,effective model verification,and a fusion of models is necessary in improving the performance of AI models.展开更多
Objective To investigate the characteristic of heart rate variability(HRV)changes in patients with posteriorcirculation cerebral infarction and its value in prognosis prediction.Methods Fifty-four cases continuously d...Objective To investigate the characteristic of heart rate variability(HRV)changes in patients with posteriorcirculation cerebral infarction and its value in prognosis prediction.Methods Fifty-four cases continuously diagnosed with acute posterior circulation cerebral infarction from March 2015 to November 2015 in the Department展开更多
Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing mod...Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing models are typically developed in a cancerspecific manner,lack extensive external validation,and often rely on molecular data that are not routinely available in clinical practice.To address these limitations,we present PROGPATH,a unified model capable of integrating histopathological image features with routinely collected clinical variables to achieve pancancer prognosis prediction.PROGPATH employs a weakly supervised deep learning architecture built upon the foundation model for image encoding.Morphological features are aggregated through an attention-guided multiple instance learning module and fused with clinical information via a cross-attention transformer.A router-based classification strategy further refines the prediction performance.PROGPATH was trained on 7999 whole-slide images(WSIs)from 6,670 patients across 15 cancer types,and extensively validated on 17 external cohorts with a total of 7374 WSIs from 4441 patients,covering 12 cancer types from 8 consortia and institutions across three continents.PROGPATH achieved consistently superior performance compared with state-of-the-art multimodal prognosis prediction models.It demonstrated strong generalizability across cancer types and robustness in stratified subgroups,including early-and advancedstage patients,treatment cohorts(radiotherapy and pharmaceutical therapy),and biomarker-defined subsets.We further provide model interpretability by identifying pathological patterns critical to PROGPATH’s risk predictions,such as the degree of cell differentiation and extent of necrosis.Together,these results highlight the potential of PROGPATH to support pancancer outcome prediction and inform personalized cancer management strategies.展开更多
Background and Objectives:Menopausal women with chronic heart failure(CHF)exhibit unique physiological characteristics and prognostic features.The aim of this study is to analyze the significant predictive factors for...Background and Objectives:Menopausal women with chronic heart failure(CHF)exhibit unique physiological characteristics and prognostic features.The aim of this study is to analyze the significant predictive factors for the prognosis of chronic heart failure in menopausal women and the impact of different nutritional interventions on prognosis.Methods and Study Design:A total of 270 menopausal women with CHF were enrolled in the study and divided into two groups based on the nutritional intervention received.Analyze the significant predictive fac tors of all-cause mortality,readmission rate,deterioration of cardiac function,deterioration of nutritional status,and deterioration of quality of life,as well as the impact of nutritional intervention on these prognoses.Build a risk score model based on significant factors in the prognostic model.Evaluate the predictive ability of the model through the ROC curve.Results:Multivariate logistic regression analysis showed that NYHA grading BNP,eGFR,The level of estradiol(E2)and nutritional intervention are significant influencing factors in multiple prog nostic indicators,among which the enhanced nutritional support and micronutrient supplementation program in nutritional intervention have a significant protective effect on poor prognosis.The constructed nutritional risk model has good discriminative ability and robustness in predicting prognosis.Conclusions:This study identified menopausal characteristics,NYHA classification,BNP,eGFR,and estradiol levels as important prognostic pre dictors in menopausal women with CHF.Enhanced nutritional support and micronutrient supplementation signif icantly improved patient prognosis.The risk model based on nutritional intervention provides scientific basis for the management strategy of chronic heart failure in menopausal women.展开更多
Current subtyping methods of diffuse large B-cell lymphoma(DLBCL)could not satisfy the clinical demands for risk assessment and prognostic prediction.We aimed to investigate the prognostic effect of autophagy-related ...Current subtyping methods of diffuse large B-cell lymphoma(DLBCL)could not satisfy the clinical demands for risk assessment and prognostic prediction.We aimed to investigate the prognostic effect of autophagy-related genes(ARGs)in DLBCL.Transcriptomic data of 1,409 DLBCL patients,531 healthy controls(HCs),and single-cell sequencing data of 4 DLBCL were included.Validation involved spatial transcriptomics from 10 DLBCL patients and 110 DLBCL proteomic data from a local cohort.We identified 153 differentially expressed ARGs between DLBCL patients(n=48)and HCs(n=531),classifying 414 DLBCL patients into two subtypes based on autophagy heterogeneity.Subtype I,characterized by upregulated T regulatory(Treg)cells(P<0.0001)and T follicular helper(Tfh)cells(P=0.0012),showed a superior prognosis(P=0.035).Eight prognostic ARGs were selected to construct an autophagy-related model,dividing patients into low-and high-risk groups.Kaplan-Meier survival analysis revealed significantly better outcomes for the low-risk group in both the discovery(P<0.0001)and validation cohorts(P=0.0041).High-risk patients exhibited elevated IDO1(P=0.042)and LAG3(P<0.001)levels.Among the eight signature proteins,higher FAS was further verified to indicate a better prognosis in the local cohort(n=110)using antibody array(P=0.0083).FAS was primarily expressed in T cells such as Treg and Tfh cells and was elevated in non-progressive disease patients.FASpositive T cells showed increased interferon-gamma(normalized enrichment score(NES)=2.196,FDR<0.0001)and alpha(NES=1.836,FDR<0.01)response activities.We constructed an autophagy-related model and identified FAS as a prognostic biomarker.FAS+Treg and Tfh cell-enriched TME indicated a favorable prognosis.展开更多
基金funded by the Capital’s Funds for Health Improve-ment and Research(grant number:2024-1G-4023)the Special Project for Director,China Center for Evidence Based Traditional Chinese Medicine(grant number:2020YJSZX-2)National Natural Science Foundation of China(grant number:72474008).
文摘Objective:Circulating tumor DNA(ctDNA)is increasingly being used as a potential biomarker in colorectal cancer(CRC)patients.However,the role of ctDNA in CRC prognosis prediction remains unclear.The objective is to systematically assess the clinical value of ctDNA in colorectal cancer prognosis prediction throughout the treatment cycle.Methods:PubMed,Web of Science,Embase,Cochrane Library,Scopus,and clinical trials.gov database was searched from January 2016 to April 2023.Observational studies and randomized clinical trials reporting on ctDNA and prognostic outcomes in CRC patients were included.Pooled hazard risk ratios(HRs)were calculated for the primary outcomes,relapse-free survival(RFS),and overall survival(OS).Random-effects models were preferred considering the potential heterogeneity.Results:Sixty-five cohort studies were included.Association between ctDNA and shorter RFS or OS was significant,especially after the full-course treatment recommended by the guidelines(HR=8.92[95%CI:6.02-13.22],P<0.001,I^(2)=73%;HR=3.05[95%CI:1.72-5.41],P<0.001,I^(2)=48%)for all types of CRC patients.Despite the presence of heterogeneity,subgroup analyses showed that the cancer type and ctDNA detection assays may be the underlying cause.Besides,ctDNA may detect recurrence earlier than radiographic progression,but no uniform sampling time point between studies might bring bias.However,ctDNA detection did not appear to correlate with pathological complete response achievement in patients with locally advanced rectal cancer.Conclusion:ctDNA detection was significantly associated with poorer prognosis.The potential applications in prognostic prediction are promising and remain to be evaluated in other fields.
基金Supported by Ministry of National Defense-Medical Affairs Bureau,Taiwan,No.MND-MAB-110-109,No.MND-MAB-D-111059Cheng-Hsin General Hospital,Taiwan,No.CHNDMC-111-4。
文摘BACKGROUND Patients with colorectal cancer(CRC)undergo surgery,as well as perioperative chemoradiation or adjuvant chemotherapy primarily based on the tumor–node–metastasis(TNM)cancer staging system.However,treatment responses and prognostic outcomes of patients within the same stage vary markedly.The potential use of novel biomarkers can improve prognostication and shared decision making before implementation into certain therapies.AIM To investigate whether SUMF2,ADAMTS5,and PXDN methylation status could be associated with CRC prognosis.METHODS We conducted a Taiwan region cohort study involving 208 patients with CRC recruited from TriService General Hospital and applied the candidate gene approach to identify three genes involved in oncogenesis pathways.A methylation-specific polymerase chain reaction(MS-PCR)and Epi TYPER DNA methylation analysis were employed to detect methylation status and to quantify the methylation level of candidate genes in tumor tissue and adjacent normal tissue from participants.We evaluated SUMF2,ADAMTS5,and PXDN methylation as predictors of prognosis,including recurrence-free survival(RFS),progression-free survival(PFS),and overall survival(OS),using a Cox regression model and Kaplan–Meier analysis.RESULTS We revealed various outcomes related to methylation and prognosis.Significantly shorter PFS and OS were associated with the CpG_3+CpG_7 hypermethylation of SUMF2 from tumor tissue compared with CpG_3+CpG_7 hypomethylation[hazard ratio(HR)=2.24,95%confidence interval(CI)=1.03-4.85 for PFS,HR=2.56 and 95%CI=1.08-6.04 for OS].By contrast,a significantly longer RFS was associated with CpG_2 and CpG_13 hypermethylation of ADAMTS5 from normal tissue compared with CpG_2 and CpG_13 hypomethylation[HR(95%CI)=0.15(0.03-0.71)for CpG_2 and 0.20(0.04-0.97)for CpG_13].The relationship between the methylation status of PXDN and the prognosis of CRC did not reach statistical significance.CONCLUSION Our study found that CpG_3+CpG_7 hypermethylation of SUMF2 from tumor tissue was associated with significantly shorter PFS and OS compared with CpG_3+CpG_7 hypomethylation.CpG_2 and CpG_13 hypermethylation of ADAMTS5 from normal tissue was associated with a significantly longer RFS compared with CpG_2 and CpG_13 hypomethylation.These methylationrelated biomarkers which have implications for CRC prognosis prediction may aid physicians in clinical decision-making.
基金supported by a grant Hebei Provincial Health Commission project from the Foundation of Basic Research(No.20191843).
文摘Objective:Through integrated bioinformatics analysis,the goal of this work was to find new,characterised N7-methylguanosine modification-related long non-coding RNAs(m7G-lncRNAs)that might be used to predict the prognosis of laryngeal squamous cell carcinoma(LSCC).Methods:The clinical data and LSCC gene expression data for the current investigation were initially retrieved from the TCGA database&sanitised.Then,using co-expression analysis of m7G-associated mRNAs&lncRNAs&differential expression analysis(DEA)among LSCC&normal sample categories,we discovered lncRNAs that were connected to m7G.The prognosis prediction model was built for the training category using univariate&multivariate COX regression&LASSO regression analyses,&the model’s efficacy was checked against the test category data.In addition,we conducted DEA of prognostic m7G-lncRNAs among LSCC&normal sample categories&compiled a list of co-expression networks&the structure of prognosis m7G-lncRNAs.To compare the prognoses for individuals with LSCC in the high-&low-risk categories in the prognosis prediction model,survival and risk assessments were also carried out.Finally,we created a nomogram to accurately forecast the outcomes of LSCC patients&created receiver operating characteristic(ROC)curves to assess the prognosis prediction model’s predictive capability.Results:Using co-expression network analysis&differential expression analysis,we discovered 774 m7G-lncRNAs and 551 DEm7G-lncRNAs,respectively.We then constructed a prognosis prediction model for six m7G-lncRNAs(FLG−AS1,RHOA−IT1,AC020913.3,AC027307.2,AC010973.2 and AC010789.1),identified 32 DEPm7G-lncRNAs,analyzed the correlation between 32 DEPm7G-lncRNAs and 13 DEPm7G-mRNAs,and performed survival analyses and risk analyses of the prognosis prediction model to assess the prognostic performance of LSCC patients.By displaying ROC curves and a nomogram,we finally checked the prognosis prediction model's accuracy.Conclusion:By creating novel predictive lncRNA signatures for clinical diagnosis&therapy,our findings will contribute to understanding the pathogenetic process of LSCC.
基金the Tianjin Municipal Natural Science Foundation,No.21JCYBJC01110。
文摘BACKGROUND The ubiquitin-proteasome pathway(UPP)has been proven to play important roles in cancer.AIM To investigate the prognostic significance of genes involved in the UPP and develop a predictive model for liver cancer based on the expression of these genes.METHODS In this study,UPP-related E1,E2,E3,deubiquitylating enzyme,and proteasome gene sets were obtained from the Kyoto Encyclopedia of Genes and Genomes(KEGG)database,aiming to screen the prognostic genes using univariate and multivariate regression analysis and develop a prognosis predictive model based RESULTS Five genes(including autophagy related 10,proteasome 20S subunit alpha 8,proteasome 20S subunit beta 2,ubiquitin specific peptidase 17 like family member 2,and ubiquitin specific peptidase 8)were proven significantly correlated with prognosis and used to develop a prognosis predictive model for liver cancer.Among training,validation,and Gene Expression Omnibus sets,the overall survival differed significantly between the high-risk and low-risk groups.The expression of the five genes was significantly associated with immunocyte infiltration,tumor stage,and postoperative recurrence.A total of 111 differentially expressed genes(DEGs)were identified between the high-risk and low-risk groups and they were enriched in 20 and 5 gene ontology and KEGG pathways.Cell division cycle 20,Kelch repeat and BTB domain containing 11,and DDB1 and CUL4 associated factor 4 like 2 were the DEGs in the E3 gene set that correlated with survival.CONCLUSION We have constructed a prognosis predictive model in patients with liver cancer,which contains five genes that associate with immunocyte infiltration,tumor stage,and postoperative recurrence.
基金The studies mentioned in this paper were supported in part by Grants R01 CA160205 and R01 CA197150 from the National Cancer Institute,National Institutes of Health,USAGrant HR15-016 from Oklahoma Center for the Advancement of Science and Technology,USA.
文摘In order to develop precision or personalized medicine,identifying new quantitative imaging markers and building machine learning models to predict cancer risk and prognosis has been attracting broad research interest recently.Most of these research approaches use the similar concepts of the conventional computer-aided detection schemes of medical images,which include steps in detecting and segmenting suspicious regions or tumors,followed by training machine learning models based on the fusion of multiple image features computed from the segmented regions or tumors.However,due to the heterogeneity and boundary fuzziness of the suspicious regions or tumors,segmenting subtle regions is often difficult and unreliable.Additionally,ignoring global and/or background parenchymal tissue characteristics may also be a limitation of the conventional approaches.In our recent studies,we investigated the feasibility of developing new computer-aided schemes implemented with the machine learning models that are trained by global image features to predict cancer risk and prognosis.We trained and tested several models using images obtained from full-field digital mammography,magnetic resonance imaging,and computed tomography of breast,lung,and ovarian cancers.Study results showed that many of these new models yielded higher performance than other approaches used in current clinical practice.Furthermore,the computed global image features also contain complementary information from the features computed from the segmented regions or tumors in predicting cancer prognosis.Therefore,the global image features can be used alone to develop new case-based prediction models or can be added to current tumor-based models to increase their discriminatory power.
基金supported by the Sanming Project of Medicine in Shenzhen (SZSM202211017)。
文摘Accurate cancer staging is the foundation of precision oncology and guides prognosis prediction and therapeutic decision-making. The conjoint TNM System by the American Joint Committee on Cancer (AJCC) and the International Union Against Cancer (UICC) has served as the global standard for tumor classification since inception.
基金Research on the Measurement of Pulmonary Compliance and Its Guided Therapeutic Efficacy Analysis in Patients with ARDS Secondary to Severe Multiple Injuries(Project No.:XSD2023002)。
文摘Objective:To evaluate the predictive value of Modified Early Warning Score(MEWS)for neurological disease prognosis and identify prognostic factors.Methods:This retrospective study analyzed 768 neurological patients with MEWS≥4(June 2022–June 2024).Patients were stratified by outcomes(favorable/unfavorable).Multivariable logistic regression and ROC analysis were performed.Results:108 cases(13.1%)had unfavorable outcomes.Significant prognostic factors included:age,TBI history,onset-to-admission time,PT,MEWS score,and MEWS≥4 frequency(all P<0.05).MEWS showed AUC=0.749(sensitivity 62.0%,specificity 77.4%).Conclusion:MEWS demonstrates moderate predictive value(AUC=0.749)for neurological outcomes.Consciousness assessment limitations(56.5%impaired cases)may affect sensitivity.A specialized model incorporating pupillary reflexes and GCS is recommended for improved early warning.
基金Supported by Beijing Bethune Charitable Foundation and Provincial Natural Science Foundation of Liaoning,No.2022-MS-190.
文摘BACKGROUND Circulating tumor DNA(ctDNA)-based liquid biopsy has been found to be effective for the detection of minimal residual disease and the evaluation of prognostic risk in various solid tumors,with good sensitivity and specificity for identifying patients at high risk of recurrence.However,use of its results as a biomarker for guiding the treatment and predicting the prognosis of naso-pharyngeal carcinoma(NPC)has not been reported.CASE SUMMARY In this case study of a patient with stage IVb NPC,we utilized ctDNA as an independent biomarker to guide treatment.Chemotherapy was administered in the early stages of the disease,and local intensity-modulated radiation therapy was added when the patient tested positive for ctDNA,while radiation therapy was stopped and the patient was observed when the ctDNA test was negative.During the follow-up period,ctDNA signals became positive before tumor progression and became negative again at the end of treatment.We also explored the potential of ctDNA in combination with Epstein-Barr virus(EBV)DNA status to predict the prognosis of NPC patients,as well as the criteria for selecting genetic mutations and the testing cycle for ctDNA analysis.CONCLUSION The results of ctDNA-based liquid biopsy can serve as an independent biomarker,either independently or in conjunction with EBV DNA status,to guide the treatment and predict the prognosis of NPC.
基金supported by the National Natural Science Foundation of China(Nos.82203502,81670144,and 82403850)in addition,it was also funded by the Cross-innovation Talent Project at Renmin Hospital of Wuhan University(No.JCRCGW-2022-002).
文摘Objective This study aimed to develop an effective predictive tool that combines radiomics and clinical information to predict the survival outcomes of patients with advanced non-small cell lung cancer(NSCLC)undergoing chemoimmunotherapy.Methods Data were collected from 201 patients with advanced NSCLC who received first-line chemoimmunotherapy across three institutions:those from Centers I&II(n=164)were randomly split in a 7:3 ratio into training(n=115)and validation(n=49)cohorts,and those form Center III(n=37)were designated as the external test cohort.The analysis was conducted using CT images and clinical data obtained before and after induction chemoimmunotherapy.We developed multiple intratumoral and peritumoral radiomics-based models,along with clinical prediction model that integrated patients’baseline clinicopathological characteristics with plasma biomarker profiles,to predict progression-free survival(PFS).Based on expectations derived from prior established models,a stepwise backward elimination approach was utilized to select candidate submodels for the combined model construction.This combined model was internally validated using time-dependent ROC curves in training and validation sets and externally validated in the external test set.Results The combined model was constructed by integrating four candidate sub-models(DeltaSub,Clinical,P4mm,and Habitat)selected through the stepwise regression analysis.The combined model demonstrated superior performance compared to conventional models that utilized only clinical features,as well as Classical-Pre,Classical-Post,delta intratumor feature-based,and peritumor feature-based models.The combined model demonstrated satisfactory predictive performance across all three datasets,achieving a C-index of 0.849(95%CI:0.812–0.885)in the training set,0.744(95%CI:0.664–0.842)in the validation set,and 0.731(95%CI:0.639–0.824)in the external test set for PFS.Conclusions We developed a novel radiomic-clinical model to predict PFS for advanced NSCLC patients treated with first-line chemoimmunotherapy.This model enhanced survival assessment through comprehensive feature integration.
基金National Key R&D Program of China,No.2017YFC0908300.
文摘Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in the gastric cancer field based on its efficient computational power and learning capacities,such as imagebased diagnosis and prognosis prediction.AI-assisted diagnosis includes pathology,endoscopy,and computerized tomography,while researchers in the prognosis circle focus on recurrence,metastasis,and survival prediction.In this review,a comprehensive literature search was performed on articles published up to April 2020 from the databases of PubMed,Embase,Web of Science,and the Cochrane Library.Thereby the current status of AI-applications was systematically summarized in gastric cancer.Moreover,future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.
基金Supported by The National Natural Science Foundation of China,No.81871317.
文摘The small intestine is located in the middle of the gastrointestinal tract,so small intestinal diseases are more difficult to diagnose than other gastrointestinal diseases.However,with the extensive application of artificial intelligence in the field of small intestinal diseases,with its efficient learning capacities and computational power,artificial intelligence plays an important role in the auxiliary diagnosis and prognosis prediction based on the capsule endoscopy and other examination methods,which improves the accuracy of diagnosis and prediction and reduces the workload of doctors.In this review,a comprehensive retrieval was performed on articles published up to October 2020 from PubMed and other databases.Thereby the application status of artificial intelligence in small intestinal diseases was systematically introduced,and the challenges and prospects in this field were also analyzed.
基金supported by Pudong New Area Health System leadership program(No.PWRd2016-11)National Natural Science Foundation of China(No.81360231)
文摘Objective： To compare the feasibility and applicability of predicting the prognosis of patients using the Early Warning Score（MEWS） system and the Acute Physiology and Chronic Health Evaluation（APACHE Ⅱ） system in the Emergency Department.Methods： Using a prospective study method, the APACHE Ⅱ and MEWS data for 640 patients hospitalized in the Emergency Internal Medicine Department were collected. The prognoses, two scores to predict the corresponding prediction index of sensitivity, specificity and positive predictive value for the prognosis,the negative predictive value and the ROC curve for predicting the prognosis were analyzed for all patients.Results： In the prediction of the risk of mortality, the MEWS system had a high resolution. The MEWS area under the ROC curve was 0.93. The area under the ROC curve for the APACHE score was 0.79, and the difference was statistically significant（Z =4.348, P 〈 0.01）.Conclusions： Both the MEWS and APACHE Ⅱ systems can be used to determine the severity of emergency patients and have a certain predictive value for the patient＇s mortality risk. However, the MEWS system is simple and quick to operate, making it a useful supplement for APACHE Ⅱ score.
基金Supported by Key Disciplines Group Construction Project of Shanghai Pudong New Area Health Commission,No.PWZxq2022-06Medical discipline Construction Project of Pudong Health Committee of Shanghai,No.PWYgf2021-02+1 种基金Joint Tackling Project of Pudong Health Committee of Shanghai,No.PW2022D08the Medical Innovation Research Project of the Shanghai Science and Technology Commission,No.22Y11908400.
文摘BACKGROUND Upper gastrointestinal bleeding(UGIB)is a common medical emergency and early assessment of its outcomes is vital for treatment decisions.AIM To develop a new scoring system to predict its prognosis.METHODS In this retrospective study,692 patients with UGIB were enrolled from two cen-ters and divided into a training(n=591)and a validation cohort(n=101).The clinical data were collected to develop new prognostic prediction models.The en-dpoint was compound outcome defined as(1)demand for emergency surgery or vascular intervention,(2)being transferred to the intensive care unit,or(3)death during hos-pitalization.The models’predictive ability was compared with previously esta-blished scores by receiver operating characteristic(ROC)curves.RESULTS Totally 22.2%(131/591)patients in the training cohort and 22.8%(23/101)in the validation cohort presented poor outcomes.Based on the stepwise-forward Lo-gistic regression analysis,eight predictors were integrated to determine a new post-endoscopic prognostic scoring system(MH-STRALP);a nomogram was de-termined to present the model.Compared with the previous scores(GBS,Rock-all,ABC,AIMS65,and PNED score),MH-STRALP showed the best prognostic prediction ability with area under the ROC curves(AUROCs)of 0.899 and 0.826 in the training and validation cohorts,respectively.According to the calibration cur-ve,decision curve analysis,and internal cross-validation,the nomogram showed good calibration ability and net clinical benefit in both cohorts.After removing the endoscopic indicators,the pre-endoscopic model(pre-MH-STRALP score)was conducted.Similarly,the pre-MHSTRALP score showed better predictive value(AUROCs of 0.868 and 0.767 in the training and validation cohorts,respectively)than the other pre-endoscopic scores.CONCLUSION The MH-STRALP score and pre-MH-STRALP score are simple,convenient,and accurate tools for prognosis prediction of UGIB,and may be applied for early decision on its management strategies.
基金Funded by the Health Science and Technology Program of Inner Mongolia Autonomous Region(no.202201061)Supported by the Joint Project of theMillion Science and Technology Initiatives of Inner Mongolia Medical University(no.YKD2020KJBW(LH)057).
文摘Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of spread through air space(STAS),a distinct mode of lung cancer infiltration,has rarely been reported.Therefore,this study aimed to explore the relationship between STAS tumor cells and the clinical and molecular characteristics of patients with lung adenocarcinoma,as well as their impact on prognosis.Methods:This study included 147 patients who were diagnosed with lung adenocarcinoma at the Inner Mongolia Autonomous Region Cancer Institute between January 2014 and December 2017.Surgical resection specimens were retrospectively analyzed.Using univariate and multivariate Cox analyses,we assessed the association between STAS and the clinicopathological features and molecular characteristics of patients with lung adenocarcinoma.Furthermore,we investigated the effects on patient prognosis.In addition,we developed a column–line plot prediction model and performed internal validation.Results:Patients with positive STAS had a significantly higher proportion of tumors with a diameter≥2 cm,with infiltration around the pleura,blood vessels,and nerves,and a pathological stage>IIB than in STAS-negative patients(P<0.05).Cox multivariate survival analysis revealed that clinical stage,STAS status,tumor size,and visceral pleural invasion were independent prognostic factors influencing the 5-year progression-free survival in patients with lung adenocarcinoma.The predictive values and P values from the Hosmer-Lemeshow test were 0.8 and 0.2,respectively,indicating no statistical difference.Receiver operating characteristic curve analysis demonstrated areas under the curve of 0.884 and 0.872 for the training and validation groups,respectively.The nomogram model exhibited the best fit with a value of 192.09.Conclusions:Clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis are independent prognostic factors for patients with STAS-positive lung adenocarcinoma.The nomogrambased on the clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis showed good accuracy,differentiation,and clinical practicality.
基金supported by the Major Program of Collaborative Innovation of Guangzhou(No.201508030042)the Natural Science Foundation of Guangdong Province(No.2015A030313089,2018A030313631)+3 种基金Guangdong Provincial Scientific and Technology Project(No.2014A020232331)Guangzhou Medical,Health Science and Technology Project(No.20151A011077)China Postdoctoral Science Foundation Grant(No.2017M622879)National Natural Science Foundation of China(No.81802451).
文摘Background:The 8th edition of the American Joint Committee on Cancer/Union for International Cancer Control(AJCC/UICC)pathological tumor-node-metastasis(pTNM)staging system may have increased accuracy in predicting prognosis of gastric cancer due to its important modifications from previous editions.However,the homogeneity in prognosis within each subgroup classified according to the 8th edition may still exist.This study aimed to compare and analyze the prognosis prediction abilities of the 8th and 7th editions of AJCC/UICC pTNM staging system for gastric cancer and propose a modified pTNM staging system with external validation.Methods:In total,clinical data of 7911 patients from three high-capacity institutions in China and 10,208 cases from the Surveillance,Epidemiology,and End Results(SEER)Program Registry were analyzed.The homogeneity,discrimina-tory ability,and monotonicity of the gradient assessments of the 8th and 7th editions of AJCC/UICC pTNM staging system were compared using log-rank χ^(2),linear-trend χ^(2),likelihood-ratioχ2 statistics and Akaike information criterion(AIC)calculations,on which a modified pTNM classification with external validation using the SEER database was proposed.Results:Considerable stage migration,mainly for stage III,between the 8th and 7th editions was observed in both cohorts.The survival rates of subgroups of patients within stage IIIA,IIIB,or IIIC classified according to both editions were significantly different,demonstrating poor homogeneity for patient stratification.A modified pTNM staging system using data from the Chinese cohort was then formulated and demonstrated an improved homogeneity in these abovementioned subgroups.This staging system was further validated using data from the SEER cohort,and similar promising results were obtained.Compared with the 8th and 7th editions,the modified pTNM staging system displayed the highest log-rank χ^(2),linear-trend χ^(2),likelihood-ratio χ^(2),and lowest AIC values,indicating its superior discriminatory ability,monotonicity,homogeneity and prognosis prediction ability in both populations.Conclusions:The 8th edition of AJCC/UICC pTNM staging system is superior to the 7th edition,but still results in homogeneity in prognosis prediction.Our modified pTNM staging system demonstrated the optimal stratification and prognosis prediction ability in two large cohorts of different gastric cancer populations.
基金financially supported by the Natural Science Foundation of Beijing(No.M21012)National Natural Science Foundation of China(No.82174533)Key Technologies R and D Program of the China Academy of Chinese Medical Sciences(No.CI2021A00920).
文摘Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new insights into the development and use of artificial intelligence(AI)predictive models in clinical decision-making for COVID-19 and other diseases.Materials and Methods:We compared two proposed prediction models for COVID-19 prognosis that use a decision tree and logistic regression modeling.We evaluated the effectiveness of different model-building strategies using laboratory tests and/or clinical record data,their sensitivity and robustness to the timings of records used and the presence of missing data,and their predictive performance and capabilities in single-site and multicenter settings.Results:The predictive accuracies of the two models after retraining were improved to 93.2% and 93.9%,compared with that of the models directly used,with accuracies of 84.3% and 87.9%,indicating that the prediction models could not be used directly and require retraining based on actual data.In addition,based on the prediction model,new features obtained by model comparison and literature evidence were transferred to integrate the new models with better performance.Conclusions:Comparing the characteristics and differences of datasets used in model training,effective model verification,and a fusion of models is necessary in improving the performance of AI models.
文摘Objective To investigate the characteristic of heart rate variability(HRV)changes in patients with posteriorcirculation cerebral infarction and its value in prognosis prediction.Methods Fifty-four cases continuously diagnosed with acute posterior circulation cerebral infarction from March 2015 to November 2015 in the Department
基金supported in part by the National Cancer Institute under award numbers R01CA268287A1,U01CA269181,R01CA26820701A1,R01CA249992-01A1,R01CA202752-01A1,R01CA208236-01A1,R01CA216579-01A1,R01CA220581-01A1,R01CA257612-01A1,1U01CA239055-01,1U01CA248226-01,1U54CA254566-01National Heart,Lung and Blood Institute 1R01HL15127701A1,R01HL15807101A1+8 种基金National Institute of Biomedical Imaging and Bioengineering 1R43EB028736-01VA Merit Review Award IBX004121A from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service the Office of the Assistant Secretary of Defense for Health Affairs,through the Breast Cancer Research Program(W81XWH-19-1-0668)the Prostate Cancer Research Program(W81XWH-20-1-0851)the Lung Cancer Research Program(W81XWH-18-1-0440,W81XWH-20-1-0595)the Peer Reviewed Cancer Research Program(W81XWH-18-1-0404,W81XWH-21-1-0345,W81XWH-211-0160)the Kidney Precision Medicine Project(KPMP)Glue Grant and sponsored research agreements from Bristol Myers-Squibb,Boehringer-Ingelheim,Eli-Lilly and Astrazenecasupported in part by the National Natural Science Foundation of China general program(No.61571314)the Sichuan University-Yibin City Strategic Cooperation Special Fund(No.2020CDYB-27)Support Program of Sichuan Science and Technology Department(No.2023YFS0327-LH).
文摘Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing models are typically developed in a cancerspecific manner,lack extensive external validation,and often rely on molecular data that are not routinely available in clinical practice.To address these limitations,we present PROGPATH,a unified model capable of integrating histopathological image features with routinely collected clinical variables to achieve pancancer prognosis prediction.PROGPATH employs a weakly supervised deep learning architecture built upon the foundation model for image encoding.Morphological features are aggregated through an attention-guided multiple instance learning module and fused with clinical information via a cross-attention transformer.A router-based classification strategy further refines the prediction performance.PROGPATH was trained on 7999 whole-slide images(WSIs)from 6,670 patients across 15 cancer types,and extensively validated on 17 external cohorts with a total of 7374 WSIs from 4441 patients,covering 12 cancer types from 8 consortia and institutions across three continents.PROGPATH achieved consistently superior performance compared with state-of-the-art multimodal prognosis prediction models.It demonstrated strong generalizability across cancer types and robustness in stratified subgroups,including early-and advancedstage patients,treatment cohorts(radiotherapy and pharmaceutical therapy),and biomarker-defined subsets.We further provide model interpretability by identifying pathological patterns critical to PROGPATH’s risk predictions,such as the degree of cell differentiation and extent of necrosis.Together,these results highlight the potential of PROGPATH to support pancancer outcome prediction and inform personalized cancer management strategies.
文摘Background and Objectives:Menopausal women with chronic heart failure(CHF)exhibit unique physiological characteristics and prognostic features.The aim of this study is to analyze the significant predictive factors for the prognosis of chronic heart failure in menopausal women and the impact of different nutritional interventions on prognosis.Methods and Study Design:A total of 270 menopausal women with CHF were enrolled in the study and divided into two groups based on the nutritional intervention received.Analyze the significant predictive fac tors of all-cause mortality,readmission rate,deterioration of cardiac function,deterioration of nutritional status,and deterioration of quality of life,as well as the impact of nutritional intervention on these prognoses.Build a risk score model based on significant factors in the prognostic model.Evaluate the predictive ability of the model through the ROC curve.Results:Multivariate logistic regression analysis showed that NYHA grading BNP,eGFR,The level of estradiol(E2)and nutritional intervention are significant influencing factors in multiple prog nostic indicators,among which the enhanced nutritional support and micronutrient supplementation program in nutritional intervention have a significant protective effect on poor prognosis.The constructed nutritional risk model has good discriminative ability and robustness in predicting prognosis.Conclusions:This study identified menopausal characteristics,NYHA classification,BNP,eGFR,and estradiol levels as important prognostic pre dictors in menopausal women with CHF.Enhanced nutritional support and micronutrient supplementation signif icantly improved patient prognosis.The risk model based on nutritional intervention provides scientific basis for the management strategy of chronic heart failure in menopausal women.
基金supported by Chinese Academy of Medical Sciences(CAMS)Innovation Fund for Medical Sciences(CIFMS 2021-12M-1003)National High Level Hospital Clinical Research Funding(2022-PUMCH-D-002)China National Major Project for New Drug Innovation(2019ZX09201-002)。
文摘Current subtyping methods of diffuse large B-cell lymphoma(DLBCL)could not satisfy the clinical demands for risk assessment and prognostic prediction.We aimed to investigate the prognostic effect of autophagy-related genes(ARGs)in DLBCL.Transcriptomic data of 1,409 DLBCL patients,531 healthy controls(HCs),and single-cell sequencing data of 4 DLBCL were included.Validation involved spatial transcriptomics from 10 DLBCL patients and 110 DLBCL proteomic data from a local cohort.We identified 153 differentially expressed ARGs between DLBCL patients(n=48)and HCs(n=531),classifying 414 DLBCL patients into two subtypes based on autophagy heterogeneity.Subtype I,characterized by upregulated T regulatory(Treg)cells(P<0.0001)and T follicular helper(Tfh)cells(P=0.0012),showed a superior prognosis(P=0.035).Eight prognostic ARGs were selected to construct an autophagy-related model,dividing patients into low-and high-risk groups.Kaplan-Meier survival analysis revealed significantly better outcomes for the low-risk group in both the discovery(P<0.0001)and validation cohorts(P=0.0041).High-risk patients exhibited elevated IDO1(P=0.042)and LAG3(P<0.001)levels.Among the eight signature proteins,higher FAS was further verified to indicate a better prognosis in the local cohort(n=110)using antibody array(P=0.0083).FAS was primarily expressed in T cells such as Treg and Tfh cells and was elevated in non-progressive disease patients.FASpositive T cells showed increased interferon-gamma(normalized enrichment score(NES)=2.196,FDR<0.0001)and alpha(NES=1.836,FDR<0.01)response activities.We constructed an autophagy-related model and identified FAS as a prognostic biomarker.FAS+Treg and Tfh cell-enriched TME indicated a favorable prognosis.
