BACKGROUND Colorectal cancer significantly impacts global health,with unplanned reoperations post-surgery being key determinants of patient outcomes.Existing predictive models for these reoperations lack precision in ...BACKGROUND Colorectal cancer significantly impacts global health,with unplanned reoperations post-surgery being key determinants of patient outcomes.Existing predictive models for these reoperations lack precision in integrating complex clinical data.AIM To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients.METHODS Data of patients treated for colorectal cancer(n=2044)at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected.Patients were divided into an experimental group(n=60)and a control group(n=1984)according to unplanned reoperation occurrence.Patients were also divided into a training group and a validation group(7:3 ratio).We used three different machine learning methods to screen characteristic variables.A nomogram was created based on multifactor logistic regression,and the model performance was assessed using receiver operating characteristic curve,calibration curve,Hosmer-Lemeshow test,and decision curve analysis.The risk scores of the two groups were calculated and compared to validate the model.RESULTS More patients in the experimental group were≥60 years old,male,and had a history of hypertension,laparotomy,and hypoproteinemia,compared to the control group.Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation(P<0.05):Prognostic Nutritional Index value,history of laparotomy,hypertension,or stroke,hypoproteinemia,age,tumor-node-metastasis staging,surgical time,gender,and American Society of Anesthesiologists classification.Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility.CONCLUSION This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer,which can improve treatment decisions and prognosis.展开更多
BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-bas...BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-based computer-assisted detection(CADe)techniques were established from small single-center datasets,and unrepresentative learning materials might confine their application and generalization in wide practice.Although CADes have been reported to identify polyps in colonoscopic images and videos in real time,their diagnostic performance deserves to be further validated in clinical practice.AIM To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.METHODS With high-quality screening and labeling from 55 qualified colonoscopists,a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe.In addition,the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps.Finally,we conducted a selfcontrolled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.RESULTS The CADe was able to identify polyps in the test dataset with 95.0%sensitivity and 99.1%specificity.For colonoscopy videos,all 86 polyps were detected with 92.2%sensitivity and 93.6%specificity in frame-by-frame analysis.In the prospective validation,the sensitivity of CAD in identifying polyps was 98.4%(185/188).Folds,reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies.Colonoscopists can detect more polyps(0.90 vs 0.82,P<0.001)and adenomas(0.32 vs 0.30,P=0.045)with the aid of CADe,particularly polyps<5 mm and flat polyps(0.65 vs 0.57,P<0.001;0.74 vs 0.67,P=0.001,respectively).However,high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time(P=0.32;P=0.16,respectively).CONCLUSION CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas,and further confirmation is warranted.展开更多
Objective To experimentally validate clinical samples,analyze the mRNA expression of the FYVE domain containing phosphatidylinositol 3-phosphate 5 kinase(PIKFYVE)gene,and its clinical significance based on the Cancer ...Objective To experimentally validate clinical samples,analyze the mRNA expression of the FYVE domain containing phosphatidylinositol 3-phosphate 5 kinase(PIKFYVE)gene,and its clinical significance based on the Cancer Genome Atlas(TCGA)database in hepatocellular carcinoma(HCC).MethodssData information on 424 clinical samples(including 374 cases of HCC tissues and 50 cases of non-tumorous liver tissues)were collected based on the TCGA database.Cox regression analysis and the Kaplan-Meier method were used to analyze the relationship between mRNA expression of the PIKFYVE gene and the clinical characteristics as well as survival prognosis in patients with HCC.The relationship betwen the PIKFYVE gene and immune cell infiltration was examined by correlation analysis with 24 kinds of immune cells.In addition,the mRNA expression level of the PIKFYVE gene and RACalpha serine/threonine-protein kinase(AKT1),phosphatase and tensin homolog(PTEN),protein kinase C alpha(PRKCA),inositol polyphosphate-5-phosphatase(INPP5D),phosphoinositide-3-kinase regulatory subunit 1(PIK3R1),inositol polyphosphate 4-phosphatase type II(INPP4B)and phospholipase C beta 4(PLCB4)gene correlations were analyzed in HCC tissues.At the same time,paraffin sections of highly differentiated,moderately differentiated,poorly differentiated,and non-tumor liver tissues from patients with HCC were collected from the Department of Pathology of the First Affiliated Hospital of Xinjiang Medical University.The histopathological observation was performed by HE staining.Immunohistochemistry was used to verify the expression levels of the PIKFYVE and Ki67 proteins in each clinical sample.The t-test was used for intergroup comparison of continuous data.The X test and Wilcoxon rank sum test were used for intergroup comparison of enumeration data.The Kaplan-Meier method was used for survival analysis.Results The expression level of the PIKFYVE gene was higher in the HCC tumor than that in normal liver tissue(P<0.01).The overall survival time of patients was significantly longer in the low expression group than that in the high expression group(HR=1.57,95%CI:1.10-2.25,P=0.014).The results of univariate Cox regression analysis showed that tumor stage,pathological grade,tumor status,residual tumor,and PIKFYVE expression level all had an effect on OS(P<0.05).The PIKFYVE prognostic risk model had a proportionate score of HR=1.533(95%CI:1.077-2.181,P=0.018).Multivariate Cox risk regression analysis showed that the PIKFYVE prognostic risk model had a proportionate score of HR=1.481(95%CI:0.886-2.476,P=0.134)and an area under the receiver operating characteristic curve of 0.559,indicating that it had predictive value for survival prediction.The results of the correlation analysis showed that the expression level of PIKFYVE was strongly correlated with immune cell infiltration and TP53(P<0.01).The results of immunohistochemical staining showed that the expression level of PIKFYVECwas significantly higher in HCC tissue samples than that in non-tumor liver tissues(P<0.01),and was negatively correlated with the degree of differentiation.Conclusion PIKFYVE,as an independent risk factor,is expected to be developed into a biomarker for clinical diagnosis,offering a reference for novel therapeutic agents in HCC.展开更多
Objective To evaluate the clinical reliability and validity of the sub-axial injury classification (SLIC) system proposed by the Spine Trauma Study Group (STSG) in 2007. Methods Thirty cases of cervical injury were ra...Objective To evaluate the clinical reliability and validity of the sub-axial injury classification (SLIC) system proposed by the Spine Trauma Study Group (STSG) in 2007. Methods Thirty cases of cervical injury were randomly chosen展开更多
Objective To develop and validate clinical predictive models for identifying poor short-term response to recombinant human growth hormone (rhGH) treatment in children with short stature.Methods A retrospective analysi...Objective To develop and validate clinical predictive models for identifying poor short-term response to recombinant human growth hormone (rhGH) treatment in children with short stature.Methods A retrospective analysis was conducted on 118 children diagnosed with growth hormone deficiency or idiopathic short stature who were treated at the First Affiliated Hospital of Zhengzhou University and two other hospitals between January 1,2020,and January 1,2024.展开更多
The first decade since the completion of the Human Genome Project has been marked with rapid development of genomic technologies and their immediate clinical applications. Genomic analysis using oligonucleotide array ...The first decade since the completion of the Human Genome Project has been marked with rapid development of genomic technologies and their immediate clinical applications. Genomic analysis using oligonucleotide array comparative genomic hybridization （aCGH） or single nucleotide polymorphism （SNP） chips has been applied to pediatric patients with developmental and intellectual disabilities （DD/ ID）, multiple congenital anomalies （MCA） and autistic spectrum disorders （ASD）. Evaluation of analytical and clinical validities of aCGH showed 〉 99% sensitivity and specificity and increased analytical resolution by higher density probe coverage. Reviews of case series, multi-center comparison and large patient-control studies demonstrated a diagnostic yield of 12%--20%; approximately 60% of these abnormalities were recurrent genomic disorders. This pediatric experience has been extended toward prenatal diagnosis. A series of reports indicated approximately 10% of pregnancies with ultrasound-detected structural anomalies and normal cytogenetic findings had genomic abnormalities, and 30% of these abnormalities were syndromic genomic disorders. Evidence-based practice guidelines and standards for implementing genomic analysis and web-delivered knowledge resources for interpreting genomic findings have been established. The progress from this technology-driven and evidence-based genomic analysis provides not only opportunities to dissect disease-causing mechanisms and develop rational therapeutic interventions but also important lessons for integrating genomic sequencing into pediatric and prenatal genetic evaluation.展开更多
基金This study has been reviewed and approved by the Clinical Research Ethics Committee of Wenzhou Central Hospital and the First Hospital Affiliated to Wenzhou Medical University,No.KY2024-R016.
文摘BACKGROUND Colorectal cancer significantly impacts global health,with unplanned reoperations post-surgery being key determinants of patient outcomes.Existing predictive models for these reoperations lack precision in integrating complex clinical data.AIM To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients.METHODS Data of patients treated for colorectal cancer(n=2044)at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected.Patients were divided into an experimental group(n=60)and a control group(n=1984)according to unplanned reoperation occurrence.Patients were also divided into a training group and a validation group(7:3 ratio).We used three different machine learning methods to screen characteristic variables.A nomogram was created based on multifactor logistic regression,and the model performance was assessed using receiver operating characteristic curve,calibration curve,Hosmer-Lemeshow test,and decision curve analysis.The risk scores of the two groups were calculated and compared to validate the model.RESULTS More patients in the experimental group were≥60 years old,male,and had a history of hypertension,laparotomy,and hypoproteinemia,compared to the control group.Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation(P<0.05):Prognostic Nutritional Index value,history of laparotomy,hypertension,or stroke,hypoproteinemia,age,tumor-node-metastasis staging,surgical time,gender,and American Society of Anesthesiologists classification.Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility.CONCLUSION This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer,which can improve treatment decisions and prognosis.
基金the National Key R&D Program of China,No.2018YFC1313103the National Natural Science Foundation of China,No.81670473 and No.81873546+1 种基金the“Shu Guang”Project of Shanghai Municipal Education Commission and Shanghai Education Development Foundation,No.19SG30the Key Area Research and Development Program of Guangdong Province,China,No.2018B010111001.
文摘BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-based computer-assisted detection(CADe)techniques were established from small single-center datasets,and unrepresentative learning materials might confine their application and generalization in wide practice.Although CADes have been reported to identify polyps in colonoscopic images and videos in real time,their diagnostic performance deserves to be further validated in clinical practice.AIM To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.METHODS With high-quality screening and labeling from 55 qualified colonoscopists,a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe.In addition,the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps.Finally,we conducted a selfcontrolled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.RESULTS The CADe was able to identify polyps in the test dataset with 95.0%sensitivity and 99.1%specificity.For colonoscopy videos,all 86 polyps were detected with 92.2%sensitivity and 93.6%specificity in frame-by-frame analysis.In the prospective validation,the sensitivity of CAD in identifying polyps was 98.4%(185/188).Folds,reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies.Colonoscopists can detect more polyps(0.90 vs 0.82,P<0.001)and adenomas(0.32 vs 0.30,P=0.045)with the aid of CADe,particularly polyps<5 mm and flat polyps(0.65 vs 0.57,P<0.001;0.74 vs 0.67,P=0.001,respectively).However,high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time(P=0.32;P=0.16,respectively).CONCLUSION CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas,and further confirmation is warranted.
文摘Objective To experimentally validate clinical samples,analyze the mRNA expression of the FYVE domain containing phosphatidylinositol 3-phosphate 5 kinase(PIKFYVE)gene,and its clinical significance based on the Cancer Genome Atlas(TCGA)database in hepatocellular carcinoma(HCC).MethodssData information on 424 clinical samples(including 374 cases of HCC tissues and 50 cases of non-tumorous liver tissues)were collected based on the TCGA database.Cox regression analysis and the Kaplan-Meier method were used to analyze the relationship between mRNA expression of the PIKFYVE gene and the clinical characteristics as well as survival prognosis in patients with HCC.The relationship betwen the PIKFYVE gene and immune cell infiltration was examined by correlation analysis with 24 kinds of immune cells.In addition,the mRNA expression level of the PIKFYVE gene and RACalpha serine/threonine-protein kinase(AKT1),phosphatase and tensin homolog(PTEN),protein kinase C alpha(PRKCA),inositol polyphosphate-5-phosphatase(INPP5D),phosphoinositide-3-kinase regulatory subunit 1(PIK3R1),inositol polyphosphate 4-phosphatase type II(INPP4B)and phospholipase C beta 4(PLCB4)gene correlations were analyzed in HCC tissues.At the same time,paraffin sections of highly differentiated,moderately differentiated,poorly differentiated,and non-tumor liver tissues from patients with HCC were collected from the Department of Pathology of the First Affiliated Hospital of Xinjiang Medical University.The histopathological observation was performed by HE staining.Immunohistochemistry was used to verify the expression levels of the PIKFYVE and Ki67 proteins in each clinical sample.The t-test was used for intergroup comparison of continuous data.The X test and Wilcoxon rank sum test were used for intergroup comparison of enumeration data.The Kaplan-Meier method was used for survival analysis.Results The expression level of the PIKFYVE gene was higher in the HCC tumor than that in normal liver tissue(P<0.01).The overall survival time of patients was significantly longer in the low expression group than that in the high expression group(HR=1.57,95%CI:1.10-2.25,P=0.014).The results of univariate Cox regression analysis showed that tumor stage,pathological grade,tumor status,residual tumor,and PIKFYVE expression level all had an effect on OS(P<0.05).The PIKFYVE prognostic risk model had a proportionate score of HR=1.533(95%CI:1.077-2.181,P=0.018).Multivariate Cox risk regression analysis showed that the PIKFYVE prognostic risk model had a proportionate score of HR=1.481(95%CI:0.886-2.476,P=0.134)and an area under the receiver operating characteristic curve of 0.559,indicating that it had predictive value for survival prediction.The results of the correlation analysis showed that the expression level of PIKFYVE was strongly correlated with immune cell infiltration and TP53(P<0.01).The results of immunohistochemical staining showed that the expression level of PIKFYVECwas significantly higher in HCC tissue samples than that in non-tumor liver tissues(P<0.01),and was negatively correlated with the degree of differentiation.Conclusion PIKFYVE,as an independent risk factor,is expected to be developed into a biomarker for clinical diagnosis,offering a reference for novel therapeutic agents in HCC.
文摘Objective To evaluate the clinical reliability and validity of the sub-axial injury classification (SLIC) system proposed by the Spine Trauma Study Group (STSG) in 2007. Methods Thirty cases of cervical injury were randomly chosen
文摘Objective To develop and validate clinical predictive models for identifying poor short-term response to recombinant human growth hormone (rhGH) treatment in children with short stature.Methods A retrospective analysis was conducted on 118 children diagnosed with growth hormone deficiency or idiopathic short stature who were treated at the First Affiliated Hospital of Zhengzhou University and two other hospitals between January 1,2020,and January 1,2024.
基金supported in part by fellowship award from the China Scholarship Council to Yuan Wei
文摘The first decade since the completion of the Human Genome Project has been marked with rapid development of genomic technologies and their immediate clinical applications. Genomic analysis using oligonucleotide array comparative genomic hybridization （aCGH） or single nucleotide polymorphism （SNP） chips has been applied to pediatric patients with developmental and intellectual disabilities （DD/ ID）, multiple congenital anomalies （MCA） and autistic spectrum disorders （ASD）. Evaluation of analytical and clinical validities of aCGH showed 〉 99% sensitivity and specificity and increased analytical resolution by higher density probe coverage. Reviews of case series, multi-center comparison and large patient-control studies demonstrated a diagnostic yield of 12%--20%; approximately 60% of these abnormalities were recurrent genomic disorders. This pediatric experience has been extended toward prenatal diagnosis. A series of reports indicated approximately 10% of pregnancies with ultrasound-detected structural anomalies and normal cytogenetic findings had genomic abnormalities, and 30% of these abnormalities were syndromic genomic disorders. Evidence-based practice guidelines and standards for implementing genomic analysis and web-delivered knowledge resources for interpreting genomic findings have been established. The progress from this technology-driven and evidence-based genomic analysis provides not only opportunities to dissect disease-causing mechanisms and develop rational therapeutic interventions but also important lessons for integrating genomic sequencing into pediatric and prenatal genetic evaluation.
