BACKGROUND Cancer care faces challenges due to tumor heterogeneity and rapidly evolving therapies,necessitating artificial intelligence(AI)-driven clinical decision support.While general-purpose models like ChatGPT of...BACKGROUND Cancer care faces challenges due to tumor heterogeneity and rapidly evolving therapies,necessitating artificial intelligence(AI)-driven clinical decision support.While general-purpose models like ChatGPT offer adaptability,domain-specific systems(e.g.,DeepSeek)may better align with clinical guidelines.However,their comparative efficacy in oncology remains underexplored.This study hypothesizes that domain-specific AI will outperform general-purpose models in technical accuracy,while the latter will excel in patient-centered communication.AIMS To compare ChatGPT and DeepSeek in oncology decision support for diagnosis,treatment,and patient communication.METHODS A retrospective analysis was conducted using 1200 anonymized oncology cases(2018–2023)from The Cancer Genome Atlas and institutional databases,covering six cancer types.Each case included histopathology,imaging,genomic profiles,and treatment histories.Both models generated diagnostic interpretations,staging assessments,and therapy recommendations.Performance was evaluated against NCCN/ESMO guidelines and expert oncologist panels using F1-scores,Cohen'sκ,Likert-scale ratings,and readability metrics.Statistical significance was assessed via analysis of variance and post-hoc Tukey tests.RESULTS DeepSeek demonstrated superior performance in diagnostic accuracy(F1-score:89.2%vs ChatGPT's 76.5%,P<0.001)and treatment alignment with guidelines(κ=0.82 vs 0.67,P=0.003).ChatGPT exhibited strengths in patient communi-cation,generating layman-friendly explanations(readability score:8.2/10 vs DeepSeek's 6.5/10,P=0.012).Both models showed limitations in rare cancer subtypes(e.g.,cholangiocarcinoma),with accuracy dropping below 60%.Clinicians rated DeepSeek's outputs as more actionable(4.3/5 vs 3.7/5,P=0.021)but highlighted ChatGPT's utility in palliative care discussions.CONCLUSION Domain-specific AI(DeepSeek)excels in technical precision,while general-purpose models(ChatGPT)enhance patient engagement.A hybrid system integrating both approaches may optimize oncology workflows,contingent on expanded training for rare cancers and real-time guideline updates.展开更多
Objective Great obstetrical syndrome(GOS)represents a group of pregnancy-related diseases that result in inadequate placentation.Most GOS cases end in preterm,either spontaneously or indicatively,and the use of antena...Objective Great obstetrical syndrome(GOS)represents a group of pregnancy-related diseases that result in inadequate placentation.Most GOS cases end in preterm,either spontaneously or indicatively,and the use of antenatal corticosteroids(ACS)is inevitably discussed.The placenta is an important,transient fetal-derived organ and is the embodiment of maternal or fetal well-being.However,few studies provide histological evidence of the placenta in GOS.This study aims to address these issues.Methods A total of 831 pregnant women were prospectively recruited.Placenta tissue was collected immediately and fixed with 4%paraformaldehyde solution for future H&E analysis.A novel checklist was devised to evaluate maternal vascular malperfusion sections on the basis of the commonly accepted Amsterdam placental workshop group consensus statement.Results A total of 131 patients were classified as having GOS.Comparisons between those with and without GOS revealed significant differences,including higher levels of distal villous hypoplasia,increased syncytial knots,accelerated villous maturation,and higher total scores in GOS.We found significant negative associations between GOS and neonatal weight,neonatal height,head circumference,placental surface area,placental volume,and placenta gross examination score.GOS neonates were 1.25 times more likely to have hyperbilirubinemia.Regarding the effect of ACS,a significant reduction in birthweight,height,and head circumference was observed,along with an increased risk of hyperbilirubinemia.Conclusion This study provides histological evidence of the GOS that supports the defective deep placentation hypothesis.Our research also contributes to benefit-risk consultation in the GOS,such as in cases of PE and FGR,where a balance between fetal lung maturation and short-term neonatal outcomes is crucial.展开更多
Objective Sleep is fundamental to the physical and mental health of both the general population and pregnant women.Most studies have focused on the impact of certain trimester sleep behaviors on gestational complicati...Objective Sleep is fundamental to the physical and mental health of both the general population and pregnant women.Most studies have focused on the impact of certain trimester sleep behaviors on gestational complications and birth outcomes.This study aimed to explore the association between maternal sleep duration and fetal growth development from as early as 23 gestational weeks to birth.Methods A total of 803 pregnant women were prospectively enrolled.The self-reported maternal nocturnal sleep duration during all 3 trimesters was recorded.The outcome measures were reference-population-based Z-scores of fetal biometric measurements obtained through routine ultrasonographic examination.Results Using multiple linear regression,a marginally significant negative association was observed between second-trimester sleep duration and second-trimester fetal head circumference(HC)and third-trimester fetal biparietal diameter(BPD).Then the associations of long sleep duration in each trimester with fetal biometry extreme values were evaluated.A significant impact of second-trimester long sleep duration on the second-trimester BPD below the 10th percentile of the reference population was observed.Longitudinal analysis reported similar results for BPD and HC.Conclusions Overall,a negative association between sleep duration and fetal biometric measurements was observed.Long sleep durations in the second trimester might negatively impact fetal growth,particularly brain parameters,including BPD and HC.展开更多
In today’s society, the incidence of cardiopulmonary diseases is increasing annually, seriously affecting patients’ quality of life. Therefore, developing a scientific and effective rehabilitation training program i...In today’s society, the incidence of cardiopulmonary diseases is increasing annually, seriously affecting patients’ quality of life. Therefore, developing a scientific and effective rehabilitation training program is of great significance. This study first analyzes the theoretical basis of cardiopulmonary rehabilitation training, including the effects of aerobic exercise, interval training, and strength training on cardiopulmonary function. Based on this, a comprehensive rehabilitation training program is designed, which includes personalized training plans, comprehensive interventions, multidisciplinary collaboration, patient education, and regular follow-up visits. The cardiopulmonary rehabilitation training plan developed in this study has certain scientific practicability, which provides a theoretical basis for cardiopulmonary rehabilitation training, and also provides a reference for medical institutions, rehabilitation centers and communities, which is helpful for promotion and application to a wider range of patients with cardiopulmonary diseases.展开更多
Objective: To explore nutritional support under the Neuman systems model in treating dysphagia in stroke patients. Methods: In this retrospective study, we enrolled 97 patients with dysphagia after stroke admitted to ...Objective: To explore nutritional support under the Neuman systems model in treating dysphagia in stroke patients. Methods: In this retrospective study, we enrolled 97 patients with dysphagia after stroke admitted to our hospital, and randomly divided them into the Neuman group (n = 51) given nursing intervention based on Neuman systems model and a control group (n = 46) given routine nursing intervention. Both groups received nutritional support for 3 months. Nutritional indexes (serum total protein, plasma albumin, serum albumin, hemoglobin and transferrin levels) and immune indexes (immunoglobulin (Ig) A, IgG, IgM and total lymphocyte count (TLC) in both groups were recorded and compared. Pulmonary function recovery, video fluoroscopic swallowing study score, water swallowing test score, complication rate, and health knowledge mastery level were also compared between the two groups. Results: After the intervention, the Neuman group showed less decrease in the nutritional and immune index scores (serum total protein, plasma albumin, hemoglobin, serum albumin;IgA, IgG, IgM, and TLC;all P Conclusion: For patients with stroke and dysphagia, comprehensive nursing intervention (e.g., nutritional support) under theNeuman systems model can promote the recovery of immune, swallowing, and pulmonary function, reduce complication incidence and facilitate comprehensive rehabilitation, ensuring adequate nutritional intake.展开更多
文摘BACKGROUND Cancer care faces challenges due to tumor heterogeneity and rapidly evolving therapies,necessitating artificial intelligence(AI)-driven clinical decision support.While general-purpose models like ChatGPT offer adaptability,domain-specific systems(e.g.,DeepSeek)may better align with clinical guidelines.However,their comparative efficacy in oncology remains underexplored.This study hypothesizes that domain-specific AI will outperform general-purpose models in technical accuracy,while the latter will excel in patient-centered communication.AIMS To compare ChatGPT and DeepSeek in oncology decision support for diagnosis,treatment,and patient communication.METHODS A retrospective analysis was conducted using 1200 anonymized oncology cases(2018–2023)from The Cancer Genome Atlas and institutional databases,covering six cancer types.Each case included histopathology,imaging,genomic profiles,and treatment histories.Both models generated diagnostic interpretations,staging assessments,and therapy recommendations.Performance was evaluated against NCCN/ESMO guidelines and expert oncologist panels using F1-scores,Cohen'sκ,Likert-scale ratings,and readability metrics.Statistical significance was assessed via analysis of variance and post-hoc Tukey tests.RESULTS DeepSeek demonstrated superior performance in diagnostic accuracy(F1-score:89.2%vs ChatGPT's 76.5%,P<0.001)and treatment alignment with guidelines(κ=0.82 vs 0.67,P=0.003).ChatGPT exhibited strengths in patient communi-cation,generating layman-friendly explanations(readability score:8.2/10 vs DeepSeek's 6.5/10,P=0.012).Both models showed limitations in rare cancer subtypes(e.g.,cholangiocarcinoma),with accuracy dropping below 60%.Clinicians rated DeepSeek's outputs as more actionable(4.3/5 vs 3.7/5,P=0.021)but highlighted ChatGPT's utility in palliative care discussions.CONCLUSION Domain-specific AI(DeepSeek)excels in technical precision,while general-purpose models(ChatGPT)enhance patient engagement.A hybrid system integrating both approaches may optimize oncology workflows,contingent on expanded training for rare cancers and real-time guideline updates.
基金supported by the National Science Foundation of China(No.81873843)the National Science and Technology Pillar Program of China during the Twelfth Five-Year Plan Period(No.2014BA105B05)the Fundamental Research Funds for the Central Universities(No.2017 KFYXJJ102 and No.2019 KFYXKJC053).
文摘Objective Great obstetrical syndrome(GOS)represents a group of pregnancy-related diseases that result in inadequate placentation.Most GOS cases end in preterm,either spontaneously or indicatively,and the use of antenatal corticosteroids(ACS)is inevitably discussed.The placenta is an important,transient fetal-derived organ and is the embodiment of maternal or fetal well-being.However,few studies provide histological evidence of the placenta in GOS.This study aims to address these issues.Methods A total of 831 pregnant women were prospectively recruited.Placenta tissue was collected immediately and fixed with 4%paraformaldehyde solution for future H&E analysis.A novel checklist was devised to evaluate maternal vascular malperfusion sections on the basis of the commonly accepted Amsterdam placental workshop group consensus statement.Results A total of 131 patients were classified as having GOS.Comparisons between those with and without GOS revealed significant differences,including higher levels of distal villous hypoplasia,increased syncytial knots,accelerated villous maturation,and higher total scores in GOS.We found significant negative associations between GOS and neonatal weight,neonatal height,head circumference,placental surface area,placental volume,and placenta gross examination score.GOS neonates were 1.25 times more likely to have hyperbilirubinemia.Regarding the effect of ACS,a significant reduction in birthweight,height,and head circumference was observed,along with an increased risk of hyperbilirubinemia.Conclusion This study provides histological evidence of the GOS that supports the defective deep placentation hypothesis.Our research also contributes to benefit-risk consultation in the GOS,such as in cases of PE and FGR,where a balance between fetal lung maturation and short-term neonatal outcomes is crucial.
基金supported by the National Natural Science Foundation of China(No.81873843)the National Science and Technology Pillar Program of China during the Twelfth Five-Year Plan Period(No.2014BAI05B05)the Fundamental Research Funds for the Central Universities(No.2017KFYXJJ102 and 2019KFYXKJC053).
文摘Objective Sleep is fundamental to the physical and mental health of both the general population and pregnant women.Most studies have focused on the impact of certain trimester sleep behaviors on gestational complications and birth outcomes.This study aimed to explore the association between maternal sleep duration and fetal growth development from as early as 23 gestational weeks to birth.Methods A total of 803 pregnant women were prospectively enrolled.The self-reported maternal nocturnal sleep duration during all 3 trimesters was recorded.The outcome measures were reference-population-based Z-scores of fetal biometric measurements obtained through routine ultrasonographic examination.Results Using multiple linear regression,a marginally significant negative association was observed between second-trimester sleep duration and second-trimester fetal head circumference(HC)and third-trimester fetal biparietal diameter(BPD).Then the associations of long sleep duration in each trimester with fetal biometry extreme values were evaluated.A significant impact of second-trimester long sleep duration on the second-trimester BPD below the 10th percentile of the reference population was observed.Longitudinal analysis reported similar results for BPD and HC.Conclusions Overall,a negative association between sleep duration and fetal biometric measurements was observed.Long sleep durations in the second trimester might negatively impact fetal growth,particularly brain parameters,including BPD and HC.
文摘In today’s society, the incidence of cardiopulmonary diseases is increasing annually, seriously affecting patients’ quality of life. Therefore, developing a scientific and effective rehabilitation training program is of great significance. This study first analyzes the theoretical basis of cardiopulmonary rehabilitation training, including the effects of aerobic exercise, interval training, and strength training on cardiopulmonary function. Based on this, a comprehensive rehabilitation training program is designed, which includes personalized training plans, comprehensive interventions, multidisciplinary collaboration, patient education, and regular follow-up visits. The cardiopulmonary rehabilitation training plan developed in this study has certain scientific practicability, which provides a theoretical basis for cardiopulmonary rehabilitation training, and also provides a reference for medical institutions, rehabilitation centers and communities, which is helpful for promotion and application to a wider range of patients with cardiopulmonary diseases.
文摘Objective: To explore nutritional support under the Neuman systems model in treating dysphagia in stroke patients. Methods: In this retrospective study, we enrolled 97 patients with dysphagia after stroke admitted to our hospital, and randomly divided them into the Neuman group (n = 51) given nursing intervention based on Neuman systems model and a control group (n = 46) given routine nursing intervention. Both groups received nutritional support for 3 months. Nutritional indexes (serum total protein, plasma albumin, serum albumin, hemoglobin and transferrin levels) and immune indexes (immunoglobulin (Ig) A, IgG, IgM and total lymphocyte count (TLC) in both groups were recorded and compared. Pulmonary function recovery, video fluoroscopic swallowing study score, water swallowing test score, complication rate, and health knowledge mastery level were also compared between the two groups. Results: After the intervention, the Neuman group showed less decrease in the nutritional and immune index scores (serum total protein, plasma albumin, hemoglobin, serum albumin;IgA, IgG, IgM, and TLC;all P Conclusion: For patients with stroke and dysphagia, comprehensive nursing intervention (e.g., nutritional support) under theNeuman systems model can promote the recovery of immune, swallowing, and pulmonary function, reduce complication incidence and facilitate comprehensive rehabilitation, ensuring adequate nutritional intake.
