论文视频
系统性炎症反应指数与慢性肾病的关联：一项基于人群的研究
一句话总结：Li 等基于NHANES 1999-2020横断面调查，纳入41,089例美国成年人群，采用加权多变量逻辑回归和广义加性模型分析发现，全身炎症反应指数（SIRI）每升高1个单位，慢性肾脏病（CKD）风险增加23%（OR=1.23, 95%CI 1.18-1.28），且SIRI与白蛋白尿及低eGFR均
参考文献与摘要
参考文献：Xiaowan Li. Association between systemic inflammation response index and chronic kidney disease: a population-based study[J]. Introduction: Our objective was to explore the potential link between systemic inflammation response index (SIRI) and chronic kidney disease (CKD), 2024.
CKD-心血管-肾-代谢综合征0-3期患者估计葡萄糖处置率与心血管疾病风险预测之间的关系：一项全国前瞻性队列研究
一句话总结：Tian 等基于中国健康与养老追踪调查（CHARLS）的前瞻性队列研究，纳入6,752例心血管-肾脏-代谢综合征（CKM）0-3期个体，采用多变量logistic回归和限制性立方样条分析发现，与最低eGDR水平（<7.37 mg/kg/min）相比，最高eGDR水平（≥11.16 mg/kg/min
参考文献与摘要
参考文献：Jing Tian1, Hu Chen2, Yan Luo1, Zhen Zhang1, Shiqiang Xiong1,3* and Hanxiong Liu1*[J].
摘要：Background Insulin resistance is a crucial factor in the development of cardiovascular diseases (CVD), yet the relationship between the estimated glucose disposal rate (eGDR), an index reflecting insulin resistance, and the risk of new-onset CVD among individuals with cardiovascular-kidney-metabolic (CKM) syndrome stage 0–3 remains underexplored, and large-scale prospective cohort studies are needed to clarify this relationship. Methods All data for this study were extracted from the China Health and Retirement Longitudinal Study (CHARLS). The primary outcome was the incidence of new-onset CVD (including heart diseases (HD) and stroke) during the follow-up period (from 2013 to 2020). Multivariable logistic regression models were applied to elucidate the relationship between the eGDR and the risk of developing CVD. The restricted cubic splines (RCS), mediation analysis, and stratified analyses were also employed. Results This study included 6752 participants, of whom 1495 (22%) developed CVD. Odds ratios and 95% confidence intervals from lowest eGDR level (<7.37 mg/kg/min) to highest eGDR level (≥ 11.16 mg/kg/min) were 1.00 (reference), 0.81 (0.68, 0.96), 0.72 (0.58, 0.88), and 0.74 (0.58, 0.94) respectively, for the occurrence of CVD; 1.00 (reference), 0.81 (0.67,0.97), 0.72 (0.57,0.90), and 0.75 (0.58,0.97) respectively, for the occurrence of HD; 1.00 (reference), 0.91 (0.74,1.12), 0.80 (0.62,1.04), and 0.71 (0.52,0.97) respectively, for the occurrence of stroke after adjusting for all potential covariates. The RCS analysis discovered an approximately inverse “L” correlation between eGDR and the occurrence of CVD and HD across all individuals with CKM syndrome stages 0–3 (All P for overall < 0.001, All P for nonlinear = 0.005), while there was a negative linear correla
一种机器学习模型，用于利用治疗早期体重变化特征预测减重成功率
一句话总结：Shahabi 等基于三项减重试验（SMART、Opt-IN、ENGAGED，共1,058例肥胖参与者）的回顾性队列研究，采用随机森林分类器训练预测模型，并以80% SMART数据训练、20% SMART数据及另两项试验数据验证，发现模型预测6个月减重成功的AUROC达84.5%、AUPRC达86.
参考文献与摘要
参考文献：Farzad Shahabi. A machine-learned model for predicting weight loss success using weight change features early in treatment[J]. npj Digital Medicine, 2024.
利用机器学习预测南亚心血管疾病风险因素的控制医学
一句话总结：Reuter 等基于两项已完成随机对照试验的纵向数据（纳入1,502例印度和巴基斯坦城市糖尿病患者）的机器学习预测模型研究，采用随机森林分类器预测基线后1年未能达到心血管风险因素控制目标或实现有意义改善的风险，发现将预测风险评分处于最高四分位的患者识别为高危人群时，预测未达标的精确率分别为HbA1c
参考文献与摘要
参考文献：Anna Reuter. Predicting control of cardiovascular disease risk factors in South Asia using machine learning[J]. npj Digital Medicine, 2024.
比较SHAP与临床友好解释，揭示对临床决策行为的影响医学
一句话总结：Hur 等基于63名外科医生和内科医师的随机对照试验，采用反平衡设计比较三种临床决策支持系统解释方法（仅结果、SHAP解释、临床解释）对临床决策行为的影响，发现提供临床解释显著提升临床医生的接受度（优于仅结果和SHAP解释），且信任度、满意度和可用性与接受度正相关，提示在AI辅助临床决策中应优先采用
参考文献与摘要
参考文献：Sujeong Hur. Comparison of SHAP and clinician friendly explanations reveals effects on clinical decision behaviour[J]. npj Digital Medicine, 2025.
一种机器学习模型，用于利用治疗早期体重变化特征预测减重成功率
一句话总结：Shahabi 等基于三项随机对照试验（SMART、Opt-IN、ENGAGED，共1,058例肥胖个体）的机器学习模型研究，采用随机森林分类器训练并测试（80% SMART数据训练，20% SMART及另两项试验共529例验证），发现模型预测6个月减重成功的AUROC为84.5%、AUPRC为86
参考文献与摘要
参考文献：Farzad Shahabi. A machine-learned model for predicting weight loss success using weight change features early in treatment[J]. npj Digital Medicine, 2024.