Development and validation of data-driven, decision tree-based algorithms for identifying Behçet's disease in claims data.

Association between the platelet to white blood cell ratio and short term mortality in critically ill patients with atherosclerotic cardiovascular disease: A retrospective study and machine learning with external validation.

External validation of prognostic multivariable risk models for surgical site infections after open lower extremity revascularization for peripheral arterial disease.

Development and external validation of a mortality prediction model for community-dwelling adults aged ≥50 years with frailty or pre-frailty.

Artificial Intelligence Applications for Automated Data Extraction and Secondary Use of Clinical Information in Uro-oncology: A Systematic Review.

Therapeutic drug monitoring is essential for ensuring the efficacy and safety of vancomycin therapy in critically ill patients. This study aimed to develop a machine learning model for individualized prediction of vancomycin concentration-time curves in ICU patients. Adult ICU patients who received intravenous vancomycin and underwent therapeutic drug monitoring at Peking Union Medical College Hospital between January 2014 and December 2023 were retrospectively included. A total of 401 patients were randomly divided into training (n = 280) and testing (n = 121) cohorts. Individual pharmacokinetic parameters were estimated using Bayesian posterior inference and served as reference targets. Five machine learning algorithms were evaluated, and the two with the best predictive performance, Lasso Regression and LightGBM, were integrated with a one-compartment pharmacokinetic model to construct the final predictive model. In the internal testing cohort, the model achieved a mean absolute percentage error (MAPE) of 39.5% for vancomycin concentration prediction. External validation in an independent cohort of 2283 patients showed consistent performance (MAPE = 35.6%). The machine learning-based model significantly outperformed the classic pharmacokinetic model (p < 0.001) in both internal and external validations. A user-friendly software tool based on the model was also developed to facilitate clinical implementation. These findings suggest that the proposed model offers a robust and practical decision-support tool for optimizing individualized vancomycin dosing in ICU settings. Trial Registration: ClinicalTrials.gov identifier: NCT06431412.

Empirical evaluation of variability and multi-institutional generalizability of deep learning survival models: application to renal cancer CT scans.

External validation of a predictive system from the Swedish colorectal cancer registry to predict the risk of permanent stoma after rectal cancer surgery: A multicenter study in Spain.

Development and validation of interpretable machine learning models for dynamic prediction of prognosis in acute pancreatitis complicated by acute kidney injury: A multicenter study.

Development and validation of machine learning models to predict PTSD at multiple time points in hospitalized trauma patients.

Revolutionizing hepatic fibrosis staging: A machine learning approach combining clinical, biochemical, and microbiome insights.

Artificial intelligence in emergency medicine: a narrative review.

Mitigating data center bias in cancer classification: Transfer bias unlearning and feature size reduction via conflict-of-interest free multi-objective optimization.

Integrative transcriptomic and machine learning analysis identifies CDH17 and HOXC13 as robust candidate prognostic biomarkers in uveal melanoma.

Accurate positioning in lateral knee radiographs is essential for diagnostic quality but prone to inter-observer variability. Artificial intelligence (AI) may standardize quality assessment, yet its influence on radiographers' critical reasoning and decisions is unclear. The purpose of this study was to externally validate a pre-trained hybrid convolutional neural network for assessing femoral condyle alignment and to evaluate its effect on radiographers' classification performance. A previously developed AI model (Xception architecture, area under the curve [AUC] = 0.97) was applied to 400 consecutive weight-bearing lateral knee radiographs. Nine clinical diagnostic radiographers from three different institutions independently classified images as accepted or rejected according to predefined positioning criteria, first without AI support and again after a one-month wash-out period with AI assistance consisting of color-coded feedback (green = accepted, red = rejected). Reader performance was compared with a consensus reference using Chi-square tests, diagnostic accuracy measures, fixed-effects meta-analysis, and intra-/inter-reader intraclass correlation coefficients (ICC). According to the reference standard, 77.7 % of images were acceptable. The AI alone achieved 78.4 % accuracy (sensitivity 52.3 %, specificity 85.8 %). Across readers, AI support increased accepted classifications from 73.4 % to 77.2 % (P < 0.001) and correct classifications from 84.5 % to 89.8 % (P < 0.001). Sensitivity decreased while specificity increased with the use of AI. Inter-reader agreement improved from ICC 0.52 to 0.59. AI decision support modestly improved accuracy and specificity but did not override professional judgment and clinical reasoning. Radiographers maintained independent decision-making, demonstrating that experienced clinical practitioners were not overruled by AI despite real-time feedback. AI decision support can enhance radiographic quality assessment consistency while preserving radiographers' independent clinical judgment.

Contamination of organophosphate esters in soil surrounding paint factories: Machine learning-based distribution prediction and risk prioritization assessment.

External validation and recalibration of cardiovascular risk scores for prediction of 10-year risk of fatal cardiovascular disease: a prospective, observational, population-based cohort analysis of adults in Mexico City.

Development and validation of an Interpretable Machine learning model for Discriminating between benign and malignant breast cancer.

Predictions of Health-Related Quality of Life (HRQoL) outcomes could support realistic recovery expectations after breast cancer (BC) surgery. We aimed to develop and validate prediction models for HRQoL outcomes after BC surgery. We used three datasets of BC patients from Berlin, Germany; Ljubljana, Slovenia; and Rotterdam; Netherlands. We included non-metastasised patients who were surgically treated for an initial diagnosis of BC and completed pre- and postoperative validated questionnaires. We used linear mixed models to analyse 15 domains of the EORTC QLQ-C30 and EORTC QLQ-BR23 over a two-year horizon. Baseline domain score (measured pre-operatively), age, BMI, smoking, TN stage, receptor status, neoadjuvant chemotherapy, axillary surgery and surgery type (breast-conserving, mastectomy, and immediate implant-based reconstruction) were included as predictors. Predictive performance at validation was assessed by the proportion of variance explained (marginal R2; mR2). We included N=795 patients from Germany for development and N=623 from Slovenia and N=417 from Netherlands for validation. The largest proportion of variance was explained by the prediction models for sexual functioning (SF, mR2 35%), physical functioning (PF, mR2 29%), body image (BI, mR2 26%), and cognitive functioning (CF, mR2 25%). The models captured meaningfully different trends over time for different outcomes and surgery types. The predictive performance of the models was largely driven by the baseline domain score. Performance was reasonable at external validation, with r2 values of 19-33% for PF, 10-17% for CF, 15-18% for BI, and 22-28% for SF, although some other outcomes (e.g. breast symptoms and role functioning) showed miscalibration, indicating a need for recalibration. HRQoL after breast cancer surgery can be predicted using simple models with baseline domain scores and surgery type, demonstrating a new opportunity for Patient-Reported Outcome Measures (PROMs) in personalized care.

Interpretable machine learning-based prediction of liver metastasis risk in elderly patients with small cell lung Cancer: A study based on the SEER database and external validation in a Chinese cohort.