Medicine & Health
456 items
In a single-center cohort of 232 papillary thyroid carcinoma patients, an SVM model predicted lymph node metastasis with validation AUC 0.849, and removing BRAF changed AUC by only 0.007
This retrospective study of 232 patients who underwent thyroid surgery at Tongling People's Hospital used LASSO to select six features from 32 candidates (BRAF mutation status, tumor size, capsular invasion, extrathyroidal invasion, multifocality, and TSH), compared seven machine learning algorithms, found the Support Vector Machine best in the validation cohort (AUC 0.849, 95% CI 0.756–0.934; accuracy 0.768), identified TSH and tumor size as the top SHAP contributors, and showed in an ablation analysis that removing BRAF lowered validation AUC from 0.849 to 0.843 (P = 0.671).
A mechanism-informed ML framework predicts polymeric long-acting injectable release with XGBoost (test R² = 0.9774) and finds predictive importance nearly uncorrelated with intervention effects (r = 0.132 and −0.021)
The study builds a mechanism-informed machine learning framework that chains a pharmaceutical-knowledge-driven directed acyclic graph, causal structure discovery (PC, NOTEARS, DirectLiNGAM), XGBoost release prediction, explainable AI (SHAP), ATE/CATE intervention-effect estimation, and counterfactual formulation analysis; on a public dataset of 181 release profiles, 3,783 fractional release measurements, and 43 drug-polymer pairs, XGBoost reached test R² = 0.9774, RMSE = 0.0491, and MAE = 0.0339, and correlation and SHAP importance agreed strongly (r = 0.761) while both agreed poorly with intervention-effect estimates (r = 0.132 and −0.021), indicating that variables useful for prediction differ from those that can be manipulated.
Across 5,298 FAERS echinocandin reports, caspofungin showed a unique DRESS signal (ROR 16.62) while caspofungin and micafungin showed exceptionally strong resistance-related signals
This pharmacovigilance study extracted 5,298 FAERS reports with echinocandins as the primary suspect drug from Q1 2004 to Q4 2025 and applied four disproportionality algorithms (ROR, PRR, IC025, EBGM05, with a positive signal requiring all four to be positive) to compare caspofungin, micafungin, anidulafungin, and rezafungin, finding a unique caspofungin-DRESS association (46 cases, ROR = 16.62, IC025 = 3.21; 31 cases with ROR = 14.89, IC025 = 3.05 in a sensitivity analysis restricted to caspofungin as the sole suspected drug) and exceptionally strong resistance-related signals for caspofungin ("pathogen resistance" ROR = 68.83; "drug resistance" ROR = 22.32) and micafungin ("bronchopulmonary aspergillosis" ROR = 71.99; "Candida infection" ROR = 23.
Clustering routine ICU data yields three overlapping HFpEF phenotypes but no phenotype-specific medication associations, with a TabPFN classifier reaching internal-validation AUCs of 0.951–0.969
In this multicohort retrospective study, K-prototypes clustering of first-24-hour ICU variables in 2,511 patients with HFpEF from MIMIC-IV produced three clinically interpretable but partially overlapping phenotypes—cardiorenal-metabolic, hypertensive-pulmonary, and low-blood-pressure/arrhythmia (K = 2 had a higher mean silhouette width than K = 3, 0.083 versus 0.060, while both showed high median resampling stability, ARI 0.940 versus 0.924)—with a graded 365-day mortality difference in the derivation cohort (38.3%, 31.5%, 23.
Across CHARLS and ELSA, pain was the strongest predictor of incident frailty in MASLD, with depressive symptoms mediating 74.0% and 46.1% of the effect
Using two prospective cohorts, the China Health and Retirement Longitudinal Study (CHARLS, 2011–2018, n=3,622) and the English Longitudinal Study of Ageing (ELSA, 2012–2020, n=2,059), this study followed middle-aged and older adults with LAP-defined MASLD and no baseline frailty, selected 14 consensus predictors from 31 candidates via LASSO, Boruta, and recursive feature elimination, and trained nine machine learning models; logistic regression performed best (internal test AUC 0.740; external validation AUC 0.753), pain was the top predictor (mean absolute SHAP 0.184), pain remained associated with incident frailty after full adjustment including baseline frailty index (CHARLS RR 1.219; ELSA RR 1.310) with PAFs of 8.01% and 11.
Across 2,907 FAERS reports on methotrexate in pediatric leukemia, nervous system disorders gave the strongest signal, febrile neutropenia was the most reported PT, and 72.1% of evaluable onsets fell within 30 days
Drawing 2,907 FAERS reports (Q1 2018–Q1 2025) in which methotrexate was the primary suspect drug for pediatric leukemia, the study applied four disproportionality methods (ROR, PRR, BCPNN, MGPS) with sex and five age strata and fitted time-to-onset with a Weibull distribution, finding that nervous system disorders had the largest SOC-level report count (1,691 cases, ROR 2.87, 95% CI 2.69–3.05), that febrile neutropenia led at the PT level (446 reports) followed by neurotoxicity (238) and mucosal inflammation (170), that confusional state, dehydration, and epistaxis showed greater reporting disproportionality in males, that six PTs were detected in all five age strata, and that 681 of 944 evaluable onset reports (72.
Repeated ChatGPT runs for the ATBC oral PDE returned values from 5 to 300 mg/day, prompting a modular, human-supervised LLM workflow for toxicological risk assessment
A collaborative working group reviewed the principles, strengths, and limits of large language models (LLMs) in toxicological risk assessment (TRA) and then used an exemplar case study, the derivation of the oral Permitted Daily Exposure (PDE) for acetyl tributyl citrate (ATBC, CAS 77-90-7) under the draft ICH Q3E guideline, testing zero-shot end-to-end prompts, structured step-guided prompts, and a document-constrained configuration with ChatGPT (GPT-5 and later GPT-5.
Review of 86 MRI-based autism AI studies: single-site accuracy reaches 99%, but leave-one-site-out validation lands near 67%
Following PRISMA, this review searched Scopus, Web of Science, and PubMed for 2015–2026 studies and included 86 Q1 journal articles, systematically mapping MRI-based machine learning and deep learning studies for autism spectrum disorder (ASD) classification across datasets, preprocessing pipelines, brain atlases, model architectures, and validation strategies; it finds fMRI is the most used modality with graph neural networks and transformers as dominant trends, and shows reported accuracy depends heavily on evaluation setup—single-site studies reach 87.4%–99.39%, the full ABIDE cohort sits around 70%–75%, and the strictest leave-one-site-out testing lands near 67%.
This short communication proposes that AI could ease seafarers' limited healthcare access, fatigue, and mental health risks through telemedicine, clinical decision support, and predictive analytics, provided data privacy, transparency, and equitable access are safeguarded.
This short communication explores the potential role of artificial intelligence in seafarers' occupational health, noting that seafarers face persistent challenges including limited access to healthcare, fatigue, and mental health risks, and suggesting that AI-enabled applications in telemedicine, clinical decision support, and predictive analytics could enhance prevention, early detection, and continuity of care at sea, while stressing that effective integration requires ethical safeguards for data privacy, transparency, and equitable access, which may contribute to safer and more resilient maritime health systems.
Page 8 · showing 10