Music taste reveals almost nothing about your mental health, machine learning benchmark shows
A rigorous machine learning benchmark of a widely reused music survey finds that genre preferences and listening habits explain at ...
A rigorous machine learning benchmark of a widely reused music survey finds that genre preferences and listening habits explain at ...
A retrospective single-centre study found that XGBoost, random forest and LightGBM models classified preoperative anxiety in 271 femoral neck fracture ...
A new study shows that a conventional Random Forest, adjusted with an upper-quantile correction, outperformed boosting and deep tabular models ...
A retrospective study of 519 thoracic surgery patients found that a random forest model predicted intraoperative oxygenation impairment during one-lung ...
A multicenter case-control study in Henan Province, China, reports an interpretable XGBoost model that distinguishes active pulmonary tuberculosis from latent ...
A retrospective study of 1,012 children found that XGBoost predicted late-onset PICU infection risk with a test-set AUC of 0.839, ...
A study of 5,000 Turkish tweets found that SHAP offered detailed feature attributions while local LLM explanations were clearer, with ...
An Android screening app trained on Indonesian survey data used XGBoost and SHAP to explain dysglycemia risk, achieving a 0.72 ...
A proof-of-concept study reports that a two-stage deep learning pipeline analyzing video of breast crawl sessions can grade newborn crawl ...
A two-flight UAV framework combining pre-season bare-soil imagery with pod-filling canopy indices modestly improved field-scale soybean yield prediction in Northeast ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine