Results 191 to 200 of about 95,729 (269)

An explainable AI-driven hybrid feature selection approach for coronary artery disease diagnosis. [PDF]

Sci Rep
Elemam T, Refaat H, Makhlouf M.
europepmc   +1 more source

Metabolic Signatures and Diagnostic Prediction Models for Coronary Artery Disease and Type 2 Diabetes Mellitus: Insights From an Exploratory Study

iNew Medicine, EarlyView.
Metabolomic & lipidomic analysis reveals metabolic overlap between CAD & T2DM, highlighting 7 key metabolites as potential biomarkers. A predictive model based on these achieves high accuracy, potentially advancing precision medicine & metabolic insights.
Zhihua Wang, Meiming Su, Ying Li, Yapei Li, Shuo Chen, Ting Peng, Hans Strijdom, Jiangang Wang, Jianping Weng, Suowen Xu   +9 more
wiley   +1 more source

Interpretable machine learning enables early and accurate detection of drug‐induced liver injury: A multicenter study with real‐world clinical translation

Interdisciplinary Medicine, EarlyView.
This study develops an interpretable gradient‐boosting model that accurately identifies drug‐induced liver injury (DILI) using routine laboratory data. The model explains key clinical features through SHapley Additive exPlanations analysis and detects DILI earlier than expert evaluation, offering a transparent and practical tool for precision ...
Jingyi Ling, Shian Zhang, Jun Lin, Zhengju Xu, Runcheng Xu, Qian Lv, Kaixiang Zhang, Sheng Liu, Jie Guo, Cheng Hua, Yin Jia, Xiaoyu Xu, Kun Qian, Shanrong Liu   +13 more
wiley   +1 more source

Predicting the risk of mental disorders using complete blood count indicators: a machine learning approach. [PDF]

Front Med (Lausanne)
Su Y, Xiong Q, Wei X, Jia K, Xie C, Zou Y.   +5 more
europepmc   +1 more source

Decoding temporal miRNA signatures of semen under in vitro exposure for forensic time since deposition estimation using machine learning‐driven modeling

Interdisciplinary Medicine, EarlyView.
This study develops a novel miRNA‐based framework for estimating the time since deposition of semen stains, combining small RNA sequencing with machine learning. Time‐dependent miRNA modules were identified using Mfuzz clustering and WGCNA, followed by a multi‐stage feature selection pipeline that reduced 261 candidate miRNAs to a minimal 7‐miRNA panel.
Meiming Cai, Qiong Lan, Tong Xie, Qinglin Liu, Ming Zhao, Xiaolian Wu, Xin Shi, Ruonan Shen, Yiman Wu, Chen Mao, Bin Cong, Bofeng Zhu   +11 more
wiley   +1 more source

Comparative machine learning to predict acute kidney injury in traumatic brain injury: a MIMIC-IV cohort with SHAP interpretation. [PDF]

Front Med (Lausanne)
Gu Z, Qian K, Wang X, Li M, Zhang B.
europepmc   +1 more source

Magnetocardiography combined with machine learning for pulmonary hypertension detection and improved short‐term risk assessment

Interdisciplinary Medicine, EarlyView.
Magnetocardiography (MCG) enables non‐invasive mapping of cardiac magnetic fields. In this study, an MCG‐based machine learning model detects pulmonary hypertension with robust performance. Furthermore, MCG features may improve the accuracy of short‐term risk assessment.
Yuankun Qi, Jiaqi Liang, Kai Ma, Xiaoyu Hu, Yu Zhang, Xiaole Han, Dong Xu, Xu Zhang, Xiaopei Cui, Min Xiang, Hongyu Zhang, Jiancheng Fang   +11 more
wiley   +1 more source

Advanced machine learning approaches for predicting Neglected Tropical Disease co-endemicity in Kenya: A focus on soil-transmitted helminths, schistosomiasis, and lymphatic filariasis. [PDF]

PLoS Negl Trop Dis
Nyerere N, Mulwa DF.
europepmc   +1 more source

Deep Learning‐Based Skin Lesion Classification

Journal of Ultrasound in Medicine, EarlyView.
High‐frequency ultrasound (HFUS) is valuable for assessing skin lesions, supporting diagnosis, treatment monitoring, and surgical planning. This study evaluates deep learning models for binary classification of HFUS images acquired in B‐mode and Doppler mode.
Isabela Rocha Veiga da Silva, André Gonçalves Jardim, Giulia Rita de Souza Faés, Thatiane Alves Pianoschi Alva, Carla Diniz Lopes Becker, Viviane Rodrigues Botelho   +5 more
wiley   +1 more source