Results 261 to 270 of about 11,307,335 (373)

Phylogeny, species delimitation and machine learning bridge the gap between DNA sequences and morphology in the lichen genus Arctomia (Arctomiaceae, Ascomycota)

TAXON, EarlyView.
Abstract This study investigates species boundaries in the lichen genus Arctomia (Arctomiaceae, Ascomycota) using an integrative approach combining molecular phylogenetics, full Bayesian population delimitation, heuristic and model‐based species delimitation, and supervised machine learning applied to morphological data.
Stefan Ekman, Måns Svensson, Martin Westberg   +2 more
wiley   +1 more source

Decoding heart failure subtypes with neural networks via differential explanation analysis. [PDF]

Brief Bioinform
Ruz Jurado M, Rodriguez Morales D, Genetzakis E, Ardakani FB, Zanders L, Fischer A, Buettner F, Schulz MH, Dimmeler S, John D.   +9 more
europepmc   +1 more source

Electronic health records improve the diagnosis and prognosis of pulmonary fungal infections in lung cancer patients

VIEW, EarlyView.
Pulmonary fungal infections are life‐threatening complications in lung cancer patients, posing significant challenges in clinical management. To address this, we developed machine learning tools that translate routine electronic health record data into actionable insights for diagnosing infections and assessing prognosis.
Hongwei Meng, Jiayun Yang, Shouzhi Yang, Ayizekeranmu Yiming, Wenjun Yu, Yuewei Zhao, Chunmeng Ding, Kexin Meng, Si Gao, Yang Li, Nan Dan, Dandan Feng, Yunhua Xu, Lin Huang, Yongxia Qiao   +14 more
wiley   +1 more source

Transforming acute exacerbations of chronic obstructive pulmonary disease (AECOPD) risk assessment: A multi‐algorithm machine learning approach for precise clinical phenotyping

VIEW, EarlyView.
We addressed the clinical need for individualized early identification of AECOPD by analyzing a longitudinal cohort of 878 COPD patients (20072024) and benchmarking 91 algorithms, yielding an interpretable ensemble model (AECOPD‐RS). The model showed strong performance (C‐index 0.815; validation 1/3/5‐year AUCs 0.864/0.865/0.855), with SHAP/VIMP ...
Yiqun Dong, Junyi Shen, Chaofan Fan, Anqi Lin, Peng Luo, Xin Chen   +5 more
wiley   +1 more source

An incentive-aware federated bargaining approach for client selection in decentralized federated learning for IoT smart homes. [PDF]

Sci Rep
L JV.
europepmc   +1 more source

Shapley value-based cost allocation for Battery Energy Storage Systems in Power Grids with a High Share of Renewables [PDF]

Rebecca Bauer, Xinliang Dai, Frederik Zahn, Veit Hagenmeyer   +3 more
openalex   +1 more source

A multimodal deep learning framework for predicting sunitinib response in advanced clear cell renal cell carcinoma

VIEW, EarlyView.
In this study, we constructed a prognostic model for ccRCC patients treated with Sunitinib through a deep learning‐based multimodal approach. Our CGPR model further confirms the feasibility of integrating multimodal and provides guidance for future tumor patients to receive precision therapy.
Xi Tian, Yuchen Jiang, Shuxuan Zhu, Xiaohang Liu, Aihetaimujiang Anwaier, Shiqi Ye, Kun Chang, Yuanyuan Qu, Ya‐Jia Gu, Hailiang Zhang, Dingwei Ye, Wenhao Xu   +11 more
wiley   +1 more source

Pseudo datasets estimate feature attribution in artificial neural networks. [PDF]

Sci Rep
Yang HY, Chen YH, Cheng HM, Guo CY.
europepmc   +1 more source

Pixel Lens: A Granular Assessment of Saliency Explanations

Artificial Intelligence for Engineering, EarlyView.
We propose a pipeline that detects shortcut‐dominated classifiers by comparing predictions on clean and shortcut‐perturbed images and checking dominance via a Shapley‐based ground‐truth explainer. The workflow quantifies the explanation quality of different explainable artificial intelligence (XAI) methods.
Kanglong Fan, Chen Ma, Yifan Peng, Jinglong Yang, Qilin Sun, Yuming Fang   +5 more
wiley   +1 more source