Construction of a prediction and visualization system for cognitive impairment in elderly COPD patients based on self-assigning feature weights and residual evolution model DOI Creative Commons
Wenwen Cheng, Yù Chen, Xiaohui Liu

et al.

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 8

Published: Feb. 7, 2025

Assessing cognitive function in patients with chronic obstructive pulmonary disease (COPD) is crucial for ensuring treatment efficacy and avoiding moderate impairment (MCI) or dementia. We aimed to build better machine learning models provide useful tools guidance assistance COPD patients' care. A total of 863 from a local general hospital were collected screened, they separated into two groups: (356 patients) cognitively normal (507 patients). The Montreal Cognitive Assessment (MoCA) was used test function. swarm intelligence optimization algorithm (SIOA) direct feature weighting hyperparameter optimization, which considered simultaneous activities. self-assigning weights residual evolution (SAFWRE) built on the concept linear nonlinear information fusion. best method SIOA circle search algorithm. On training set, SAFWRE's ROC-AUC 0.9727, its PR-AUC 0.9663; receiver operating characteristic-area under curve (ROC-AUC) 0.9243, precision recall-area (PR-AUC) 0.9059, performance much superior than that control technique. In terms external data, classification prediction various are comprehensively evaluated. SAFWRE has most excellent performance, 0.8865 pr-auc 0.8299. This work develops practical visualization system based these weight attributes strong application importance promotion value.

Language: Английский

Construction of a prediction and visualization system for cognitive impairment in elderly COPD patients based on self-assigning feature weights and residual evolution model DOI Creative Commons
Wenwen Cheng, Yù Chen, Xiaohui Liu

et al.

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 8

Published: Feb. 7, 2025

Assessing cognitive function in patients with chronic obstructive pulmonary disease (COPD) is crucial for ensuring treatment efficacy and avoiding moderate impairment (MCI) or dementia. We aimed to build better machine learning models provide useful tools guidance assistance COPD patients' care. A total of 863 from a local general hospital were collected screened, they separated into two groups: (356 patients) cognitively normal (507 patients). The Montreal Cognitive Assessment (MoCA) was used test function. swarm intelligence optimization algorithm (SIOA) direct feature weighting hyperparameter optimization, which considered simultaneous activities. self-assigning weights residual evolution (SAFWRE) built on the concept linear nonlinear information fusion. best method SIOA circle search algorithm. On training set, SAFWRE's ROC-AUC 0.9727, its PR-AUC 0.9663; receiver operating characteristic-area under curve (ROC-AUC) 0.9243, precision recall-area (PR-AUC) 0.9059, performance much superior than that control technique. In terms external data, classification prediction various are comprehensively evaluated. SAFWRE has most excellent performance, 0.8865 pr-auc 0.8299. This work develops practical visualization system based these weight attributes strong application importance promotion value.

Language: Английский

Citations

0