{"doi":"10.1017/dmp.2025.10179","title":"Deep Learning-based Gait Recognition and Evaluation of the Wounded","abstract":"<h4>Objectives</h4>Remote injury assessment during natural disasters poses major challenges for healthcare providers due to the inaccessibility of disaster sites. This study aimed to explore the feasibility of using artificial intelligence (AI) techniques for rapid assessment of traumatic injuries based on gait analysis.<h4>Methods</h4>We conducted an AI-based investigation using a dataset of 4500 gait images across 3 species: humans, dogs, and rabbits. Each image was categorized as either normal or limping. A deep learning model, YOLOv5-a state-of-the-art object detection algorithm-was trained to identify and classify limping gait patterns from normal ones. Model performance was evaluated through repeated experiments and statistical validation.<h4>Results</h4>The YOLOv5 model demonstrated high accuracy in distinguishing between normal and limp gaits across species. Quantitative performance metrics confirmed the model's reliability, and qualitative case studies highlighted its potential application in remote, fast traumatic assessment scenarios.<h4>Conclusions</h4>The use of AI, particularly deep convolutional neural networks like YOLOv5, shows promise in enabling fast, remote traumatic injury assessment during disaster response. This approach could assist healthcare professionals in identifying injury risks when physical access to patients is restricted, thereby improving triage efficiency and early intervention.","journal":"Disaster Medicine and Public Health Preparedness","year":2025,"id":200,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0879,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1641,"name":"Ling-Hu Cai","orcid":null,"position":1,"is_corresponding":false},{"id":1642,"name":"Yi-Fei Shen","orcid":null,"position":2,"is_corresponding":false},{"id":1643,"name":"Zhuo Li","orcid":"0000-0002-8184-6678","position":3,"is_corresponding":false},{"id":1644,"name":"Zhi-Jian He","orcid":null,"position":4,"is_corresponding":false},{"id":1645,"name":"Xiang-Yu Chen","orcid":null,"position":5,"is_corresponding":false},{"id":1646,"name":"Liang Zhang","orcid":null,"position":6,"is_corresponding":false},{"id":1647,"name":"Yi Zhang","orcid":"0000-0002-2789-0811","position":7,"is_corresponding":false},{"id":1648,"name":"Yao Xiao","orcid":"0000-0003-2316-692X","position":8,"is_corresponding":false},{"id":1649,"name":"Feng Zeng","orcid":null,"position":9,"is_corresponding":false},{"id":1650,"name":"Minghua Liu","orcid":null,"position":10,"is_corresponding":false},{"id":1640,"name":"Chuanchuan Liu","orcid":null,"position":0,"is_corresponding":true}],"reference_count":33,"raw_metadata":null,"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}