{"id":"W4206200000","doi":"10.2196/32724","title":"Prediction of Physical Frailty in Orthogeriatric Patients Using Sensor Insole–Based Gait Analysis and Machine Learning Algorithms: Cross-sectional Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Frailty in Older Adults","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Gait; Machine learning; Stairs; Cross-validation; Stair climbing; Random forest; Test (biology); Physical medicine and rehabilitation; Cross-sectional study; Computer science; Medicine; Physical therapy; Algorithm; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006702456,0.0001841951,0.0005282234,0.0007558506,0.0001725513,0.00002244501,0.000117401,0.0001084914,0.0002763202],"category_scores_gemma":[0.000435681,0.0001686117,0.0001408579,0.001659313,0.0001305135,0.0001797962,0.0002098009,0.0009440738,0.000002089564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002139562,"about_ca_system_score_gemma":0.0001863275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001833482,"about_ca_topic_score_gemma":0.00002098699,"domain_scores_codex":[0.9964056,0.0001606868,0.001065078,0.0001851969,0.001928474,0.0002549669],"domain_scores_gemma":[0.9988323,0.0002013884,0.0003600605,0.0002167287,0.0001657493,0.0002237452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001560604,0.001674412,0.9856774,0.0001607201,0.0002145792,0.00001421642,0.003871186,0.005298234,0.00001636857,0.000001142388,0.000009281998,0.002906402],"study_design_scores_gemma":[0.003330675,0.00076849,0.5435485,0.00001626693,0.0001399743,0.000008460431,0.0007743547,0.4512632,0.00001162206,0.00000147778,0.00006761352,0.00006943195],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975303,0.00001036891,0.001297777,0.00002406215,0.0001008563,0.0007362053,0.0001637245,0.00005403004,0.00008266518],"genre_scores_gemma":[0.9981419,0.000002294666,0.001076922,0.0001219464,0.00007979244,0.00006699999,0.0004585515,0.000016115,0.00003551078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.445965,"threshold_uncertainty_score":0.6875786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03308542034136721,"score_gpt":0.3204782670081959,"score_spread":0.2873928466668287,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}