{"id":"W3120661261","doi":"10.1016/j.msard.2021.102740","title":"Predicting falls and injuries in people with multiple sclerosis using machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"Multiple Sclerosis and Related Disorders","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Machine learning; Decision tree; Medicine; Artificial intelligence; Algorithm; Falling (accident); Confusion; Multiple sclerosis; Recall; Scale (ratio); Expanded Disability Status Scale; Computer science; Psychology; Psychiatry; Cognitive psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007356773,0.0005621559,0.0007352007,0.002685121,0.0003822644,0.0008444931,0.0003512792,0.0008746081,0.0008890849],"category_scores_gemma":[0.003907942,0.0001917035,0.0008045128,0.001027417,0.000160684,0.0005197832,0.0005083387,0.000629404,0.0002362709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003640777,"about_ca_system_score_gemma":0.0005058296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009355992,"about_ca_topic_score_gemma":0.009423777,"domain_scores_codex":[0.9996535,0.0000693247,0.00006935314,0.0000673676,0.00008593364,0.00005461624],"domain_scores_gemma":[0.998943,0.0005075895,0.0002140806,0.00003458729,0.0002136713,0.00008703541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003256218,0.0004553638,0.9359968,0.00004735991,0.0002406748,0.0001189417,0.00003709407,0.01880404,0.0002706888,0.00008771642,0.0007539177,0.04286187],"study_design_scores_gemma":[0.00005877916,0.0004309285,0.4987535,0.0001002592,0.0002120681,0.0004163992,0.0003354994,0.496539,0.0005055098,0.002235314,0.0003886442,0.00002403401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920118,0.0006487046,0.005392224,0.0003253578,0.00003792952,0.00004350773,0.0008073567,0.000069266,0.000663826],"genre_scores_gemma":[0.9954567,0.0002844557,0.003033063,0.00003665868,0.00003808672,0.00002389374,0.0008301169,0.000003032728,0.0002939777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009355992,"threshold_uncertainty_score":0.01860309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02901582879710924,"score_gpt":0.2763994065536786,"score_spread":0.2473835777565694,"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."}}