{"id":"W2761866725","doi":"10.2196/mhealth.8201","title":"Fall Detection in Individuals With Lower Limb Amputations Using Mobile Phones: Machine Learning Enhances Robustness for Real-World Applications","year":2017,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"mHealth; Robustness (evolution); Computer science; Artificial intelligence; Mobile phone; Physical medicine and rehabilitation; Human–computer interaction; Computer vision; Machine learning; Medicine; Psychological intervention; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001048066,0.0007160747,0.0005694135,0.0008870144,0.0002538251,0.0007112721,0.0004518203,0.0007169881,0.0009436036],"category_scores_gemma":[0.003550217,0.0001715835,0.0005067746,0.0004395669,0.0002428433,0.0005711463,0.0005138529,0.0005958073,0.0005587925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003305805,"about_ca_system_score_gemma":0.000308331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002888787,"about_ca_topic_score_gemma":0.003054978,"domain_scores_codex":[0.9995891,0.00009636376,0.00003322027,0.0001170179,0.0001042562,0.00006001112],"domain_scores_gemma":[0.9986045,0.0007214121,0.0001466787,0.0001384884,0.0003241921,0.00006487318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001148409,0.0007410658,0.1743536,0.0002467614,0.0004164022,0.0006419981,0.0002267665,0.1712879,0.03888255,0.0003834526,0.003047822,0.6086231],"study_design_scores_gemma":[0.00001449623,0.000515875,0.06667409,0.00004227103,0.00007024995,0.0003663667,0.00009888943,0.9231084,0.00757071,0.000666656,0.0008373078,0.00003474698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8576316,0.0011934,0.136345,0.0006716925,0.000141277,0.000162052,0.0003849019,0.001261353,0.00220878],"genre_scores_gemma":[0.9756917,0.0002028538,0.02315632,0.00007993767,0.00003558343,0.00004097695,0.0002406312,0.00001262631,0.0005393501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002888787,"threshold_uncertainty_score":0.00574398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02779344436051441,"score_gpt":0.341511451177986,"score_spread":0.3137180068174716,"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."}}