{"id":"W4416956046","doi":"10.1080/10400435.2025.2587794","title":"Machine learning model for predicting shear forces at the body-seat interface in wheelchair users: A novel approach","year":2025,"lang":"en","type":"article","venue":"Assistive Technology","topic":"Pressure Ulcer Prevention and Management","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Centres Intégré Universitaires de Santé et de Services Sociaux","funders":"","keywords":"Wheelchair; Random forest; Accelerometer; Support vector machine; Center of pressure (fluid mechanics); Range (aeronautics); Work (physics); Interface (matter)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009555646,0.0001749487,0.0002914932,0.0003893152,0.0007647242,0.000009074692,0.0004069225,0.0003003241,0.0000409713],"category_scores_gemma":[0.0005583895,0.000133659,0.00007320067,0.0004270993,0.0001383358,0.00007677438,0.001038512,0.0008024604,0.00002032444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002949993,"about_ca_system_score_gemma":0.00007778026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001312125,"about_ca_topic_score_gemma":0.000758094,"domain_scores_codex":[0.9983637,0.0001713069,0.0004290182,0.0004408527,0.000106758,0.0004883396],"domain_scores_gemma":[0.9989688,0.0003604545,0.0001944364,0.0003580366,0.00009091589,0.00002735593],"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":[0.001048597,0.0008597276,0.6024609,0.002026175,0.0009560583,0.000003573895,0.004350872,0.03425373,0.003927887,0.2952532,0.03110063,0.02375874],"study_design_scores_gemma":[0.002314684,0.00007381554,0.009770601,0.0002877619,0.00008562989,8.502516e-7,0.00459241,0.9066899,0.0001486378,0.003421277,0.07244029,0.0001741241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01561703,0.000525493,0.9422453,0.009336118,0.0002619781,0.002624541,0.00003009272,0.0005227583,0.02883671],"genre_scores_gemma":[0.9232476,0.00003213052,0.005404236,0.0005139895,0.00001955575,0.001749942,0.00002454335,0.00002215445,0.06898589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368411,"threshold_uncertainty_score":0.5881717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04139277531850393,"score_gpt":0.3782381888871137,"score_spread":0.3368454135686098,"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."}}