{"id":"W7115889060","doi":"10.2196/85614","title":"Evaluation of Few-Shot AI-Generated Feedback on Case Reports in Physical Therapy Education: Mixed Methods Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reflection (computer programming); Visual feedback; Physical activity; Action (physics); Simulated patient","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06005633,0.0009712264,0.001327338,0.002845413,0.001193162,0.001553374,0.001479051,0.001097177,0.001689333],"category_scores_gemma":[0.1047437,0.0006285404,0.001581736,0.001453573,0.001440585,0.001106913,0.001687555,0.0006419579,0.0002988444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002205021,"about_ca_system_score_gemma":0.002636255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007668677,"about_ca_topic_score_gemma":0.001871095,"domain_scores_codex":[0.9342177,0.0479326,0.006687104,0.003097911,0.007162724,0.0009020108],"domain_scores_gemma":[0.8081986,0.1402536,0.02077389,0.008423926,0.02051551,0.001834654],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.01034481,0.02372371,0.2164642,0.01501303,0.001478648,0.002296404,0.1821396,0.001805562,0.01420884,0.0009237501,0.001049541,0.5305519],"study_design_scores_gemma":[0.003977777,0.116699,0.5867426,0.008496026,0.003428532,0.00402282,0.1945773,0.0127874,0.04710671,0.002261779,0.01898048,0.0009195654],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984139,0.0006625832,0.006520851,0.00007161524,0.00003381539,0.007665921,0.0001368151,0.00002702441,0.0007424073],"genre_scores_gemma":[0.9471682,0.0009856628,0.03036579,0.0002509297,0.00008748835,0.02031359,0.0002082406,0.00002458875,0.0005955477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9399437,"threshold_uncertainty_score":0.317612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06719029324216029,"score_gpt":0.5429899308784939,"score_spread":0.4757996376363336,"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."}}