{"id":"W4415526077","doi":"10.2196/85624","title":"Peer Review of “Interactive Evaluation of an Adaptive-Questioning Symptom Checker Using Standardized Clinical Vignettes (Preprint)”","year":2025,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"MEDLINE; Reliability (semiconductor); Data collection; Quality of life (healthcare)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009146905,0.0001318132,0.0008122562,0.00008953255,0.00003029853,0.000007147511,0.00009215411,0.000130654,0.0003716311],"category_scores_gemma":[0.2332034,0.0001101317,0.0002509665,0.000266708,0.0001426472,0.00007762144,0.00005867264,0.0002748435,0.000005004651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001296676,"about_ca_system_score_gemma":0.0007577633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007394228,"about_ca_topic_score_gemma":0.000004754907,"domain_scores_codex":[0.9965869,0.0006618467,0.001085789,0.0003413217,0.001179549,0.0001446191],"domain_scores_gemma":[0.9874511,0.006270525,0.0005380065,0.0005273742,0.005075017,0.00013792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008984725,0.005775802,0.1620324,0.004699439,0.002580842,0.00003761126,0.001305824,0.0006121723,0.006565115,0.002947445,0.03387862,0.77058],"study_design_scores_gemma":[0.01941557,0.002401453,0.5545044,0.3361984,0.006632042,0.00002916046,0.0007192009,0.05456099,0.01759044,0.002194951,0.005246603,0.0005067589],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794495,0.003607947,0.003502254,0.004538385,0.0004754017,0.0015325,0.00002304516,0.00004844139,0.006822488],"genre_scores_gemma":[0.985765,0.0007226845,0.01142438,0.0008641083,0.0001267796,0.00005284828,0.00007054072,0.000016914,0.0009567645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7700732,"threshold_uncertainty_score":0.7732556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112590480294335,"score_gpt":0.5112773889591795,"score_spread":0.3986869086648445,"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."}}