{"id":"W3210097349","doi":"10.2196/32005","title":"Medical Needs Extraction for Breast Cancer Patients from Question and Answer Services: Natural Language Processing-Based Approach","year":2021,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Health, Labour and Welfare","keywords":"Relevance (law); Information needs; Computer science; Thematic analysis; Service (business); Breast cancer; Information retrieval; Natural language processing; Artificial intelligence; Medicine; Cancer; Psychology; World Wide Web; Qualitative research; Sociology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004214171,0.0001454514,0.0002148467,0.00006671722,0.0004617568,0.00003904488,0.00009686926,0.0002833017,0.001461671],"category_scores_gemma":[0.0000609293,0.0001163428,0.00003794614,0.0002590048,0.00003345007,0.0009160319,0.00003637582,0.0005101174,0.000007695334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002852037,"about_ca_system_score_gemma":0.001119087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002276545,"about_ca_topic_score_gemma":0.001466581,"domain_scores_codex":[0.9981983,0.0001719552,0.0006680582,0.0002667188,0.0003641646,0.0003308242],"domain_scores_gemma":[0.9984569,0.000142425,0.0003611321,0.0001646829,0.0006690392,0.0002058173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005637522,0.0003044069,0.5126892,0.006181496,0.00002154433,7.548625e-7,0.01601209,0.00001634108,0.00005069689,0.0000384747,0.00296552,0.4611557],"study_design_scores_gemma":[0.003224843,0.00002053675,0.8318006,0.001579309,0.00002908401,8.326375e-7,0.004131932,0.1191484,0.0000530375,0.00002760123,0.03972508,0.000258727],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867643,0.002805328,0.002204605,0.002878157,0.001561389,0.001509072,0.001391661,0.0001427046,0.0007427933],"genre_scores_gemma":[0.9815863,0.00005924482,0.0007251541,0.01340041,0.0007857531,0.001951291,0.001031706,0.0000194663,0.0004406452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4608969,"threshold_uncertainty_score":0.9994511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01800451693124583,"score_gpt":0.4401115837458187,"score_spread":0.4221070668145729,"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."}}