{"id":"W2979284462","doi":"10.2196/15980","title":"Cohort Selection for Clinical Trials From Longitudinal Patient Records: Text Mining Approach","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Context (archaeology); Clinical trial; Task (project management); Medical record; Executable; Natural language processing; Artificial intelligence; Selection (genetic algorithm); Psychological intervention; Medicine; Information retrieval; Data mining; Nursing","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":[],"consensus_categories":[],"category_scores_codex":[0.007342878,0.0002062787,0.0007631587,0.0001151724,0.0001253071,0.0001529274,0.0008381767,0.0004210483,0.0002052697],"category_scores_gemma":[0.0042993,0.0001626901,0.000236429,0.0003231479,0.00005479521,0.0004996488,0.0002835886,0.0007780297,0.0001582411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008864115,"about_ca_system_score_gemma":0.0004036855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006808592,"about_ca_topic_score_gemma":0.000007089175,"domain_scores_codex":[0.995066,0.0006421609,0.002419133,0.0003258415,0.001114496,0.0004323945],"domain_scores_gemma":[0.9941871,0.00370735,0.0009114062,0.0005587304,0.0002039261,0.0004314419],"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":[0.00007366334,0.0001860439,0.4810789,0.000310759,0.0001059652,0.000001103848,0.004958655,0.00009658044,4.99776e-7,0.001453592,0.02422931,0.4875049],"study_design_scores_gemma":[0.001049914,0.0006280464,0.02545458,0.0001301996,0.00001697002,0.00001772134,0.0004200379,0.943043,0.000004952475,0.0002026009,0.02879974,0.0002322377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5051977,0.00004264548,0.4873956,0.0006362956,0.001972394,0.001868791,0.00001099292,0.000262326,0.002613263],"genre_scores_gemma":[0.4860599,0.00006061067,0.5086867,0.003217691,0.001050508,0.0005124669,0.0001583217,0.00003093168,0.0002229081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9429464,"threshold_uncertainty_score":0.6634311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131650521275603,"score_gpt":0.4321035775214888,"score_spread":0.3189385253939285,"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."}}