{"id":"W3003864713","doi":"10.2196/15516","title":"Machine Learning Models for the Prediction of Postpartum Depression: Application and Comparison Based on a Cohort Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Maternal Mental Health During Pregnancy and Postpartum","field":"Medicine","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Graduate Research and Innovation Projects of Jiangsu Province; Central South University; National Natural Science Foundation of China","keywords":"Feature selection; Machine learning; Random forest; Support vector machine; Artificial intelligence; Postpartum depression; Computer science; Ranking (information retrieval); Predictive modelling; Medicine; Pregnancy","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":[],"consensus_categories":[],"category_scores_codex":[0.03888384,0.0009565686,0.001157266,0.001392034,0.0004720676,0.0007208844,0.001159928,0.001012553,0.001165202],"category_scores_gemma":[0.04101374,0.0003624016,0.003125808,0.0006939423,0.0003174919,0.0006846792,0.0008011517,0.00146032,0.0001614686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007908443,"about_ca_system_score_gemma":0.001156942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01301185,"about_ca_topic_score_gemma":0.004919167,"domain_scores_codex":[0.9940012,0.00491573,0.0002439895,0.0003446015,0.0003480938,0.0001463099],"domain_scores_gemma":[0.9469284,0.04561775,0.001165016,0.003195775,0.002543058,0.0005499594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01676841,0.003396952,0.749216,0.0002992171,0.007480574,0.0004785144,0.000555491,0.1224077,0.0007000994,0.001102039,0.002427421,0.09516748],"study_design_scores_gemma":[0.00150441,0.009939687,0.209377,0.0001592601,0.002452953,0.0003948375,0.0004915561,0.7723045,0.0007933873,0.001364429,0.001098296,0.0001196263],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771444,0.001057444,0.01997035,0.0002413653,0.0001179628,0.0004504117,0.0006059435,0.0000847862,0.0003272541],"genre_scores_gemma":[0.9865308,0.0004459218,0.01179865,0.00004268984,0.00003531327,0.0003183403,0.0005955198,0.00001286212,0.00021988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03888384,"threshold_uncertainty_score":0.2056399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03812021716726826,"score_gpt":0.3268525918423547,"score_spread":0.2887323746750864,"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."}}