{"id":"W4386153521","doi":"10.1002/jmv.29036","title":"Long‐term SARS‐CoV‐2 neutralizing antibody level prediction using multimodal deep learning: A prospective cohort study on longitudinal data in Wuhan, China","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Virology","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; Wuhan Municipal Science and Technology Bureau; Tongji University; National Natural Science Foundation of China","keywords":"Medicine; Cohort; Receiver operating characteristic; Imputation (statistics); Interpretability; Prospective cohort study; Antibody; Immunology; Artificial intelligence; Virology; Internal medicine; Machine learning; Computer science; Missing data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001968983,0.0006842261,0.0006345707,0.0007238073,0.0006730619,0.0005047118,0.001073425,0.0006064964,0.0007839361],"category_scores_gemma":[0.002441486,0.0004208488,0.0009493613,0.0007530191,0.0004100599,0.0004587679,0.0009373865,0.00103211,0.0001968088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542394,"about_ca_system_score_gemma":0.002000627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.118199,"about_ca_topic_score_gemma":0.08287935,"domain_scores_codex":[0.9994568,0.000127801,0.00003659954,0.000183944,0.00006851572,0.0001263501],"domain_scores_gemma":[0.9987504,0.0001732995,0.0001548055,0.000290263,0.0003670203,0.0002641413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002157694,0.0001807272,0.9909367,0.00001871671,0.0003197581,0.0003042319,0.0002693619,0.00136376,0.0004803736,0.0001263918,0.001011176,0.004773074],"study_design_scores_gemma":[0.00003511276,0.0001881864,0.9709315,0.00001692413,0.0001993904,0.0001840911,0.0004914248,0.02664698,0.0002702964,0.0002162058,0.000785272,0.00003456097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983945,0.00006420638,0.000499047,0.00008987473,0.000006311196,0.00001491717,0.000831496,0.000009398364,0.00009027357],"genre_scores_gemma":[0.9965422,0.00006841188,0.0004696836,0.0000527534,0.00001126214,0.00004653993,0.002412974,0.000007133231,0.0003890423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.118199,"threshold_uncertainty_score":0.2350221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440714102192658,"score_gpt":0.4585990679145363,"score_spread":0.3145276576952704,"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."}}