{"id":"W4387669078","doi":"10.1186/s12911-023-02315-z","title":"Leveraging machine learning approaches for predicting potential Lyme disease cases and incidence rates in the United States using Twitter","year":2023,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Lyme disease; Incidence (geometry); Health informatics; Computer science; Machine learning; Artificial intelligence; Data science; Medicine; Public health; Virology; Nursing; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001935747,0.000162692,0.000269827,0.0003243449,0.0002680963,0.0001631399,0.0001327233,0.00006150949,0.00001448955],"category_scores_gemma":[0.004474575,0.0001077162,0.00004920158,0.000465892,0.0001224032,0.0002091126,0.000270452,0.0002537582,0.0000021436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002249749,"about_ca_system_score_gemma":0.0001284462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003882914,"about_ca_topic_score_gemma":0.00001803763,"domain_scores_codex":[0.9981184,0.00009327476,0.0006006755,0.0001750854,0.0007059061,0.0003066686],"domain_scores_gemma":[0.9954158,0.00393904,0.0001663081,0.0001869532,0.00005964154,0.0002322402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00112565,0.00007236557,0.847772,0.001800757,0.00004856666,0.0004829991,0.005811339,0.0491343,0.000004905892,0.00007289751,0.0004361378,0.09323808],"study_design_scores_gemma":[0.00115152,0.00003958595,0.0417621,0.001156483,0.00004605308,0.0001543969,0.00578373,0.9491071,7.741969e-7,0.0004834882,0.0001983328,0.0001164995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.850512,0.000314905,0.1486164,0.00007407599,0.0000502657,0.0003356282,0.00002819276,0.00005955987,0.000008995433],"genre_scores_gemma":[0.9810117,0.0002139425,0.01747538,0.0008689699,0.00007766987,0.00002173786,0.0003101796,0.00001620077,0.000004256667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8999727,"threshold_uncertainty_score":0.5356808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1093300986281306,"score_gpt":0.3594793083299754,"score_spread":0.2501492097018448,"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."}}