{"id":"W4307185864","doi":"10.21203/rs.3.rs-2136402/v1","title":"Leveraging Machine Learning Approaches for Predicting Potential Lyme Disease Cases and Incidence Rates in United States Using Twitter","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Viral Infections and Vectors","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Lyme disease; Artificial intelligence; Machine learning; Word2vec; Support vector machine; Computer science; LYME; Logistic regression; Natural language processing; Medicine; Embedding; Borrelia burgdorferi","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010265,0.0005626844,0.0003855878,0.004122735,0.0003383915,0.0009172519,0.0004067188,0.0005794877,0.001081912],"category_scores_gemma":[0.004196256,0.0001670338,0.0005226944,0.001845599,0.0001547136,0.001290487,0.00056518,0.0006131568,0.0009795878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005289168,"about_ca_system_score_gemma":0.0004132954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007498506,"about_ca_topic_score_gemma":0.0123499,"domain_scores_codex":[0.9995446,0.0001476346,0.00005802589,0.0001156728,0.00008374443,0.00005028331],"domain_scores_gemma":[0.9976323,0.001455869,0.0003480315,0.0001062657,0.0003521931,0.0001054229],"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":[0.0005586249,0.0007420047,0.6475663,0.0003775684,0.0003483542,0.0003760807,0.000404584,0.1014162,0.004690372,0.000822599,0.01125488,0.2314424],"study_design_scores_gemma":[0.00001152807,0.0001458382,0.07638902,0.00006895955,0.00005403104,0.0001071853,0.00049252,0.9166386,0.002125281,0.001451817,0.002488049,0.00002725428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9536948,0.001085895,0.02715145,0.001708873,0.0001816945,0.0001517625,0.009997294,0.001028434,0.004999851],"genre_scores_gemma":[0.9784303,0.0003018802,0.01352052,0.0001237227,0.0001391784,0.00006784934,0.006437192,0.00002217328,0.0009572876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007498506,"threshold_uncertainty_score":0.01490968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2108972967479404,"score_gpt":0.4268476427160025,"score_spread":0.215950345968062,"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."}}