{"id":"W4379380826","doi":"10.1101/2023.05.26.23290608","title":"Feature Selection for an Explainability Analysis in Detection of COVID-19 Active Cases from Facebook User-Based Online Surveys","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agencia Estatal de Investigación; European Commission; European Regional Development Fund; Comunidad de Madrid","keywords":"Random forest; Machine learning; Artificial intelligence; Gradient boosting; Receiver operating characteristic; Computer science; Feature selection; Boosting (machine learning); Binary classification; Feature (linguistics); Metric (unit); Tree (set theory); Data mining; Support vector machine; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002403286,0.0004518859,0.001327117,0.001547728,0.0001040483,0.00003111978,0.0002332481,0.0007447813,0.00005551931],"category_scores_gemma":[0.01005963,0.0004667312,0.0005832121,0.001639099,0.0001137067,0.00008190477,0.0001349151,0.0008966067,0.00000256428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002080265,"about_ca_system_score_gemma":0.001578708,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04463397,"about_ca_topic_score_gemma":0.2604946,"domain_scores_codex":[0.9957233,0.001470688,0.0006064745,0.001360626,0.0004881091,0.0003508079],"domain_scores_gemma":[0.9933136,0.004258283,0.0005597274,0.001015316,0.0005539773,0.0002990595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001787818,0.001382904,0.9125109,0.001728714,0.001127615,0.00004506392,0.0009223184,0.06262945,0.01452387,5.832242e-7,0.0003587781,0.002981937],"study_design_scores_gemma":[0.002105154,0.0006145236,0.9030981,0.0002353817,0.002368928,0.000001913091,0.0003318103,0.04356658,0.04479375,0.0001774557,0.002306931,0.0003994768],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9447235,0.00003781551,0.0425561,0.006892791,0.0003177511,0.002953466,0.002211017,0.0003068463,7.034846e-7],"genre_scores_gemma":[0.9923842,0.00002504596,0.001214065,0.0009939091,0.0002053692,0.0009960982,0.003999574,0.00008201812,0.00009974784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2158606,"threshold_uncertainty_score":0.9997784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1136302867478259,"score_gpt":0.3990870075844862,"score_spread":0.2854567208366603,"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."}}