{"id":"W2967730738","doi":"10.1037/pas0000764","title":"Scoring algorithms for a computer-based cognitive screening tool: An illustrative example of overfitting machine learning approaches and the impact on estimates of classification accuracy.","year":2019,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Saskatchewan","funders":"Canadian Institutes of Health Research; University of Toronto; Consortium canadien en neurodégénérescence associée au vieillissement","keywords":"Overfitting; Logistic regression; Machine learning; Decision tree; Artificial intelligence; Medical diagnosis; Cross-validation; Regression; Psychology; Statistics; Computer science; Mathematics; Medicine; Artificial neural network","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1263505,0.002393249,0.001884168,0.00502543,0.001947381,0.004606779,0.003613089,0.003813213,0.00169276],"category_scores_gemma":[0.3840478,0.00109592,0.001624011,0.006314298,0.003167557,0.00338197,0.002913393,0.004928021,0.001393545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002442706,"about_ca_system_score_gemma":0.002294558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006505,"about_ca_topic_score_gemma":0.006912726,"domain_scores_codex":[0.8878257,0.08370505,0.00593682,0.005898886,0.01595779,0.0006756785],"domain_scores_gemma":[0.5990905,0.3327075,0.01476417,0.02450065,0.02820709,0.0007302132],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009193035,0.0005930142,0.1829159,0.001666182,0.001765207,0.0009084758,0.004341161,0.08489974,0.004623805,0.0260113,0.01990126,0.6714547],"study_design_scores_gemma":[0.0003116167,0.001271985,0.09919737,0.003166066,0.0005638389,0.003449785,0.001597998,0.7058761,0.01096595,0.1366964,0.03641259,0.0004902728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07360292,0.004740849,0.9098065,0.003665508,0.0004026166,0.000921762,0.0005140065,0.001743061,0.004602733],"genre_scores_gemma":[0.3103314,0.001109679,0.6820336,0.002401549,0.0001310747,0.001405675,0.0006968348,0.0005121348,0.001378112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8736495,"threshold_uncertainty_score":0.6682132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2068108851245482,"score_gpt":0.445626754101562,"score_spread":0.2388158689770138,"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."}}