{"id":"W4223941278","doi":"10.21203/rs.3.rs-1550479/v1","title":"A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer’s Disease","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Regione Puglia; F. Hoffmann-La Roche; Biogen; BioClinica; European Regional Development Fund; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Neuropsychology; Dementia; Neurocognitive; Disease; Cognition; Reliability (semiconductor); Psychology; Multivariate statistics; Cognitive impairment; Multivariate analysis; Alzheimer's disease; Neuropsychological test; Clinical psychology; Cognitive psychology; Medicine; Machine learning; Computer science; Psychiatry; Internal medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008498511,0.0003270858,0.0006588059,0.0004464513,0.0003749116,0.00008135964,0.0003685041,0.0001692644,0.001189125],"category_scores_gemma":[0.006513092,0.0002514088,0.0001877452,0.000880775,0.002205017,0.00007269953,0.003882728,0.002169593,0.000004064867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000218886,"about_ca_system_score_gemma":0.001447259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008515806,"about_ca_topic_score_gemma":0.00003141632,"domain_scores_codex":[0.9929143,0.002066419,0.0007590117,0.001110592,0.002357393,0.0007923499],"domain_scores_gemma":[0.9934493,0.002713008,0.0001745749,0.0009973339,0.001737276,0.0009284953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.03288132,0.004360254,0.9029421,0.01977767,0.001078461,0.000192358,0.009926283,0.0003022182,0.0003197086,0.001959434,0.0005715202,0.0256887],"study_design_scores_gemma":[0.0006247096,0.006146211,0.8881689,0.005893987,0.000606531,0.000004758328,0.0454984,0.002453979,0.01055915,0.03945203,0.0001346462,0.0004567024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835444,0.002565277,0.0005496126,0.004627325,0.00006294818,0.007616073,0.0006614451,0.00002233983,0.0003505751],"genre_scores_gemma":[0.9965723,0.0008794943,0.0007424895,0.00009008861,0.00005543482,0.001489077,0.00009608356,0.00003450281,0.00004050943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0374926,"threshold_uncertainty_score":0.9999938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1402864250704882,"score_gpt":0.4099339368302704,"score_spread":0.2696475117597822,"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."}}