{"id":"W4402852726","doi":"10.1101/2024.09.23.24314186","title":"Cascaded Multimodal Deep Learning in the Differential Diagnosis, Progression Prediction, and Staging of Alzheimer’s and Frontotemporal Dementia","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Sächsische Aufbaubank; Eisai; Deutsche Forschungsgemeinschaft; Mrs Gladys Row Fogo Charitable Trust; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Frontotemporal dementia; Dementia; Differential diagnosis; Psychology; Artificial intelligence; Neuroscience; Medicine; Cognitive psychology; Computer science; Internal medicine; Disease; Pathology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002550453,0.0007901709,0.0004432799,0.0007734508,0.000248985,0.0005651806,0.0006284976,0.0007322723,0.0007543065],"category_scores_gemma":[0.004426205,0.0002742838,0.000816321,0.0003979272,0.0003792685,0.0008566632,0.001303725,0.00106148,0.0002013706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000696766,"about_ca_system_score_gemma":0.0007253434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00682634,"about_ca_topic_score_gemma":0.00732507,"domain_scores_codex":[0.9995155,0.0002008234,0.00002864413,0.0001330387,0.00006583449,0.00005608388],"domain_scores_gemma":[0.9992237,0.0004601243,0.00008385418,0.0000691161,0.0001006964,0.00006249344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002127155,0.0006692488,0.06250818,0.0002776635,0.0005523138,0.0007778918,0.0005874527,0.4303967,0.02677738,0.003709667,0.003494456,0.468122],"study_design_scores_gemma":[0.00001860987,0.0001602747,0.006254015,0.00002101723,0.00006417849,0.0001085192,0.00004751726,0.9847712,0.004795118,0.003350986,0.0003898408,0.00001872152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6841742,0.001747925,0.3092409,0.0008404806,0.0001095219,0.0001437322,0.0006277622,0.001206505,0.001909057],"genre_scores_gemma":[0.9712366,0.0001570581,0.0276624,0.0001091976,0.00002189188,0.00003525713,0.0002968055,0.00001625841,0.0004643614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00682634,"threshold_uncertainty_score":0.01357323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0269480623055687,"score_gpt":0.3344697299000318,"score_spread":0.3075216675944631,"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."}}