{"id":"W4390666240","doi":"10.3389/frai.2023.1334613","title":"Explaining graph convolutional network predictions for clinicians—An explainable AI approach to Alzheimer's disease classification","year":2024,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":18,"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; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Knut och Alice Wallenbergs Stiftelse; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; National Institute on Aging; Alzheimer's Association","keywords":"Neurocognitive; Computer science; Graph; Cognition; Correctness; Neuroimaging; Modalities; Node (physics); Artificial intelligence; Cognitive impairment; Disease; Cognitive psychology; Psychology; Machine learning; Medicine; Theoretical computer science; Psychiatry; Algorithm","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"],"consensus_categories":[],"category_scores_codex":[0.001535867,0.0002416434,0.0002568845,0.0004621518,0.0004863172,0.0004265027,0.001017588,0.0001489203,0.000006889565],"category_scores_gemma":[0.0003981446,0.0002672119,0.0001267715,0.001592556,0.0001107348,0.0008694089,0.0001294756,0.0005406105,0.00003272575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000173833,"about_ca_system_score_gemma":0.0004023453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007657129,"about_ca_topic_score_gemma":0.00003771065,"domain_scores_codex":[0.9967402,0.0002685791,0.0007675777,0.001115104,0.0004105463,0.0006979984],"domain_scores_gemma":[0.9982492,0.0003578358,0.00009161799,0.0006923657,0.0002066376,0.0004023844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008515096,0.0001433565,0.00279812,0.00006290663,0.00002987672,0.000006727469,0.001810927,0.3382197,0.000002494901,0.5374763,0.02845725,0.09090717],"study_design_scores_gemma":[0.00001944817,0.000116642,0.001137229,0.00009977021,0.00001898704,0.000001474667,0.0006996721,0.8713732,0.00001442676,0.1146536,0.01161891,0.0002466397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000215125,0.001428016,0.9764715,0.003074209,0.01699511,0.0009990622,0.00002947568,0.0004738592,0.0003136069],"genre_scores_gemma":[0.6255409,0.00003442326,0.3698269,0.0006297569,0.00273265,0.001038619,0.00009765726,0.00003856113,0.00006049806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6253258,"threshold_uncertainty_score":0.999978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0973616743444762,"score_gpt":0.3636093378979696,"score_spread":0.2662476635534934,"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."}}