{"id":"W4413761376","doi":"10.1101/2025.08.26.672412","title":"Predicting Alzheimer’s Disease Progression from Sparse Multimodal Data by NeuralODE Models","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"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; U.S. Department of Defense; European Commission; Meso Scale Diagnostics; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; Pfizer; Novartis Pharmaceuticals Corporation; Eisai; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Gruppo Nazionale per il Calcolo Scientifico; Biogen","keywords":"Disease; Modalities; Computer science; Machine learning; Artificial intelligence; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009484825,0.0009534659,0.000804458,0.0003036503,0.0004693291,0.0008529502,0.007257401,0.0006353966,0.00001697458],"category_scores_gemma":[0.0006441611,0.001016038,0.0001577152,0.0006747639,0.0001174743,0.001212712,0.01080009,0.002287963,0.00003290512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002176045,"about_ca_system_score_gemma":0.001814448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001743918,"about_ca_topic_score_gemma":0.00001014672,"domain_scores_codex":[0.9925601,0.0007107754,0.0009989953,0.003599414,0.001101125,0.001029573],"domain_scores_gemma":[0.9891506,0.0003223483,0.000847317,0.008267147,0.000490414,0.0009222177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005601211,0.002891479,0.8463234,0.005341608,0.002309237,0.001622027,0.0004264292,0.06502153,0.03418472,0.008715762,0.03084516,0.001758546],"study_design_scores_gemma":[0.0004350967,0.00002605669,0.03298388,0.001354322,0.0001846831,6.821222e-9,8.081681e-7,0.9602442,0.00201406,0.00002930149,0.001794594,0.0009329725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4235033,0.03935951,0.4805142,0.009040676,0.0122657,0.006714051,0.01940064,0.009149794,0.00005212685],"genre_scores_gemma":[0.8980113,0.000229901,0.1001496,0.0005802548,0.0005916043,0.0002947379,0.00002409339,0.0001134478,0.000005026322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8952227,"threshold_uncertainty_score":0.999229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04795047967876526,"score_gpt":0.2996779229042625,"score_spread":0.2517274432254973,"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."}}