{"id":"W2909627766","doi":"10.1016/j.media.2019.01.004","title":"Training recurrent neural networks robust to incomplete data: Application to Alzheimer’s disease progression modeling","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; U.S. Department of Defense","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Training (meteorology); Disease; Training set; Recurrent neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003068212,0.0007695731,0.001095674,0.0005080865,0.0003565924,0.0006693081,0.001015154,0.001179623,0.0006447097],"category_scores_gemma":[0.008045124,0.0004889395,0.0007778706,0.0005209272,0.0003152607,0.0007228577,0.0006577712,0.00150039,0.0002202048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000570056,"about_ca_system_score_gemma":0.0009317692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01412633,"about_ca_topic_score_gemma":0.01336428,"domain_scores_codex":[0.9996454,0.0001103191,0.00002882706,0.0001018326,0.00006498949,0.00004864834],"domain_scores_gemma":[0.9974291,0.00159714,0.0002348002,0.0002383234,0.0004398416,0.00006082455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002598576,0.0001564628,0.003810405,0.00006580545,0.0001756158,0.0001506503,0.00007966424,0.8519515,0.00361537,0.001338887,0.001472028,0.1369238],"study_design_scores_gemma":[0.000002700415,0.00001310507,0.0002791666,0.000001727267,0.000007879628,0.000006265387,0.000002361101,0.9988511,0.0003669624,0.0004106675,0.00005560285,0.000002451666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3500481,0.00158948,0.6441994,0.0008067304,0.0001423552,0.00006891978,0.0004754177,0.00165994,0.001009525],"genre_scores_gemma":[0.9429883,0.0002532738,0.05412593,0.00007491896,0.00006801993,0.00004862385,0.0006849683,0.00007840546,0.001677545],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01412633,"threshold_uncertainty_score":0.02808821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08360766209578195,"score_gpt":0.3858014648162579,"score_spread":0.3021938027204759,"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."}}