{"id":"W4309264259","doi":"10.1371/journal.pone.0272825","title":"A novel method to derive personalized minimum viable recommendations for type 2 diabetes prevention based on counterfactual explanations","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Compagnia di San Paolo","keywords":"Medicine; Counterfactual thinking; Type 2 diabetes; Diabetes mellitus; Body mass index; Internal medicine; Psychology; Endocrinology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006511061,0.00010482,0.0001671523,0.0001998405,0.0004883375,0.00006432758,0.0004242147,0.00002661459,0.0004024052],"category_scores_gemma":[0.0003813641,0.0001206181,0.00004678153,0.0004635558,0.00000715737,0.0001231197,0.000132491,0.0001869793,0.00002064268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001875754,"about_ca_system_score_gemma":0.0001656032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003096112,"about_ca_topic_score_gemma":0.00001069444,"domain_scores_codex":[0.9985507,0.0002588644,0.0001978079,0.0003645526,0.0003850746,0.0002430312],"domain_scores_gemma":[0.9984697,0.0008276419,0.0001037919,0.0003217637,0.0001893504,0.00008782189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001693043,0.04316045,0.01297975,0.002605023,0.002264708,0.00000886809,0.05495178,0.1944456,0.322683,0.1486243,0.1151758,0.1014076],"study_design_scores_gemma":[0.0007510313,0.001427799,0.0002216328,0.00008052135,0.00003529402,6.475883e-7,0.0001669624,0.9789879,0.00263847,0.0005632349,0.01492584,0.0002006977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01585623,0.00001838255,0.9510206,0.03138276,0.0001814417,0.001003538,0.0001552855,0.0001621184,0.0002196582],"genre_scores_gemma":[0.09613032,7.684047e-7,0.8973897,0.003755948,0.00005316643,0.001166543,0.0002020886,0.00002062338,0.001280807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7845423,"threshold_uncertainty_score":0.4918664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1495686149418002,"score_gpt":0.3655659205258006,"score_spread":0.2159973055840004,"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."}}