{"id":"W4406229301","doi":"10.1371/journal.pcbi.1012711","title":"Eight quick tips for biologically and medically informed machine learning","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ministero dell'Università e della Ricerca; European Commission; Dipartimenti di Eccellenza","keywords":"Machine learning; Computer science; Artificial intelligence; Domain (mathematical analysis); Informatics; Health informatics; Data science; Health care; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003124927,0.0001381445,0.0002189561,0.0001773701,0.0002586475,0.00006572868,0.0004947817,0.0001339479,0.00002385096],"category_scores_gemma":[0.001148359,0.0001119379,0.00004713898,0.0002965129,0.0002012142,0.0001498328,0.0002988656,0.0001693835,0.00003402612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003908596,"about_ca_system_score_gemma":0.0002072035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001602328,"about_ca_topic_score_gemma":0.00001948464,"domain_scores_codex":[0.9987334,0.0001092476,0.0003584369,0.0003947652,0.0001010237,0.0003031355],"domain_scores_gemma":[0.9973064,0.002152193,0.00009852983,0.0001310698,0.0002327163,0.00007908288],"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":[0.00004473449,0.00008574878,0.005796204,0.0000401964,0.00007453345,0.000003183062,0.0002209756,0.001945677,0.001322612,0.9441864,0.0006904586,0.0455892],"study_design_scores_gemma":[0.0002968565,0.0003926044,0.001341992,0.00002439835,0.000007837148,0.000009733496,0.00002435804,0.6552022,0.0009512964,0.315082,0.02649425,0.0001725302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02394651,0.0003865979,0.9672726,0.00636828,0.0002024637,0.0003126314,0.00001100492,0.0001626322,0.001337236],"genre_scores_gemma":[0.835609,0.00008072826,0.1604379,0.003300423,0.00006667656,0.0000906921,0.000155305,0.000006434874,0.0002529117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8116624,"threshold_uncertainty_score":0.4564693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03053365570194182,"score_gpt":0.3040615140094066,"score_spread":0.2735278583074647,"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."}}