{"id":"W7117111774","doi":"10.3390/jcp6010002","title":"Using Secure Multi-Party Computation to Create Clinical Trial Cohorts","year":2025,"lang":"en","type":"article","venue":"Journal of Cybersecurity and Privacy","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Interoperability; Cryptography; Health care; Key (lock); Secure multi-party computation; Clinical trial; Python (programming language); Data integrity; Data anonymization","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":[0.001786992,0.0001544705,0.0004534927,0.0002965832,0.0001970732,0.0002645591,0.0005844738,0.0001384388,0.000006401444],"category_scores_gemma":[0.0004247615,0.0001355624,0.0002343101,0.0005576223,0.0000793105,0.0008126447,0.0003920338,0.0004645722,0.000002049027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002678388,"about_ca_system_score_gemma":0.000203015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003103889,"about_ca_topic_score_gemma":0.00001500663,"domain_scores_codex":[0.9980165,0.0003131961,0.0008821822,0.0002876041,0.0002850089,0.0002154653],"domain_scores_gemma":[0.9984563,0.0003360122,0.0004014003,0.0003090184,0.0002463572,0.0002509342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.04270015,0.009368657,0.09588245,0.0006299998,0.002263315,0.001100569,0.04182243,0.001533349,0.000953037,0.4826552,0.05980156,0.2612893],"study_design_scores_gemma":[0.189637,0.006135306,0.1534737,0.001869986,0.0009547027,0.0008338954,0.0009500372,0.1200292,0.001556057,0.3010717,0.2210848,0.002403627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5119072,0.0002774601,0.4857185,0.0006603072,0.001111649,0.0001978015,0.000006303809,0.00001832833,0.0001023472],"genre_scores_gemma":[0.8316709,0.0001452534,0.1672262,0.0007145472,0.0002321334,0.000001117761,0.000002079926,0.000004231403,0.000003506881],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3197636,"threshold_uncertainty_score":0.5528075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1026479021444132,"score_gpt":0.413843831321857,"score_spread":0.3111959291774438,"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."}}