{"id":"W4415900298","doi":"10.1136/jitc-2025-sitc2025.0097","title":"97 Statistical and systematic uncertainties affect biomarker reliability: a case study in multiplex immunofluorescence","year":2025,"lang":"","type":"article","venue":"Regular and Young Investigator Award Abstracts","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Multiplex; Biomarker; Immunofluorescence; Affect (linguistics)","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":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02033352,0.0008706836,0.001916002,0.0007789184,0.0007958395,0.001605929,0.0007206884,0.0004194017,0.00004091349],"category_scores_gemma":[0.02773328,0.0007048125,0.0001958816,0.001467513,0.002332051,0.0007029854,0.0006225563,0.0007863512,0.0000352731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003909318,"about_ca_system_score_gemma":0.0009636009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005592987,"about_ca_topic_score_gemma":0.00166856,"domain_scores_codex":[0.9874678,0.003505121,0.00361119,0.002214716,0.002193557,0.001007569],"domain_scores_gemma":[0.9914002,0.004651144,0.0006753939,0.001818284,0.0005577257,0.000897242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006240028,0.003759238,0.9116843,0.03758249,0.0008236869,0.008122471,0.01846422,0.0007429695,0.003182787,0.00128309,0.001740955,0.0119898],"study_design_scores_gemma":[0.006469405,0.001293779,0.8240275,0.02068035,0.001235195,0.001231843,0.09796921,0.02912739,0.000804911,0.01503226,0.0003053786,0.001822734],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843964,0.00707841,0.0003429133,0.001191949,0.001311748,0.005415051,0.0000546027,0.0000532898,0.0001556292],"genre_scores_gemma":[0.9977437,0.0002944605,0.0008988049,0.0001970685,0.00003320166,0.0002316039,0.00000439511,0.00002749074,0.0005692639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08765674,"threshold_uncertainty_score":0.9995403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06942844363114892,"score_gpt":0.3442540651931056,"score_spread":0.2748256215619567,"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."}}