{"id":"W4392157110","doi":"10.1002/cyto.b.22166","title":"Recommendations for using artificial intelligence in clinical flow cytometry","year":2024,"lang":"en","type":"review","venue":"Cytometry Part B Clinical Cytometry","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Computer science; Multidisciplinary approach; Identification (biology); Medical physics; Cytometry; Artificial intelligence; Data science; Flow cytometry; Medicine; Immunology; Biology","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":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.006946231,0.001303369,0.004100528,0.002051025,0.000234106,0.0002998005,0.0015146,0.003488477,0.0001475478],"category_scores_gemma":[0.00548891,0.00120075,0.004068013,0.004642788,0.0006278462,0.0000274505,0.0006598901,0.002745476,0.0003740632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002271761,"about_ca_system_score_gemma":0.001190367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009538642,"about_ca_topic_score_gemma":0.00003092038,"domain_scores_codex":[0.9873338,0.001176585,0.006850174,0.002832292,0.0005243892,0.001282774],"domain_scores_gemma":[0.9941279,0.002143516,0.001077651,0.001689319,0.0003005337,0.000661107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002017742,0.001369891,0.0005502527,0.005483487,0.0009003353,0.00004183058,0.000007644264,0.000007951389,0.00002805799,0.0002401573,0.00483615,0.9863325],"study_design_scores_gemma":[0.0004482837,0.0009857171,0.00001910515,0.00484031,0.001850579,0.00005993822,0.00004986526,0.001218717,0.00007785827,0.0004692302,0.9884592,0.001521146],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0006077582,0.9002661,0.08378694,0.0001150329,0.01144493,0.002000201,0.001432598,0.000124389,0.0002221217],"genre_scores_gemma":[0.001566692,0.966449,0.02048176,0.000442219,0.007645138,0.0002355963,0.002422481,0.0003757784,0.0003813431],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9848113,"threshold_uncertainty_score":0.9999718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3952808734457134,"score_gpt":0.5153069385140041,"score_spread":0.1200260650682907,"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."}}