{"id":"W4402744904","doi":"10.1101/2024.09.21.24314128","title":"Morphology-based classification of sickle cell disease and β-thalassemia using a low-cost automated microscope and machine learning","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Paul's Hospital; Providence Health Care; BC Children's Hospital; University of British Columbia","funders":"Centre for Blood Research, University of British Columbia; Canada Research Chairs; BC Children's Hospital","keywords":"Thalassemia; Computer science; Artificial intelligence; Microscope; Medicine; Pathology; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005630557,0.0005265413,0.000457965,0.001961145,0.0004306125,0.000774548,0.0008598217,0.0008345446,0.001242594],"category_scores_gemma":[0.001236765,0.000281139,0.0006926195,0.0007644733,0.0002861919,0.0002849156,0.0007007826,0.0003963832,0.0006916285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001397705,"about_ca_system_score_gemma":0.001118714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04947708,"about_ca_topic_score_gemma":0.07960661,"domain_scores_codex":[0.9995342,0.00005456037,0.00003426331,0.0001630491,0.0001209704,0.00009293644],"domain_scores_gemma":[0.9993039,0.0001512448,0.00007351712,0.0001033662,0.0003221344,0.00004584475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001379442,0.0008639282,0.3634011,0.001523738,0.0007721702,0.002835243,0.0004679476,0.06271102,0.2319904,0.00150703,0.04492835,0.2876196],"study_design_scores_gemma":[0.0001022808,0.0002550777,0.3706711,0.0001699407,0.0002847527,0.00279037,0.0005418654,0.5239091,0.08181625,0.001523773,0.01782507,0.000110407],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.917885,0.001633309,0.04198779,0.0006834277,0.0001288786,0.0003876195,0.0291285,0.003239578,0.004925849],"genre_scores_gemma":[0.8598925,0.0007157353,0.085986,0.0003902058,0.00005255113,0.0001857277,0.04967071,0.000143779,0.002962747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04947708,"threshold_uncertainty_score":0.09837818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02511550184438466,"score_gpt":0.2760679344801018,"score_spread":0.2509524326357171,"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."}}