{"id":"W4376612861","doi":"10.2196/44549","title":"Evaluation of the EsteR Toolkit for COVID-19 Decision Support: Sensitivity Analysis and Usability Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Leibniz-Gemeinschaft; Bundesministerium für Bildung und Forschung","keywords":"Usability; Computer science; Test (biology); Stability (learning theory); Coronavirus disease 2019 (COVID-19); Decision support system; Machine learning; Artificial intelligence; Human–computer interaction; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02539167,0.00006848515,0.0001659261,0.0004616769,0.0003431391,0.0001651322,0.0003886809,0.00003192868,0.00002338817],"category_scores_gemma":[0.003037587,0.0000454515,0.0000812992,0.003915977,0.0001393645,0.000589,0.0007472152,0.0001022748,0.00001394208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001374589,"about_ca_system_score_gemma":0.0003527406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004143313,"about_ca_topic_score_gemma":0.0003223014,"domain_scores_codex":[0.9956815,0.001615947,0.0002863385,0.0002740044,0.001926019,0.0002161449],"domain_scores_gemma":[0.9962727,0.00166503,0.00009385076,0.000632347,0.001234816,0.0001012859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001725859,0.002593568,0.3456127,0.0004540389,0.001260833,0.000006822357,0.1316839,0.009965137,0.000366941,0.01827583,0.03255992,0.4570477],"study_design_scores_gemma":[0.000480761,0.0001436186,0.2828464,0.000003862493,0.00004878397,4.752412e-7,0.001332853,0.7109359,0.0001235646,0.003673967,0.0003624916,0.00004735273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6418074,0.000002128092,0.3561791,0.0006636991,0.00004424946,0.001120098,0.00007082352,0.00002741373,0.00008508551],"genre_scores_gemma":[0.9994977,0.000003043344,0.0002676434,0.00005878608,0.0000078163,0.00008106839,0.00002321297,0.000002742937,0.00005802197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7009708,"threshold_uncertainty_score":0.8800296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2211729651340077,"score_gpt":0.5383628778568699,"score_spread":0.3171899127228622,"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."}}