2026-10-07T23:11:24Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34048751 2026-10-01T17:36:28Z category_1 category_13 category_21 category_734 category_931 category_811 category_69 category_128 portal_5 item_type_1 month_year_10_2026

<p>Calibration analysis for the STREAM ICU mortality prediction model.</p> Ali Namvar (9279350) Sundaresh Ram (10428439) Wassim W. Labaki (10704446) Stefanie Galban (10428445) Njira L. Lugogo (13119569) Craig J. Galban (10428469) Biophysics Genetics Biotechnology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Mathematical Sciences not elsewhere classified Inorganic Chemistry Hematology track physiological instability support clinical assessment provide limited insight multidimensional physiological space monitoring systems face method &# 8217 existing approaches rely distinct clinical signatures applies geometric analysis 6 %, 16 movement toward higher state trajectory representation physiological state monitoring linking state dynamics derived physiological states aware monitoring ), mortality prediction achieved evaluated stream using fold higher mortality icu stay within expected calibration error routine icu data fold higher expected state icu mortality state outliers risk states respectively ), remained within outcome prediction nearest state assigned states vital signs strong discrimination static thresholds spent less severity scores laboratory values interpretable patterns external validation excellent calibration driven framework discover data developed stream critical gap 8 hours 72 hours 002 ). <p>(A) Reliability diagram comparing predicted probabilities with observed mortality for the original model (red), Platt scaling (green), and isotonic regression (blue); the dashed line indicates perfect calibration. (B) Predicted probability distributions showing concentration of the original model in very low-probability ranges (<0.1) and more appropriate spread after calibration. (C) Expected Calibration Error (ECE) comparison demonstrating substantial reduction in calibration error for both calibrated models relative to the original, confirming that post-hoc calibration successfully corrected probability estimates while maintaining identical discriminative performance (AUROC).</p> <p>(TIF)</p> 2026-10-01T17:36:17Z Image Figure 10.1371/journal.pdig.0001753.s008 https://figshare.com/articles/figure/_p_Calibration_analysis_for_the_STREAM_ICU_mortality_prediction_model_p_/34048751 CC BY 4.0