Dynamic Mortality Risk Predictions for Children in ICUs: Development and Validation of Machine Learning Models*

Abstract

Hospital mortality risk estimates determined at 6-hour time periods during care in the ICU. Models were truncated at 180 hours due to decreased sample size secondary to discharges and deaths. MEASUREMENTS AND MAIN RESULTS:The Criticality Index, based on physiology, therapy, and care intensity, was computed for each admission for each time period and calibrated to hospital mortality risk (Criticality Index-Mortality [CI-M]) at each of 29 time periods (initial assessment: 6 hr; last assessment: 180 hr). Performance metrics and clinical validity were determined from the held-out test sample (n = 3,453, 13%). Discrimination assessed with the area under the receiver operating characteristic curve was 0.852 (95% CI, 0.843-0.861) overall and greater than or equal to 0.80 for all individual time periods. Calibration assessed by the Hosmer-Lemeshow goodness-of-fit test showed good fit overall (p = 0.196) and was statistically not significant for 28 of the 29 time periods. Calibration plots for all models revealed the intercept ranged from--0.002 to 0.009, the slope ranged from 0.867 to 1.415, and the R 2 ranged from 0.862 to 0.989. Clinical validity assessed using population trajectories and changes in the risk status of admissions (clinical volatility) revealed clinical trajectories consistent with clinical expectations and greater clinical volatility in deaths than survivors (p < 0.001). CONCLUSIONS:Machine learning models incorporating physiology, therapy, and care intensity can track changes in hospital mortality risk during intensive care. The CI-M's framework and modeling method are potentially applicable to monitoring clinical improvement and deterioration in real time.

Pediatric Deterioration Detection Using Machine Learning*

“…These include variables such as “parent/caregiver gut feeling” as well as “increased edema” and other nursing assessments. This weakness has also been present for other recently reported dynamic prediction models in our field (12, 13).…”

Identification and Optimization of Contributing Factors for Precocious Puberty by Machine/Deep Learning Methods in Chinese Girls

“…To shed some light, besides the traditional logistic regression, we also employed 12 additional machine learning algorithms to compare their prediction performance from various aspects. These machine learning algorithms have shown great promise in application to many areas in clinical practice and health care, such as assisted disease diagnosis, clinical outcome prediction and automated image interpretation (19)(20)(21)(22). By comparison, we found the prediction performance of GBM algorithm is best, and this algorithm focuses on improved prediction by combining information from many variables that individually may not be significant but together are very informative; of less concern is the functional form of any one variable (23).…”

Editor’s Choice Articles for May

“…Trujillo Rivera EA, Chamberlain JM, Patel AK, et al: Dynamic Mortality Risk Predictions For Children in ICUs: Development and Validation of Machine Learning Models (1).…”