Development and Internal-External Validation of a Post-Operative Mortality Risk Calculator for Pediatric Surgical Patients in Low- and Middle- Income Countries Using Machine Learning

jpedsurg.org

The KidsOR post-operative mortality risk algorithm had outstanding cross-validated discrimination and strong cross-validated calibration. Across all external validation sites, discrimination of Super Learner models trained on the remaining sites was excellent, though re-calibration may be necessary prior to use at new sites. This model has the potential to inform clinical practice and guide resource allocation at KidsOR sites world-wide.

jpedsurg.org shows its articles on its own site.

Read the article on jpedsurg.org ↗

Article · Aug 2024 · 1 min read

In brief

Researchers developed a machine learning algorithm to predict postoperative mortality risk in pediatric surgical patients across low- and middle-income countries. The Super Learner model demonstrated excellent discrimination and calibration when validated across multiple KidsOR sites, offering a tool to guide clinical decision-making and optimize resource allocation in resource-limited settings.

Machine learning model achieved excellent discrimination for predicting post-operative mortality in pediatric surgical patients across LMIC sites.
External validation demonstrated strong performance, though site-specific recalibration may be needed before deployment.
Algorithm can guide clinical decision-making and optimize resource allocation in resource-limited surgical settings.

Written by the GCMD Library team from the article.

Read it at the source ↗