Publications by authors named "Lakshya Singhal"
Article Synopsis
- The 'eARDS' machine learning algorithm predicts Acute Respiratory Distress Syndrome (ARDS) in COVID-19 patients in ICUs, identifying risk up to 12 hours prior to meeting the Berlin clinical criteria.
- The analysis used clinical data from 35,804 patients and demonstrated a strong predictive performance with an AUROC of 0.89 and sensitivity of 0.77.
- Key predictive features included minimum oxygen saturation and blood pressure variations, with the algorithm performing best in younger patients (ages 18-40) and showing robust consistency across different health systems.
