Jude Savarraj, PhD: Applying Machine Learning to Predict Outcomes
The research scientist from the University of Texas Medical School discussed how he would like to use machine learning to aid in prediction and prophylactic treatment.
“If your brain is in a state of increased pressure for a prolonged time that worsens the outcome. So, if you have a computer algorithm that can predict when this patient is going to develop an increased intracranial pressure crisis, then such a model would be useful for prophylactic treatment as well.”
Jude Savarraj, PhD, research scientist, department of neurosurgery, University of Texas Medical School at Houston, and colleagues recently published a study that suggests machine learning (ML) models used to predict delayed cerebral ischemia (DCI) and functional outcomes significantly outperformed standard models (SMs) when used in subarachnoid hemorrhage (SAH) care.
The ML model outperformed the SM in area under the curve (AUC) by 0.20 (95% CI; -0.02 to 0.4) for DCI, 0.07 (standard deviation [SD], 0.03; 95% CI, 0.0018–0.14) for discharge outcomes, and by 0.14 (95% CI, 0.03–0.24) for 3-month outcomes. Additionally, ML models matched physician performance in predicting 3-month outcomes.
The ML models initially only used routine variables included in a patients’ electronic medical record (EMR), but Savarraj and colleagues found that the ML models performed even better when they also assessed clinician-determined Hunt-Hess Scale score in addition to standard EMR variables (AUC, 0.85; SD, 0.05; 95% CI, 0.75–0.92). Only using EMR data yielded an AUC of 0.81 (SD, 0.05; 95% CI, 0.71–0.89; P <.05).
In this interview, NeurologyLive spoke with Savarraj to learn more about the use of machine learning and other opportunities the technology could be applied to in order to improve the care of patients.
