Related Experiment Video
Updated: Jun 9, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Risk Factors for Perinatal Arterial Ischemic Stroke: A Machine Learning Approach
Ratika Srivastava1, Lauran Cole1, Kimberly Amador1
1From the Division of Pediatric Neurology (R.S., L.C.), Department of Pediatrics, University of Alberta; Alberta Children's Hospital Research Institute and Department of Clinical Neurosciences (K.A.); Department of Clinical Neurosciences (N.D.F.); Department of Pediatrics and Clinical Neurosciences (M.D.), University of Calgary, Alberta; Departments of Pediatrics and Neurology/Neurosurgery (M.I.S., M.O.), McGill University, Montreal, Quebec, Canada; Newcastle upon Tyne Hospitals (A.P.B.), NHS Foundation Trust, Newcastle upon Tyne, United Kingdom; Department of Neurology (M.J.R.), Boston Children's Hospital and Department of Neurology, Harvard Medical School, Boston, MA; Department of Neonatology (E.S.), Soroka University Medical Center and Faculty of Health sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel; Department of Neonatology (L.S.V.), University Medical Center Utrecht, The Netherlands; Departments of Pediatrics and Community Health Sciences (D.D.), Owerko Centre at the Alberta Children's Hospital Research Institute, Hotchkiss Brain Institute, Cummings School of Medicine; Faculty of Nursing and Cumming School of Medicine (N.L.), Departments of Pediatrics, Psychiatry and Community Health Sciences; Alberta Children's Hospital Research Institute and Department of Clinical Neurosciences (P.M.); Departments of Clinical Neurosciences (M.D.H.), Community Health Sciences, Medicine and Radiology, Hotchkiss Brain Institute and Department of Pediatrics (A.K.), Cumming School of Medicine, University of Calgary, Alberta, Canada.
Insights
Machine learning identified key clinical factors for perinatal arterial ischemic stroke (PAIS), a leading cause of cerebral palsy. This data-driven approach accurately predicts PAIS risk in neonates, outperforming traditional models.
Area of Science:
- Neurology
- Pediatrics
- Data Science
Background:
- Perinatal arterial ischemic stroke (PAIS) is a significant cause of hemiparetic cerebral palsy.
- Previous studies on PAIS predictors were limited by sample size and complex factor interactions.
Purpose of the Study:
- To apply machine learning to large datasets for unbiased identification of PAIS clinical predictors.
- To compare a data-driven machine learning model with traditional literature-driven prediction models for PAIS.
Main Methods:
- Utilized common data elements from three PAIS registries and a healthy control cohort.
- Employed a random forest machine learning pipeline on data from 2,571 neonates (527 cases, 2,044 controls).
- Included maternal/pregnancy, intrapartum, and neonatal factors in the analysis.
Main Results:
- The machine learning model achieved 86.5% balanced accuracy in predicting PAIS.
- Identified key predictors including maternal age, substance exposure, intrapartum fever, and Apgar scores.
- The machine learning model (AUC 0.93) significantly outperformed the literature-driven model (AUC 0.73).
Conclusions:
- Machine learning offers an unbiased method for identifying PAIS clinical predictors.
- The findings support the multifactorial nature of PAIS pathophysiology.
- Neonates at risk for PAIS can be identified using this approach.
Background And Objectives:
Perinatal arterial ischemic stroke (PAIS) is a focal vascular brain injury presumed to occur between the fetal period and the first 28 days of life. It is the leading cause of hemiparetic cerebral palsy. Multiple maternal, intrapartum, delivery, and fetal factors have been associated with PAIS, but studies are limited by modest sample sizes and complex interactions between factors. Machine learning approaches use large and complex data sets to enable unbiased identification of clinical predictors but have not yet been applied to PAIS. We combined large PAIS data sets and used machine learning methods to identify clinical PAIS factors and compare this data-driven approach with previously described literature-driven clinical prediction models.
Methods:
Common data elements from 3 registries with patients with PAIS, the Alberta Perinatal Stroke Project, Canadian Cerebral Palsy Registry, International Pediatric Stroke Study, and a longitudinal cohort of healthy controls (Alberta Pregnancy Outcomes and Nutrition Study), were used to identify potential predictors of PAIS. Inclusion criteria were term birth and idiopathic PAIS (absence of primary causative medical condition). Data including maternal/pregnancy, intrapartum, and neonatal factors were collected between January 2003 and March 2020. Common data elements were entered into a validated random forest machine learning pipeline to identify the highest predictive features and develop a predictive model. Univariable analyses were completed post hoc to assess the relationship between each predictor and outcome.
Results:
A machine learning model was developed using data from 2,571 neonates, including 527 cases (20%) and 2,044 controls (80%). With a mean of 21 features selected, the random forest machine learning approach predicted the outcome with approximately 86.5% balanced accuracy. Factors that were selected a priori through literature-driven variable selection that were also identified as most important by the machine learning model were maternal age, recreational substance exposure, tobacco exposure, intrapartum maternal fever, and low Apgar score at 5 minutes. Additional variables identified through machine learning included in utero alcohol exposure, infertility, miscarriage, primigravida, meconium, spontaneous vaginal delivery, neonatal head circumference, and 1-minute Apgar score. Overall, the machine learning model performed better (area under the curve [AUC] 0.93) than the literature-driven model (AUC 0.73).
Discussion:
Machine learning may be an alternative, unbiased method to identify clinical predictors associated with PAIS. Identification of previously suggested and novel clinical factors requires cautious interpretation but supports the multifactorial nature of PAIS pathophysiology. Our results suggest that identification of neonates at risk of PAIS is possible.
