Matthew Engelhard
Duke University, NC·Computer Science·Early-career
Children with autism spectrum disorder (ASD) or attention-deficit hyperactivity disorder (ADHD) do better over time when they are treated early. Early treatment depends on spotting at-risk children promptly and accurately.
- Fields
Computer Science
Medicine & Clinical Research
Public Health & Epidemiology
- Topics
autism spectrum disorder
attention-deficit hyperactivity disorder
electronic health record
- Grants
- 1 known grant, through Aug 2027
What they work on
- Develop machine-learning models that predict autism spectrum disorder and ADHD from early electronic health record data, such as diagnosis codes, labs, vitals and clinical notes, while correcting for differences in health care use.
- Build methods that update each child's predicted ASD and ADHD risk over time, so at-risk children are identified as early as possible without losing accuracy.
- Evaluate the risk models prospectively and deploy them within the Duke University Health System electronic health record.
- Design and test, with clinicians, a prototype EHR dashboard showing ASD and ADHD risk and projected follow-up length to guide clinical decisions.
More about the research
Many early warning signs, such as premature birth or complications around birth, are already recorded during routine medical care in the electronic health record (EHR). However, these records have not been used at scale to sort children by risk or to improve early screening.
Why it matters
Earlier identification of children at risk for autism or ADHD could get them to evaluation and treatment sooner, when it does the most good. Because the models use information already in routine health records, they could support pediatric screening without extra testing. Attention to differences in health care use is meant to keep predictions fair across families.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Yair Bannett
Stanford University, CA·Medicine & Clinical Research·Early-career
Develop guideline-based quality measures for primary care treatment of children aged 4–11 with ADHD, combining machine learning analysis of free-text clinical notes with structured electronic health record data.
Sampath Jayarathna
Old Dominion University, VA·Computer Science·Early-career
Build a "streaming hub," a framework for real-time, computationally efficient processing of eye-tracking data from one or more users, in place of offline batch analysis.
Jacqueline Stocking
University of California-Davis, CA·Medicine & Clinical Research·Early-career
Optimize and validate an automated, EHR-based model predicting postoperative respiratory failure, using surgical patient data from 2014 to 2021 and pre- and intra-operative risk factors.
The school
Duke University: 61 labs on PI Pages, $1.6B a year on research, 417 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.