Summary
This project aims to characterize gastrointestinal (GI) disorder trajectories in autistic sub-groups by developing predictive models of risk profiles and treatment response, utilizing qualitative, participatory, and machine learning approaches.
What they want
The research involves three main aims: (1) Qualitatively describing GI experiences across the lifespan through narrative interviews with 25 autistic adults and 25 caregivers of autistic children/youth. (2) Quantitatively characterizing GI symptom rates, presentations, trajectories, and treatment responses using electronic health records (EHRs) from Children’s Hospital Los Angeles (N=7,478 autistic children/youth), including structured data and unstructured data processed via natural language processing. (3) Building predictive models for GI symptom profiles and treatment response using both traditional and machine learning methods on the EHR dataset and a matched non-autistic cohort. A community advisory board, comprising autistic adults and caregivers, will guide the participatory research approach.
Deliverables
- Qualitative description of autistic people’s GI experiences throughout the lifespan
- Quantitative characterization of GI symptom rates, presentations, trajectories, and responses to treatment
- Predictive models of risk of GI symptom profiles and response to treatment
Technical requirements
- Qualitative research methods (narrative interviews, analysis)
- Quantitative data analysis
- Machine learning approaches for prediction models
- Natural Language Processing (NLP) for extracting keywords from clinical notes
- Use of Electronic Health Records (EHRs)
- Participatory research approach with a community advisory board
