Camille Parchment(she/her/hers)
Faculty Mentor:
Amber Angell PhD, OTR/L, FAOTA
Research Lab: Disparity Reduction and Equity in Autism Services (DREAmS)
Year of Entry: 2021
I am a PhD student within the Chan Division of Occupational Science and Occupational Therapy, under the mentorship of Dr. Amber Angell. My research interests are healthcare implementation, occupational justice in healthcare and more specifically, improving access to mental health services for all, including underserved members of the mental health community. As a research assistant within the Disparity Reduction and Equity in Autism Services (DREAmS) lab, I support research projects that aim to reduce disparities in autism diagnosis and services, particularly among autistic women and girls.
Bachelor of Science (BS)
in Bio-Behavioral Health
2012 | The Pennsylvania State University
Angell, A., Li, Y., Hakimjavadi, H., Parchment, C., Yin, L., Chamala, S., Bian, J., Thompson, L., & Guo, Y. (2026). Autism spectrum disorder computable phenotyping using electronic health records with verified autism diagnoses. In 2026 IEEE 14th International Conference on Healthcare Informatics (ICHI) (pp. 1087–1095). IEEE. https://doi.org/10.1109/ICHI69079.2026.00134 Show abstract
As the prevalence of autism spectrum disorder (ASD) in children increases, there are increasing opportunities to use real-world clinical data to improve care. Existing ASD computable phenotypes (CPs) use outdated diagnosis codes (ICD-9) and rely on clinician verification of ASD diagnosis through chart review. We built upon and updated these CPs by including updated ICD-10 codes and verified ASD diagnosis via the Autism Diagnostic Observation Schedule™, Second Edition (ADOS™-2). Using electronic health records (EHRs) from two sites, Children’s Hospital Los Angeles (CHLA) and the University of Florida (UF) Health System, we identified ASD-related keywords/keyword phrases from clinical notes. We developed CP rules at each site using our gold standard (verified) cohorts, then refined and evaluated the rules. Our internal evaluation rules achieved a high positive predictive value (PPV), particularly our ADOS™-2-verified gold standard cohorts. Our performance patterns were also similar in direction at both sides. Our rules are therefore able to identify ASD cases with high precision. These findings provide an updated process for ASD cohort identification and lay the groundwork for a machine learning prediction model that can be used to support clinical decision making and precision medicine in autism.
Keywords. autism spectrum disorder, electronic health records, computable phenotypes
Angell, A. M., Wee, C. P., Deavenport-Saman, A., Parchment, C., Bai, C., Solomon, O., & Yin, L. (2025). Sleep disorders and constipation in autistic children and youth: Who receives standard of care drug treatments? Journal of Autism and Developmental Disorders, 55(12), 4365–4371. https://doi.org/10.1007/s10803-025-06762-7 Show abstract
Purpose. The purpose of this retrospective cohort analysis was to investigate sex differences in receipt of standard of care sleep and constipation drug treatments among autistic children and youth with sleep disorder and constipation, respectively.
Methods. We used the data from the OneFlorida + Data Trust to analyze healthcare claims for 19,877 autistic patients with sleep disorder and 32,355 patients with constipation, ages 1 to 22. We used logistic regression to examine sex differences in receiving sleep and constipation treatments, and a multivariate logistic regression model to further assess sex differences in ever receiving sleep and constipation treatments, adjusting for age, race, ethnicity, and urbanicity.
Results. In our multivariate analysis, autistic girls with sleep disorder were 1.27 times more likely than boys to receive sleep treatment (p < 0.0001). Although autistic girls with constipation appeared to be 1.10 times more likely than boys to receive treatment, it was not significantly different after adjusting for demographic and socio-economic characteristics (p = 0.372). Older children were 1.09 times more likely than younger children to receive sleep treatment (p < 0.0001) and 1.07 times more likely to receive constipation treatment (p < 0.0001).
Conclusion. We did not find sex differences among autistic children for treatment of constipation, but autistic girls with sleep disorder were significantly more likely to have ever received treatment, which could indicate that girls experience more significant sleep disorders.
Angell, A. M., Li, Y., Bian, J., Parchment, C., Yin, L., Chamala, S., Hakimjavadi, H., Thompson, L., & Guo, Y. (2005). Algorithmic fairness in machine learning prediction of autism using electronic health records. Studies in Health Technologies and Informatics, 7, 329. https://doi.org/10.3233/SHTI251025 Show abstract
Efforts to improve early diagnosis of autism spectrum disorder (ASD) in children are beginning to use machine learning (ML) approaches applied to real-world clinical datasets, such as electronic health records (EHRs). However, sex-based disparities in ASD diagnosis highlight the need for fair prediction models that ensure equitable performance across demographic groups for ASD identification. This retrospective case-control study aimed to develop ML-based prediction models for ASD diagnosis using risk factors found in EHRs and assess their algorithmic fairness. The study cohorts included 70,803 children diagnosed with ASD and 212,409 matched controls without ASD. We built logistic regression and Xgboost models and evaluated their performance using standard metrics, including accuracy, recall, precision, F1-score, and area under the curve (AUC). To assess fairness, we examined model performance by sex and calculated fairness-specific metrics, such as equal opportunity (recall parity) and equalized odds, to identify potential biases in model predictions between boys and girls. Our results revealed significant fairness issues in ML models for ASD prediction using EHRs.
Machine learning prediction of persistent adverse mental health outcomes for autistic children: Leveraging social determinants of health from clinical data
September 2025
–
July 2030
|
PhD Student
|
Active
⋯
Social
Facebook Instagram LinkedIn TikTok YouTube