About

Barbara H Chaiyachati, MD, PhD, is an Assistant Professor of Pediatrics (General Pediatrics) at the Children's Hospital of Philadelphia. She is also a researcher at the Lifespan Brain Institute at Children's Hospital of Philadelphia, an affiliate member of the Institute for Translational Medicine and Therapeutics at the University of Pennsylvania School of Medicine, and an attending physician in the Division of General Pediatrics. Her educational background includes a BA in Biology from Macalester College, a PhD in Cell Biology from Yale University, and an MD from Yale University School of Medicine. Her research focuses on pediatric health, with particular interest in behavioral health diagnoses, race and ethnicity data stability, epigenetic age acceleration in adolescents, perinatal toxicology testing, and child health and development. She has contributed to various studies and presentations in these areas, emphasizing her commitment to advancing pediatric medicine and health equity.

Research topics

• Medicine
• Psychology
• Psychiatry
• Clinical psychology
• Developmental psychology

Selected publications

• Substance use patterns among individuals who consume alcohol during pregnancy: Results from a US multi-site study

  Drug and Alcohol Dependence · 2026-02-28

  articleOpen access
  PublisherOA PDFDOI

• Health System Scale Semantic Search Across Unstructured Clinical Notes

  ArXiv.org · 2026-04-28

  articleOpen access

  Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keyword matching, offers substantial advantages for retrieval of clinical information. However, deploying semantic search across entire health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors in a managed database with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system through three experiments: optimization of embedding model and chunking strategy using a physician-authored benchmark dataset, characterization of full-scale performance (cost, latency, retrieval quality), and clinical utility assessment via comparison of chart abstraction efficiency across three tasks. Results: The system delivers sub-second query latency (median 237 ms single-user, 451 ms 20-user concurrency) with monthly costs of approximately USD 4,000. Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark. In clinical utility evaluation across three abstraction tasks, semantic search reduced time-to-completion by 24 to 89% compared to clinician-performed chart review while maintaining comparable inter-rater agreement. Conclusion: Health-system-scale semantic search is both technically and operationally feasible. The system provides infrastructure supporting interactive search, cohort generation, and downstream LLM-powered clinical applications without requiring specialized informatics expertise.

  PublisherOA PDF

• Health System Scale Semantic Search Across Unstructured Clinical Notes

  arXiv (Cornell University) · 2026-04-28

  preprintOpen access

  Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keyword matching, offers substantial advantages for retrieval of clinical information. However, deploying semantic search across entire health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors in a managed database with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system through three experiments: optimization of embedding model and chunking strategy using a physician-authored benchmark dataset, characterization of full-scale performance (cost, latency, retrieval quality), and clinical utility assessment via comparison of chart abstraction efficiency across three tasks. Results: The system delivers sub-second query latency (median 237 ms single-user, 451 ms 20-user concurrency) with monthly costs of approximately USD 4,000. Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark. In clinical utility evaluation across three abstraction tasks, semantic search reduced time-to-completion by 24 to 89% compared to clinician-performed chart review while maintaining comparable inter-rater agreement. Conclusion: Health-system-scale semantic search is both technically and operationally feasible. The system provides infrastructure supporting interactive search, cohort generation, and downstream LLM-powered clinical applications without requiring specialized informatics expertise.

  PublisherDOI

• Variation in Perinatal Toxicology Testing and Consent Practices Among United States Birthing Hospitals: Results From a National Survey

  Women s Health Issues · 2026-03-01 · 1 citations

  article
  PublisherDOI

• Reference Trajectories of Extra-Axial Cerebrospinal Fluid during Childhood and Adolescence Defined in a Clinically Acquired MRI Dataset.

  Apollo (University of Cambridge) · 2026-01-01

  articleOpen access

  Purpose To build extra-axial cerebrospinal fluid (eaCSF) growth charts that define key diagnostic criteria for benign enlargement of the subarachnoid space (BESS) by providing an age-related reference benchmark to aid in assessing atypical eaCSF development. Materials and Methods In this retrospective study, T1-weighted MRI scans from patients who underwent imaging at a pediatric health care system between January 2004 and December 2023 were accessed to form a clinical control group. Nine scans from patients diagnosed with BESS by a board-certified pediatric neuroradiologist were also reviewed. T1-weighted scans were segmented into various tissue types, including eaCSF. Growth charts of eaCSF were modeled using the clinical control group. The results of patients with confirmed BESS were then benchmarked against these charts to test the performance of the eaCSF growth charts. Generalized additive models of location, scale, and shape were used. Results The eaCSF measurements were obtained for 1205 patients (619 female; age range, 0.19-19.6 years). Measurements show that eaCSF evolved dynamically with age, steadily decreasing from birth to 2 years, then trending upward in childhood. Seven of the nine patients with a clinical diagnosis of BESS had eaCSF measurements above the 97.5th percentile for at least one measurement. Percentile scores distinguished patients with BESS from controls with areas under the receiver operating characteristic curve of greater than 0.95. Conclusion MRI-derived eaCSF measurements evolved dynamically throughout early life. Patients with atypical CSF development could be differentiated from clinical controls using computational measurements paired with normative modeling. Keywords: MRI, Brain/Brain Stem, Pediatrics, Benign Enlargement of Subarachnoid Space Supplemental material is available for this article. © The Author(s) 2025. Published by the Radiological Society of North America under a CC BY-NC-ND license.

  PublisherOA PDFDOI

• Child Physical Abuse During the COVID-19 Pandemic Across Levels of Community Advantage

  Academic Pediatrics · 2026-03-22

  article
  PublisherDOI

• Perspectives of Mothers With Substance Use Disorder on Naloxone Education: “I’m Ready to Have Those Conversations About Who I Was, Because That’s Not Who I Am”

  Journal of Addiction Medicine · 2025-06-20

  article

  OBJECTIVES: Approximately 3 million U.S. children live with a parent with an illicit or prescription substance use disorder (SUD) and may be at risk of witnessing an overdose. Parents with SUD offer valuable perspectives on how to facilitate conversations around overdose response. Our aim was to assess attitudes of parents with SUD towards discussing naloxone with their children. METHODS: Parents with SUD were recruited from SUD treatment programs, social media, and a research website to participate in semistructured virtual focus groups facilitated by peers with lived experience of SUD while parenting. The interview guide was informed by study teams' clinical experiences. We used an inductive thematic analysis approach; transcripts were double-coded. RESULTS: Fifteen parents identifying as mothers participated in 4 focus groups. Four themes were identified. First, most mothers had not discussed naloxone use with their children, yet felt it was important to prepare them to respond to potential overdoses. Second, mothers highlighted that normalizing naloxone education through comparisons to other emergency responses may reduce stigma and expand learning opportunities. Third, mothers noted that overdose response involves physical, cognitive, and emotional processing skills that are acquired at different stages of child development. Fourth, mothers shared that naloxone discussions often require disclosing their own substance use, which was identified as a challenging conversation that mothers were variably ready to navigate. CONCLUSIONS: Mothers with SUD believed their children would benefit from naloxone education. Supporting parents navigating their own SUD disclosure and identifying developmentally appropriate tools are important steps in devising education strategies.

  PublisherDOI

• Reference Trajectories of Extra-Axial Cerebrospinal Fluid during Childhood and Adolescence Defined in a Clinically Acquired MRI Dataset

  Radiology Artificial Intelligence · 2025-12-10

  articleOpen access

  MRI-derived brain growth charts demonstrated dynamic changes in extra-axial cerebrospinal fluid in early life, challenging fixed-measurement guidelines for diagnosing benign enlargement of the subarachnoid space and atypical cerebrospinal fluid development.

  PublisherOA PDFDOI

• Mediating Role of Trauma Connecting Psychiatric Family History and Adolescent Mental Health

  Biological Psychiatry Global Open Science · 2025-05-02 · 1 citations

  articleOpen access1st authorCorresponding

  Adolescent mental health is influenced by family history. Experiences of trauma also convey substantial risk for mental health challenges. Mediation of the association of family history with adolescent mental health by trauma experiences could be actionable and warrants evaluation. We sought to interrogate the mediating role of trauma in the association of psychiatric family history (FH) with adolescent general psychopathology, accounting for shared environment and genetics. The Philadelphia Neurodevelopmental Cohort was a cross-sectional study of participants aged 8 to 21 with English fluency, in good medical health with characterization from November 2009 through December 2011. Analysis reported here was completed from March 2023 through February 2025. Among 7840 participants, we tested associations of first-degree FH (category count [0-4]: psychosis, mood, suicide attempt, substance use), youth exposure to trauma, neighborhood environment (block-level geocoded socioeconomic indices), and genomic factor of polygenic scores for psychopathologies (depression, PTSD, schizophrenia, bipolar, cross-disorder) with adolescent general psychopathology modeled as P-factor. Association of FH with general psychopathology was assessed with structural equation modeling, querying for an indirect pathway via trauma, with stepwise accounting of genomics and shared environment, controlling for age and sex. Of 7,840 participants, 31% had FH and trauma exposure was reported in 44% of youth. Trauma had substantial direct association with general psychopathology and consistently mediated more than 20% of variance from FH to psychopathology, accounting for neighborhood and genomic predisposition. Trauma exposures mediate a substantial portion of association between FH and adolescent psychopathology, an opportunity for transgenerational intervention. One potentially modifiable environmental risk factor for youth mental health is early-life exposure to traumatic stressful experiences (trauma). Many studies have reported associations of trauma exposure with psychiatric illness, including in adolescence.( 8 , 9 , 10 , 11 , 12 ) Moreover, caregiver ill mental health has been shown to increase risk for child trauma exposures.( 13 ) It is also critical to consider the complex network structure of environment (exposome), whereby individual-level adversity often co-occurs with structural stressors.( 14 ) For example, the likelihood of trauma exposure may be influenced by neighborhood environment such as through frequency of violent crime.( 15 )

  PublisherDOI

• Children Exposed to Substances in Pregnancy

  American Academy of PediatricsItasca, IL eBooks · 2025-10-16

  book-chapter1st authorCorresponding
  PublisherDOI

Recent grants

• Clinical and biologic health trajectories after early life adversity

  NIH · $726k · 2022–2027

Frequent coauthors

• Ran Barzilay

  University of Pennsylvania

  129 shared

• Raquel E. Gur

  Children's Hospital of Philadelphia

  120 shared

• Lauren K. White

  University of Pennsylvania Health System

  84 shared

• Jakob Seidlitz

  71 shared

• Megan M. Himes

  Children's Hospital of Philadelphia

  63 shared

• Wanjikũ Njoroge

  University of Pennsylvania

  57 shared

• Tyler M. Moore

  California University of Pennsylvania

  53 shared

• Heather H. Burris

  University of Pennsylvania

  41 shared