Comparison of Expert Vocabulary Usage Patterns Between Mental Health and Nonmental Health Clinicians When Diagnosing Pediatric Anxiety Disorders

Chandrashekar, Mayanka; Tschida, Jordan; Strawn, Jeffrey R.; Hanson, Heidi A.; Santel, Daniel; Goethert, Ian; Kapadia, Anuj J.; Glauser, Tracy; Pestian, John; Agasthya, Greeshma A.

doi:10.1016/j.jpeds.2025.114735

Comparison of Expert Vocabulary Usage Patterns Between Mental Health and Nonmental Health Clinicians When Diagnosing Pediatric Anxiety Disorders

Journal Article · Fri Jul 18 00:00:00 EDT 2025 · The Journal of Pediatrics

DOI:https://doi.org/10.1016/j.jpeds.2025.114735· OSTI ID:2583836

^[1]; ^[1]; Strawn, Jeffrey R. ^[2]; Hanson, Heidi A. ^[1]; Santel, Daniel ^[2]; ^[1]; ^[1]; ^[2]; Pestian, John ^[3]; Agasthya, Greeshma A. ^[1]

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Univ. of Cincinnati, OH (United States)
Univ. of Cincinnati College of Medicine, OH (United States). Cincinnati Children's Hospital Medical Center

Objective: To compare the utilization patterns of expert vocabulary (EVo) in diagnosing pediatric anxiety between mental health and non-mental health clinical notes from electronic health records to understand the role of Evo in informing classification and decision-making in anxiety diagnoses. Study design: We conducted a retrospective study using a cohort less than age 25 from Cincinnati Children's Hospital including 897 685 patients with 61 586 446 notes. We analyzed EVo, collected from mental health clinicians, in both mental and nonmental health notes. We compared classification accuracy using EVo-based patient-level embedding from all clinical notes, mental-health notes, and nonmental health notes for 2 tasks: 1) pre-vs postdiagnosis anxiety patients, and 2) prediagnosis anxiety vs nonanxiety patients. Results: EVo usage was highest in prediagnosis anxiety, lower in nonanxiety, and lowest in post-diagnosis. Classification models using EVo features from all, mental-health, and non-mental health notes showed similar F1 scores for prediagnosis anxiety (0.70 ± 0.2 for 2 categories). For anxiety vs nonanxiety classification, all clinical and nonmental health notes had better F1 scores than mental-health notes (above 0.90 for 3 categories). There was a notable difference in class-wise performance across both tasks. Conclusions: There are significant differences in anxiety EVo use between mental health and nonmental health clinicians. Despite less anxiety-specific terminology, non-mental health notes still captured key aspects of patient presentations, emphasizing the importance of including all clinicians' notes in analysis. EVo's utility for anxiety classification is most effective in prediagnostic phases, suggesting the need for a dedicated diagnostic lexicon and further study before incorporating EVo into classification models.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2583836

Journal Information:: The Journal of Pediatrics, Journal Name: The Journal of Pediatrics Vol. 286; ISSN 0022-3476

Publisher:: Elsevier BVCopyright Statement

Country of Publication:: United States

Language:: English

References (35)

Screening for Pediatric Anxiety Disorders Walkup, John T.; Green, Cori M.; Strawn, Jeffrey R. JAMA, Vol. 328, Issue 14 https://doi.org/10.1001/jama.2022.15224	journal	October 2022
Screening for Anxiety in Children and Adolescents No authors listed JAMA, Vol. 328, Issue 14 https://doi.org/10.1001/jama.2022.16936	journal	October 2022
Worldwide Prevalence and Disability From Mental Disorders Across Childhood and Adolescence Kieling, Christian; Buchweitz, Claudia; Caye, Arthur JAMA Psychiatry, Vol. 81, Issue 4 https://doi.org/10.1001/jamapsychiatry.2023.5051	journal	April 2024
Social anxiety disorder in callers to the Anxiety Disorders Association of America Zhang, Wei; Ross, Jerilyn; Davidson, Jonathan R. T. Depression and Anxiety, Vol. 20, Issue 3 https://doi.org/10.1002/da.20020	journal	January 2004
Human and economic burden of generalized anxiety disorder Hoffman, Deborah L.; Dukes, Ellen M.; Wittchen, Hans-Ulrich Depression and Anxiety, Vol. 25, Issue 1 https://doi.org/10.1002/da.20257	journal	January 2008
Using Machine Learning to Identify Health Outcomes from Electronic Health Record Data Wong, Jenna; Murray Horwitz, Mara; Zhou, Li Current Epidemiology Reports, Vol. 5, Issue 4 https://doi.org/10.1007/s40471-018-0165-9	journal	September 2018
A measure of anxiety symptoms among children Spence, Susan H. Behaviour Research and Therapy, Vol. 36, Issue 5 https://doi.org/10.1016/S0005-7967(98)00034-5	journal	May 1998
Developmental Epidemiology of Anxiety Disorders Beesdo-Baum, Katja; Knappe, Susanne Child and Adolescent Psychiatric Clinics of North America, Vol. 21, Issue 3 https://doi.org/10.1016/j.chc.2012.05.001	journal	July 2012
Risk Factors for Pediatric Anxiety Disorders Warner, Emily N.; Strawn, Jeffrey R. Child and Adolescent Psychiatric Clinics of North America, Vol. 32, Issue 3 https://doi.org/10.1016/j.chc.2022.10.001	journal	July 2023
Developmental Epidemiology of Pediatric Anxiety Disorders Warner, Emily N.; Ammerman, Robert T.; Glauser, Tracy A. Child and Adolescent Psychiatric Clinics of North America, Vol. 32, Issue 3 https://doi.org/10.1016/j.chc.2023.02.001	journal	July 2023
Linguistic markers predict onset of Alzheimer's disease Eyigoz, Elif; Mathur, Sachin; Santamaria, Mar EClinicalMedicine, Vol. 28 https://doi.org/10.1016/j.eclinm.2020.100583	journal	November 2020
Physician nurse care: A new use of UMLS to measure professional contribution Boyd, Andrew D.; Dunn Lopez, Karen; Lugaresi, Camillo International Journal of Medical Informatics, Vol. 113 https://doi.org/10.1016/j.ijmedinf.2018.02.002	journal	May 2018
Finding warning markers: Leveraging natural language processing and machine learning technologies to detect risk of school violence Ni, Yizhao; Barzman, Drew; Bachtel, Alycia International Journal of Medical Informatics, Vol. 139 https://doi.org/10.1016/j.ijmedinf.2020.104137	journal	July 2020
Prevalence and Correlates of Mental Disorders in Children Aged 9 and 10 Years: Results From the ABCD Study Olfson, Mark; Wall, Melanie M.; Wang, Shuai Journal of the American Academy of Child & Adolescent Psychiatry, Vol. 62, Issue 8 https://doi.org/10.1016/j.jaac.2023.04.005	journal	August 2023
Linguistic markers of anxiety and depression in Somatic Symptom and Related Disorders: Observational study of a digital intervention Malgaroli, Matteo; Hull, Thomas D.; Calderon, Adam Journal of Affective Disorders, Vol. 352 https://doi.org/10.1016/j.jad.2024.02.012	journal	May 2024
Prevalence and Treatment of Depression, Anxiety, and Conduct Problems in US Children Ghandour, Reem M.; Sherman, Laura J.; Vladutiu, Catherine J. The Journal of Pediatrics, Vol. 206 https://doi.org/10.1016/j.jpeds.2018.09.021	journal	March 2019
Quantitative forecasting of PTSD from early trauma responses: A Machine Learning application Galatzer-Levy, Isaac R.; Karstoft, Karen-Inge; Statnikov, Alexander Journal of Psychiatric Research, Vol. 59 https://doi.org/10.1016/j.jpsychires.2014.08.017	journal	December 2014
Depression and anxiety have distinct and overlapping language patterns: Results from a clinical interview. Stade, Elizabeth C.; Ungar, Lyle; Eichstaedt, Johannes C. Journal of Psychopathology and Clinical Science, Vol. 132, Issue 8 https://doi.org/10.1037/abn0000850	journal	November 2023
More than a biomarker: could language be a biosocial marker of psychosis? Palaniyappan, Lena npj Schizophrenia, Vol. 7, Issue 1 https://doi.org/10.1038/s41537-021-00172-1	journal	August 2021
Large language models encode clinical knowledge Singhal, Karan; Azizi, Shekoofeh; Tu, Tao Nature, Vol. 620, Issue 7972 https://doi.org/10.1038/s41586-023-06291-2	journal	July 2023
A natural language processing approach for identifying temporal disease onset information from mental healthcare text Viani, Natalia; Botelle, Riley; Kerwin, Jack Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-020-80457-0	journal	January 2021
Expert-augmented machine learning Gennatas, Efstathios D.; Friedman, Jerome H.; Ungar, Lyle H. Proceedings of the National Academy of Sciences, Vol. 117, Issue 9 https://doi.org/10.1073/pnas.1906831117	journal	February 2020
Linguistic measures of psychological distance track symptom levels and treatment outcomes in a large set of psychotherapy transcripts Nook, Erik C.; Hull, Thomas D.; Nock, Matthew K. Proceedings of the National Academy of Sciences, Vol. 119, Issue 13 https://doi.org/10.1073/pnas.2114737119	journal	March 2022
Age of onset of mental disorders: a review of recent literature Kessler, Ronald C.; Amminger, G. Paul; Aguilar-Gaxiola, Sergio Current Opinion in Psychiatry, Vol. 20, Issue 4 https://doi.org/10.1097/YCO.0b013e32816ebc8c	journal	January 2007
Research Review: Pediatric anxiety disorders – what have we learnt in the last 10 years? Strawn, Jeffrey R.; Lu, Lu; Peris, Tara S. Journal of Child Psychology and Psychiatry, Vol. 62, Issue 2 https://doi.org/10.1111/jcpp.13262	journal	June 2020
Anxiety symptom trajectories from treatment to 5‐ to 12‐year follow‐up across childhood and adolescence Bai, Sunhye; Rolon‐Arroyo, Benjamin; Walkup, John T. Journal of Child Psychology and Psychiatry, Vol. 64, Issue 9 https://doi.org/10.1111/jcpp.13796	journal	April 2023
A Machine Learning Approach to Identifying the Thought Markers of Suicidal Subjects: A Prospective Multicenter Trial Pestian, John P.; Sorter, Michael; Connolly, Brian Suicide and Life-Threatening Behavior, Vol. 47, Issue 1 https://doi.org/10.1111/sltb.12312	journal	November 2016
A Machine Learning Approach to Identifying Changes in Suicidal Language Pestian, John; Santel, Daniel; Sorter, Michael Suicide and Life-Threatening Behavior, Vol. 50, Issue 5 https://doi.org/10.1111/sltb.12642	journal	June 2020
Natural Language Processing-Based Quantication of the Mental State of Psychiatric Patients Mukherjee, Sankha S.; Yu, Jiawei; Won, Yida Computational Psychiatry, Vol. 4, Issue 0 https://doi.org/10.1162/cpsy_a_00030	journal	December 2020
How accurately can supervised machine learning model predict a targeted psychiatric disorder? Jahrami, Haitham; Pakpour, Amir H.; Husain, Waqar BMC Psychiatry, Vol. 24, Issue 1 https://doi.org/10.1186/s12888-024-06152-w	journal	October 2024
Development and psychometric evaluation of the Decision Tool Anxiety Disorders, OCD and PTSD (DTAOP): Facilitating the early detection of patients in need of highly specialized care van Krugten, Frédérique C. W.; Kaddouri, Meriam; Goorden, Maartje PLOS ONE, Vol. 16, Issue 8 https://doi.org/10.1371/journal.pone.0256384	journal	August 2021
Mental Health Surveillance Among Children — United States, 2013–2019 Bitsko, Rebecca H.; Claussen, Angelika H.; Lichstein, Jesse MMWR Supplements, Vol. 71, Issue 2 https://doi.org/10.15585/mmwr.su7102a1	journal	February 2022
Toward Linguistic Recognition of Generalized Anxiety Disorder Rook, Laurens; Mazza, Maria Chiara; Lefter, Iulia Frontiers in Digital Health, Vol. 4 https://doi.org/10.3389/fdgth.2022.779039	journal	April 2022
The Next Generation of Medical Decision Support: A Roadmap Toward Transparent Expert Companions Bruckert, Sebastian; Finzel, Bettina; Schmid, Ute Frontiers in Artificial Intelligence, Vol. 3 https://doi.org/10.3389/frai.2020.507973	journal	September 2020
What's in a Note: Construction of a Suicide Note Corpus Pestian, John P.; Matykiewicz, Pawel; Linn-Gust, Michelle Biomedical Informatics Insights, Vol. 5 https://doi.org/10.4137/BII.S10213	journal	January 2012

Similar Records

Decoding substance use disorder severity from clinical notes using a large language model

Journal Article · Thu Feb 06 19:00:00 EST 2025 · npj Mental Health Research (Online) · OSTI ID:2538026

Health-Related Quality of Life in Cervical Cancer Survivors: A Population-Based Survey

Journal Article · Wed Apr 01 00:00:00 EDT 2009 · International Journal of Radiation Oncology, Biology and Physics · OSTI ID:21276750

Mental health effects of the Three Mile Island nuclear reactor restart

Journal Article · Sat Aug 01 00:00:00 EDT 1987 · Am. J. Psychiatry; (United States) · OSTI ID:6205209

Related Subjects

feature engineering
lexicon
machine learning
mental health
pediatric anxiety

Comparison of Expert Vocabulary Usage Patterns Between Mental Health and Nonmental Health Clinicians When Diagnosing Pediatric Anxiety Disorders

Citation Formats

References (35)

Similar Records

Related Subjects