Machine Learning Data Sources in Pediatric Sleep Research: Assessing Racial/ethnic Differences in Electronic Health Record-based Clinical Notes Prior to Model Training

Overview

Journal Front Sleep

Date 2024 May 31

PMID 38817450

Authors

Mattina A Davenport

Joseph W Sirrianni

Deena J Chisolm

Affiliations

Soon will be listed here.

Abstract

Introduction: Pediatric sleep problems can be detected across racial/ethnic subpopulations in primary care settings. However, the electronic health record (EHR) data documentation that describes patients' sleep problems may be inherently biased due to both historical biases and informed presence. This study assessed racial/ethnic differences in natural language processing (NLP) training data (e.g., pediatric sleep-related keywords in primary care clinical notes) prior to model training.

Methods: We used a predefined keyword features set containing 178 Peds B-SATED keywords. We then queried all the clinical notes from patients seen in pediatric primary care between the ages of 5 and 18 from January 2018 to December 2021. A least absolute shrinkage and selection operator (LASSO) regression model was used to investigate whether there were racial/ethnic differences in the documentation of Peds B-SATED keywords. Then, mixed-effects logistic regression was used to determine whether the odds of the presence of global Peds B-SATED dimensions also differed across racial/ethnic subpopulations.

Results: Using both LASSO and multilevel modeling approaches, the current study found that there were racial/ethnic differences in providers' documentation of Peds B-SATED keywords and global dimensions. In addition, the most frequently documented Peds B-SATED keyword rankings qualitatively differed across racial/ethnic subpopulations.

Conclusion: This study revealed providers' differential patterns of documenting Peds B-SATED keywords and global dimensions that may account for the under-detection of pediatric sleep problems among racial/ethnic subpopulations. In research, these findings have important implications for the equitable clinical documentation of sleep problems in pediatric primary care settings and extend prior retrospective work in pediatric sleep specialty settings.

References

Reynolds A, Spaeth A, Hale L, Williamson A, LeBourgeois M, Wong S . Pediatric sleep: current knowledge, gaps, and opportunities for the future. Sleep. 2023; 46(7). PMC: 10334737. DOI: 10.1093/sleep/zsad060. View

Kang J, Hanif M, Mirza E, Khan M, Malik M . Machine learning in primary care: potential to improve public health. J Med Eng Technol. 2020; 45(1):75-80. DOI: 10.1080/03091902.2020.1853839. View

Harada T, Miyagami T, Kunitomo K, Shimizu T . Clinical Decision Support Systems for Diagnosis in Primary Care: A Scoping Review. Int J Environ Res Public Health. 2021; 18(16). PMC: 8391274. DOI: 10.3390/ijerph18168435. View

Honaker S, Dugan T, Daftary A, Davis S, Saha C, Baye F . Unexplained Practice Variation in Primary Care Providers' Concern for Pediatric Obstructive Sleep Apnea. Acad Pediatr. 2018; 18(4):418-424. DOI: 10.1016/j.acap.2018.01.011. View

Honaker S, Street A, Daftary A, Downs S . The Use of Computer Decision Support for Pediatric Obstructive Sleep Apnea Detection in Primary Care. J Clin Sleep Med. 2019; 15(3):453-462. PMC: 6411194. DOI: 10.5664/jcsm.7674. View

Golden M, Cosottile M, Meadows T, Parikh M, ODell S . Primary care providers' practices regarding patient sleep: Impact of integrated behavioral health. Fam Syst Health. 2022; 41(2):192-200. DOI: 10.1037/fsh0000695. View

Gueye-Ndiaye S, Williamson A, Redline S . Disparities in Sleep-Disordered Breathing: Upstream Risk Factors, Mechanisms, and Implications. Clin Chest Med. 2023; 44(3):585-603. PMC: 10513750. DOI: 10.1016/j.ccm.2023.03.012. View

Honaker S, Meltzer L . Sleep in pediatric primary care: A review of the literature. Sleep Med Rev. 2015; 25:31-9. DOI: 10.1016/j.smrv.2015.01.004. View

Rubens S, Patrick K, Williamson A, Moore M, Mindell J . Individual and socio-demographic factors related to presenting problem and diagnostic impressions at a pediatric sleep clinic. Sleep Med. 2016; 25:67-72. DOI: 10.1016/j.sleep.2016.06.017. View

10.

Ramgopal S, Sanchez-Pinto L, Horvat C, Carroll M, Luo Y, Florin T . Artificial intelligence-based clinical decision support in pediatrics. Pediatr Res. 2022; 93(2):334-341. PMC: 9668209. DOI: 10.1038/s41390-022-02226-1. View

11.

Willis V, Craig K, Jabbarpour Y, Scheufele E, Arriaga Y, Ajinkya M . Digital Health Interventions to Enhance Prevention in Primary Care: Scoping Review. JMIR Med Inform. 2022; 10(1):e33518. PMC: 8817213. DOI: 10.2196/33518. View

12.

Thompson H, Sharma B, Bhalla S, Boley R, McCluskey C, Dligach D . Bias and fairness assessment of a natural language processing opioid misuse classifier: detection and mitigation of electronic health record data disadvantages across racial subgroups. J Am Med Inform Assoc. 2021; 28(11):2393-2403. PMC: 8510285. DOI: 10.1093/jamia/ocab148. View

13.

Mosher W, Piccinini-Vallis H . Assessing the frequency with which primary care providers address sleep of infants and young children. J Sleep Res. 2022; 31(5):e13579. DOI: 10.1111/jsr.13579. View

14.

Rozier M, Patel K, Cross D . Electronic Health Records as Biased Tools or Tools Against Bias: A Conceptual Model. Milbank Q. 2021; 100(1):134-150. PMC: 8932623. DOI: 10.1111/1468-0009.12545. View

15.

Wallace D, Pace Gallagher J, Peterson S, Ndiaye-Gueye S, Fox K, Redline S . Is exposure to chemical pollutants associated with sleep outcomes? A systematic review. Sleep Med Rev. 2023; 70:101805. PMC: 10528206. DOI: 10.1016/j.smrv.2023.101805. View

16.

Meltzer L, Johnson C, Crosette J, Ramos M, Mindell J . Prevalence of diagnosed sleep disorders in pediatric primary care practices. Pediatrics. 2010; 125(6):e1410-8. PMC: 3089951. DOI: 10.1542/peds.2009-2725. View

17.

Hamilton A, Strauss A, Martinez D, Hinson J, Levin S, Lin G . Machine learning and artificial intelligence: applications in healthcare epidemiology. Antimicrob Steward Healthc Epidemiol. 2022; 1(1):e28. PMC: 9495400. DOI: 10.1017/ash.2021.192. View

18.

Huang J, Galal G, Etemadi M, Vaidyanathan M . Evaluation and Mitigation of Racial Bias in Clinical Machine Learning Models: Scoping Review. JMIR Med Inform. 2022; 10(5):e36388. PMC: 9198828. DOI: 10.2196/36388. View

19.

Carson M, Cicalese O, Bhandari E, Stefanovski D, Fiks A, Mindell J . Discrepancies Between Caregiver Reported Early Childhood Sleep Problems and Clinician Documentation and Referral. Acad Pediatr. 2023; 23(6):1234-1241. PMC: 10409870. DOI: 10.1016/j.acap.2023.02.001. View

20.

Williamson A, Soehner A, Boyd R, Buysse D, Harvey A, Jonassaint C . A protocol for applying health equity-informed implementation science models and frameworks to adapt a sleep intervention for adolescents at risk for suicidal thoughts and behaviors. Front Public Health. 2022; 10:971754. PMC: 9597692. DOI: 10.3389/fpubh.2022.971754. View