Accepted for/Published in: JMIR Formative Research
Date Submitted: Jun 13, 2024
Date Accepted: Sep 21, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Decoding Pain Chronicity in Electronic Health Records: Feasibility of Automated Annotation of Pain Chronicity in Chronic Low Back Pain Patients
ABSTRACT
Background:
Background:
Chronic low back pain is a severe health condition with underlying biopsychosocial factors that make diagnosis difficult and pain chronicity has been shown to be an important variable for studying patient outcomes.
Objective:
Objective:
Pain chronicity is not typically recorded in Electronic Health Records (EHRs) and currently needs to be manually annotated by experts. Using a dataset from an interdisciplinary spine clinic consisting of 386 patients manually annotated with pain chronicity by clinical experts, our study has two objectives: firstly, to study the relationship between expert-annotated chronicity and social determinant variables presents in EHRs and secondly, to study the feasibility of extraction of chronicity from the EHR without expert annotation.
Methods:
Methods:
We performed a univariate regression to study associations between manually annotated pain chronicity and the structured variables in EHRs. Next, we trained a random forest model using caret in R to predict chronicity using structured data and unstructured data extracted by the NLP tool.
Results:
Results:
Our random forest model using structured data showed a statistically significant correlation of 0.887 with MAE of 18.45 while our model that utilized the NLP tool to extract information from the unstructured clinical notes and structured data showed a slightly higher correlation of 0.968 with MAE of 10.87 between predicted and observed chronicity
Conclusions:
Conclusion: Our study indicates that pain chronicity from EHR data could be used to study more topics on larger datasets in the future without the need for manual annotation and that using NLP tools to automate prediction is feasible. Funded by NIH U19AR076737.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.