Previously submitted to: JMIR Medical Informatics (no longer under consideration since Aug 06, 2026)
Date Submitted: Jul 20, 2026
Open Peer Review Period: Aug 6, 2026 - Aug 6, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited.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.
Effect of a Clinical Decision Support System on Medical Record Quality: An Interrupted Time Series Analysis Using Generalized Linear Models
ABSTRACT
Background:
Clinical decision support systems (CDSS) have become key tools for medical record quality control, yet evidence from rigorous quasi-experimental designs remains limited. Traditional linear models for percentage outcomes are prone to boundary violations and heteroscedasticity, which can bias effect estimates.
Objective:
To evaluate the effect of CDSS on medical record quality using interrupted time series (ITS) analysis with generalized linear models (GLM), principal component analysis (PCA) for dimensionality reduction, and Fourier seasonal adjustment.
Methods:
We conducted an ITS quasi-experimental study using 36 consecutive months (December 2022 to November 2025) of monthly quality control data from a tertiary hospital in China. Three highly correlated indicators (record score, grade A rate, and problems per record) were reduced via PCA to a composite quality index (first principal component explaining 93.2% of variance). For 8 percentage indicators, we fitted ITS segmented regression using GLM with binomial distribution and logit link, with frequency weights (monthly sample size n=2,843 records) to correct standard errors for aggregated proportions. Fourier sine/cosine terms controlled seasonal effects. Benjamini-Hochberg false discovery rate (FDR) correction was applied to 18 hypothesis tests (9 indicators x 2 coefficients). Average marginal effects (AME) in percentage points were computed for clinical interpretability.
Results:
After FDR correction, level changes (β2) were significant for 8 of 9 indicators (q<.05). The largest AMEs were observed for critical value processing completeness (10.26 percentage points), 8-hour first progress note completion (7.48 pp), and principal diagnosis coding accuracy (3.25 pp). Trend changes (β3) were significant for all 9 indicators. The 24-hour discharge record completion rate showed no significant level change (q=.093) but a significant positive trend. Counterfactual analysis estimated net effects up to 29.87 pp for admission record completion. The GLM-logit model naturally constrained predictions within (0, 100)%, eliminating boundary violations present in linear models.
Conclusions:
CDSS effectively curbed declining trends in medical record quality and shifted physician behavior from passive remediation to proactive compliance. For indicators constrained by physical workflow processes, we recommend advancing CDSS alert nodes to natural pause points in clinical workflows rather than relying solely on post-event reminders. GLM-logit ITS analysis provides methodologically superior inference for percentage outcomes in health informatics evaluation. Clinical Trial: no
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.