Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 28, 2022
Open Peer Review Period: Apr 28, 2022 - Jun 23, 2022
Date Accepted: Dec 19, 2022
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited.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.
Association between co-morbidities and prescribed drugs in obstructive sleep apnea suspected patients: an inductive rule learning approach
ABSTRACT
Background:
One way to partially impute missing clinical variables is to find associations with other informative variables described in electronic health records, as obstructive sleep apnea (OSA) has multiple clinical presentations.
Objective:
To explore disease-drug associations in obstructive sleep apnea (OSA) suspected patients to improve missed diagnoses and clinical data completeness in electronic health records.
Methods:
We conducted a retrospective study from a cohort of adult patients referred to the Sleep Laboratory of the University Hospital Center of São João who performed in-laboratory polysomnography. Inclusion criteria were age above eighteen years old, with a suspicion of OSA and having undergone polysomnography between January 2011 and December 2019.
Results:
A total of 481 patients taking any drug were included, resulting in 29 disease-drug strong association rules. The prescribed drugs were related to the alimentary tract and metabolism (A), cardiovascular (C), and nervous system (N). Three strong rules were obtained, describing the relationships between A10 (drugs used in diabetes) and diabetes (Lift: 2.05, Confidence: 91%), C10 (lipid modifying agents) and dyslipidemia (L: 1.28; C: 87%), and C09 (agents acting on the renin-angiotensin system) and arterial hypertension (L: 1.24; C: 95%).
Conclusions:
We found three strong disease-drug associations rules in OSA suspected patients that can help to improve missed diagnosis in 4%, 2%, and 1% in diabetes, arterial hypertension, and dyslipidemia, respectively, based on three 2nd level ATC-codes (A10, C09, and C10).
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.