Quantifying the impact of chronic conditions on a diagnosis of major depressive disorder in adults: a cohort study using linked electronic medical records

Abstract

Background: Major depressive disorder (MDD) is often comorbid with other chronic mental and physical health conditions. Although the literature widely acknowledges the association of many chronic conditions with the risk of MDD, the relative importance of these conditions on MDD risk in the presence of other conditions is not well investigated. In this study, we aimed to quantify the relative contribution of selected chronic conditions to identify the conditions most influential to MDD risk in adults and identify differences by age.

Methods: This study used electronic health record (EHR) data on patients empanelled with primary care at Mayo Clinic in June 2013. A validated EHR-based algorithm was applied to identify newly diagnosed MDD patients between 2000 and 2013. Non-MDD controls were matched 1:1 to MDD cases on birth year (±2 years), sex, and outpatient clinic visits in the same year of MDD case diagnosis. Twenty-four chronic conditions defined by Chronic Conditions Data Warehouse were ascertained in both cases and controls using diagnosis codes within 5 years of index dates (diagnosis dates for cases, and the first clinic visit dates for matched controls). For each age group (45 years or younger, between 46 and 60, and over 60 years), conditional logistic regression models were used to test the association between each condition and subsequent MDD risk, adjusting for educational attainment and obesity. The relative influence of these conditions on the risk of MDD was quantified using gradient boosting machine models.

Results: A total of 11,375 incident MDD cases were identified between 2000 and 2013. Most chronic conditions (except for eye conditions) were associated with risk of MDD, with different association patterns observed depending on age. Among 24 chronic conditions, the greatest relative contribution was observed for diabetes mellitus for subjects aged ≤ 60 years and rheumatoid arthritis/osteoarthritis for those over 60 years.

Conclusions: Our results suggest that specific chronic conditions such as diabetes mellitus and rheumatoid arthritis/osteoarthritis may have greater influence than others on the risk of MDD.

Keywords: Comorbidity; Depression; Major depressive disorder; Multimorbidity; Relative influence; Risk factors.

Fig. 1

Frequency of chronic conditions occurred prior to index dates, separately by cases and controls. Proportions for prostate cancer and benign prostate hyperplasia were among men and endometrial cancer was among women

Fig. 2

Association of each chronic condition with the risk of MDD, stratified by different age group and adjusted by education attainment and obesity. Three different age groups were used: subjects aged 45 or younger (a), subjects aged between 46 and 60 (b), and subjects aged 61 or older (c)

Fig. 3

Relative influence (%) of chronic conditions on MDD risk, stratified by different age group. Three different age groups were used: subjects aged 45 or younger (a), subjects aged between 46 and 60 (b), and subjects aged 61 or older (c)