Prescription Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) and Incidence of Depression Among Older Cancer Survivors With Osteoarthritis: A Machine Learning Analysis

Abstract

Objectives: This study examined prescription NSAIDs as one of the leading predictors of incident depression and assessed the direction of the association among older cancer survivors with osteoarthritis.

Methods: This study used a retrospective cohort (N = 14, 992) of older adults with incident cancer (breast, prostate, colorectal cancers, or non-Hodgkin's lymphoma) and osteoarthritis. We used the longitudinal data from the linked Surveillance, Epidemiology, and End Results -Medicare data for the study period from 2006 through 2016, with a 12-month baseline and 12-month follow-up period. Cumulative NSAIDs days was assessed during the baseline period and incident depression was assessed during the follow-up period. An eXtreme Gradient Boosting (XGBoost) model was built with 10-fold repeated stratified cross-validation and hyperparameter tuning using the training dataset. The final model selected from the training data demonstrated high performance (Accuracy: 0.82, Recall: 0.75, Precision: 0.75) when applied to the test data. SHapley Additive exPlanations (SHAP) was used to interpret the output from the XGBoost model.

Results: Over 50% of the study cohort had at least one prescption of NSAIDs. Nearly 13% of the cohort were diagnosed with incident depression, with the rates ranging between 7.4% for prostate cancer and 17.0% for colorectal cancer. The highest incident depression rate of 25% was observed at 90 and 120 cumulative NSAIDs days thresholds. Cumulative NSAIDs days was the sixth leading predictor of incident depression among older adults with OA and cancer. Age, education, care fragmentation, polypharmacy, and zip code level poverty were the top 5 predictors of incident depression.

Conclusion: Overall, 1 in 8 older adults with cancer and OA were diagnosed with incident depression. Cumulative NSAIDs days was the sixth leading predictor with an overall positive association with incident depression. However, the association was complex and varied by the cumulative NSAIDs days.

Keywords: NSAIDs; Osteoarthritis; cancer; depression; inflammation; machine learning; older adults.

Figure 1.

Incident depression rates by cumulative continuous NSAIDs days among fee-for-service medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with cancer and osteoarthritis in linked SEER Cancer Registry and Medicare Claims files, 2006 to 2016. Based on 14,992 older adults (age ⩾ 67 years at incident cancer diagnosis) with cancer and OA, who were continuously enrolled in Medicare Part A, and Part B during the study period, and Part D during baseline period and follow-up period. Abbreviations: NSAIDs, non-steroidal anti-inflammatory drugs; SEER, Surveillance, Epidemiology, and End Results Cancer Registry.

Figure 2.

Simplified relationships between top predictors and incident depression among fee-for-service medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with cancer and osteoarthritis in linked SEER Cancer Registry and Medicare Claims files, 2006 to 2016. The x-axis represents the marginal contribution of a feature to the change in the predicted probability of incident depression diagnosis; pink color represent increase and blue color represents decrease in the incidence of depression. Based on 14,992 older fee-for-service Medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with incident cancer and pre-existing OA and who were continuously enrolled in Medicare Part A, and Part B during the study period, and Part D during baseline period and follow-up period. Care fragmentation = Bice-Boxerman continuity of care index to calculate care fragmentation during the 12-month baseline period (See Methods). Age: age at incident cancer diagnosis; Median income: Zip-level median income from Census Bureau file; Poverty: percent zip-level persons living below poverty from Census Bureau file linkage; Education level: zip-level percent persons with less than high school diploma from Census Bureau file linkage; Oncology and screening centers: area-level information from area health resource file linkage. Abbreviations: NSAIDs, non-steroidal anti-inflammatory drugs; OA, osteoarthritis; SEER, Surveillance, Epidemiology, and End Results Cancer Registry; SHAP, Shapley Additive exPlanations.

Figure 3.

Heterogeneity in relationships between predictors and incident depression. SHAP dependence plots among fee-for-service medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with cancer and osteoarthritis in linked SEER Cancer Registry and Medicare Claims files, 2006-2016. The figures represent the SHAP log-odd values by cumulative continuous NSAIDs days (a), care fragmentation (b), age (c), and polypharmacy (d). In all the figures the x-axis represents the numeric value of each feature, and the y-axis represents the marginal contribution of the feature to the change in the predicted probability of incident depression diagnosis for each individual in the dataset. Based on 14 992 older fee-for-service Medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with incident cancer and pre-existing Osteoarthritis and who were continuously enrolled in Medicare Part A, and Part B during the study period, and Part D during baseline period and follow-up period. Abbreviations: NSAIDs, non-steroidal anti-inflammatory drugs; SEER, Surveillance, Epidemiology, and End Results Cancer Registry; SHAP, Shapley Additive exPlanations.

Appendix 1.

Patient attrition flow chart for fee-for-service medicare beneficiaries (age ⩾ 67 years at incident cancer diagnosis) with cancer and osteoarthritis in linked SEER Cancer Registry and Medicare Claims files, 2006 to 2016.