Dataset Information

A Machine Learning Approach to Identify Predictors of Potentially Inappropriate Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) Use in Older Adults with Osteoarthritis.

ABSTRACT: Evidence from some studies suggest that osteoarthritis (OA) patients are often prescribed non-steroidal anti-inflammatory drugs (NSAIDs) that are not in accordance with their cardiovascular (CV) or gastrointestinal (GI) risk profiles. However, no such study has been carried out in the United States. Therefore, we sought to examine the prevalence and predictors of potentially inappropriate NSAIDs use in older adults (age > 65) with OA using machine learning with real-world data from Optum De-identified Clinformatics^® Data Mart. We identified a retrospective cohort of eligible individuals using data from 2015 (baseline) and 2016 (follow-up). Potentially inappropriate NSAIDs use was identified using the type (COX-2 selective vs. non-selective) and length of NSAIDs use and an individual's CV and GI risk. Predictors of potentially inappropriate NSAIDs use were identified using eXtreme Gradient Boosting. Our study cohort comprised of 44,990 individuals (mean age 75.9 years). We found that 12.8% individuals had potentially inappropriate NSAIDs use, but the rate was disproportionately higher (44.5%) in individuals at low CV/high GI risk. Longer duration of NSAIDs use during baseline (AOR 1.02; 95% CI:1.02-1.02 for both non-selective and selective NSAIDs) was associated with a higher risk of potentially inappropriate NSAIDs use. Additionally, individuals with low CV/high GI (AOR 1.34; 95% CI:1.20-1.50) and high CV/low GI risk (AOR 1.61; 95% CI:1.34-1.93) were also more likely to have potentially inappropriate NSAIDs use. Heightened surveillance of older adults with OA requiring NSAIDs is warranted.

SUBMITTER: Patel J

PROVIDER: S-EPMC7794853 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Approach to Identify Predictors of Potentially Inappropriate Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) Use in Older Adults with Osteoarthritis.

Patel Jayeshkumar J Ladani Amit A Sambamoorthi Nethra N LeMasters Traci T Dwibedi Nilanjana N Sambamoorthi Usha U

International journal of environmental research and public health 20201228 1

Evidence from some studies suggest that osteoarthritis (OA) patients are often prescribed non-steroidal anti-inflammatory drugs (NSAIDs) that are not in accordance with their cardiovascular (CV) or gastrointestinal (GI) risk profiles. However, no such study has been carried out in the United States. Therefore, we sought to examine the prevalence and predictors of potentially inappropriate NSAIDs use in older adults (age > 65) with OA using machine learning with real-world data from Optum De-iden ...[more]

PMID: 33379288

Similar Datasets

Project description:Globally, usage of non-steroidal anti-inflammatory drugs (NSAIDs) in elderly with chronic pain has been reported as frequent. Though NSAIDs are fundamental in maintaining their quality of life, the risk of polypharmacy, drug interactions and adverse effects is of paramount importance as the elderly usually require multiple medications for their co-morbidities. If prescriptions are not appropriately monitored and managed, they are likely to expose patients to serious drug interactions and potentially fatal adverse effects. This study was conducted to assess the appropriateness of NSAIDs use and determine the risk of NSAIDs related potential interactions in elderly. An analytical cross-sectional study was conducted among elderly out-patients (aged 60 and above) who visited three hospitals in Asmara, Eritrea, between August 22 and September 29, 2018. A stratified random sampling design was employed and data was collected using an interview-based questionnaire and by abstracting information from patients' prescriptions and medical cards. Descriptive and analytical statistics including chi-square test and logistic regression were employed using IBM SPSS (version 22). A total of 285 respondents were enrolled in the study with similar male to female ratio. One in four of all respondents were chronic NSAIDs users and NSAIDs risk practice was reported in 24%. Using chronic NSAIDs without prophylactic gastro-protective agents, self-medication, polypharmacy and drug-drug interactions were the main problems identified. A total of 322 potential interactions in 205 patients were identified and of which, 97.2% were classified as moderate, 0.6% severe and the rest were mild. Those who involved in self-medication were more likely to be exposed to drug interactions. Diabetes (AOR = 2.39, 95% CI: 1.14, 5.02) and hypertension (AOR = 9.06, 95% CI: 4.00, 20.51) were associated with chronic NSAIDs use and incidence of potential drug interactions (AOR = 3.5, 95%CI: 1.68, 4.3; AOR = 2.81, 95%CI: 1.61, 4.9 respectively), while diabetes AOR = 4.5, 95% CI: 2.43, 8.35) and cardiac problems (AOR = 4.29, 95% CI: 1.17, 15.73) were more likely to be associated with incidence of polypharmacy. In conclusion, chronic use of NSAIDs without gastro-protective agents and therapeutic duplication of NSAIDs were commonly which requires attention from programmers, health facility managers and healthcare professionals to safeguard elderlies from preventable harm.

Project description:BackgroundOsteoarthritis (OA) is a major cause of chronic pain. Non-steroidal anti-inflammatory drugs (NSAIDs) are analgesics commonly used for musculoskeletal pain; however, NSAIDs can increase the risk of certain adverse events, such as gastrointestinal bleeding, edema, heart failure, and hypertension.ObjectiveThe objective of this study was to characterize existing comorbidities among patients with OA. For patients with OA with and without a coexisting medical condition of interest (CMCOI), we estimated the prevalence of prescribing and dispensing NSAIDs pre-OA and post-OA diagnosis.MethodsData from three large administrative claims databases were used to construct an OA retrospective cohort. Databases leveraged were IBM MarketScan Medicare Supplemental Database (MDCR), IBM MarketScan Commercial Database (CCAE), and Optum's de-identified Clinformatics® Data Mart Database (Optum CDM). The OA study population was defined to be those patients who had an OA diagnosis from an inpatient or outpatient visit with at least 365 days of prior observation time in the database during January 2000 through May 2021. Asthma, cardiovascular disorders, renal impairment, and gastrointestinal bleeding risks were the CMCOI of interest. Patients with OA were then classified as having or not having evidence of a CMCOI. For both groups, NSAID dispensing patterns pre-OA and post-OA diagnosis were identified. Descriptive analysis was performed within the Observational Health Data Sciences and Informatics framework.ResultsIn each database, the proportion of the OA population with at least one CMCOI was nearly 50% or more (48.0% CCAE; 74.4% MDCR; 68.6% Optum CDM). Cardiovascular disease was the most commonly observed CMCOI in each database, and in two databases, nearly one in four patients with OA had two or more CMCOI (23.2% MDCR; 22.6% Optum CDM). Among the OA population with CMCOI, NSAID utilization post-OA diagnosis ranged from 33.0 to 46.2%. Following diagnosis of OA, an increase in the prescribing and dispensing of NSAIDs was observed in all databases, regardless of patient CMCOI presence.ConclusionsThis study provides real-world evidence of the pattern of prescribing and dispensing of NSAIDs among patients with OA with and without CMCOI, which indicates that at least half of patients with OA in the USA have a coexisting condition. These conditions may increase the risk of side effects commonly associated with NSAIDs. Yet, at least 32% of these patients were prescribed and dispensed NSAIDs. These data support the importance of shared decision making between healthcare professionals and patients when considering NSAIDs for the treatment of OA in patients with NSAID-relevant coexisting medical conditions.

Dataset Information

A Machine Learning Approach to Identify Predictors of Potentially Inappropriate Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) Use in Older Adults with Osteoarthritis.

Publications

A Machine Learning Approach to Identify Predictors of Potentially Inappropriate Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) Use in Older Adults with Osteoarthritis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets