Browsing by Author "Sambamoorthi, Usha"
Now showing 1 - 20 of 27
- Results Per Page
- Sort Options
Item A Machine Learning Approach to Identify Predictors of Potentially Inappropriate Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) Use in Older Adults with Osteoarthritis(MDPI, 2020-12-28) Patel, Jayeshkumar; Ladani, Amit; Sambamoorthi, Nethra; LeMasters, Traci; Dwibedi, Nilanjana; Sambamoorthi, UshaEvidence 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((R)) 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.Item A Multi-Level Analysis of Individual and Neighborhood Factors Associated with Patient Portal Use among Adult Emergency Department Patients with Multimorbidity(MDPI, 2023-01-22) Wang, Hao; Shen, Chan; Barbaro, Michael; Ho, Amy F.; Pathak, Mona; Dunn, Cita; Sambamoorthi, UshaBACKGROUND: Patient portals tethered to electronic health records (EHR) have become vital to patient engagement and better disease management, specifically among adults with multimorbidity. We determined individual and neighborhood factors associated with patient portal use (MyChart) among adult patients with multimorbidity seen in an Emergency Department (ED). METHODS: This study adopted a cross-sectional study design and used a linked database of EHR from a single ED site to patients' neighborhood characteristics (i.e., zip code level) from the American Community Survey. The study population included all adults (age > 18 years), with at least one visit to an ED and multimorbidity between 1 January 2019 to 31 December 2020 (N = 40,544). Patient and neighborhood characteristics were compared among patients with and without MyChart use. Random-intercept multi-level logistic regressions were used to analyze the associations of patient and neighborhood factors with MyChart use. RESULTS: Only 19% (N = 7757) of adults with multimorbidity used the patient portal. In the fully adjusted multi-level model, at the patient level, having a primary care physician (AOR = 5.55, 95% CI 5.07-6.07, p < 0.001) and health insurance coverage (AOR = 2.41, 95% CI 2.23-2.61, p < 0.001) were associated with MyChart use. At the neighborhood level, 4.73% of the variation in MyChart use was due to differences in neighborhood factors. However, significant heterogeneity existed in patient portal use when neighborhood characteristics were included in the model. CONCLUSIONS: Among ED patients with multimorbidity, one in five adults used patient portals. Patient-level factors, such as having primary care physicians and insurance, may promote patient portal use.Item Association of Cancer with Alzheimer's Disease and related Dementias among older adults with chronic pains: TriNetX analysis with Multi-institutional Electronic Health Records(2023) PITHUA, PATRICK; PAHAK, MONA; Bo, Zhou; Pinnamraju, Jahnvani; Sambamoorthi, UshaIntroduction Recent retrospective cohort studies have reported that non-cancer chronic pain, specifically non-cancer pain conditions (NCPCs), are associated with an increased risk of Alzheimer's disease and related dementias (ADRD) in older adults. However, a recent case-control study found that cancer-induced pain had a protective association with ADRD, suggesting that cancer pain's association with ADRD is inconclusive. Therefore, we analyzed the association of cancer with ADRD among older adults with chronic pain. Methods We adopted a retrospective cohort analysis. The cohort consisted of older adults with chronic pain in 2016 and 2017. The data used in this study is from the TriNetX Research Network, which provided access to electronic medical records (diagnoses, procedures, medications, and laboratory values) for patients from 64 healthcare organizations (HCOs). A propensity score-matched analysis of cancer and non-cancer patients used age, sex, race/ethnicity, surgery, factors influencing health status and contact with health services; endocrine, nutritional, and metabolic diseases; diseases of the circulatory system; nervous system; digestive system; musculoskeletal system and connective tissue; and mental, behavioral and neurodevelopmental disorders. The outcome variable was ADRD incidence, which occurred at least one year after the first chronic pain diagnosis. Results Before matching, among older adults with cancer, there were 212,739 and 465,316 with and without cancer, respectively. The 3-year cumulative incidence of ADRD was 2.97% (N = 6320) in the cancer group and 1.96% (N = 9096) in the non-cancer group. After propensity matching, there were 195289 participants in both groups. The cumulative incidence of ADRD was 2.79% (N = 5457) in the cancer group and 2.62% (N = 5124) in the non-cancer group (Risk Ratio = 1.07, 95% CI: 1.02-1.10). Secondary analysis of ADRD incidence in adults who died did not reveal a significant association between cancer with ADRD. Conclusion Our research has found that cancer is not associated with the risk of ADRD among patients with chronic pain. Our study estimates of ADRD incidence are lower than the national rates, suggesting the limitations of electronic health records in capturing true ADRD incidence. The study's findings must be interpreted in the context of the study's strengths and limitations. For example, data were from 64 HCOs, and the study did not adjust for case-mix or practice differences. In addition, the study is limited to those seeking care in these HCOs and may have missed care obtained outside of these organizations. Thus, our estimates of ADRD incidence are substantially lower than the national ADRD incidence. Nevertheless, the study's strengths are the use of multi-institutional electronic health records, large numbers of cases and controls, and the ability to conduct propensity score-matched analysis with a comprehensive list of risk factors. Keywords: Dementia, Alzheimer's disease, and Related Disorders, Cancer, Chronic Pain, EHRItem Association of multimorbidity with the use of health information technology(Sage Publications, 2023-05-01) Manning, Sydney E.; Wang, Hao; Dwibedi, Nilanjana; Shen, Chan; Wiener, R. Constance; Findley, Patricia A.; Mitra, Sophie; Sambamoorthi, UshaOBJECTIVE: To examine the association of multimorbidity with health information technology use among adults in the USA. METHODS: We used cross-sectional study design and data from the Health Information National Trends Survey 5 Cycle 4. Health information technology use was measured with ten variables comprising access, recent use, and healthcare management. Unadjusted and adjusted logistic and multinomial logistic regressions were used to model the associations of multimorbidity with health information technology use. RESULTS: Among adults with multimorbidity, health information technology use for specific purposes ranged from 37.8% for helping make medical decisions to 51.7% for communicating with healthcare providers. In multivariable regressions, individuals with multimorbidity were more likely to report general use of health information technology (adjusted odds ratios = 1.48, 95% confidence intervals = 1.01-2.15) and more likely to use health information technology to check test results (adjusted odds ratios = 1.85, 95% confidence intervals = 1.33-2.58) compared to adults with only one chronic condition, however, there were no significant differences in other forms of health information technology use. We also observed interactive associations of multimorbidity and age on various components of health information technology use. Compared to younger adults with multimorbidity, older adults (>/= 65 years of age) with multimorbidity were less likely to use almost all aspects of health information technology. CONCLUSION: Health information technology use disparities by age and multimorbidity were observed. Education and interventions are needed to promote health information technology use among older adults in general and specifically among older adults with multimorbidity.Item The Association of Multimorbidity with Whole Health-Centric Provider Communication among Older Adults in the US(2024-03-21) Shaikh, Shawana; Sambamoorthi, Usha; Pinnamraju, JahnaviThe Association of Multimorbidity with Whole Health-centric Provider Communication among Older Adults in the US Shawana Shaikh, OMS II, Jahnavi Pinnamraju PharmD, MS, Usha Sambamoorthi, MA, PhD Background Whole Health is a person-centered approach diverging from the biomedical focus on diseases and emphasizes nutrition, recharging, spiritual, social support, physical well-being, environmental factors, and mental health. Incorporating the central tenant of “what matters to you” is key in whole health-centric patient-provider communication. This starts with inquiring patients about health goals and life quality. Nearly, 38.0 million (73%) of Americans aged > 65 years have multimorbidity. For individuals with multimorbidity, challenges exist to implementing evidence-based practices for each disease. Therefore, it is necessary to focus on the whole person and incorporate individuals' health goals and life quality for optimal management. The purpose of this study is to examine the prevalence of whole health-centered provider communication among community-dwelling older adults aged > 65 years. Methods A cross-sectional study design with data on older adults (age > 65 years) from the publicly available 2020 Medicare Current Beneficiary Survey was used. Whole health variables included how often providers asked about health goals (definitely, somewhat, never) and life quality (never, sometimes, usually, always). Multimorbidity was defined as the presence of two or more chronic conditions. Rao-Scott Chi-square tests and multinomial logistic regression were used to identify the association of multimorbidity with whole health variables while controlling for age, sex, and social determinants of health such as education, poverty, food security, supplemental health insurance, problems paying medical bills, metropolitan area, and marital status. All analyses were conducted with replicate weights using SAS 9.4 survey procedures. Results There were 5,516 older adults in our sample representing ~38.71 million older adults in the US. Overall, 43% reported that their healthcare providers 'definitely' inquired about their health goals while 31.1% reported they were 'not' asked. Additionally, only 17.5% reported being inquired ‘always’ about their life quality, while 46.5% reported 'never'. A higher percentage of those with multimorbidity were ‘definitely’ asked about health goals (69.5% vs 65.7%) compared to those without multimorbidity. However, a lower percentage of those with multimorbidity (16.5% vs. 21.6%) were ‘always’ asked about life quality. In adjusted multinomial logistic regressions, older adults with multimorbidity were more likely to 'definitely' be asked about their health goals (aOR = 1.56, 95% CI 1.26, 1.94, p < 0.001) and less likely to ‘always’ be asked about life quality (aOR = 0.65, 95% CI = 0.53, 0.79 p < 0.001) compared to those without multimorbidity. Conclusion Overall, whole health-centric communication was poor. Older adults with multimorbidity were more likely to be asked about health goals but less likely to be asked about life quality. Our findings suggest missed opportunities by providers to engage in whole health communication with patients including those with multimorbidity. Health encounters with patients can be an opportunity to empower patients to achieve person-centered health. Integrating health goals and quality-of-life questions into visits can assist providers in developing customized management to empower patients in achieving optimal and whole health.Item Association of Pediatric Head Trauma with Attention Deficit Hyperactivity Disorder (ADHD) among School-aged Children in the United States(2024-03-21) Eberwein, Andrew; Pinnamraju, Jahnavi; Sambamoorthi, UshaBackground Pediatric concussion is an important issue in healthcare that has gained recognition in recent years. Concussion may lead to negative emotional and cognitive consequences. ADHD may be a potential neurobehavioral consequence of head trauma, with evidence suggesting an increased likelihood of ADHD in individuals who have experienced concussions or have a history of head trauma. Objective This study examined disparities in pediatric head trauma and the association of a history of pediatric head trauma with ADHD using nationally representative data from the United States. Methods We performed a cross-sectional study using the 2021 National Health Interview Survey (NHIS). The study was restricted to school-aged children (5-17 years) with no missing information on ADHD or head trauma. There were 5,960 participants representing ~52.11 million US children. Our key independent variable was concussion (Yes/No) with yes indicating a positive response to any question in the 2021 NHIS survey fitting the following descriptions: “ever lost consciousness”, “ever told had a concussion”, “ever dazed or memory gap”, and “ever headache, vomit, blurred vision, or mood change after blow to the head.” ADHD was derived from a question that asked about the diagnosis of ADHD by a health professional or doctor. We performed Rao-Scott Chi-square tests and logistic regression analyses to identify the association of concussion with ADHD while controlling for other explanatory variables (sex, race & ethnicity, age, poverty status, food security, housing security, problem paying medical bills, health insurance, region, metro, family structure, adult education level). All analyses were conducted with SAS 9.4 survey procedures. Results Among the sample, 8.1% had experienced head trauma, and 10.6% had been diagnosed with ADHD. A lower percentage of Non-Hispanic Blacks (NHB) experienced head trauma (5.5% vs. 9.6%) compared to Non-Hispanic Whites (NHW). A higher percentage of males (9.1% vs. 7.0%) had head trauma compared to females. The prevalence of head trauma was higher in minors 14-17 years (13.3% vs. 4.9%) compared to 5–10-year-old children. A higher percentage of those with head trauma (20.7% vs 9.8%) had ADHD compared to those without head trauma. After adjustment for other covariates, children with concussion were more likely to report ADHD (aOR = 1.81, 95% CI = 1.34, 2.45) compared to those without concussion. Conclusion NHWs, males, and minors aged between 14-17 years were more likely to report a history of head trauma. Head trauma was associated with ADHD even when adjusted for confounding variables. It has been speculated in the past that NHW predominance in head trauma may represent greater prevalence of reporting rather than an actual increase in head trauma in this group raising the question of whether lack of injury recognition in minority demographics represents a possible area of improvement for improved health outcomes. In addition, the positive correlation between ADHD and pediatric head trauma warrants further investigation to establish possible causal relationships.Item Barriers to in-Person Focus Group Participation during the Third-Year of COVID-19 Pandemic: A Case Study of Colorectal Cancer (CRC) Screening in Underrepresented Groups(2023) Kamt, Sulin; Rasu, Rafia; Miller-Wilson, Lesley-Ann; White, Annesha; Chhetri, Shlesma; Hittson-Smith, Rachal; Fernandez, Denise; Sambamoorthi, UshaPURPOSE: In the process of conducting research to understand barriers to colorectal cancer (CRC) screening in underrepresented groups such as Blacks and Hispanics, it became evident that there were also barriers to recruitment in this population. This study assesses the challenges faced in recruitment of focus group participants regarding CRC screening practices among underrepresented groups. Since the COVID-19 pandemic, qualitative research participants have primarily been interviewed through online video or audio interactions. However, as restrictions on in-person interactions have been lifted, in-person focus groups are being increasingly considered. METHODS: The study investigators began recruitment through community health workers in August 2022, when COVID-19 vaccines were available for all adults (age>18 years). Eligible individuals were: age 45-75, Black or Hispanic, with Medicaid or no insurance, and no family history of CRC or diagnosis of certain colon-related diseases. We combined in-person and virtual recruitment strategies, including posting flyers in communities, advertising our study at health fairs, and on social media. Participants would receive a $50 gift card. RESULTS: Fifty-five met the eligibility criteria among 144 respondents, and 45 subjects (29 women and 16 men) agreed to be contacted. An average of 2.5 attempts were made per eligible subject. Unfortunately, we were able to recruit only four women (3 Hispanic and one non-Hispanic black). Traveling to the research site was a barrier to participation. Many subjects (49%) requested virtual participation (online video or audio interactions); some declined because the topic was too sensitive (considered taboo), and eligible men were reluctant to participate in-person. CONCLUSIONS: The requirement of in-person participation affected our recruitment goals, suggesting that COVID-19 has shifted the preferences of research participants to virtual interaction. In response to the eligible participant preferences, the study protocol has been revised to re-contact patients and schedule virtual FG sessions.Item Community perspectives on AI/ML and health equity: AIM-AHEAD nationwide stakeholder listening sessions(PLOS, 2023-06-30) Vishwanatha, Jamboor K.; Christian, Allison; Sambamoorthi, Usha; Thompson, Erika L.; Stinson, Katie; Syed, Toufeeq A.Artificial intelligence and machine learning (AI/ML) tools have the potential to improve health equity. However, many historically underrepresented communities have not been engaged in AI/ML training, research, and infrastructure development. Therefore, AIM-AHEAD (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity) seeks to increase participation and engagement of researchers and communities through mutually beneficial partnerships. The purpose of this paper is to summarize feedback from listening sessions conducted by the AIM-AHEAD Coordinating Center in February 2022, titled the "AIM-AHEAD Community Building Convention (ACBC)." A total of six listening sessions were held over three days. A total of 977 people registered with AIM-AHEAD to attend ACBC and 557 individuals attended the listening sessions across stakeholder groups. Facilitators led the conversation based on a series of guiding questions, and responses were captured through voice and chat via the Slido platform. A professional third-party provider transcribed the audio. Qualitative analysis included data from transcripts and chat logs. Thematic analysis was then used to identify common and unique themes across all transcripts. Six main themes arose from the sessions. Attendees felt that storytelling would be a powerful tool in communicating the impact of AI/ML in promoting health equity, trust building is vital and can be fostered through existing trusted relationships, and diverse communities should be involved every step of the way. Attendees shared a wealth of information that will guide AIM-AHEAD's future activities. The sessions highlighted the need for researchers to translate AI/ML concepts into vignettes that are digestible to the larger public, the importance of diversity, and how open-science platforms can be used to encourage multi-disciplinary collaboration. While the sessions confirmed some of the existing barriers in applying AI/ML for health equity, they also offered new insights that were captured in the six themes.Item Coronavirus disease 2019 pandemic associated with anxiety and depression among Non-Hispanic whites with chronic conditions in the US(Elsevier B.V., 2022-02-22) Wang, Hao; Paul, Jenny; Ye, Ivana; Blalock, Jake; Wiener, R. Constance; Ho, Amy F.; Alanis, Naomi; Sambamoorthi, UshaOBJECTIVES: During the coronavirus 2019 (COVID-19) pandemic, increased anxiety and depression were reported, with mixed findings among individuals of different races/ethnicities. This study examines whether anxiety and depression increased during the COVID-19 pandemic compared to the pre-COVD-19 period among different racial/ethnic groups in the US. METHODS: The Health Information National Trend Surveys 5 (HINTS 5) Cycle 4 data was analyzed. We used the time when the survey was administered as the pre-COVID-19 period (before March 11, 2020, weighted N = 77,501,549) and during the COVID-19 period (on and after March 11, 2020, weighted N = 37,222,019). The Patient Health Questionnaire (PHQ) was used to measure anxiety/depression and further compared before and during COVID-19. Separate multivariable logistic regression analyses were used to determine the association of the COVID-19 pandemic with anxiety/depression after adjusting for age, sex, insurance, income, and education. RESULT: A higher percentage of Non-Hispanic whites (NHW) with chronic conditions reported anxiety (24.3% vs. 11.5%, p = 0.0021) and depression (20.7% vs. 9.3%, p = 0.0034) during COVID-19 than pre-COVID-19. The adjusted odds ratio (AOR) of anxiety and depression for NHWs with chronic conditions during the COVID-19 pandemic was 2.02 (95% confidence interval of 1.10-3.73, p = 0.025) and 2.33 (1.17-4.65, p = 0.018) compared to NHWs who participated in the survey before the COVID-19. LIMITATIONS: Limited to the NHW US population. PHQ can only be used as the initial screening tool. CONCLUSION: The COVID-19 pandemic was associated with an increased prevalence of anxiety and depression among NHW adults with chronic conditions, but not among people of color.Item Evaluating Equity in XGBoost Predictions of High Healthcare Expenditures for Older Women with Osteoarthritis in the United States(2024-03-21) Elchehabi, Sahar; Dehghan, Arshama; Pathak, Mona; Sambamoorthi, Nethra; Park, Chanhyun; Shen, Chan; Sambamoorthi, UshaPurpose: Osteoarthritis (OA) is a highly prevalent and debilitating condition among older adults. Studies suggest that women are more prone to develop symptomatic disease than men. OA is associated with high direct healthcare costs, attributable to its complex disease management. Furthermore, a small segment of this population may incur very high costs. Identifying these high-cost users is important for allocation of resources, cost containment, quality improvement, and population health management. However, current research in the prediction of high-cost users in OA using machine learning (ML) models is limited. Furthermore, ML model predictions of high-cost users must be equitable across sensitive attributes such as race and ethnicity and socio-economic status. This study investigated the leading predictors of high-cost users among older women with OA utilizing ML methods and the fairness of the ML algorithm in its predictions across subgroups of race and ethnicity, poverty, and education. Methods: A cross-sectional study was conducted using data from older women (age>65 years) with OA from the 2021 Medical Expenditure Panel Survey, a nationally representative survey of the non-institutionalized civilian households in the US. High-cost users were identified as having higher than the 90th percentile (>$39,388) in total healthcare expenditures. Key predictors were identified using interpretable ML model eXtreme Gradient Boosting (XGBoost) Classification and SHapley Additive exPlanations (SHAP). Overall model fit was evaluated with AUC, recall, and precision. Fairness was measured with demographic parity (equalization of odds, disparate impact, and equal opportunity) across racial and ethnic groups (Non-Hispanic White (NHW), Non-Hispanic Black (NHB), Hispanic ethnicity), education (no college and college) and poverty status (low income and high income). Counterfactual fairness was evaluated to ensure consistency in high-cost predictions between actual scenarios and counterfactual situations where individuals belong to different groups. Results: A higher percentage of Hispanic (12.2%) and NHB (14.4%) were high-cost users compared to NHW (9.0%). A higher percentage of older women without college education (10.7%) and with low income (11.2%) compared to those with college education (2.5%) and high income (5.2%) were high-cost users. The overall model fit was acceptable with AUC 0.81, recall 0.62, and precision 0.91. Multimorbidity, high school education level, and anxiety were the top 3 predictors of high-cost users. Prediction was lower among older women without college education (AUC = 0.80) and low income compared (AUC = 0.77) compared to overall prediction (AUC = 0.81). Demographic parity revealed little to no differences across racial and ethnic, education, and income groups. Conclusion: The fairness metrics indicated no bias in the predictions, likely attributable to the nationally representative nature of the survey sample and its large size. These findings need to be confirmed with other data that contain diverse populations. Leading predictors indicated that effective management of multimorbidity may reduce the risk of high-cost use in older women with OA.Item Factors associated with COVID-19-related mental health among Asian Indians in the United States(Elsevier B.V., 2023-01-11) Ikram, Mohammad; Shaikh, Nazneen F.; Siddiqui, Zasim A.; Dwibedi, Nilanjana; Misra, Ranjita; Vishwanatha, Jamboor K.; Sambamoorthi, UshaBACKGROUND: In the United States, the COVID-19 pandemic has caused increased mental health symptoms and mental illness. Specific subgroups such as Asian Indians in the US have also been subject to additional stressors due to unprecedented loss of lives in their home country and increased Asian hate due to the misperception that Asians are to be blamed for the spread of the SARS-CoV-2. OBJECTIVE: We examined the various factors including discrimination associated with COVID-19-related mental health symptoms among Asian Indians. METHODS: We administered an online survey between May 2021 and July 2021 using convenient and snowball sampling methods to recruit Asian Indian adults (age > 18 years, N = 289). The survey included questions on mental health and the experience with unfair treatment in day-to-day life. Descriptive analysis and logistic regressions were performed. RESULTS: Overall, 46.0% reported feeling down, depressed, or lonely and feeling nervous, tense, or worried due to the COVID-19 pandemic; 90.0% had received at least one dose of vaccination and 74.7% reported some form of discrimination. In the fully-adjusted logistic regression, age (AOR = 0.95; 95%CI- 0.92, 0.97;p < 0.01) and general health (AOR=0.84; 95%CI- 0.73, 0.97; p < 0.015) were negatively associated with mental health symptoms. Participants who experienced discrimination were more likely (AOR=1.26; 95%CI- 1.08, 1.46; p < 0.01) to report mental health symptoms. CONCLUSION: In this highly vaccinated group of Asian Indians discriminatory behaviors were associated with mental health symptoms suggesting the need for novel institutional level policy responses to reduce anti-Asian racism.Item Increase in body mass index during the COVID-19 pandemic among people who smoke: An analysis of multi-site electronic health records(PLOS, 2023-04-12) Wiener, R. Constance; Waters, Christopher; Morgan, Emily; Findley, Patricia A.; Shen, Chan; Wang, Hao; Sambamoorthi, UshaThe effects of the COVID-19 period among people who smoke (compared by sex) are largely unknown. The purpose of this study was to compare body mass index (BMI) increase among men and women who smoked during the pandemic. We used a retrospective longitudinal, observational study design of secondary data. We used electronic health records from TriNetX network (n = 486,072) from April 13, 2020-May 5, 2022 among adults aged 18-64 who smoked and had a normal BMI prior to the pandemic. The main measure was a change of BMI from < 25 to >/=25. Risk ratio was determined between men and women with propensity score matching. Overall, 15.8% increased BMI to >/=25; 44,540 (18.3%) were women and 32,341 (13.3%) were men (Risk Ratio = 1.38, 95% CI: 1.36, 1.40; p < .0001). Adults with diabetes, hypertension, asthma, COPD or emphysema or who were women, were more likely to develop BMI>/=25 during the pandemic. Women who smoked were more likely to have an increase in BMI than men who smoked during the COVID-19 period.Item Interactive Association of Chronic Illness and Food Insecurity with Emergency Room Visits among School-aged Children in the United States(2022) Ghani, Farheen; Manning, Sydney E.; Sambamoorthi, UshaObjective: This study examined the prevalence of food insecurity among children aged 6-17 years and the interactive association of chronic conditions and food insecurity with healthcare utilization, specifically ER visits. Methods: Data on children aged 6-17 (N = 5,518, representing 50,479,419 children) were obtained from the 2017 Medical Expenditure Panel Survey (MEPS). We measured food insecurity (Yes/No) using responses to a 10-item food security scale developed and validated by the USDA, adapted here for the MEPS 30-day window. Healthcare utilization consisted of cumulative ER visits in 12 months. Chi-square tests and adjusted Poisson regression were used to determine interactive associations of chronic conditions and food insecurity on ER visits. All analyses involved complex survey procedures. Results: 20% of school-aged children had food insecurity; 21% had a chronic condition. After adjusting for age, sex, race, insurance coverage, poverty status, physical and mental health status, obesity, and region, we observed that children with chronic conditions and food insecurity had a higher number of ER visits (Incident rate ratio = 2.79, 95% CI = 1.892, 4.120), compared to children without food insecurity and chronic conditions. Conclusions: 1 in 16 school-aged children had both a chronic condition and experienced food insecurity in the last 12 months. Food insecurity in children with chronic conditions was associated with more ER visits. Our findings suggest that policies and programs that provide linkages to community resources can help reduce food insecurity among children in the US and reduce healthcare utilization.Item Leading Predictors and Their Associations with Combination Pain Therapy in Older Adults with Cancer: Application of Machine Learning Approaches(2022) Manning, Sydney E.; Madhavan, Suresh; Rasu, Rafia; Sambamoorthi, UshaOBJECTIVES: Opioid combination therapy is frequently prescribed in older adult cancer survivors despite negative outcomes. The objective of this study was to identify the leading predictors and their associations with opioid combination therapy prescribing after cancer diagnosis using interpretable machine learning approaches. METHODS: This is a retrospective longitudinal cohort of older (> 66 years old) cancer survivors (N = 2,673) diagnosed with primary and incident cancer in 2014 using the Surveillance, Epidemiology, and End Results (SEER) cancer registry linked with Medicare claims. Recursive feature elimination with random forest was used to extract the optimal number of predictors out of 119 likely ones for predictive modeling. eXtreme Gradient Boosting (XGBoost), SHapley Additive exPlanations (SHAP), and global feature importance were used to identify the leading predictors and their associations with opioid combination therapy. SAS 9.4 was used for data management and Python 3.9.7 was used for machine learning model calibration and tuning. RESULTS: Specificity (0.858), sensitivity (0.843), and area under the curve (AUC, 0.85) of our predictive model were high. Thirty-four features were included in the final predictive model. Baseline use of NSAIDs, opioids, benzodiazepines, and gabapentinoids, and chemotherapy, surgery, Complex relationships were observed between zip code percent of Hispanic and Native American residents living below poverty, care fragmentation (FCI), age at diagnosis, and opioid combination therapy. CONCLUSIONS: 1 in 3 older cancer survivors were prescribed opioid combination therapy. Patient-level baseline medication use, biological factors, cancer treatment, and zip code level social determinants were leading predictors of opioid combination therapy. Although observed relationships were complex, further analysis of predictors may help compute individual risk of patients on combination therapy, which in turn may help clinicians and policy makers utilize targeted interventions at the outset and prevent long-term effects of combination pain therapy such as prolonged and inappropriate use.Item Leading Predictors of COVID-19-Related Poor Mental Health in Adult Asian Indians: An Application of Extreme Gradient Boosting and Shapley Additive Explanations(MDPI, 2023-01-09) Ikram, Mohammad; Shaikh, Nazneen F.; Vishwanatha, Jamboor K.; Sambamoorthi, UshaDuring the COVID-19 pandemic, an increase in poor mental health among Asian Indians was observed in the United States. However, the leading predictors of poor mental health during the COVID-19 pandemic in Asian Indians remained unknown. A cross-sectional online survey was administered to self-identified Asian Indians aged 18 and older (N = 289). Survey collected information on demographic and socio-economic characteristics and the COVID-19 burden. Two novel machine learning techniques-eXtreme Gradient Boosting and Shapley Additive exPlanations (SHAP) were used to identify the leading predictors and explain their associations with poor mental health. A majority of the study participants were female (65.1%), below 50 years of age (73.3%), and had income >/= $75,000 (81.0%). The six leading predictors of poor mental health among Asian Indians were sleep disturbance, age, general health, income, wearing a mask, and self-reported discrimination. SHAP plots indicated that higher age, wearing a mask, and maintaining social distancing all the time were negatively associated with poor mental health while having sleep disturbance and imputed income levels were positively associated with poor mental health. The model performance metrics indicated high accuracy (0.77), precision (0.78), F1 score (0.77), recall (0.77), and AUROC (0.87). Nearly one in two adults reported poor mental health, and one in five reported sleep disturbance. Findings from our study suggest a paradoxical relationship between income and poor mental health; further studies are needed to confirm our study findings. Sleep disturbance and perceived discrimination can be targeted through tailored intervention to reduce the risk of poor mental health in Asian Indians.Item Leading Predictors of Economic Burden Among Postmenopausal Women with Heart Failure: An Application of Machine Learning with XGBoost and SHapley Additive exPlanations(2023) Dehghan, Arshama; Park, Chanhyun; Sambamoorthi, Nethra; Shen, Chan; Shara, Nawar; Sambamoorthi, UshaObjective: Heart Failure is associated with high direct healthcare costs, including out-of-pocket spending by the patients. However, there are knowledge gaps in HF research among postmenopausal women. Therefore, this study uses machine learning methods to identify leading predictors and their associations with economic burden among postmenopausal women (age > 50 years) with heart failure. Methods: This cross-sectional study used data from postmenopausal women with heart failure from the 2020 Medical Expenditure Panel Survey (MEPS: weighted N= 600,742). The economic burden was measured with total healthcare expenditures by the payors (third-party expenditures) and out-of-pocket expenditures by the patients and their families. We employed eXtreme Gradient Boosting (XGBoost) regression to determine key predictors. Global and local interpretations of associations were performed using SHapley Additive exPlanations (SHAP). Our predictive model used 21 features such as age, health status including comorbidities (anxiety, arthritis, asthma, cancer, COPD, depression, diabetes, high cholesterol, hypertension, and thyroid disease), perceived physical and mental health status, and polypharmacy. Social determinants of health (SDoH) consisted of marital status, health insurance coverage, prescription drug coverage, education, poverty status, and region. The model building included 70% training and 30% testing split of the data, 10-fold cross-validations, and up to six rounds of optimization using Python 3.9.12. Model performance metrics included absolute mean squared errors, root mean squared error and coefficient of determination; these were evaluated using the test dataset. Results: The model offered excellent accuracy as evidenced by its low mean absolute errors (0.442,0.310), root mean square errors (0.452,0.342), and high coefficients of determination (0.935,0.987) for third-party and out-of-pocket expenditures, respectively. The top 10 leading predictors of third-party expenditures included polypharmacy, age, resident of the Midwest region, asthma, perceived physical and mental health, anxiety, hypertension, white race, and low income. The SHAP plots from the third-party expenditures revealed complex relationships of age, physical, and mental health with the target variable. Polypharmacy, low income, anxiety, and asthma were associated with higher third-party expenditures. Non-Hispanic white Women and those with hypertension had lower third-party expenditures. The top 10 leading predictors of out-of-pocket expenditures included age, Latinx ethnicity, asthma, cancer, being poor, having middle income and high income, prescription drug coverage, private insurance, and polypharmacy. Out-of-pocket expenditure plots only highlighted age as the key complex factor. Being poor, having middle income, and reporting Latinx ethnicity were associated with lower out-of-pocket expenditures. High income, prescription drug coverage, private insurance, polypharmacy, and the presence of asthma and cancer were associated with higher out-of-pocket expenditures. Conclusion: The leading predictors differed by payor source. SDoH were associated with economic burden, suggesting that addressing SDoH may reduce healthcare costs. Cost-containment policies, programs, and interventions at the payor and patient levels need to include effective comorbidity management strategies. The limitations of this study include cross-sectional study design, self-reported data that may be subject to recall bias, and severity of comorbidities that may affect the economic burden. However, the study also has several strengths, such as nationally representative data, the inclusion of SDoH, validated information on expenditures, and robust interpretable machine learning methods.Item Multimorbidity and chronic pain management with opioids and other therapies among adults in the United States: A cross-sectional study(Sage Publications, 2024-03-08) Neba, Rolake A.; Wang, Hao; Kolala, Misozi; Sambamoorthi, UshaBACKGROUND: Multimorbidity, defined as the concurrent presence of >/= 2 chronic conditions, and chronic pain (i.e., pain lasting >/=3 months) often co-exist. Multimodal pain management that includes non-pharmacologic treatment and non-opioid therapy is recommended to prevent serious risks associated with opioids. PURPOSE: Estimate the prevalence of types of pain treatment and analyze their associations with multimorbidity using a nationally representative survey in the United States (US). METHODS: Data was collected from the 2020 National Health Interview Survey among adults with chronic pain and chronic conditions (N= 12,028). Chronic pain management was grouped into four categories: opioid therapy; non-opioid multimodal pain treatment; pain treatment with monotherapy; and no pain treatment. Chi-square tests and multivariable multinomial logistic regressions were used to analyze the association of multimorbidity with types of pain treatment after controlling for age, sex, social determinants of health (SDoH), and lifestyle characteristics. RESULTS: Among NHIS respondents, 68% had multimorbidity. In adjusted multinomial logistic regressions with "pain management with monotherapy" as the reference group, those with multimorbidity were more likely to utilize opioids (AOR=1.63, 95% CI=1.23, 2.17). Those with severe pain were also more likely to use opioid therapy (AOR=19.36, 95% CI=13.35, 28.06) than those with little pain. Those with low income and education were less likely to have multimodal pain management without opioids. CONCLUSION: Seven in 10 adults had multimorbidity. Those with multimorbidity reported severe pain and relied on opioids for pain control. Regardless of multimorbidity status, SDoH was associated with types of chronic pain management.Item Multimorbidity and Whole Health among Adults in the United States: Evidence from the NHIS and BRFSS(2022) Warner, Mayela; Neba, Rolake A.; Manning, Sydney E.; Wiener, Constance; Sambamoorthi, UshaPUPROSE Whole health is a patient-centered approach that promotes self-management of what matters to the patient. Whole health focuses on mind-body, recharge(sleep), healthy diet, emotional health, and movement, all of which are critical for those with multimorbidity. We examined the association of multimorbidity with good whole health among adults in the United States. METHODS We conducted a cross-sectional design. As no one dataset provided information on all components of whole health, we analyzed mind-body therapies, recharge, emotional health, and movement from the 2017 National Health Interview Survey (NHIS), and healthy diet from the 2017 Behavioral Risk Factor Surveillance System (BRFSS). Multimorbidity was defined as the co-occurrence of two or more chronic conditions. Recharge was measured by adequate duration of sleep and the Kessler Psychological Distress Scale (K6) was used to measure emotional health. All unadjusted and adjusted analyses were conducted using the SAS survey procedures. The samples from NHIS (N=25,134) and BRFSS (N=347,029) represented 213 million and 183 million adults, respectively. RESULTS Prevalence of the whole health components varied from 24.4% (mind-body therapies use), 55.7% (healthy-diet), 57.1% (movement), 63.9% (adequate sleep), and good emotional health (78.4%). Based on NHIS, only 3.4% reported good health in all four components. A lower percentage of adults with multimorbidity used mind-body therapies (22.9% vs 25.2%), had adequate sleep (58.2% vs 67.1%), good emotional health (71.8% vs 82.1%), adequate movement (16.2% vs 28.2%), and healthy diet (54.5% vs 56.5%) compared to those without multimorbidity (p < .001). Adjusted analyses revealed that those with multimorbidity were less likely to engage in whole health practices compared to those without multimorbidity. CONCLUSIONS Seven in 10 adults had poor health in two or more components of whole health. Adults with multimorbidity were found to have poorer health in all components of whole health. Nationally representative data surveys should strive to collect information on all components of whole health with standardized measures.Item Prescription Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) and Incidence of Depression Among Older Cancer Survivors With Osteoarthritis: A Machine Learning Analysis(Sage Publications, 2023-04-27) Shaikh, Nazneen F.; Shen, Chan; LeMasters, Traci; Dwibedi, Nilanjana; Ladani, Amit; Sambamoorthi, UshaOBJECTIVES: 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.Item Prevalence and Factors Associated with SSRI Use Among Adults with Depressive and Thyroid Disorders in the United States(2023) Arif, Atiqa; Pinnamraju, Jahnavi; Sambamoorthi, UshaBackground: Patients with hypothyroidism and hyperthyroidism are at high risk for developing anxiety and depression. Sixty percent of adults in the United States with thyroid disorders have depression. Selective serotonin reuptake inhibitors (SSRIs) are used to treat depression. However, SSRIs reduce thyroid function during treatment suggesting SSRIs may not be used in treating depression among adults with thyroid disorders. Few studies have investigated the prevalence and factors associated with SSRI use in adults with diagnosed depression and thyroid disorders. Objective: This study estimated the prevalence of SSRI use in adults with diagnosed thyroid and depressive disorders in the United States and examined the factors associated with SSRI use. Methods: The study used a cross-sectional design using pooled data from multiple years (2018-2020) of the Medical Expenditure Panel Survey (MEPS), a nationally representative survey of the civilian non-institutionalized population in the US, to gain an adequate sample size. The study was restricted to adults with diagnosed thyroid and depressive disorders with health insurance. The final sample was (Unweighted N=729; Weighted N= 3,090,551). SSRI use was identified from prescription drug files using Multum drug classifications. Rao-Scott Chi-square tests were used to examine the unadjusted group differences in SSRI use. Multivariable logistic regression was used to analyze factors associated with SSRI use. The logistic regressions adjusted for age, sex, race and ethnicity, education, income, insurance coverage, prescription drug coverage, polypharmacy (>6 drug classes excluding antidepressants and thyroid hormones), perceived physical and mental health rating, pain, and thyroid hormones. Results: A majority (61.6%) of adults diagnosed with thyroid and depression used SSRIs. A lower percentage of African Americans (28.5%vs.61.9%; p<.05) used SSRIs compared to NHWs; Only 47.0% of those reporting poor health used SSRI compared to those reporting excellent physical health (73.8%) (p<0.01). A lower percentage of adults with extreme pain (49.5%vs.65.8%) used SSRIs compared to those with mild or no pain (p<.05). A lower percentage of adults with moderate to vigorous physical activity of 5 days/week used SSRIs compared to adults with no exercise. (54.2%vs.65.3%; p<.05). A lower percentage of adults with polypharmacy (53.0%vs.67.5%; p<0.01) used SSRI compared to those without polypharmacy. In multivariable logistic regression, African Americans had lower odds of SSRI use (AOR=0.28; 95% CI=0.09, 0.88) compared to NHWs. Lower ratings of physical health were associated with SSRI use. Adults with polypharmacy had lower odds of SSRI use (AOR=0.65; 95% CI=0.44, 0.96). Conclusion: 6 in 10 adults with thyroid and depressive disorders used SSRIs. Racial disparities in SSRI use were observed. We speculate that SSRI use rates may be lower in those with polypharmacy and poor health to reduce the risk of drug-drug interactions and drug-disease interactions. Strengths and Limitations: Limitations include cross-sectional study design, self-reported data, no distinction between hyperthyroidism and hypothyroidism, and a small sample size despite pooling multiple years. Nevertheless, the study used nationally representative data adjusted for a comprehensive list of clinical, demographic, and psychosocial factors.