Patient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data?

There is widespread use of dietary supplements, some prescribed but many taken without a physician's guidance. There are many potential interactions between supplements and both over-the-counter and prescription medications in ways that are unknown to patients. Structured medical records do not adequately document supplement use; however, unstructured clinical notes often contain extra information on supplements. We studied a group of 377 patients from three healthcare facilities and developed a natural language processing (NLP) tool to detect supplement use. Using surveys of these patients, we investigated the correlation between self-reported supplement use and NLP extractions from the clinical notes. Our model achieved an F1 score of 0.914 for detecting all supplements. Individual supplement detection had a variable correlation with survey responses, ranging from an F1 of 0.83 for calcium to an F1 of 0.39 for folic acid. Our study demonstrated good NLP performance while also finding that self-reported supplement use is not always consistent with the documented use in clinical records.

Extracting Pain Care Quality Indicators from U.S. Veterans Health Administration Chiropractic Care Using Natural Language Processing.

BACKGROUND: Musculoskeletal pain is common in the Veterans Health Administration (VHA), and there is growing national use of chiropractic services within the VHA. Rapid expansion requires scalable and autonomous solutions, such as natural language processing (NLP), to monitor care quality. Previous work has defined indicators of pain care quality that represent essential elements of guideline-concordant, comprehensive pain assessment, treatment planning, and reassessment. OBJECTIVE: Our purpose was to identify pain care quality indicators and assess patterns across different clinic visit types using NLP on VHA chiropractic clinic documentation. METHODS: Notes from ambulatory or in-hospital chiropractic care visits from October 1, 2018 to September 30, 2019 for patients in the Women Veterans Cohort Study were included in the corpus, with visits identified as consultation visits and/or evaluation and management (E&M) visits. Descriptive statistics of pain care quality indicator classes were calculated and compared across visit types. RESULTS: There were 11,752 patients who received any chiropractic care during FY2019, with 63,812 notes included in the corpus. Consultation notes had more than twice the total number of annotations per note (87.9) as follow-up visit notes (34.7). The mean number of total classes documented per note across the entire corpus was 9.4 (standard deviation [SD] = 1.5). More total indicator classes were documented during consultation visits with (mean = 14.8, SD = 0.9) or without E&M (mean = 13.9, SD = 1.2) compared to follow-up visits with (mean = 9.1, SD = 1.4) or without E&M (mean = 8.6, SD = 1.5). Co-occurrence of pain care quality indicators describing pain assessment was high. CONCLUSION: VHA chiropractors frequently document pain care quality indicators, identifiable using NLP, with variability across different visit types.

Complementary and Integrative Health Approaches and Pain Care Quality in the Veterans Health Administration Primary Care Setting: A Quasi-Experimental Analysis.

Background: Complementary and integrative health (CIH) approaches have been recommended in national and international clinical guidelines for chronic pain management. We set out to determine whether exposure to CIH approaches is associated with pain care quality (PCQ) in the Veterans Health Administration (VHA) primary care setting. Methods: We followed a cohort of 62,721 Veterans with newly diagnosed musculoskeletal disorders between October 2016 and September 2017 over 1-year. PCQ scores were derived from primary care progress notes using natural language processing. CIH exposure was defined as documentation of acupuncture, chiropractic or massage therapies by providers. Propensity scores (PSs) were used to match one control for each Veteran with CIH exposure. Generalized estimating equations were used to examine associations between CIH exposure and PCQ scores, accounting for potential selection and confounding bias. Results: CIH was documented for 14,114 (22.5%) Veterans over 16,015 primary care clinic visits during the follow-up period. The CIH exposure group and the 1:1 PS-matched control group achieved superior balance on all measured baseline covariates, with standardized differences ranging from 0.000 to 0.045. CIH exposure was associated with an adjusted rate ratio (aRR) of 1.147 (95% confidence interval [CI]: 1.142, 1.151) on PCQ total score (mean: 8.36). Sensitivity analyses using an alternative PCQ scoring algorithm (aRR: 1.155; 95% CI: 1.150-1.160) and redefining CIH exposure by chiropractic alone (aRR: 1.118; 95% CI: 1.110-1.126) derived consistent results. Discussion: Our data suggest that incorporating CIH approaches may reflect higher overall quality of care for patients with musculoskeletal pain seen in primary care settings, supporting VHA initiatives and the Declaration of Astana to build comprehensive, sustainable primary care capacity for pain management. Future investigation is warranted to better understand whether and to what degree the observed association may reflect the therapeutic benefits patients actually received or other factors such as empowering provider-patient education and communication about these approaches.

Pharmacogenomics driven decision support prototype with machine learning: A framework for improving patient care.

Introduction: A growing number of healthcare providers make complex treatment decisions guided by electronic health record (EHR) software interfaces. Many interfaces integrate multiple sources of data (e.g., labs, pharmacy, diagnoses) successfully, though relatively few have incorporated genetic data. Method: This study utilizes informatics methods with predictive modeling to create and validate algorithms to enable informed pharmacogenomic decision-making at the point of care in near real-time. The proposed framework integrates EHR and genetic data relevant to the patient's current medications including decision support mechanisms based on predictive modeling. We created a prototype with EHR and linked genetic data from the Department of Veterans Affairs (VA), the largest integrated healthcare system in the US. The EHR data included diagnoses, medication fills, and outpatient clinic visits for 2,600 people with HIV and matched uninfected controls linked to prototypic genetic data (variations in single or multiple positions in the DNA sequence). We then mapped the medications that patients were prescribed to medications defined in the drug-gene interaction mapping of the Clinical Pharmacogenomics Implementation Consortium's (CPIC) level A (i.e., sufficient evidence for at least one prescribing action) guidelines that predict adverse events. CPIC is a National Institute of Health funded group of experts who develop evidence based pharmacogenomic guidelines. Preventable adverse events (PAE) can be defined as a harmful outcome from an intervention that could have been prevented. For this study, we focused on potential PAEs resulting from a medication-gene interaction. Results: The final model showed AUC scores of 0.972 with an F1 score of 0.97 with genetic data as compared to 0.766 and 0.73 respectively, without genetic data integration. Discussion: Over 98% of people in the cohort were on at least one medication with CPIC level a guideline in their lifetime. We compared predictive power of machine learning models to detect a PAE between five modeling methods: Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), K Nearest neighbors (KNN), and Decision Tree. We found that XGBoost performed best for the prototype when genetic data was added to the framework and improved prediction of PAE. We compared area under the curve (AUC) between the models in the testing dataset.

Correlates of Manual Therapy and Acupuncture Use Among Rural Patients Seeking Conventional Pain Management: A Cross-sectional Study.

OBJECTIVE: In this cross-sectional study, we examined correlates of manual therapy (spinal manipulation, massage therapy) and/or acupuncture use in a population engaging in conventional pain care in West Virginia. METHODS: Participants were patients (aged 18+ years) from 4 Appalachian pain and rheumatology clinics. Of those eligible (N = 343), 88% completed an anonymous survey including questions regarding health history, pain distress (Short Form Global Pain Scale), prescription medications, and current use of complementary health approaches for pain management. We used age-adjusted logistic regression to assess the relation of sociodemographic, lifestyle, and health-related factors to use of manual therapies and/or acupuncture for pain (complete-case N = 253). RESULTS: The majority of participants were white (92%), female (56%), and middle aged (mean age, 54.8 ± 13.4 years). Nearly all reported current chronic pain (94%), and 56% reported ≥5 comorbidities (mean, 5.6 ± 3.1). Manual therapy and/or acupuncture was used by 26% of participants for pain management (n = 66). Current or prior opioid use was reported by 37% of those using manual therapies. Manual therapy and/or acupuncture use was significantly elevated in those using other complementary health approaches (adjusted odds ratio, 3.0; 95% confidence interval, 1.5-5.8). Overall Short Form Global Pain Scale scores were not significantly associated with use of manual therapies and/or acupuncture after adjustment (adjusted odds ratio per 1-point increase, 1.01; 95% confidence interval, 1.00-1.03). CONCLUSION: We found no evidence for an association of pain-related distress and use of manual therapies and/or acupuncture, but identified a strong association with use of dietary supplements and mind-body therapies. Larger studies are needed to further examine these connections in the context of clinical outcomes and cost-effectiveness in rural adults given their high pain burden and unique challenges in access to care.

Exploring supervised machine learning approaches to predicting Veterans Health Administration chiropractic service utilization.

BACKGROUND: Chronic spinal pain conditions affect millions of US adults and carry a high healthcare cost burden, both direct and indirect. Conservative interventions for spinal pain conditions, including chiropractic care, have been associated with lower healthcare costs and improvements in pain status in different clinical populations, including veterans. Little is currently known about predicting healthcare service utilization in the domain of conservative interventions for spinal pain conditions, including the frequency of use of chiropractic services. The purpose of this retrospective cohort study was to explore the use of supervised machine learning approaches to predicting one-year chiropractic service utilization by veterans receiving VA chiropractic care. METHODS: We included 19,946 veterans who entered the Musculoskeletal Diagnosis Cohort between October 1, 2003 and September 30, 2013 and utilized VA chiropractic services within one year of cohort entry. The primary outcome was one-year chiropractic service utilization following index chiropractic visit, split into quartiles represented by the following classes: 1 visit, 2 to 3 visits, 4 to 6 visits, and 7 or greater visits. We compared the performance of four multiclass classification algorithms (gradient boosted classifier, stochastic gradient descent classifier, support vector classifier, and artificial neural network) in predicting visit quartile using 158 sociodemographic and clinical features. RESULTS: The selected algorithms demonstrated poor prediction capabilities. Subset accuracy was 42.1% for the gradient boosted classifier, 38.6% for the stochastic gradient descent classifier, 41.4% for the support vector classifier, and 40.3% for the artificial neural network. The micro-averaged area under the precision-recall curve for each one-versus-rest classifier was 0.43 for the gradient boosted classifier, 0.38 for the stochastic gradient descent classifier, 0.43 for the support vector classifier, and 0.42 for the artificial neural network. Performance of each model yielded only a small positive shift in prediction probability (approximately 15%) compared to naïve classification. CONCLUSIONS: Using supervised machine learning to predict chiropractic service utilization remains challenging, with only a small shift in predictive probability over naïve classification and limited clinical utility. Future work should examine mechanisms to improve model performance.

Factors Associated With Posttraumatic Stress Disorder Among Veterans of Recent Wars Receiving Veterans Affairs Chiropractic Care.

OBJECTIVES: Post-traumatic stress disorder (PTSD) is thought to complicate pain management outcomes, which is consistent with the impact of other psychosocial factors in the biopsychosocial model of pain. This study aimed to identify patient sociodemographic and clinical characteristics associated with PTSD prevalence among veterans of Operations Enduring Freedom/Iraqi Freedom/New Dawn (OEF/OIF/OND) who received Veterans Affairs (VA) chiropractic care. METHODS: A cross-sectional analysis of electronic health record data from a national cohort study of OEF/OIF/OND veterans with at least 1 visit to a VA chiropractic clinic from 2001 to 2014 was performed. The primary outcome measure was a prior PTSD diagnosis. Variables including sex, race, age, body mass index, pain intensity, alcohol and substance use disorders, and smoking status were examined in association with PTSD diagnosis using logistic regression. RESULTS: We identified 14,025 OEF/OIF/OND veterans with at least 1 VA chiropractic visit, with a mean age of 38 years and 54.2% having a diagnosis of PTSD. Male sex (adjusted odds ratio [OR] = 1.23, 95% CI = 1.11-1.37), younger age (OR = 0.99, CI = 0.98-0.99), moderate-to-severe pain intensity (numerical rating scale ≥ 4) (OR = 1.72, CI = 1.59-1.87), body mass index ≥ 30 (OR = 1.34, CI = 1.24-1.45), current smoking (OR = 1.32, CI = 1.20-1.44), and having an alcohol or substance use disorder (OR = 4.51, CI = 4.01-5.08) were significantly associated with a higher likelihood of PTSD diagnosis. CONCLUSION: Post-traumatic stress disorder is a common comorbidity among OEF/OIF/OND veterans receiving VA chiropractic care and is significantly associated with several patient characteristics. Recognition of these factors is important for the appropriate diagnosis and management of veterans with PTSD seeking chiropractic treatment for pain conditions.

Trauma and Sexual Risk: Do Men and Women Veterans Differ?

PURPOSE: Trauma has been associated with risky sexual behavior in diverse populations. However, little is known about this association among men and women veterans. This study hypothesized that 1) a history of trauma would be associated with risky sexual behavior among men and women veterans, 2) interpersonal trauma would predict risky sexual behavior among women, whereas noninterpersonal trauma would predict risky sexual behavior among men, and 3) military-related trauma would constitute additional risk. Using data from 567 women and 524 men veterans enrolled at the Veterans Health Administration, this study investigated the association between trauma-related experiences and risky sexual behavior in the last 12 months. Risk and protective factors that have been frequently associated with sexual behavior in previous research were also included in the model. METHODS: This study was drawn from the Women Veterans Cohort Study, a national survey of veterans. Bivariate and multivariate analyses were performed after multiple imputation for missing data. RESULTS: Predictive factors associated with risky sexual behavior differed between men and women veterans. Among women, childhood sexual victimization and intimate partner violence were associated with risky sexual behavior. Among men, binge drinking was the single significant risk factor. Military exposures were not significantly associated with risky sexual behavior in either men or women. CONCLUSIONS: This study lays the groundwork for theory-generating research into the psychological underpinnings of noted associations and underscores the importance of integrated health services to address the range of issues affecting sexual behavior and related health outcomes.

Evaluation of Complementary and Integrative Health Approaches Among US Veterans with Musculoskeletal Pain Using Propensity Score Methods.

Objectives: To examine the treatment effectiveness of complementary and integrative health approaches (CIH) on chronic pain using Propensity Score (PS) methods. Design, Settings, and Participants: A retrospective cohort of 309,277 veterans with chronic musculoskeletal pain assessed over three years after initial diagnosis. Methods: CIH exposure was defined as one or more clinical visits for massage, acupuncture, or chiropractic care. The treatment effect of CIH on self-rated pain intensity was examined using a longitudinal model. PS-matching and inverse probability of treatment weighting (IPTW) were used to account for potential selection and confounding biases. Results: At baseline, veterans with (7,621) and without (301,656) CIH exposure differed significantly in 21 out of 35 covariates. During the follow-up period, on average CIH recipients had 0.83 (95% confidence interval [CI] = 0.77 to 0.89) points higher pain intensity ratings (range = 0-10) than nonrecipients. This apparent unfavorable effect size was reduced to 0.37 (95% CI = 0.28 to 0.45) after PS matching, 0.36 (95% CI = 0.29 to 0.44) with IPTW on the treated (IPTW-T) weighting, and diminished to null when integrating IPTW-T with PS matching (0.004, 95% CI = -0.09 to 0.10). An alternative IPTW model and conventional covariate adjustment appeared least powerful in terms of potential bias reduction. Sensitivity analyses restricting the follow-up period to one year after CIH initiation derived consistent results. Conclusions: PS-based causal methods successfully eliminated baseline difference between exposure groups in all measured covariates, yet they did not detect a significant difference in the self-rated pain intensity outcome between veterans who received CIHs and those who did not during the follow-up period.

Opioid Use Among Veterans of Recent Wars Receiving Veterans Affairs Chiropractic Care.

Objective: To examine patient sociodemographic and clinical characteristics associated with opioid use among Veterans of Operations Enduring Freedom/Iraqi Freedom/New Dawn (OEF/OIF/OND) who receive chiropractic care, and to explore the relationship between timing of a chiropractic visit and receipt of an opioid prescription. Methods: Cross-sectional analysis of administrative data on OEF/OIF/OND veterans who had at least one visit to a Veterans Affairs (VA) chiropractic clinic between 2004 and 2014. Opioid receipt was defined as at least one prescription within a window of 90 days before to 90 days after the index chiropractic clinic visit. Results: We identified 14,025 OEF/OIF/OND veterans with at least one chiropractic visit, and 4,396 (31.3%) of them also received one or more opioid prescriptions. Moderate/severe pain (odds ratio [OR] = 1.87, 95% confidence interval [CI] = 1.72-2.03), PTSD (OR = 1.55, 95% CI = 1.41-1.69), depression (OR = 1.40, 95% CI = 1.29-1.53), and current smoking (OR = 1.39, 95% CI = 1.26-1.52) were associated with a higher likelihood of receiving an opioid prescription. The percentage of veterans receiving opioid prescriptions was lower in each of the three 30-day time frames assessed after the index chiropractic visit than before. Conclusions: Nearly one-third of OEF/OIF/OND veterans receiving VA chiropractic services also received an opioid prescription, yet the frequency of opioid prescriptions was lower after the index chiropractic visit than before. Further study is warranted to assess the relationship between opioid use and chiropractic care.

Examining Gender as a Correlate of Self-Reported Pain Treatment Use Among Recent Service Veterans with Deployment-Related Musculoskeletal Disorders.

OBJECTIVE: Women veterans with chronic pain utilize health care with greater frequency than their male counterparts. However, little is known about gender differences in the use of specialty pain care in this population. This investigation examined gender differences in self-reported use of opioids, interventional pain treatments, rehabilitation therapies, and complementary and integrative health (CIH) services for chronic pain treatment both within and outside of the Veterans Health Administration in a sample of veterans who served in support of recent conflicts. METHODS: Participants included 325 veterans (54% women) who completed a baseline survey as part of the Women Veterans Cohort Study and reported deployment-related musculoskeletal conditions and chronic pain. Measures included self-reported use of pain treatment modalities, pain severity, self-rated health, access to specialty care, disability status, and presence of a mental health condition. RESULTS: Men were more likely to report a persistent deployment-related musculoskeletal condition but were no more likely than women to report chronic pain. Overall, 21% of the sample reported using opioids, 27% used interventional strategies, 59% used rehabilitation therapies, and 57% used CIH services. No significant gender differences in use of any pain treatment modality were observed. CONCLUSIONS: Use of pain specialty services was common among men and women, particularly rehabilitative and CIH services. There were no gender differences in the self-reported use of different modalities. These results are inconsistent with documented gender differences in pain care. They encourage further examination of gender differences in preferences and other individual difference variables as predictors of specialty pain care utilization.

Trends in the Use and Characteristics of Chiropractic Services in the Department of Veterans Affairs.

OBJECTIVES: The purpose of this study was to analyze national trends and key features of the Department of Veterans Affairs' (VA's) chiropractic service delivery and chiropractic provider workforce since their initial inception. METHODS: This was a serial cross-sectional analysis of the VA administrative data sampled from the first record of chiropractic services in VA through September 30, 2015. Data were obtained from VA's Corporate Data Warehouse and analyzed with descriptive statistics. RESULTS: From October 1, 2004, through September 30, 2015, the annual number of patients seen in VA chiropractic clinics increased from 4052 to 37349 (821.7%), and the annual number of chiropractic visits increased from 20072 to 159366 (693.9%). The typical VA chiropractic patient is male, is between the ages of 45 and 64, is seen for low back and/or neck conditions, and receives chiropractic spinal manipulation and evaluation and management services. The total number of VA chiropractic clinics grew from 27 to 65 (9.4% annually), and the number of chiropractor employees grew from 13 to 86 (21.3% annually). The typical VA chiropractor employee is a 45.9-year-old man, has worked in VA for 4.5 years, and receives annual compensation of $97860. VA also purchased care from private sector chiropractors starting in 2000, growing to 159533 chiropractic visits for 19435 patients at a cost of $11155654 annually. CONCLUSIONS: Use of chiropractic services and the chiropractic workforce in VA have grown substantially over more than a decade since their introduction.