Dataset Information

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

ABSTRACT:

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.

SUBMITTER: C Coleman B

PROVIDER: S-EPMC10411229 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

C Coleman Brian B Finch Dezon D Wang Rixin R L Luther Stephen S Heapy Alicia A Brandt Cynthia C J Lisi Anthony A

Applied clinical informatics 20230510 3

<h4>Background</h4>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.<h4>Objective</h4 ...[more]

PMID: 37164327

Similar Datasets

Project description:BackgroundOver 25% of veterans seeking care at U.S. Veterans Health Administration facilities have chronic low back pain (LBP), with high rates of mental health comorbidities. The primary objective of this study was to assess the feasibility of participant recruitment, retention, and electronic data collection to prepare for the subsequent randomized trial of multimodal chiropractic care for pain management of veterans with chronic low back pain. The secondary objectives were to estimate effect sizes and variability of the primary outcome and choose secondary outcomes for the full-scale trial.MethodsThis single-arm pilot trial enrolled 40 veterans with chronic LBP at one Veterans Health Administration facility for a 10-week course of pragmatic multimodal chiropractic care. Recruitment was by (1) provider referral, (2) invitational letter from the electronic health record pre-screening, and (3) standard direct recruitment. We administered patient-reported outcome assessments through an email link to REDCap, an electronic data capture platform, at baseline and 5 additional timepoints. Retention was tracked through adherence to the treatment plan and completion rates of outcome assessments. Descriptive statistics were calculated for baseline characteristics and outcome variables.ResultsWe screened 91 veterans over 6 months to enroll our goal of 40 participants. Seventy percent were recruited through provider referrals. Mean age (range) was 53 (22-79) years and 23% were female; 95% had mental health comorbidities. The mean number of chiropractic visits was 4.5 (1-7). Participants adhered to their treatment plan, with exception of 3 who attended only their first visit. All participants completed assessments at the in-person baseline visit and 80% at the week 10 final endpoint. We had no issues administering assessments via REDCap. We observed clinically important improvements on the Roland-Morris Disability Questionnaire [mean change (SD): 3.6 (6.1)] and on PROMIS® pain interference [mean change (SD): 3.6 (5.6)], which will be our primary and key secondary outcome, respectively, for the full-scale trial.ConclusionsWe demonstrated the feasibility of participant recruitment, retention, and electronic data collection for conducting a pragmatic clinical trial of chiropractic care in a Veterans Health Administration facility. Using the pilot data and lessons learned, we modified and refined a protocol for a full-scale, multisite, pragmatic, National Institutes of Health-funded randomized trial of multimodal chiropractic care for veterans with chronic LBP that began recruitment in February 2021.Trial registrationClinicalTrials.gov NCT03254719.

Project description:BackgroundChiropractors' clinical indicators for recommending preventive continued care to patients with low back pain include previous pain episodes, a history of long pain duration and improvement after initial treatment. Our objectives were, in a cohort of patients with neck pain, to examine whether these clinical indicators were associated with being recommended continued care beyond 4 weeks, and if so whether this recommendation was dependent of chiropractor characteristics, as well as if the number of clinical indicators influenced this recommendation.MethodsIn this multi-center observational study, 172 patients seeking care for a new episode of neck pain in chiropractic practice in Norway were included between September 2015 and May 2016. The chiropractors treated their patients as per usual, and for this study, baseline data and 4-week follow-up data were used. Patient data included the clinical indicators (1) previous episodes of neck pain, (2) a history of long duration neck pain and (3) improvement four weeks after initial treatment. The recruiting chiropractors were asked at 4-week follow-up if each patient was recommended continued care, defined as care planned beyond the first 4 weeks. Univariate and multivariable logistic regression models investigated the association between clinical indicators and the continued care recommendation, as well as the influence of chiropractor characteristics on this recommendation. Cross tabulations investigated the relationship between the number of indicators present and recommendation of continued care.ResultsLong duration of neck pain was the strongest clinical indicator for being recommended continued care 4 weeks after the initial treatment. Chiropractor characteristics were not associated with this recommendation. In patients with all three clinical indicators present, 39% were recommended continued care. When two and one indicators were present, the percentages of those recommended continued care were 25% and 10%, respectively.ConclusionChiropractors recommended continued care for patients experiencing neck pain based on their history of long pain duration, and this was not influenced by characteristics of the chiropractor. This differs from previous studies of indicators for maintenance care in patients with low back pain.

Project description:BackgroundChronic 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.MethodsWe 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.ResultsThe 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.ConclusionsUsing 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.

Project description:The cognitive approach to psychotherapy aims to change patients' maladaptive schemas, that is, overly negative views on themselves, the world, or the future. To obtain awareness of these views, they record their thought processes in situations that caused pathogenic emotional responses. The schemas underlying such thought records have, thus far, been largely manually identified. Using recent advances in natural language processing, we take this one step further by automatically extracting schemas from thought records. To this end, we asked 320 healthy participants on Amazon Mechanical Turk to each complete five thought records consisting of several utterances reflecting cognitive processes. Agreement between two raters on manually scoring the utterances with respect to how much they reflect each schema was substantial (Cohen's κ = 0.79). Natural language processing software pretrained on all English Wikipedia articles from 2014 (GLoVE embeddings) was used to represent words and utterances, which were then mapped to schemas using k-nearest neighbors algorithms, support vector machines, and recurrent neural networks. For the more frequently occurring schemas, all algorithms were able to leverage linguistic patterns. For example, the scores assigned to the Competence schema by the algorithms correlated with the manually assigned scores with Spearman correlations ranging between 0.64 and 0.76. For six of the nine schemas, a set of recurrent neural networks trained separately for each of the schemas outperformed the other algorithms. We present our results here as a benchmark solution, since we conducted this research to explore the possibility of automatically processing qualitative mental health data and did not aim to achieve optimal performance with any of the explored models. The dataset of 1600 thought records comprising 5747 utterances is published together with this article for researchers and machine learning enthusiasts to improve upon our outcomes. Based on our promising results, we see further opportunities for using free-text input and subsequent natural language processing in other common therapeutic tools, such as ecological momentary assessments, automated case conceptualizations, and, more generally, as an alternative to mental health scales.

Project description:BackgroundLow back pain (LBP) is common among military veterans seeking treatment in Department of Veterans Affairs (VA) healthcare facilities. As chiropractic services within VA expand, well-designed pragmatic trials and implementation studies are needed to assess clinical effectiveness and program uptake. This study evaluated veteran stakeholder perceptions of the feasibility and acceptability of care delivery and research processes in a pilot trial of multimodal chiropractic care for chronic LBP.MethodsThe qualitative study was completed within a mixed-method, single-arm, pragmatic, pilot clinical trial of chiropractic care for LBP conducted in VA chiropractic clinics. Study coordinators completed semi-structured, in person or telephone interviews with veterans near the end of the 10-week trial. Interviews were audiorecorded and transcribed verbatim. Qualitative content analysis using a directed approach explored salient themes related to trial implementation and delivery of chiropractic services.ResultsOf 40 participants, 24 completed interviews (60% response; 67% male gender; mean age 51.7 years). Overall, participants considered the trial protocol and procedures feasible and reported that the chiropractic care and recruitment methods were acceptable. Findings were organized into 4 domains, 10 themes, and 21 subthemes. Chiropractic service delivery domain encompassed 3 themes/8 subthemes: scheduling process (limited clinic hours, scheduling future appointments, attendance barriers); treatment frequency (treatment sufficient for LBP complaint, more/less frequent treatments); and chiropractic clinic considerations (hire more chiropractors, including female chiropractors; chiropractic clinic environment; patient-centered treatment visits). Outcome measures domain comprised 3 themes/4 subthemes: questionnaire burden (low burden vs. time-consuming or repetitive); relevance (items relevant for LBP study); and timing and individualization of measures (questionnaire timing relative to symptoms, personalized approach to outcomes measures). The online data collection domain included 2 themes/4 subthemes: user concerns (little difficulty vs. form challenges, required computer skills); and technology issues (computer/internet access, junk mail). Clinical trial planning domain included 2 themes/5 subthemes: participant recruitment (altruistic service by veterans, awareness of chiropractic availability, financial compensation); and communication methods (preferences, potential barriers).ConclusionsThis qualitative study highlighted veteran stakeholders' perceptions of VA-based chiropractic services and offered important suggestions for conducting a full-scale, veteran-focused, randomized trial of multimodal chiropractic care for chronic LBP in this clinical setting.Trial registrationClinicalTrials.gov NCT03254719.

Dataset Information

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

Background

Objective

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets