7 results
Enhancing an enterprise data warehouse for research with data extracted using natural language processing
- Tanja Magoc, Russell Everson, Christopher A. Harle
-
- Journal:
- Journal of Clinical and Translational Science / Volume 7 / Issue 1 / 2023
- Published online by Cambridge University Press:
- 13 June 2023, e149
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
Objective:
This study aims to develop a generalizable architecture for enhancing an enterprise data warehouse for research (EDW4R) with results from a natural language processing (NLP) model, which allows discrete data derived from clinical notes to be made broadly available for research use without need for NLP expertise. The study also quantifies the additional value that information extracted from clinical narratives brings to EDW4R.
Materials and methods:Clinical notes written during one month at an academic health center were used to evaluate the performance of an existing NLP model and to quantify its value added to the structured data. Manual review was utilized for performance analysis. The architecture for enhancing the EDW4R is described in detail to enable reproducibility.
Results:Two weeks were needed to enhance EDW4R with data from 250 million clinical notes. NLP generated 16 and 39% increase in data availability for two variables.
Discussion:Our architecture is highly generalizable to a new NLP model. The positive predictive value obtained by an independent team showed only slightly lower NLP performance than the values reported by the NLP developers. The NLP showed significant value added to data already available in structured format.
Conclusion:Given the value added by data extracted using NLP, it is important to enhance EDW4R with these data to enable research teams without NLP expertise to benefit from value added by NLP models.
Implementation context for addressing social needs in a learning health system: a qualitative study
- Ryan P. Theis, Katherine Blackburn, Gloria Lipori, Christopher A. Harle, Michelle M. Alvarado, Peter J. Carek, Nadine Zemon, Angela Howard, Ramzi G. Salloum, Elizabeth A. Shenkman, the UF CTSI Learning Health System Program
-
- Journal:
- Journal of Clinical and Translational Science / Volume 5 / Issue 1 / 2021
- Published online by Cambridge University Press:
- 31 August 2021, e201
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
Introduction.
Unmet social needs contribute to growing health disparities and rising health care costs. Strategies to collect and integrate information on social needs into patients’ electronic health records (EHRs) show promise for connecting patients with community resources. However, gaps remain in understanding the contextual factors that impact implementing these interventions in clinical settings.
Methods.We conducted qualitative interviews with patients and focus groups with providers (January−September 2020) in two primary care clinics to inform the implementation of a module that collects and integrates patient-reported social needs information into the EHR. Questions addressed constructs within the Theoretical Framework for Acceptability and the Consolidated Framework for Implementation Research. Data were coded deductively using team-based framework analysis, followed by inductive coding and matrix analyses.
Results.Forty patients participated in interviews, with 20 recruited at the clinics and 20 from home. Two focus groups were conducted with a total of 12 providers. Factors salient to acceptability and feasibility included patients’ discomfort answering sensitive questions, concerns about privacy, difficulty reading/understanding module content, and technological literacy. Rapport with providers was a facilitator for patients to discuss social needs. Providers stressed that limited time with patients would be a barrier, and expressed concerns about the lack of available community resources.
Conclusion.Findings highlight the need for flexible approaches to assessing and discussing social needs with patients. Feasibility of the intervention is contingent upon support from the health system to facilitate social needs assessment and discussion. Further study of availability of community resources is needed to ensure intervention effectiveness.
Research informatics and the COVID-19 pandemic: Challenges, innovations, lessons learned, and recommendations
- Richard J. Bookman, James J. Cimino, Christopher A. Harle, Rhonda G. Kost, Sean Mooney, Emily Pfaff, Svetlana Rojevsky, Jonathan N. Tobin, Adam Wilcox, Nick F. Tsinoremas
-
- Journal:
- Journal of Clinical and Translational Science / Volume 5 / Issue 1 / 2021
- Published online by Cambridge University Press:
- 16 March 2021, e110
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
The recipients of NIH’s Clinical and Translational Science Awards (CTSA) have worked for over a decade to build informatics infrastructure in support of clinical and translational research. This infrastructure has proved invaluable for supporting responses to the current COVID-19 pandemic through direct patient care, clinical decision support, training researchers and practitioners, as well as public health surveillance and clinical research to levels that could not have been accomplished without the years of ground-laying work by the CTSAs. In this paper, we provide a perspective on our COVID-19 work and present relevant results of a survey of CTSA sites to broaden our understanding of the key features of their informatics programs, the informatics-related challenges they have experienced under COVID-19, and some of the innovations and solutions they developed in response to the pandemic. Responses demonstrated increased reliance by healthcare providers and researchers on access to electronic health record (EHR) data, both for local needs and for sharing with other institutions and national consortia. The initial work of the CTSAs on data capture, standards, interchange, and sharing policies all contributed to solutions, best illustrated by the creation, in record time, of a national clinical data repository in the National COVID-19 Cohort Collaborative (N3C). The survey data support seven recommendations for areas of informatics and public health investment and further study to support clinical and translational research in the post-COVID-19 era.
3022 Barriers to Accessing Follow-up Care and Changes in Medical Needs after Childhood Injury
- Teresa Maria Bell, Ashley N Vetor, Dennis P Watson, Christopher A Harle, Aaron E Carroll
-
- Journal:
- Journal of Clinical and Translational Science / Volume 3 / Issue s1 / March 2019
- Published online by Cambridge University Press:
- 26 March 2019, pp. 140-141
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: The objective of this study was to prospectively assess caregiver-perceived barriers to accessing post-acute care for their injured child and determine if caregivers report ongoing, unmet health needs for their children after trauma. METHODS/STUDY POPULATION: This was a prospective cohort study that followed 50 participants for 6 months and administered surveys to parents of children who are admitted to a pediatric level 1 trauma center for injury. Surveys were given bi-weekly regarding care children received after hospital discharge. At 3 months, parents were surveyed over the phone on whether they were able to access all needed health services and if there were any perceived barriers to obtaining or providing at-home care. At 6 months, parents were given the Child & Family Follow-up Survey to assess ongoing physical, mental, social, and scholastic needs. Free responses and transcribed interviews were analyzed using thematic content analysis and frequencies are reported for discrete data. RESULTS/ANTICIPATED RESULTS: Out of 50 families recruited, 47 completed follow-up assessments. At 3 months, common themes regarding challenges after hospital discharge included difficulty scheduling specialist care; uncertainty in managing their child’s pain; transitioning home without enough knowledge to meet their child’s medical needs; lack of communication between multiple providers; distress at having providers release children to full activities before caregivers were comfortable. At 6 months, approximately 24% of parents reported children had ongoing cognitive limitations, 29% reported emotional problems, 19% reported physical limitations, 33.3% reported difficulty in school, and 15% reported play/social difficulties. DISCUSSION/SIGNIFICANCE OF IMPACT: Evidence suggests families face significant barriers in accessing follow-up care, despite nearly universal health insurance coverage for children. Further, a large percentage of parents report ongoing health needs, despite the majority of the cohort having only mild or moderate severity injuries. Making follow-up care more patient-centered for families of traumatically injured children may improve compliance with medical regiments and reduce the likelihood of future disability. Examples of this may be coordinating care among multiple specialty providers, so that patients with multiple injuries can schedule multiple follow-up appointments on the same day. Additionally, more caregiver education on administering pain medication, caring for wounds, and safe practices for returning to full activities would be beneficial for families.
3038 Examining the association between inpatient opioid prescribing and patient satisfaction.
- Olena Mazurenko, Justin Blackburn, Matthew Bair, Areeba Kara, Christopher A. Harle
-
- Journal:
- Journal of Clinical and Translational Science / Volume 3 / Issue s1 / March 2019
- Published online by Cambridge University Press:
- 26 March 2019, pp. 121-122
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Research overview: Providing patient-centered care is increasingly a top priority in the U.S. healthcare system.1,2 Hospitals are required to publicly report patient-centered assessments, including results from the Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) patient satisfaction surveys.3 Furthermore, clinician and hospital reimbursements are partially determined by performance on patient satisfaction measures.3 Consequently, hospitals and clinicians may be incentivized to improve patient satisfaction scores over other important outcomes.4 Paradoxically then, the pursuit of patient-centered care may lead clinicians to fulfill patient requests for unnecessary and potentially harmful treatments.5 Opioid prescribing during hospitalizations may be particularly affected by clinicians’ seeking to optimize patient satisfaction scores.6,7 Satisfaction with pain care is an important predictor of overall patient satisfaction in the HCAHPS surveys,8,9 and clinicians report increased pressure to fulfill patient requests for immediate pain-relief.10,11 Therefore, clinicians may prescribe opioids to avoid receiving lower patient satisfaction scores.12,13 Furthermore, clinicians lack clear guidance on opioid prescribing for some populations, including non-surgical inpatients, who represent almost half of all hospitalizations.14 To reduce clinicians’ incentive to prescribe opioids as a means of achieving patient satisfaction, the Center for Medicare and Medicaid Services (CMS) temporarily removed questions related to patient satisfaction with pain care from the clinician and hospital reimbursement formulas beginning in 2018.15 Importantly, prior research16-20 has not rigorously tested the hypothesis implied by the CMS policy change: that certain opioid prescribing practices in inpatient pain care are associated with higher patient satisfaction. Objectives: The purpose of this study was to evaluate the association between the receipt/dose of opioids during non-surgical hospitalizations and patient satisfaction measured by the HCAHPS survey. METHODS/STUDY POPULATION: Methods/Study Population: We conducted a pooled cross-sectional study of adults (18 and older) with non-surgical hospitalizations within the 11-hospital healthcare system in a Midwestern state from 2011-2016. Data were extracted from electronic health records and linked to HCAHPS patient satisfaction surveys. We estimated the propensity score for receipt of any opioids during hospitalization and separately the receipt of high dose opioids (≥100 morphine milligram equivalent [MME]) based on patient, encounter, and facility characteristics for all hospitalizations with complete data. We used nearest neighbor matching to construct two matched samples to minimize selection bias and confounding by indication. We used a standardized difference threshold of < 0.1 as an indication of the balance between matched groups. Outcomes were compared with a test on the equality of proportions using large-sample statistics. All analysis was performed in STATA 14.0 analytical software. Main outcomes: We analyzed four dependent variables. Two pain-specific patient satisfaction variables were derived from the responses to the following survey questions: 1) “During this hospital stay, how often your pain was well controlled? (pain control)” and 2) “During this hospital stay, how often did the hospital staff do everything they could to help you with your pain? (pain help)”, with 4-point Likert scale responses ranging from “Never” to “Always.” We also used two global satisfaction measures derived from the responses to the following survey questions: 1) “Using any number from 0 to 10, where 0 is the worst hospital possible and 10 is the best hospital possible, what number would you use to rate this hospital during your stay (overall patient satisfaction)?” and 2) “Would you recommend this hospital to your friends and family (willingness to recommend a hospital)? (4-point scale of “Definitely Yes” to “Definitely No”). Because the responses are not normally distributed, and the response options are truncated, we dichotomized each of these questions following previously published approaches8 and CMS methodology3 (e.g. “always” vs. all other responses or “9 or 10 rating” vs. all others). RESULTS/ANTICIPATED RESULTS: Results: Among 17,691 patients who reported that they needed pain medications during hospitalization in their HCAHPS survey, 43.7% (n=7,735) received opioids. Among the matched sample (n=8,848), 55% were female, 90% were white, 9% were black, 74% were emergency admissions, 29% had a circulatory diagnosis, 92% were discharged home, and the average pain score ranged from 0.2 to 7.1 during the hospital stay. Compared to matched patients hospitalized but did not receiving opioids, those who received opioids did not significantly differ in their rating of pain help (75% of patients without opioids rated that they always received help for their pain versus 75% of patients with opioids; p=.78), pain control (55% of patients without opioids reported that their pain was well controlled versus 54% on opioids; p=.93), willingness to recommend the hospital (69% of patients without opioids reported that they would definitely recommend a hospital versus 71% with opioids; p=.16) and overall rating of their care (47% of patients without opioids rated their hospitalization as 10 versus 46% on opioids; p=.22). DISCUSSION/SIGNIFICANCE OF IMPACT: Discussion: We found no evidence that receipt of opioids is associated with patient satisfaction, including at doses. To our knowledge, this is the first study that used propensity score matching to examine the association between inpatient opioid prescribing practices and patient satisfaction. Furthermore, our sample is unique in the inclusion of patients hospitalized for non-surgical indicators over a five year period in the multi-hospital healthcare system in a Midwestern state. Our findings add to the existing literature which has shown contradictory associations between opioid prescribing and patient satisfaction.16-22 Specifically, few studies that looked at surgical inpatients showed a lack of association between patient satisfaction16,18 and opioid prescribing, whereas others showed that receipt of opioids was associated with lower patient satisfaction.17-20 Our findings may imply that satisfaction with pain care may be achieved without administering opioids to non-surgical inpatients. Alternatively, satisfaction with pain care may not be influenced by opioid prescribing for non-surgical inpatients. Future research should further examine the association between opioid prescribing and patient satisfaction among non-surgical inpatients on a national scale to get a better understanding of the relationship between certain pain care practices and patient satisfaction.
2170 Risk factors for prescription opioid misuse after traumatic injury in adolescents
- Teresa M. Bell, Christopher A. Harle, Dennis P. Watson, Aaron E. Carroll
-
- Journal:
- Journal of Clinical and Translational Science / Volume 2 / Issue S1 / June 2018
- Published online by Cambridge University Press:
- 21 November 2018, p. 87
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: The objective of this study is to determine predictors and motives for sustained opioid use, prescription misuse, and nonmedical opioid use in the adolescent trauma population. METHODS/STUDY POPULATION: This is a prospective cohort study that will follow patients for 1 year and administer surveys to patients on prescription opioid usage; substance use; utilization of pain management and mental health services; mental and physical health conditions; and behavioral and social risk factors. Patient eligibility criteria include: (1) patient is 12–18 years of age; (2) admitted for trauma; (3) english speaking; (4) resides within Indianapolis, IN metropolitan area; and (5) consent can be obtained from a parent or guardian. Patients with severe brain injuries or other injuries that prevent survey participation will be excluded. The patient sample will comprise of 50 traumatically injured adolescents admitted for trauma who will be followed for 12 months after discharge. RESULTS/ANTICIPATED RESULTS: We expect that the results of this study will identify multiple risk factors for sustained opioid use that can be used to create targeted interventions to reduce opioid misuse in the adolescent trauma population. Clinical predictors such as opioid type, dosage, and duration that can be modified to reduce the risk of long-term opioid use will be identified. We expect to elucidate clinical, behavioral, and social risk factors that increase the likelihood adolescents will misuse their medication and initiate nonmedical opioid use. DISCUSSION/SIGNIFICANCE OF IMPACT: Trauma is a surgical specialty that often has limited collaboration with behavioral health providers. Collaborative care models for trauma patients to adequately address the psychological impact of a traumatic injury have become more common in recent years. These models have primarily been concerned with the prevention of post-traumatic stress disorder. We would like to apply the findings of our research to better understand what motivates adolescents to misuse pain medications as well as how clinical, individual, behavioral, and social factors affect medication usage. This may help identify patients at greater risk of developing a SUD by asking questions not commonly addressed in the hospital setting. For example, similar to how trauma centers have mandated brief interventions on alcohol use be performed for center verification, screening patients’ on their social environment may identify patients at greater risk for SUD than assumed. The long-term goal would be to prevent opioid use disorders in injured adolescents by providing better post-acute care support, possibly by developing and implementing a collaborative care model that addresses opioid use. Additionally, we believe our findings could be applied in the acute care setting as well to help inform opioid prescribing and pain management methods in the acute phase of an injury. Genetic testing to determine which opioid to prescribe pediatric surgical patients is starting to be done at some pediatric hospitals. Certain genes determine which specific opioid is most effective in controlling a patient’s pain and, further, using the optimal opioid medication can also reduce overdose. Our findings may help refine prescribing patterns that could increase or decrease the likelihood of developing SUD in patients with certain genetic, clinical, behavioral, and social characteristics.
2183 Balancing patient-centeredness and patient safety in the hospitals: The case of pain care and patient satisfaction
- Olena Mazurenko, Basia Andraka-Christou, Matthew Bair, Areeba Kara, Christopher A. Harle
-
- Journal:
- Journal of Clinical and Translational Science / Volume 2 / Issue S1 / June 2018
- Published online by Cambridge University Press:
- 21 November 2018, p. 79
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: This study seeks to understand the relationship between opioid prescribing and patient satisfaction among non-surgical, hospitalized patients. As part of this study, we qualitatively examined challenges in delivering safe and patient-centered care through voices of physicians’, and nurses.’ METHODS/STUDY POPULATION: We collected data through in-person interviews using semi-structured guides tailored to the informant roles. Study participants came from 1 healthcare system located in a mid-Western state. Each interview lasted 30–45 minutes, was audio-recorded with consent, and transcribed for analysis. Two researchers each coded 17 transcripts for discussions around patient-centeredness (including patient satisfaction, patient experiences), and patient safety for hospitalized patients experiencing pain. Analysis followed a general inductive approach, where researchers identified themes related to the research questions using an open coding technique. They discussed and reached consensus on all codes, and extracted several preliminary themes. The analysis was supported by NVivo software. RESULTS/ANTICIPATED RESULTS: The following themes emerged: (1) complex decision-making process to prescribe opioids for hospitalized patients; (2) the role of objective findings in prescribing decisions; (3) bargaining process in prescribing opioids; (4) balancing patient-centeredness and patient safety for selected populations; (5) opioids are the predominant medications for pain care. DISCUSSION/SIGNIFICANCE OF IMPACT: Clinicians’ decision to prescribe opioids for nonsurgical hospitalized patients is based on multiple factors, including patient’s condition, patient’s preference for pain medications, or standard hospital’s pain care regimen. Interventions that improve clinicians’ ability to prescribe opioids may be needed to improve delivery of patient-centered and safe pain care.