scholarly journals Preparing Clinical Text for Use in Biomedical Research

2011 ◽  
pp. 2085-2095
Author(s):  
John P. Pestian ◽  
Lukasz Itert ◽  
Charlotte Andersen

Approximately 57 different types of clinical annotations construct a patient’s medical record. These annotations include radiology reports, discharge summaries, and surgical and nursing notes. Hospitals typically produce millions of text-based medical records over the course of a year. These records are essential for the delivery of care, but many are underutilized or not utilized at all for clinical research. The textual data found in these annotations is a rich source of insights into aspects of clinical care and the clinical delivery system. Recent regulatory actions, however, require that, in many cases, data not obtained through informed consent or data not related to the delivery of care must be made anonymous (as referred to by regulators as harmless), before they can be used. This article describes a practical approach with which Cincinnati Children’s Hospital Medical Center (CCHMC), a large pediatric academic medical center with more than 761,000 annual patient encounters, developed open source software for making pediatric clinical text harmless without losing its rich meaning. Development of the software dealt with many of the issues that often arise in natural language processing, such as data collection, disambiguation, and data scrubbing.

2021 ◽  
Author(s):  
Lori Schirle ◽  
Alvin D Jeffery ◽  
Ali Yaqoob ◽  
Sandra Sanchez-Roige ◽  
David C. Samuels

Background: Although electronic health records (EHR) have significant potential for the study of opioid use disorders (OUD), detecting OUD in clinical data is challenging. Models using EHR data to predict OUD often rely on case/control classifications focused on extreme opioid use. There is a need to expand this work to characterize the spectrum of problematic opioid use. Methods: Using a large academic medical center database, we developed 2 data-driven methods of OUD detection: (1) a Comorbidity Score developed from a Phenome-Wide Association Study of phenotypes associated with OUD and (2) a Text-based Score using natural language processing to identify OUD-related concepts in clinical notes. We evaluated the performance of both scores against a manual review with correlation coefficients, Wilcoxon rank sum tests, and area-under the receiver operating characteristic curves. Records with the highest Comorbidity and Text-based scores were re-evaluated by manual review to explore discrepancies. Results: Both the Comorbidity and Text-based OUD risk scores were significantly elevated in the patients judged as High Evidence for OUD in the manual review compared to those with No Evidence (p = 1.3E-5 and 1.3E-6, respectively). The risk scores were positively correlated with each other (rho = 0.52, p < 0.001). AUCs for the Comorbidity and Text-based scores were high (0.79 and 0.76, respectively). Follow-up manual review of discrepant findings revealed strengths of data-driven methods over manual review, and opportunities for improvement in risk assessment. Conclusion: Risk scores comprising comorbidities and text offer differing but synergistic insights into characterizing problematic opioid use. This pilot project establishes a foundation for more robust work in the future.


2006 ◽  
Vol 3 (4) ◽  
pp. 495-501 ◽  
Author(s):  
Dietlind L. Wahner-Roedler ◽  
Ann Vincent ◽  
Peter L. Elkin ◽  
Laura L. Loehrer ◽  
Stephen S. Cha ◽  
...  

The purpose of this study was to evaluate the attitudes of physicians at an academic medical center toward complementary and alternative medicine (CAM) therapies and the physicians' knowledge base regarding common CAM therapies. A link to a Web-based survey was e-mailed to 660 internists at Mayo Clinic in Rochester, MN, USA. Physicians were asked about their attitudes toward CAM in general and their knowledge regarding specific CAM therapies. The level of evidence a physician would require before incorporating such therapies into clinical care was also assessed. Of the 233 physicians responding to the survey, 76% had never referred a patient to a CAM practitioner. However, 44% stated that they would refer a patient if a CAM practitioner were available at their institution. Fifty-seven percent of physicians thought that incorporating CAM therapies would have a positive effect on patient satisfaction, and 48% believed that offering CAM would attract more patients. Most physicians agreed that some CAM therapies hold promise for the treatment of symptoms or diseases, but most of them were not comfortable in counseling their patients about most CAM treatments. Prospective, randomized controlled trials were considered the level of evidence required for most physicians to consider incorporating a CAM therapy into their practice. The results of this survey provide insight into the attitudes of physicians toward CAM at an academic medical center. This study highlights the need for educational interventions and the importance of providing physicians ready access to evidence-based information regarding CAM.


Author(s):  
Brody Foster ◽  
Matthew David Krasowski

BACKGROUND Electronic health record (EHR) patient portals provide a means by which patients can access their health information, including diagnostic test results. Little is known about portal usage by emergency department (ED) patients. OBJECTIVE The study aimed to assess patient portal utilization by ED patients at an academic medical center using account activation rates along with the rates of access of diagnostic test results (laboratory results and radiology reports), analyzing the impact of age, gender, and self-reported patient race. METHODS This institutional review board–approved retrospective study was performed at a 60,000-visits-per-year university-based ED. We utilized EHR data reporting tools to examine EHR portal activation and utilization for all patients who had at least one ED encounter with one or more diagnostic tests performed between October 1, 2016, and October 1, 2017. The total dataset for laboratory testing included 208,635 laboratory tests on 25,361 unique patients, of which 9482 (37.39%) had active portal accounts. The total dataset for radiologic imaging included 23,504 radiology studies on 14,455 unique patients, of which 5439 (37.63%) had an active portal account. RESULTS Overall, 8.90% (18,573/208,635) of laboratory tests and 8.97% (2019/22,504) of radiology reports ordered in the ED were viewed in the patient portal. The highest rates of viewing of laboratory and radiology results were seen for those who were female, were aged 0 to 11 years (parent or guardian viewing by proxy) and 18 to 60 years, and self-reported their race as Caucasian or Asian. The lowest rates were for those who were teenagers, aged older than 81 years, African American/black, and Hispanic/Latino. Infectious disease, urinalysis, and pregnancy testing constituted the highest number of laboratory tests viewed. Magnetic resonance imaging reports were viewed at higher rates than computed tomography or x-ray studies (P<.001). Approximately half of all the diagnostic test results accessed by patients were reviewed within 72 hours of availability in the patient portal (laboratory results: 9904/18,573, 53.32% and radiology reports: 971/2019, 48.1%). On the other extreme, 19.9% (3701/18,573) of laboratory results and 31.6% (639/2019) of radiology reports were viewed more than 2 weeks after availability in the portal. CONCLUSIONS The data highlight the relatively low use of a patient portal by ED patients and existing disparities between patient groups. There can be wide lag time (months) between result/report availability and access by patients. Opportunities for improvement exist for both activation and more robust utilization of patient portals by ED patients.


Author(s):  
Sharon E. Fox ◽  
Richard S. Vander Heide

The SARS-CoV-2 virus has resulted in over 88 million cases worldwide of COVID-19 as of January 2021. The heart is one of the most commonly affected organs in COVID-19, but the nature and extent of the cardiac pathology has remained controversial. It has been shown that patients infected with SARS-CoV-2 can sustain type 1 myocardial infarction in the absence of significant atherosclerotic coronary artery disease. However, many patients present with small elevations of troponin enzymes of unclear etiology which correlate with overall COVID-19 disease outcome. Early autopsy reports indicated variable levels of typical lymphocytic myocarditis, while radiology reports have indicated that myocarditis can be a persistent problem after recovery from acute illness, raising concern about participation in college athletics. In this communication, we review the literature to date regarding the gross and microscopic findings of COVID-19 cardiac involvement, present the findings from over 40 cases from our academic medical center, and propose mechanisms by which patients develop small elevations in troponin.  


Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1172
Author(s):  
Anna M. Maw ◽  
Megan A. Morris ◽  
Juliana G. Barnard ◽  
Juliana Wilson ◽  
Russell E. Glasgow ◽  
...  

There is growing interest from multiple specialties, including internal medicine, to incorporate diagnostic point of care ultrasound (POCUS) into standard clinical care. However, few internists currently use POCUS. The objective of this study was to understand the current determinants of POCUS adoption at both the health system and clinician level at a U.S. academic medical center from the perspective of multi-level stakeholders. We performed semi-structured interviews of multi-level stakeholders including hospitalists, subspecialists, and hospital leaders at an academic medical center in the U.S. Questions regarding the determinants of POCUS adoption were asked of study participants. Using the framework method, team-based analysis of interview transcripts were guided by the contextual domains of the Practical Robust Implementation and Sustainability Model (PRISM). Thirty-one stakeholders with diverse roles in POCUS adoption were interviewed. Analysis of interviews revealed three overarching themes that stakeholders considered important to adoption by clinicians and health systems: clinical impact, efficiency and cost. Subthemes included two that were deemed essential to high-fidelity implementation: the development of credentialing policies and robust quality assurance processes. These findings identify potential determinants of system and clinician level adoption that may be leveraged to achieve high-fidelity implementation of POCUS applications that result in improved patient outcomes.


Author(s):  
Ronilda Lacson ◽  
Laila Cochon ◽  
Patrick R Ching ◽  
Eseosa Odigie ◽  
Neena Kapoor ◽  
...  

Abstract Objective Quantify the integrity, measured as completeness and concordance with a thoracic radiologist, of documenting pulmonary nodule characteristics in CT reports and assess impact on making follow-up recommendations. Materials and Methods This Institutional Review Board-approved, retrospective cohort study was performed at an academic medical center. Natural language processing was performed on radiology reports of CT scans of chest, abdomen, or spine completed in 2016 to assess presence of pulmonary nodules, excluding patients with lung cancer, of which 300 reports were randomly sampled to form the study cohort. Documentation of nodule characteristics were manually extracted from reports by 2 authors with 20% overlap. CT images corresponding to 60 randomly selected reports were further reviewed by a thoracic radiologist to record nodule characteristics. Documentation completeness for all characteristics were reported in percentage and compared using χ2 analysis. Concordance with a thoracic radiologist was reported as percentage agreement; impact on making follow-up recommendations was assessed using kappa. Results Documentation completeness for pulmonary nodule characteristics differed across variables (range = 2%–90%, P &lt; .001). Concordance with a thoracic radiologist was 75% for documenting nodule laterality and 29% for size. Follow-up recommendations were in agreement in 67% and 49% of reports when there was lack of completeness and concordance in documenting nodule size, respectively. Discussion Essential pulmonary nodule characteristics were under-reported, potentially impacting recommendations for pulmonary nodule follow-up. Conclusion Lack of documentation of pulmonary nodule characteristics in radiology reports is common, with potential for compromising patient care and clinical decision support tools.


2017 ◽  
Vol 35 (8_suppl) ◽  
pp. 99-99
Author(s):  
Christopher Chen ◽  
Sara DeGregorio ◽  
Margaret Soriano ◽  
Inga Tolin Lennes ◽  
Ryan Thompson ◽  
...  

99 Background: In 2012, in an effort to improve continuity between inpatient and outpatient care, Massachusetts General Hospital (MGH) began sending automated email notifications to outpatient physicians when patients with whom they have an established relationship are admitted to MGH. Physicians are allowed to bill internally for a “continuity visit” if they visit their patient during an inpatient stay. We sought to study MGH hematologist and oncologist perceptions of care continuity and the efficacy of this continuity visit program. Methods: In the summer of 2015, all MGH hematology and oncology attending physicians, regardless of whether they had previously billed for a continuity visit, were provided a small financial incentive to participate in an online survey. Ninety-one of 116 physicians responded to the survey (78%). Results: Of the respondents, 74% had previously billed for a continuity visit, although others may have performed continuity visits without formally billing for them. Ninety-six percent of respondents felt that continuity visits are either highly useful or moderately useful to their patients, namely because patients view continuity visits as an expression of interest in their well-being (90%) and/or as a welcome surprise (58%). Ninety-one percent of respondents felt that continuity visits are highly or moderately useful to the inpatient team, because they are able to informally share clinical insights that improve clinical care (71%) and/or answer questions or confirm the inpatient attending’s plan of care (79%). Furthermore, 72% of respondents felt that continuity visits improve their longitudinal relationship with their patients. Lastly, 84% of respondents expressed high or moderate satisfaction with making continuity visits. Conclusions: MGH hematologists and oncologists reported that visiting their hospitalized patients is useful to inpatient care teams and their patients. A small incentive payment may encourage such continuity visits. The next step is to evaluate whether continuity visits make a difference in clinical outcomes, such as patient experience, readmissions, and inpatient length-of-stay.


2020 ◽  
pp. 084653712090206 ◽  
Author(s):  
Waleed Abdellatif ◽  
Jeffrey Ding ◽  
Abdelmohsen Radwan Hussien ◽  
Ali Hussain ◽  
Shahin Shirzad ◽  
...  

Objectives: This study is an evaluation of the emergency department (ED) satisfaction with the current radiologic reporting system used at a major Northeastern academic medical center. The radiology reports are the main form of communication and usually the final product of any radiological investigation delivered to clinicians. The aim of this study was to improve current radiology reporting practices and to better tailor reports to match the needs and expectations of ED clinicians. Methods: A 9-question online survey was sent to ED residents, fellows, faculty, and nurse practitioners/advanced practice providers at a major Northeastern academic medical center in the United States. For the open-ended section, coding and emergent theme categorization was conducted for quantification of responses. The survey was designed to evaluate the attitudes toward the structure, style, form, and wording used in reports. Results: The response rate was 48.6% (68/140). The ED respondents were generally satisfied with radiology reports, their language, vocabulary, and clarity. They preferred the impression section to be before the findings in simple examinations and to stratify the reports according to emergency status for complex examinations. They did not like extended differential, hedge terms, and delayed reporting. Additionally, ED respondents recommended focused, fast reporting with considerable changes toward a more standardized report. Conclusions: This evaluation delivered a list of actionable recommendations. The top recommendation is to standardize reporting structure, style, and lexicon, in addition to being focused, timely, and brief.


2018 ◽  
Vol 61 (5) ◽  
pp. 830-849 ◽  
Author(s):  
Alison T. Wynn ◽  
Magali Fassiotto ◽  
Caroline Simard ◽  
Jennifer L. Raymond ◽  
Hannah Valantine

Previous research has documented the influence of overwork and inflexible hours on work-life conflict for working professionals. In this paper, we build on this literature and explore the novel theoretical concept of work-work conflict, a form of inter-role conflict analogous to work-life conflict. Drawing on 48 in-depth interviews with 42 physicians and survey data of 60 faculty at a prominent west-coast academic medical center, we find that work-work conflict is fueled by institutional structural characteristics. Institutional incentives, the extent of recognition for various work activities, and financial rewards are misaligned, causing physicians to experience competing demands across multiple organizational missions (research, teaching, clinical care, and administration/service). Other industries may face similar conditions leading to work-work conflict. We conclude that work-life interventions are necessary but not sufficient to increase employee satisfaction, and that mechanisms to alleviate work-work conflict must be incorporated in practical solutions to address burnout.


Sign in / Sign up

Export Citation Format

Share Document