National Healthcare Quality and Disparities Report
Latest available findings on quality of and access to health care
Data
- Data Infographics
- Data Visualizations
- Data Tools
- Data Innovations
- All-Payer Claims Database
- Healthcare Cost and Utilization Project (HCUP)
- Medical Expenditure Panel Survey (MEPS)
- AHRQ Quality Indicator Tools for Data Analytics
- State Snapshots
- United States Health Information Knowledgebase (USHIK)
- Data Sources Available from AHRQ
Search All Research Studies
AHRQ Research Studies Date
Topics
- Access to Care (1)
- Adverse Drug Events (ADE) (3)
- Adverse Events (10)
- Ambulatory Care and Surgery (1)
- Back Health and Pain (1)
- Behavioral Health (1)
- Blood Pressure (3)
- Cancer (7)
- Cancer: Breast Cancer (1)
- Cancer: Colorectal Cancer (1)
- Cancer: Lung Cancer (2)
- Cancer: Prostate Cancer (1)
- Cardiovascular Conditions (6)
- Care Management (1)
- Children/Adolescents (3)
- Chronic Conditions (3)
- Clinical Decision Support (CDS) (8)
- Clinician-Patient Communication (2)
- Communication (3)
- COVID-19 (2)
- Critical Care (1)
- Data (1)
- Decision Making (4)
- Dementia (2)
- Depression (1)
- Diabetes (3)
- (-) Diagnostic Safety and Quality (71)
- Disparities (1)
- Education: Continuing Medical Education (1)
- Education: Patient and Caregiver (1)
- Electronic Health Records (EHRs) (43)
- Emergency Department (3)
- Emergency Medical Services (EMS) (1)
- Eye Disease and Health (1)
- Healthcare-Associated Infections (HAIs) (2)
- Healthcare Delivery (2)
- (-) Health Information Technology (HIT) (71)
- Health Systems (1)
- Heart Disease and Health (5)
- Imaging (14)
- Injuries and Wounds (1)
- Inpatient Care (1)
- Intensive Care Unit (ICU) (1)
- Kidney Disease and Health (1)
- Learning Health Systems (1)
- Medical Errors (12)
- Medication (2)
- Medication: Safety (2)
- Neurological Disorders (2)
- Newborns/Infants (1)
- Obesity (1)
- Obesity: Weight Management (1)
- Patient-Centered Outcomes Research (1)
- Patient and Family Engagement (1)
- Patient Experience (1)
- Patient Safety (23)
- Prevention (2)
- Primary Care (4)
- Primary Care: Models of Care (1)
- Quality Improvement (6)
- Quality Measures (1)
- Quality of Care (6)
- Racial and Ethnic Minorities (1)
- Risk (2)
- Screening (1)
- Sepsis (1)
- Stroke (1)
- Surgery (3)
- Surveys on Patient Safety Culture (1)
- Telehealth (4)
- Web-Based (1)
- Women (1)
AHRQ Research Studies
Sign up: AHRQ Research Studies Email updates
Research Studies is a compilation of published research articles funded by AHRQ or authored by AHRQ researchers.
Results
1 to 25 of 71 Research Studies DisplayedLiberman AL, Wang Z, Zhu Y
Optimizing measurement of misdiagnosis-related harms using Symptom-Disease Pair Analysis of Diagnostic Error (SPADE): comparison groups to maximize SPADE validity.
The purpose of this paper was to clarify features of the Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) approach to accurately measure diagnostic errors to assure that researchers utilize this method to yield valid results, as well as improve the validity of SPADE and related approaches to quantify diagnostic error in medicine. The researchers describe four types of comparators (intra-group and inter-group), detailing the reason for selecting one over the other and conclusions that can be drawn from these comparative analyses.
AHRQ-funded; HS027614.
Citation: Liberman AL, Wang Z, Zhu Y .
Optimizing measurement of misdiagnosis-related harms using Symptom-Disease Pair Analysis of Diagnostic Error (SPADE): comparison groups to maximize SPADE validity.
Diagnosis 2023 Aug 1; 10(3):225-34. doi: 10.1515/dx-2022-0130..
Keywords: Diagnostic Safety and Quality, Medical Errors, Adverse Events, Electronic Health Records (EHRs), Health Information Technology (HIT), Patient Safety
Garber A, Garabedian P, Wu L
Developing, pilot testing, and refining requirements for 3 EHR-integrated interventions to improve diagnostic safety in acute care: a user-centered approach.
This study’s objective was to describe a user-centered approach to develop, pilot test, and refine requirements for 3 electronic health record (EHR)-integrated interventions that target key diagnostic process failures in hospitalized patients. The interventions to be developed were a Diagnostic Safety Column (DSC) within an EHR-integrated dashboard to identify at-risk patients; a Diagnostic Time-Out (DTO) for clinicians to reassess the working diagnosis; and a Patient Diagnosis Questionnaire (PDQ) to gather patient concerns about the diagnostic process. After initial refinement from an analysis, final requirements were created for 10 test cases predicted by the DSC, 18 clinician DTO participants, and 39 PDQ responses including the following: DSC configurable parameters (variables, weights) to adjust baseline risk estimates in real-time based on new clinical data collected during hospitalization; more concise DTO wording and flexibility for clinicians to conduct the DTO with or without the patient present; and integration of PDQ responses into the DSC to ensure closed-looped communication with clinicians. An analysis of focus groups confirmed that tight integration of the interventions with the EHR would be necessary to prompt clinicians to reconsider the working diagnosis in cases with elevated diagnostic error (DE) risk or uncertainty. Potential implementation barriers identified included alert fatigue and distrust of the risk algorithm (DSC); time constraints, redundancies, and concerns about disclosing uncertainty to patients (DTO); and patient disagreement with the care team's diagnosis (PDQ).
AHRQ-funded; HS026613.
Citation: Garber A, Garabedian P, Wu L .
Developing, pilot testing, and refining requirements for 3 EHR-integrated interventions to improve diagnostic safety in acute care: a user-centered approach.
JAMIA Open 2023 Jul; 6(2):ooad031. doi: 10.1093/jamiaopen/ooad031..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality, Patient Safety
Krevat SA, Samuel S, Boxley C
Identifying electronic health record contributions to diagnostic error in ambulatory settings through legal claims analysis.
The purpose of this study was to evaluate legal claims data to assess whether there is a relationship between problems with electronic health records and diagnostic errors. The researchers also explored specific types of errors that took place and at which point in the diagnostic process the errors occurred.
AHRQ-funded; HS027119.
Citation: Krevat SA, Samuel S, Boxley C .
Identifying electronic health record contributions to diagnostic error in ambulatory settings through legal claims analysis.
JAMA Netw Open 2023 Apr 3; 6(4):e238399. doi: 10.1001/jamanetworkopen.2023.8399..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality
Bell SK, Dong ZJ, Desroches CM
Partnering with patients and families living with chronic conditions to coproduce diagnostic safety through OurDX: a previsit online engagement tool.
Involving patients and their families in the diagnostic process is crucial, but there is a lack of methods for consistent engagement. The implementation of policies providing patients with access to electronic health records offers new possibilities. The researchers evaluated a novel online tool ("OurDX"), co-created with patients and families, to examine the nature and frequency of potential safety issues identified by patients and their families with chronic health conditions and whether these insights were incorporated into visit notes. At two US healthcare facilities, patients and their families were encouraged to participate via an online pre-visit questionnaire, which covered: (1) visit priorities, (2) recent medical history and symptoms, and (3) potential diagnostic concerns. Two physicians assessed patient-reported diagnostic issues to validate and classify diagnostic safety opportunities (DSOs). The researchers performed a chart review to determine if patient inputs were integrated into the visit note. Descriptive statistics were employed to report implementation outcomes, DSO verification, and chart review findings. The study found that OurDX reports were completed in 7075 of 18,129 (39%) eligible pediatric subspecialty visits (site 1) and 460 of 706 (65%) eligible adult primary care visits (site 2). Of the patients expressing diagnostic concerns, 63% were confirmed as probable DSOs. Overall, 7.5% of pediatric and adult patients and their families with chronic health conditions identified probable DSOs. The most frequent DSO types included patients and families feeling unheard; issues or delays in tests or referrals; and complications or delays in clarification or subsequent steps. The chart review revealed that most clinician notes incorporated all or some of the patient or family priorities and patient-reported histories.
AHRQ-funded; HS027367
Citation: Bell SK, Dong ZJ, Desroches CM .
Partnering with patients and families living with chronic conditions to coproduce diagnostic safety through OurDX: a previsit online engagement tool.
J Am Med Inform Assoc 2023 Mar 16;30(4):692-702. doi: 10.1093/jamia/ocad003.
Keywords: Chronic Conditions, Diagnostic Safety and Quality, Health Information Technology (HIT), Patient and Family Engagement, Healthcare Delivery
Coley RY, Smith JJ, Karliner L RY, Smith JJ, Karliner L
External validation of the eRADAR risk score for detecting undiagnosed dementia in two real-world healthcare systems.
Drupal date: Feb, 2023
It is estimated that half of the individuals with dementia remain undiagnosed. The electronic health record (EHR) Risk of Alzheimer's and Dementia Assessment Rule (eRADAR) was designed to detect older adults at risk of undiagnosed dementia using routinely gathered clinical information. The purpose of this retrospective cohort study was to externally validate eRADAR in two real-world healthcare systems, examining its performance over time and across race/ethnicity. The study found a total of 7631 dementia diagnoses were observed at KPWA and 216 at UCSF. The area under the curve was 0.84 (95% confidence interval: 0.84-0.85) at KPWA and 0.79 (0.76-0.82) at UCSF. Using the 90th percentile as the cut point for identifying high-risk patients, sensitivity was 54% (53-56%) at KPWA and 44% (38-51%) at UCSF. Performance was consistent over time, including across the transition from International Classification of Diseases, version 9 (ICD-9) to ICD-10 codes, and across racial/ethnic groups (although small samples limited precision in some groups). The study concluded that eRADAR demonstrated strong external validity for identifying undiagnosed dementia in two healthcare systems with diverse patient populations and varying availability of external healthcare data for risk calculations. This study showed that eRADAR is generalizable from a research sample to real-world clinical populations, transportable across health systems, resilient to temporal changes in healthcare, and exhibits similar performance across major racial/ethnic groups.
It is estimated that half of the individuals with dementia remain undiagnosed. The electronic health record (EHR) Risk of Alzheimer's and Dementia Assessment Rule (eRADAR) was designed to detect older adults at risk of undiagnosed dementia using routinely gathered clinical information. The purpose of this retrospective cohort study was to externally validate eRADAR in two real-world healthcare systems, examining its performance over time and across race/ethnicity. The study found a total of 7631 dementia diagnoses were observed at KPWA and 216 at UCSF. The area under the curve was 0.84 (95% confidence interval: 0.84-0.85) at KPWA and 0.79 (0.76-0.82) at UCSF. Using the 90th percentile as the cut point for identifying high-risk patients, sensitivity was 54% (53-56%) at KPWA and 44% (38-51%) at UCSF. Performance was consistent over time, including across the transition from International Classification of Diseases, version 9 (ICD-9) to ICD-10 codes, and across racial/ethnic groups (although small samples limited precision in some groups). The study concluded that eRADAR demonstrated strong external validity for identifying undiagnosed dementia in two healthcare systems with diverse patient populations and varying availability of external healthcare data for risk calculations. This study showed that eRADAR is generalizable from a research sample to real-world clinical populations, transportable across health systems, resilient to temporal changes in healthcare, and exhibits similar performance across major racial/ethnic groups.
AHRQ-funded; HS026369.
Citation: Coley RY, Smith JJ, Karliner L RY, Smith JJ, Karliner L .
External validation of the eRADAR risk score for detecting undiagnosed dementia in two real-world healthcare systems.
J Gen Intern Med 2023 Feb; 38(2):351-60. doi: 10.1007/s11606-022-07736-6..
Keywords: Dementia, Neurological Disorders, Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT)
Bell SK, Bourgeois F, Dong J
Patient identification of diagnostic safety blindspots and participation in "good catches" through shared visit notes.
The goal of this study was to investigate whether sharing clinical notes with patients supported identification of potential breakdowns in the diagnostic process that might be difficult for clinical staff to observe -- "diagnostic safety blindspots." Researchers analyzed patient-reported ambulatory documentation errors among patients at 3 U.S. healthcare centers. Older, female, unemployed, disabled, or sicker patients, or patients who worked in healthcare, were more likely to identify blindspots; patients who self-identified as Black, Asian, multiple races and those with less formal education as well as those who deferred decision-making to their providers were less likely to report blindspots. The researchers concluded that patients who read notes have unique insight about potential errors in their medical records and that organizations should encourage patient review of notes and create systems to track patient-reported blindspots.
AHRQ-funded; HS027367.
Citation: Bell SK, Bourgeois F, Dong J .
Patient identification of diagnostic safety blindspots and participation in "good catches" through shared visit notes.
Milbank Q 2022 Dec; 100(4):1121-65. doi: 10.1111/1468-0009.12593..
Keywords: Diagnostic Safety and Quality, Patient Safety, Electronic Health Records (EHRs), Health Information Technology (HIT)
Ganeshan S, Pierce L, Mourad M
Impact of patient portal-based self-scheduling of diagnostic imaging studies on health disparities.
The purpose of this study was to explore the impact of self-scheduling on equitable access to care. The researchers utilized an electronic health record patient portal at the University of California San Francisco which deployed a self-scheduling tool allowing patients to self-schedule diagnostic imaging studies. The study found that among all patient portal users, Latinx, Black/African American, and non-English speaking patients, as well as patients with Medi-Cal, California's Medicaid program, and Medicare insurance were less likely to self-schedule studies. were all less likely to self-schedule when compared with commercially insured patients.
AHRQ-funded; HS026383.
Citation: Ganeshan S, Pierce L, Mourad M .
Impact of patient portal-based self-scheduling of diagnostic imaging studies on health disparities.
J Am Med Inform Assoc 2022 Nov 14;29(12):2096-100. doi: 10.1093/jamia/ocac152..
Keywords: Disparities, Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT)
Malik MA, Motta-Calderon D, Piniella N
A structured approach to EHR surveillance of diagnostic error in acute care: an exploratory analysis of two institutionally-defined case cohorts.
The purpose of this study was to examine a structured electronic health record (EHR) case review process to identify diagnostic errors (DE) and diagnostic process failures (DPFs) in acute care. The researchers created two test cohorts of all preventable cases (n=28) and an equal number of randomly sampled non-preventable cases (n=28) from 365 adult general medicine patients who expired and were part of the mortality case review process at the research institution. Twenty-seven preventable and 24 non-preventable cases were included in the review process. The study found that the frequency of DE contributing to death was significantly higher for the preventable cohort compared to the non-preventable cohort. The researchers concluded that substantial agreement was observed among final consensus and expert panel reviews using their structured EHR case review process, and DEs contributing to death associated with DPFs were identified in institutionally designated preventable and non-preventable cases.
AHRQ-funded; HS026613.
Citation: Malik MA, Motta-Calderon D, Piniella N .
A structured approach to EHR surveillance of diagnostic error in acute care: an exploratory analysis of two institutionally-defined case cohorts.
Diagnosis 2022 Nov;9(4):446-57. doi: 10.1515/dx-2022-0032..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality, Medical Errors
Shafer GJ, Singh H, Thomas EJ
Frequency of diagnostic errors in the neonatal intensive care unit: a retrospective cohort study.
The objective of this study was to determine the frequency and etiology of diagnostic errors during the first 7 days of admission for inborn neonatal intensive care unit (NICU) patients. The "Safer Dx NICU Instrument" was used to review electronic health records. The reviewers discovered that the frequency of diagnostic error in inborn NICU patients during the first 7 days of admission was 6.2%.
AHRQ-funded; HS027363.
Citation: Shafer GJ, Singh H, Thomas EJ .
Frequency of diagnostic errors in the neonatal intensive care unit: a retrospective cohort study.
J Perinatol 2022 Oct;42(10):1312-18. doi: 10.1038/s41372-022-01359-9..
Keywords: Newborns/Infants, Intensive Care Unit (ICU), Critical Care, Diagnostic Safety and Quality, Medical Errors, Adverse Events, Patient Safety, Electronic Health Records (EHRs), Health Information Technology (HIT)
Bradford A, Shofer M, Singh H
AHRQ Author: Shofer M, Singh H
Measure Dx: implementing pathways to discover and learn from diagnostic errors.
This paper discusses Measure Dx, a new AHRQ resource that translates knowledge from diagnostic measurement research into actionable recommendations. This resource guides healthcare organizations to detect, analyze, and learn from diagnostic safety events as part of a continuous learning and feedback cycle. The goal of Measure Dx is to advance new frontiers in reducing preventable diagnostic harm to patients.
AHRQ-authored; AHRQ-funded; 233201500022I; HS027363.
Citation: Bradford A, Shofer M, Singh H .
Measure Dx: implementing pathways to discover and learn from diagnostic errors.
Int J Qual Health Care 2022 Sep 10;34(3). doi: 10.1093/intqhc/mzac068..
Keywords: Diagnostic Safety and Quality, Patient Safety, Quality Improvement, Quality of Care, Electronic Health Records (EHRs), Health Information Technology (HIT), Health Systems, Learning Health Systems
Bradford A, Shahid U, Schiff GD
AHRQ Author: DiStabile P, Timashenka A, Jalal H, and Brady PJ
Development and usability testing of the Agency for Healthcare Research and Quality common formats to capture diagnostic safety events.
The purpose of this study was to conduct a usability assessment of the Agency for Healthcare Research and Quality (AHRQ) Common Formats for Event Reporting for Diagnostic Safety Events (CFER-DS) to assist in informing future revisions and implementation. The researchers recruited quality and safety personnel from 8 U.S. healthcare organizations and invited them to use the CFER-DS to simulate reporting and then provide written and verbal qualitative feedback. The study found that feedback about item clarity and content coverage was generally positive, but that reporter burden was a potential concern. Participants also identified opportunities to improve the CFER-DS, including clarifying several conceptual definitions, improving applicability across different care settings, and creating guidance to operationalize use of the tool.
AHRQ-authored; AHRQ-funded; HS027363, 233201500022I.
Citation: Bradford A, Shahid U, Schiff GD .
Development and usability testing of the Agency for Healthcare Research and Quality common formats to capture diagnostic safety events.
J Patient Saf 2022 Sep 1;18(6):521-25. doi: 10.1097/pts.0000000000001006..
Keywords: Diagnostic Safety and Quality, Patient Safety, Health Information Technology (HIT), Adverse Events
Chang T, Sjoding MW, Wiens J
Disparate censorship & undertesting: a source of label bias in clinical machine learning.
This article examined the role of clinician and societal biases in machine learning (ML) models. This paper highlights disparate censorship (i.e., differences in testing rates across patient groups) as a source of label bias that clinical ML models may amplify, potentially causing harm. If a patient does not have test results, they are often assigned a negative label, which assumes that untested patients do not experience the outcome. Since testing may not be uniform in patient populations, this can give rise to disparate censorship. Using biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups.
AHRQ-funded; HS027431.
Citation: Chang T, Sjoding MW, Wiens J .
Disparate censorship & undertesting: a source of label bias in clinical machine learning.
Proc Mach Learn Res 2022 Aug; 182:343-90..
Keywords: Health Information Technology (HIT), Diagnostic Safety and Quality
Sun J, Peng L, Li T
Performance of a chest radiograph AI diagnostic tool for COVID-19: a prospective observational study.
The purpose of this observational study was to evaluate the real-time performance of an interpretable artificial intelligence (AI) model to detect COVID-19 on chest radiographs. The researchers utilized 95,363 chest radiographs for model training, external validation, and real-time validation. There were 5,335 real-time predictions and a COVID-19 prevalence of 4.8%. The study found that participants positive for COVID-19 had higher COVID-19 diagnostic scores than participants negative for COVID-19. Real-time model performance remained the same during the 19 weeks of implementation. Model sensitivity was higher in men than in women, but model specificity was higher in women. Sensitivity was higher for Asian and Black participants compared with White participants. The COVID-19 AI diagnostic system had worse accuracy compared with radiologist predictions. The researchers concluded that AI tools underperform when compared with radiologist results.
AHRQ-funded; HS026379.
Citation: Sun J, Peng L, Li T .
Performance of a chest radiograph AI diagnostic tool for COVID-19: a prospective observational study.
Radiol Artif Intell 2022 Jul;4(4):e210217. doi: 10.1148/ryai.210217..
Keywords: COVID-19, Imaging, Diagnostic Safety and Quality, Health Information Technology (HIT)
McCarthy DM, Formella KT, Ou EZ
There's an app for that: teaching residents to communicate diagnostic uncertainty through a mobile gaming application.
The purpose of this study was to improve doctor-patient communication by assessing the utilization of a mobile application (app) for teaching physician communication skills about diagnostic uncertainty, obtaining feedback on app utilization, and evaluating the association between app use and mastery of skills. Emergency medicine resident physicians were randomized to receive immediate or delayed access to an educational curriculum focused on diagnostic uncertainty which included a web-based interactive model and an app. Only 31.2% of the 109 participants used the app, with senior residents more likely to use the app than junior residents. Researchers report that of those who used the app, reviews were positive, with 76% indicating the app facilitated their learning. The study found that in the trial there was no significant correlation between the utilization of the app and mastery of the communication skill. The researchers concluded that without mandated use and evidence of effectiveness, apps should not be offered to physicians as an educational option and training opportunity for improving communication skills.
AHRQ-funded; HS025651.
Citation: McCarthy DM, Formella KT, Ou EZ .
There's an app for that: teaching residents to communicate diagnostic uncertainty through a mobile gaming application.
Patient Educ Couns 2022 Jun;105(6):1463-69. doi: 10.1016/j.pec.2021.09.038..
Keywords: Diagnostic Safety and Quality, Clinician-Patient Communication, Communication, Education: Continuing Medical Education, Health Information Technology (HIT)
Giardina TD, Choi DT, Upadhyay DK
Inviting patients to identify diagnostic concerns through structured evaluation of their online visit notes.
This study’s objective was to test if patients can identify concerns about their diagnosis through structured evaluation of their online visit notes in an electronic health record (EHR) system. Patients aged 18-85 years in a large integrated health system who actively used the patient portal were invited to respond to an online questionnaire if an EHR algorithm detected any recent visit following an initial primary care consultation. The authors developed and tested an instrument (Safer Dx Patient Instrument) to help patients identify concerns related to the diagnostic process based on notes review and recall of recent “at-risk” visits. The algorithm identified 1282 eligible patients, of whom 486 responded. Of the 418 patients included in the analysis, 51 patients (12.2%) identified a diagnostic concern. Patients were more likely to report a concern if they disagreed with statements "The care plan the provider developed for me addressed all my medical concerns", "I trust the provider that I saw during my visit" and agreed with the statement "I did not have a good feeling about my visit".
AHRQ-funded; HS027363; HS025474.
Citation: Giardina TD, Choi DT, Upadhyay DK .
Inviting patients to identify diagnostic concerns through structured evaluation of their online visit notes.
J Am Med Inform Assoc 2022 May 11;29(6):1091-100. doi: 10.1093/jamia/ocac036..
Keywords: Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT), Patient Experience, Patient Safety
Salwei ME, Carayon P, Wiegmann D
Usability barriers and facilitators of a human factors engineering-based clinical decision support technology for diagnosing pulmonary embolism.
The authors sought to identify and describe the usability barriers and facilitators of a human factors engineering (HFE)-based clinical decision support (CDS) prior to implementation in the emergency department. Through debrief interviews, they identified 271 occurrences of usability barriers and facilitators of the HFE-based CDS. They concluded that the systematic use of HFE principles in the design of CDS improves the usability of these technologies and recommended workflow integration in order to reduce usability barriers.
AHRQ-funded; HS026395; HS024558; HS022086.
Citation: Salwei ME, Carayon P, Wiegmann D .
Usability barriers and facilitators of a human factors engineering-based clinical decision support technology for diagnosing pulmonary embolism.
Int J Med Inform 2022 Feb;158:104657. doi: 10.1016/j.ijmedinf.2021.104657..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Diagnostic Safety and Quality
Mayampurath A, Parnianpour Z, Richards CT
Improving prehospital stroke diagnosis using natural language processing of paramedic reports.
Accurate prehospital diagnosis of stroke by emergency medical services (EMS) can increase treatments rates, mitigate disability, and reduce stroke deaths. IN this study, the investigators aimed to develop a model that utilized natural language processing of EMS reports and machine learning to improve prehospital stroke identification. The investigators conducted a retrospective study of patients transported by the Chicago EMS to 17 regional primary and comprehensive stroke centers.
AHRQ-funded; HS025359; HS027264.
Citation: Mayampurath A, Parnianpour Z, Richards CT .
Improving prehospital stroke diagnosis using natural language processing of paramedic reports.
Stroke 2021 Aug;52(8):2676-79. doi: 10.1161/strokeaha.120.033580..
Keywords: Stroke, Cardiovascular Conditions, Diagnostic Safety and Quality, Health Information Technology (HIT), Emergency Medical Services (EMS)
Soares WE, Knee A, Gemme SR
SC, et al. A prospective evaluation of Clinical HEART score agreement, accuracy, and adherence in emergency department chest pain patients.
The HEART score is a risk stratification aid that may safely reduce chest pain admissions for emergency department patients. However, differences in interpretation of subjective components potentially alters the performance of the score. In this study, the investigators compared agreement between HEART scores determined during clinical practice with research-generated scores and estimated their accuracy in predicting 30-day major adverse cardiac events.
AHRQ-funded; HS024815.
Citation: Soares WE, Knee A, Gemme SR .
SC, et al. A prospective evaluation of Clinical HEART score agreement, accuracy, and adherence in emergency department chest pain patients.
Ann Emerg Med 2021 Aug;78(2):231-41. doi: 10.1016/j.annemergmed.2021.03.024..
Keywords: Heart Disease and Health, Cardiovascular Conditions, Emergency Department, Diagnostic Safety and Quality, Clinical Decision Support (CDS), Health Information Technology (HIT)
Cifra CL, Sittig DF, Singh H
Bridging the feedback gap: a sociotechnical approach to informing clinicians of patients' subsequent clinical course and outcomes.
This paper discusses challenges to the development of systems for effective patient outcome feedback to improve diagnosis and proposes the application of a sociotechnical approach using health information technology (HIT) to support the implementation of such systems. It discusses current barriers to effective clinician feedback, reasons for them, and features of potential IT solutions. Evaluation and implementation of the feedback process within a sociotechnical health system are then discussed. The authors use an eight-dimension sociotechnical model for studying health IT by authors Sittig and Singh. The eight dimensions are hardware and software; clinical content; human–computer interface; people; workflow and communication; organisational policies and procedures; external rules, regulations and pressures; and system measurement and monitoring. A table is included that shows the potential considerations for each dimension.
AHRQ-funded; 33201500022I; HS027363.
Citation: Cifra CL, Sittig DF, Singh H .
Bridging the feedback gap: a sociotechnical approach to informing clinicians of patients' subsequent clinical course and outcomes.
BMJ Qual Saf 2021 Jul;30(7):591-97. doi: 10.1136/bmjqs-2020-012464..
Keywords: Health Information Technology (HIT), Diagnostic Safety and Quality, Patient Safety, Quality Improvement, Quality of Care
Zhu Y, Simon GJ, Wick EC
Applying machine learning across sites: external validation of a surgical site infection detection algorithm.
Surgical complications have tremendous consequences and costs. Complication detection is important for quality improvement, but traditional manual chart review is burdensome. Automated mechanisms are needed to make this more efficient. The purpose of the study was to understand the generalizability of a machine learning algorithm between sites; automated surgical site infection (SSI) detection algorithms developed at one center were tested at another distinct center.
AHRQ-funded; HS024532.
Citation: Zhu Y, Simon GJ, Wick EC .
Applying machine learning across sites: external validation of a surgical site infection detection algorithm.
J Am Coll Surg 2021 Jun;232(6):963-71.e1. doi: 10.1016/j.jamcollsurg.2021.03.026..
Keywords: Healthcare-Associated Infections (HAIs), Surgery, Adverse Events, Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT), Quality Improvement, Quality of Care
Enayati M, Sir M, Zhang X
Monitoring diagnostic safety risks in emergency departments: protocol for a machine learning study.
This study’s objective will be to identify variables associated with diagnostic errors in emergency departments using large-scale EHR data and machine learning techniques. It will use trigger algorithms with electronic health record (EHR) data repositories to generate a large data set of records that are labeled trigger-positive or trigger-negative, depending on if they meet certain criteria. This study will be conducted by 2 academic medical centers with affiliated community hospitals.
AHRQ-funded; HS027363; HS026622.
Citation: Enayati M, Sir M, Zhang X .
Monitoring diagnostic safety risks in emergency departments: protocol for a machine learning study.
JMIR Res Protoc 2021 Jun 14;10(6):e24642. doi: 10.2196/24642..
Keywords: Emergency Department, Diagnostic Safety and Quality, Patient Safety, Risk, Electronic Health Records (EHRs), Health Information Technology (HIT)
Davis K, Wilbur K, Metzger S
Symptom and needs assessment screening in oncology patients: alternate outreach methods during COVID-19.
This initiative’s goal was to develop alternate outreach methods to cancer patients without access to an electronic portal during COVID-19. The authors implemented a standardized telephone outreach process targeting patients without active electronic portal accounts to improve remote symptom monitoring. A total of 172 screens were completed, identifying 110 needs for 63 individuals. Twenty-eight patients completed patient enrollment, with outreach calls capturing a higher percentage of Black patients (34%) and older adults age 61-80 years old (69%) compared to portal users.
AHRQ-funded; HS026170.
Citation: Davis K, Wilbur K, Metzger S .
Symptom and needs assessment screening in oncology patients: alternate outreach methods during COVID-19.
J Psychosoc Oncol 2021;39(3):452-60. doi: 10.1080/07347332.2021.1890663..
Keywords: COVID-19, Cancer, Access to Care, Telehealth, Health Information Technology (HIT), Diagnostic Safety and Quality
Jones OT, Calanzani N, Saji S
Artificial intelligence techniques that may be applied to primary care data to facilitate earlier diagnosis of cancer: systematic review.
This study’s objective was a systematic review of artificial intelligence (AI) techniques that might facilitate earlier diagnosis of cancer and could be applied to primary care electronic health record (EHR) data. Findings showed that AI techniques have been applied to EHR-type data to facilitate early diagnosis of cancer, but their use in primary care settings is still at an early stage of maturity. Further evidence is needed on their performance using primary care data, implementation barriers, and cost-effectiveness before widespread adoption into routine primary care clinical practice can be recommended.
AHRQ-funded; HS027363.
Citation: Jones OT, Calanzani N, Saji S .
Artificial intelligence techniques that may be applied to primary care data to facilitate earlier diagnosis of cancer: systematic review.
J Med Internet Res 2021 Mar 3;23(3):e23483. doi: 10.2196/23483..
Keywords: Cancer, Diagnostic Safety and Quality, Primary Care, Electronic Health Records (EHRs), Health Information Technology (HIT)
Shah NR, Eisman AS, Winchester DE
E-consult protocoling to improve the quality of cardiac stress tests.
Rarely appropriate cardiac stress tests remain prevalent in the range of 10% to 20% and unnecessarily prolong wait times. To address this ongoing problem, the investigators designed the EPIQ-Stress workflow, which included a structured electronic consult (“econsult”) with all outpatient stress test orders. In this study, the investigators assessed whether EPIQ-Stress implementation was associated with a reduction in rarely appropriate testing and in order-to-report wait times.
AHRQ-funded; HS022998.
Citation: Shah NR, Eisman AS, Winchester DE .
E-consult protocoling to improve the quality of cardiac stress tests.
JACC Cardiovasc Imaging 2021 Feb;14(2):512-14. doi: 10.1016/j.jcmg.2020.08.009..
Keywords: Telehealth, Health Information Technology (HIT), Heart Disease and Health, Cardiovascular Conditions, Diagnostic Safety and Quality
Lacson R, Cochon L, Ching PR
Integrity of clinical information in radiology reports documenting pulmonary nodules.
Researchers sought to quantify the integrity, measured as completeness and concordance with a thoracic radiologist, of documenting pulmonary nodule characteristics in CT reports, and to assess impact on making follow-up recommendations. Their retrospective cohort study was performed at an academic medical center and natural language processing was used on radiology reports of CT scans of chest, abdomen, or spine to assess presence of pulmonary nodules. They found that essential pulmonary nodule characteristics were under-reported, potentially impacting recommendations for pulmonary nodule follow-up. They concluded that the lack of documentation of pulmonary nodule characteristics in radiology reports was common, with the potential for compromising patient care and clinical decision support tools.
AHRQ-funded; HS024722.
Citation: Lacson R, Cochon L, Ching PR .
Integrity of clinical information in radiology reports documenting pulmonary nodules.
J Am Med Inform Assoc 2021 Jan 15;28(1):80-85. doi: 10.1093/jamia/ocaa209..
Keywords: Imaging, Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT), Patient Safety