Search All Research Studies
AHRQ Research Studies Date
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.
Results1 to 25 of 1349 Research Studies Displayed
Jones EK, Ninkovic I, Bahr M
A novel, evidence-based, comprehensive clinical decision support system improves outcomes for patients with traumatic rib fractures.
This study’s objective to investigate if a traumatic rib fracture clinical decision support system (CDSS) reduced hospital length of stay (LOS), 90-day and 1-year mortality, unplanned ICU transfer, and the need for mechanical ventilation. The CDSS included an admission evidence-based (EB) order set and a pain-inspiratory-cough (PIC) score early warning system (EWS). The CDSS was implemented at 9 US trauma centers, with 3,279 patients meeting inclusion criteria. Hospital LOS pre vs post-intervention was unchanged but unplanned transfer to the ICU was reduced, as was 1-year mortality. Provider utilization was associated with significantly reduced LOS. The EWS triggered on 34.4% of patients; however, it was not associated with a significant reduction in hospital LOS.
Citation: Jones EK, Ninkovic I, Bahr M . A novel, evidence-based, comprehensive clinical decision support system improves outcomes for patients with traumatic rib fractures. J Trauma Acute Care Surg 2023 Aug 1; 95(2):161-71. doi: 10.1097/ta.0000000000003866..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Evidence-Based Practice, Injuries and Wounds, Trauma
Rolfzen ML, Wick A, Mascha EJ
Best Practice Alerts Informed by Inpatient Opioid Intake to Reduce Opioid Prescribing after Surgery (PRIOR): a cluster randomized multiple crossover trial.
This study tested the hypothesis that a decision-support tool embedded in electronic health records (EHRs) leads clinicians to prescribe fewer opioids at discharge after inpatient surgery. Over 21,000 surgical inpatient discharges in a cluster randomized multiple crossover trial in four Colorado hospitals were included. The results indicated that within the context of vigorous opioid education and awareness efforts a decision-support tool incorporated into EHRs did not reduce discharge opioid prescribing for postoperative patients. The authors concluded that opioid prescribing alerts might be valuable in other contexts.
Citation: Rolfzen ML, Wick A, Mascha EJ . Best Practice Alerts Informed by Inpatient Opioid Intake to Reduce Opioid Prescribing after Surgery (PRIOR): a cluster randomized multiple crossover trial. Anesthesiology 2023 Aug 1; 139(2):186-96. doi: 10.1097/aln.0000000000004607..
Keywords: Opioids, Medication, Surgery, Inpatient Care, Clinical Decision Support (CDS), Health Information Technology (HIT)
Roberts MM, Marino M, Wells R
Differences in use of clinical decision support tools and implementation of aspirin, blood pressure control, cholesterol management, and smoking cessation quality metrics in small practices by race and sex.
The objective of this cross-sectional study was to evaluate the association between population-based clinical decision support (CDS) tools and racial and sex disparities in the aspirin use, blood pressure control, cholesterol management, and smoking cessation (ABCS) care quality metrics among smaller primary care practices. Researchers used practice-level data from the EvidenceNOW initiative, from practices that submitted both survey data and electronic health record (EHR)-derived ABCS data stratified by race and sex. Their findings suggested that practices using CDS tools had small disparities but were not statistically significant; however, CDS tools were not associated with reductions in disparities. They concluded that more research was needed on effective practice-level interventions to mitigate disparities.
Citation: Roberts MM, Marino M, Wells R . Differences in use of clinical decision support tools and implementation of aspirin, blood pressure control, cholesterol management, and smoking cessation quality metrics in small practices by race and sex. JAMA Netw Open 2023 Aug; 6(8):e2326905. doi: 10.1001/jamanetworkopen.2023.26905..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Cardiovascular Conditions, Tobacco Use, Tobacco Use: Smoking Cessation, Primary Care, Evidence-Based Practice, Prevention
Sparling JL, France D, Abraham J
Handoff Effectiveness Research in periOperative environments (HERO) Design Studio: a conference report.
This conference report reviewed the historical background which led to the Handoff Effectiveness Research in periOperative environments (HERO) Design Studio. The objectives of the HERO Design Studio were to examine the existing literature base, create a national research agenda, and build the research infrastructure necessary to address critical evidence gaps in perioperative handoff quality and safety. The authors described how they prepared for the research conference and synthesized the conference’s results. They also recommended future directions regarding perioperative handoff improvement.
Citation: Sparling JL, France D, Abraham J . Handoff Effectiveness Research in periOperative environments (HERO) Design Studio: a conference report. Jt Comm J Qual Patient Saf 2023 Aug; 49(8):422-30. doi: 10.1016/j.jcjq.2023.02.004..
Keywords: Health Information Technology (HIT), Workflow, Transitions of Care, Electronic Health Records (EHRs), Evidence-Based Practice
Kalenderian E, Bangar S, Yansane A
Identifying contributing factors associated with dental adverse events through a pragmatic electronic health record-based root cause analysis.
This study’s objective was to analyze harmful dental adverse events (AEs) to assess potential contributing factors. Harmful AEs were defined as those that resulted in temporary moderate to severe harm, required hospitalization, or resulted in permanent moderate to severe harm. The authors classified potential contributing factors according to (1) who was involved (person), (2) what were they doing (tasks), (3) what tools/technologies were they using (tools/technologies), (4) where did the event take place (environment), (5) what organizational conditions contributed to the event? (organization), (6) patient (including parents), and (7) professional-professional collaboration. A second review was conducted by a blinded panel of dental experts to confirm the presence of an AE. A total of 59 cases at 2 dental institutions had 1 or more harmful AEs. The most common harmful AE was pain (27.1%) followed by nerve injury (16.9%), hard tissue injury (15.2%), and soft tissue injury (15.2%). The most common contribution factor was the care provider (training, supervision, and fatigue at 31.5%) followed by patient ((noncompliance, unsafe practices at home, low health literacy, 17.1%), and professional-professional collaboration (15.3%).
Citation: Kalenderian E, Bangar S, Yansane A . Identifying contributing factors associated with dental adverse events through a pragmatic electronic health record-based root cause analysis. J Patient Saf 2023 Aug 1; 19(5):305-12. doi: 10.1097/pts.0000000000001122..
Keywords: Dental and Oral Health, Adverse Events, Electronic Health Records (EHRs), Health Information Technology (HIT), Medical Errors, Patient Safety
Sparling JL, Hong Mershon B, Abraham J
Perioperative handoff enhancement opportunities through technology and artificial intelligence: a narrative review.
This narrative review synthesized prior research on electronic tools for perioperative handoffs, limitations of current tools and barriers to their implementation, and use of AI and machine learning in perioperative care. Results showed that several efforts have incorporated electronic tools to improve perioperative handoffs, but were limited by imprecision in selecting handoff elements. AI and machine learning use and integration into handoff workflows were not yet being studied. Existing technology such as mobile applications, barcode scanners, and radio-frequency identification tags to advance perioperative safety were similarly not applied to handoffs.
Citation: Sparling JL, Hong Mershon B, Abraham J . Perioperative handoff enhancement opportunities through technology and artificial intelligence: a narrative review. Jt Comm J Qual Patient Saf 2023 Aug; 49(8):410-21. doi: 10.1016/j.jcjq.2023.03.009..
Keywords: Health Information Technology (HIT), Workflow, Transitions of Care, Electronic Health Records (EHRs), Evidence-Based Practice
Rome D, Sales A, Cornelius T
Impact of telemedicine modality on quality metrics in diverse settings: implementation science-informed retrospective cohort study.
The objective of this study was to assess telemedicine uptake during the COVID-19 pandemic and impact of visit modality on primary care quality metrics in diverse, low socioeconomic status settings. Research was informed by the RE-AIM (Reach, Effectiveness, Adoption, Implementation, and Maintenance) framework. Researchers found that there were marginally better quality metrics for in-person care versus video and phone visits, and that de-adoption of telemedicine was marked within 2 years in the study population. They concluded that the impact of visit modality on quality outcomes, provider and patient preferences, and technological barriers in historically marginalized settings should be considered.
Citation: Rome D, Sales A, Cornelius T . Impact of telemedicine modality on quality metrics in diverse settings: implementation science-informed retrospective cohort study. J Med Internet Res 2023 Jul 26; 25:e47670. doi: 10.2196/47670..
Keywords: Telehealth, Health Information Technology (HIT), Implementation, Quality Measures, Quality of Care
Wissel BD, Greiner HM, Glauser TA
Automated, machine learning-based alerts increase epilepsy surgery referrals: a randomized controlled trial.
Researchers conducted a prospective, randomized controlled trial of a natural language processing-based clinical decision support system in the electronic health record at 14 pediatric neurology outpatient clinics to determine whether automated, electronic alerts increased referrals for epilepsy surgery. Children with epilepsy and at least two prior neurology visits were screened by the system prior to their scheduled visit to identify potential surgical candidates, and the potential candidates randomized 2:1 for their providers to receive an alert or standard of care (no alert). The results showed that patients whose providers received an alert were more likely to be referred for a presurgical evaluation. The researchers concluded that machine learning-based automated alerts may improve the utilization of referrals for epilepsy surgery evaluations.
Citation: Wissel BD, Greiner HM, Glauser TA . Automated, machine learning-based alerts increase epilepsy surgery referrals: a randomized controlled trial. Epilepsia 2023 Jul; 64(7):1791-99. doi: 10.1111/epi.17629..
Keywords: Neurological Disorders, Surgery, Health Information Technology (HIT)
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).
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
Narindrarangkura P, Alafaireet PE, Khan U
Predicting suicide attempts among people with diabetes using a large multicenter electronic health records dataset.
This study’s goal was to determine the risk factors for suicidal behaviors of people with diabetes as they have a higher risk than the general population. The authors investigated risk factors and predicted suicide attempts in people with diabetes using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. They used data from Cerner Real-World Data™ and included over 3 million diabetes patients in the study. They analyzed gender-, diabetes-type, and depression-specific LASSO regression models. The study included 7764 subjects diagnosed with suicide attempts with an average age of 45. They found risk factors for suicide attempts in diabetes patients, such as being an American Indian or Alaska Native, atypical agents, benzodiazepines, and antihistamines. Amyotrophy had a negative coefficient for suicide attempts with males with diabetes but had a positive coefficient for females. Using MAOI had a negative coefficient for suicide attempts in T1DM patients. Patients less than 20 years of age had a positive coefficient for suicide in depressed and non-depressed patients with diabetes.
Citation: Narindrarangkura P, Alafaireet PE, Khan U . Predicting suicide attempts among people with diabetes using a large multicenter electronic health records dataset. Int J Psychiatry Med 2023 Jul; 58(4):302-24. doi: 10.1177/00912174231162477..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Behavioral Health, Diabetes, Chronic Conditions
Lin YJ, Ranusch A, Seagull FJ
Dynamic interplay between available resources and implementation climate across phases of implementation: a qualitative study of a VA national population health tool.
This study analyzed the factors that may determine successful implementation of an intervention by examining the co-occurrence patterns between available resources and implementation climate across different implementation phases. There have been very few studies that have investigated how the required resources change over the phases of implementation. The authors conducted a secondary analysis of interviews that were conducted with 20 anticoagulation professionals at 17 clinical sites in the Veterans Health Administration health system about their experiences with a population health dashboard for anticoagulant management. Key relationships between available resources and implementation climate were identified and summarized. Resources necessary to support the successful implementation of an intervention were found to not be static, Both quantity and types of resources shift based on the phases of the intervention. Increased resource availability does not guarantee the sustainment of intervention success. New technological interventions require resources in the form of technological support and social/emotional support to help users establish trust. Resources that foster and maintain collaboration between users and other stakeholders can help them stay motivated during sustainment.
Citation: Lin YJ, Ranusch A, Seagull FJ . Dynamic interplay between available resources and implementation climate across phases of implementation: a qualitative study of a VA national population health tool. Implement Sci Commun 2023 Jun 29; 4(1):74. doi: 10.1186/s43058-023-00460-0..
Keywords: Implementation, Health Information Technology (HIT)
Stonko DP, Weller JH, Gonzalez Salazar AJ
A pilot machine learning study using trauma admission data to identify risk for high length of stay.
The purpose of this study was to design a tool that used only data available at time of admission for trauma to predict prolonged hospital length of stay (LOS). Data was collected from the trauma registry at an urban level-one adult trauma center. Single layer and deep artificial neural networks were trained to identify patients in the top quartile of LOS and optimized under the receiver operator characteristic curve. The results indicated that machine learning can predict which trauma patients will have prolonged LOS with physiologic and demographic data available at the time of admission. The authors concluded these patients may benefit from additional disposition planning resources at the time of admission.
AHRQ-funded; HS026640; HS024547; HS027793.
Citation: Stonko DP, Weller JH, Gonzalez Salazar AJ . A pilot machine learning study using trauma admission data to identify risk for high length of stay. Surg Innov 2023 Jun; 30(3):356-65. doi: 10.1177/15533506221139965..
Keywords: Trauma, Hospitalization, Health Information Technology (HIT)
Apathy NC, Rotenstein L, Bates DW NC, Rotenstein L, Bates DW
Documentation dynamics: note composition, burden, and physician efficiency.
This study’s objective was to analyze how physician clinical note length and composition relate to electronic health record (EHR)-based measures of burden and efficiency that have been tied to burnout. This cross-sectional study examined EHR metadata capturing physician-level measures from 203,728 US-based ambulatory physicians using the Epic Systems EHR between September 2020 and May 2021. The authors calculated physician-level averages for four measures of interest and assigned physicians to overall note length deciles and note composition deciles from six sources, including templated text, manual text, and copy/paste text. They found that physicians in the top decile of note length demonstrated greater burden and lower efficiency than physicians in the median decile level, spending 39% more time in the EHR after hours and closing 5.6 percentage points fewer visits on the same day. Copy/paste use demonstrated a similar dose/response relationship, with top-decile copy/paste users closing 6.8 percentage points fewer visits on the same day and spending more time in the EHR after hours and on days off. Templated text such as Epic’s SmartTools demonstrated a non-linear relationship with burden and efficiency, with very low and very high levels of use associated with increased EHR burden and decreased efficiency.
Citation: Apathy NC, Rotenstein L, Bates DW NC, Rotenstein L, Bates DW . Documentation dynamics: note composition, burden, and physician efficiency. Health Serv Res 2023 Jun; 58(3):674-85. doi: 10.1111/1475-6773.14097..
Keywords: Provider: Physician, Burnout, Electronic Health Records (EHRs), Health Information Technology (HIT)
Anderson NW, Halfon N, Eisenberg D
Mixed signals in child and adolescent mental health and well-being indicators in the United States: a call for improvements to population health monitoring.
The authors of this paper suggest that policies targeting social indicators of youth status may not have improved overall mental health and well-being. They contend this absence of impact is evidenced by the divergence between social indicators which are improving, such as high school graduation, food insecurity, and smoking, and those which are worsening, such as mental health and well-being. The researchers report that available data indicates that one or more common exposures may be to blame, including those inadequately captured by existing social indicators.
Citation: Anderson NW, Halfon N, Eisenberg D . Mixed signals in child and adolescent mental health and well-being indicators in the United States: a call for improvements to population health monitoring. Milbank Q 2023 Jun; 101(2):259-86. doi: 10.1111/1468-0009.12634..
Keywords: COVID-19, Telehealth, Health Information Technology (HIT), Ambulatory Care and Surgery, Cardiovascular Conditions
Blecker S, Gannon M, De Leon S
Practice facilitation for scale up of clinical decision support for hypertension management: study protocol for a cluster randomized control trial.
This paper describes a protocol for a study that will be conducted to compare the effect of hypertension-focused clinical decision support (CDS) plus practice facilitation on blood pressure (BP) control, as compared to CDS alone. The investigators will conduct a cluster randomized control trial that will include initial training on the CDS and a review of current guidelines along with follow-up for coaching and integration support. They will randomize 46 small primary care practices in New York City who use the same electronic health record vendor to intervention or control. They will also assess implementation of CDS in all practices and practice facilitation in the intervention group.
Citation: Blecker S, Gannon M, De Leon S . Practice facilitation for scale up of clinical decision support for hypertension management: study protocol for a cluster randomized control trial. Contemp Clin Trials 2023 Jun; 129:107177. doi: 10.1016/j.cct.2023.107177..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Blood Pressure, Cardiovascular Conditions
Khor S, Heagerty PJ, Basu A
Racial disparities in the ascertainment of cancer recurrence in electronic health records.
This study examined whether the accuracy of a proxy for colorectal cancer (CRC) recurrence differed by race/ethnicity and the possible mechanisms that drove the differences. Using data from a large integrated health care system, the authors identified a stratified random sample of 282 Black/African American (AA), Hispanic, and non-Hispanic White (NHW) patients with CRC who received primary treatment. The recurrence proxy was found to have excellent overall accuracy (positive predictive value [PPV] 89.4%; negative predictive value 96.5%; mean difference in timing 1.96 months); however, accuracy varied by race/ethnicity. Compared with NHW patients, PPV was 14.9% lower among Hispanic patients and 4.3% lower among Black/AA patients. The proxy disproportionately inflated the 5-year recurrence incidence for Hispanic patients by 10.6%. Compared with NHW patients, proxy recurrences for Hispanic patients were almost three times as likely to have been misclassified as positive (adjusted risk ratio 2.91). The authors theorize that higher false positives among racial/ethnic minorities may be related to higher prevalence of noncancerous lung-related problems and substantial delays in primary treatment because of insufficient patient-provider communication and abnormal treatment patterns.
Citation: Khor S, Heagerty PJ, Basu A . Racial disparities in the ascertainment of cancer recurrence in electronic health records. JCO Clin Cancer Inform 2023 Jun; 7:e2300004. doi: 10.1200/cci.23.00004..
Keywords: Cancer, Electronic Health Records (EHRs), Health Information Technology (HIT), Racial and Ethnic Minorities, Disparities
Huo T, Glueck DH, Shenkman EA
Stratified split sampling of electronic health records
Data extracted from electronic health records may require very different approaches for model building and analysis than data from clinical research. Because electronic health record data is designed for clinical use, researchers need to engage in the iterative process of defining and provide clear definitions of outcome and predictor variables and assessing associations. This process can increase Type I error rates and decrease the chance of replicability. Failure to consider subgroups may mask heterogeneous relationships between predictor and outcome by subgroups, thus decreasing the generalizability of the findings. To improve the likelihood of both replicability and generalizability, the researchers recommended utilizing a stratified split sample approach for studies using electronic health records. The researchers illustrate the approach through an electronic health record study of the relationships between socio-demographic factors and uptake of hepatic cancer screening, and potential heterogeneity of association in subgroups defined by gender, self-identified race and ethnicity, census-tract level poverty and insurance type.
Citation: Huo T, Glueck DH, Shenkman EA . Stratified split sampling of electronic health records BMC Med Res Methodol 2023 May 25; 23(1):128. doi: 10.1186/s12874-023-01938-0..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Research Methodologies, Health Services Research (HSR)
Ahmad FA, Chan P, McGovern C
Adapting an electronic STI risk assessment program for use in pediatric primary care.
This study’s goal was to evaluate the usability of an electronic risk assessment tool to support sexually transmitted disease (STI) testing in the authors’ pediatric emergency department that they had previously designed and implemented. They conducted qualitative interviews of pediatricians, clinic staff, and adolescents from 4 pediatric practices as part of a study whose goal is to ultimately implement STI screening in pediatric primary care. The goal of the interviews was (1) to understand contextual factors related to STI screening in primary care, which they reported previously, and (2) to obtain feedback on their electronic platform, the questionnaire content, and their perspective on implementing it in primary care settings. They received quantitative feedback using the System Usability Scale (SUS). The SUS is a validated, reliable tool to measure the usability of hardware, software, websites, and applications, with a score of 68 (range 0-100) being average usability. They recruited 14 physicians, 9 clinic staff, and 12 adolescents. Participants rated the tool with a median score of 92.5, which shows a high level of usability.
Citation: Ahmad FA, Chan P, McGovern C . Adapting an electronic STI risk assessment program for use in pediatric primary care. J Prim Care Community Health 2023 Jan-Dec; 14:21501319231172900. doi: 10.1177/21501319231172900..
Keywords: Children/Adolescents, Sexual Health, Infectious Diseases, Primary Care, Health Information Technology (HIT), Screening, Prevention
Chu CD, Lenoir KM, Rai NK
Concordance between clinical outcomes in the systolic blood pressure intervention trial and in the electronic health record.
This study examined the role that electronic health records (EHRs) can play in follow-up for concordance with trial-ascertained outcomes. The authors linked EHR and trial data for participants in the Systolic Blood Pressure Intervention Trial (SPRINT), a randomized trial comparing intensive and standard blood pressure targets. Among participants with available EHR data concurrent to trial-ascertained outcomes, they calculated sensitivity, specificity, positive predictive value, and negative predictive value for EHR-recorded cardiovascular disease (CVD) events, using the gold standard of SPRINT-adjudicated outcomes (myocardial infarction (MI)/acute coronary syndrome (ACS), heart failure, stroke, and composite CVD events). They additionally compared the incidence of non-CVD adverse events (hyponatremia, hypernatremia, hypokalemia, hyperkalemia, bradycardia, and hypotension) in trial versus EHR data. Of the 2468 SPRINT participants included, EHR data demonstrated ≥80% sensitivity and specificity, and ≥99% negative predictive value for MI/ACS, heart failure, stroke, and composite CVD events. Positive predictive value ranged from 26% for heart failure to 52% for MI/ACS. Conclusions were that EHR data uniformly identified more non-CVD adverse events and higher incidence rates compared with trial ascertainment.
Citation: Chu CD, Lenoir KM, Rai NK . Concordance between clinical outcomes in the systolic blood pressure intervention trial and in the electronic health record. Contemp Clin Trials 2023 May; 128:107172. doi: 10.1016/j.cct.2023.107172..
Keywords: Blood Pressure, Electronic Health Records (EHRs), Health Information Technology (HIT), Cardiovascular Conditions
Hewner S, Smith E, Sullivan SS
Identifying high-need primary care patients using nursing knowledge and machine learning methods.
This study examined how patient cohorts generated by machine learning can be enhanced with clinical knowledge to increase translational value and provide a practical approach to patient segmentation based on a mix of medical, behavioral, and social factors. The authors used a primary care practice dataset (N=3438) of high need patients defined by practice criteria and parsed it to a subset population of patients with diabetes (n=1233). Three expert nurses selected variables for k-means cluster analysis using knowledge of critical factors for care coordination, and their knowledge was again applied to describe the psychosocial phenotypes in four prominent clusters, aligned with social and medical care plans. Four distinct clusters were used to create four cohorts including: (1) A large cluster of racially diverse female, non-English speakers with low medical complexity, and history of childhood illness; (2) A large cluster of English speakers with significant comorbidities (obesity and respiratory disease); (3) A small cluster of males with substance use disorder and significant comorbidities (mental health, liver and cardiovascular disease) who frequently visit the hospital; and (4) A moderate cluster of older, racially diverse patients with renal failure.
Citation: Hewner S, Smith E, Sullivan SS . Identifying high-need primary care patients using nursing knowledge and machine learning methods. Appl Clin Inform 2023 May; 14(3):408-17. doi: 10.1055/a-2048-7343..
Keywords: Primary Care, Health Information Technology (HIT), Nursing
Kimchi A, Aronow HU, Ni YM
Postdischarge noninvasive telemonitoring and nurse telephone coaching improve outcomes in heart failure patients with high burden of comorbidity.
The purpose of this study was to explore how comorbidity burden modulates the effectiveness of Noninvasive telemonitoring and nurse telephone coaching (NTM-NTC) and identify patients with HF who may benefit from postdischarge NTM-NTC based on their burden of comorbidity. METHODS AND RESULTS: In the Better Effectiveness After Transition - Heart Failure trial, patients hospitalized for acute decompensated HF were randomized to postdischarge NTM-NTC or usual care. In this secondary analysis of 1313 patients with complete data, comorbidity burden was assessed by scoring complication and coexisting diagnoses from index admissions. Clinical outcomes included 30-day and 180-day readmissions, mortality, days alive, and combined days alive and out of the hospital. Patients had a mean of 5.7 comorbidities and were stratified into low (0-2), moderate (3-8), and high comorbidity (≥9) subgroups. Increased comorbidity burden was associated with worse outcomes. NTM-NTC was not associated with readmission rates in any comorbidity subgroup. Among high comorbidity patients, NTM-NTC was associated with significantly lower mortality at 30 days (hazard ratio 0.25, 95% confidence interval 0.07-0.90) and 180 days (hazard ratio 0.51, 95% confidence interval 0.27-0.98), as well as more days alive (160.1 vs 140.3, P = .029) and days alive out of the hospital (152.0 vs 133.2, P = .044) compared with usual care. CONCLUSIONS: Postdischarge NTM-NTC improved survival among patients with HF with a high comorbidity burden. Comorbidity burden may be useful for identifying patients likely to benefit from this management strategy.
Citation: Kimchi A, Aronow HU, Ni YM . Postdischarge noninvasive telemonitoring and nurse telephone coaching improve outcomes in heart failure patients with high burden of comorbidity. J Card Fail 2023 May; 29(5):774-83. doi: 10.1016/j.cardfail.2022.11.012..
Keywords: Heart Disease and Health, Cardiovascular Conditions, Telehealth, Health Information Technology (HIT), Hospital Discharge
Cantor AG, Nelson HD, Pappas M
Telehealth for women's preventive services for reproductive health and intimate partner violence: a comparative effectiveness review.
This comparative effectiveness review was conducted on the effectiveness and harms of telehealth interventions for women's reproductive health and intimate partner violence (IPV) services. A literature search was conducted for randomized controlled trials (RCTs) and observational studies of telehealth strategies for women's reproductive health and IPV versus usual care for the period July 2016 to May 2022. Eight RCTs, 1 nonrandomized trial, and 7 observational studies were included (7 studies of contraceptive care and 9 of IPV services). Telehealth services demonstrated similar care as usual care for contraceptive use, sexually transmitted infections, and pregnancy (low strength of evidence [SOE]). Evidence on abortion was insufficient. Outcomes were also similar between telehealth and usual care interventions to replace or supplement IPV services and comparators for repeat IPV, depression, posttraumatic stress disorder, fear of partner, coercive control, self-efficacy, and safety behaviors (low SOE). Telehealth barriers identified included limited internet access, digital literacy, technical challenges, and confidentiality concerns. Safety strategies increased telehealth use for IPV services. Evidence lacked on access, health equity, or harms.
Citation: Cantor AG, Nelson HD, Pappas M . Telehealth for women's preventive services for reproductive health and intimate partner violence: a comparative effectiveness review. J Gen Intern Med 2023 May; 38(7):1735-43. doi: 10.1007/s11606-023-08033-6..
Keywords: Telehealth, Health Information Technology (HIT), Women, Prevention, Domestic Violence, Evidence-Based Practice, Maternal Care, Sexual Health, Patient-Centered Outcomes Research, Comparative Effectiveness
Zhang J, Kummerfield E, Hultman G
Application of causal discovery algorithms in studying the nephrotoxicity of remdesivir using longitudinal data from the EHR.
Researchers analyzed the role of remdesivir in the mechanism and optimal treatment of the development of acute kidney injury (AKI) in the setting of COVID. Applying causal discovery machine learning techniques, they built multifactorial causal models of COVID-AKI; risk factors and renal function measures were represented in a temporal sequence using longitudinal data from Electronic Health Records. Their results indicated a need for assessment of renal function on second- and third-day use of remdesivir, and also showed that remdesivir may pose less risk to AKI than existing conditions of chronic kidney disease.
Citation: Zhang J, Kummerfield E, Hultman G . Application of causal discovery algorithms in studying the nephrotoxicity of remdesivir using longitudinal data from the EHR. AMIA Annu Symp Proc 2023 Apr 29; 2022:1227-36..
Keywords: COVID-19, Electronic Health Records (EHRs), Health Information Technology (HIT), Medication, Adverse Drug Events (ADE), Adverse Events
Hobensack M, Song J, Chae S
Capturing concerns about patient deterioration in narrative documentation in home healthcare.
This study aimed to build machine learning algorithms to identify “concerning” narrative notes of home healthcare (HHC) patients and identify emergency themes to support early identification of patients at risk for deterioration. Six algorithms were applied to 4000 narrative notes from a HHC agency to classify notes as either "concerning" or "not concerning." Emerging themes were identified using Latent Dirichlet Allocation bag of words topic modeling. Emerging themes of concern included patient-clinician communication, HHC services provided, gait challenges, mobility concerns, wounds, and caregivers. Most of these themes had already been identified in previous literature as increasing risk for adverse events.
Citation: Hobensack M, Song J, Chae S . Capturing concerns about patient deterioration in narrative documentation in home healthcare. AMIA Annu Symp Proc 2023 Apr 29; 2022:552-59..
Keywords: Home Healthcare, Electronic Health Records (EHRs), Health Information Technology (HIT)
Moy AJ, Cato KD, Withall J
Using time series clustering to segment and infer emergency department nursing shifts from electronic health record log files.
Clinical shifts are an essential unit of work recognized in clinical settings and may function as a primary unit of analysis in the study of documentation burden. The purpose of this proof- of-concept study was to investigate the feasibility of a new approach utilizing time series clustering to segment and infer clinician shifts from electronic health record (HER) log files. The researchers recorded 33,535,585 events between April-June 2021 and computationally identified 43,911 potential shifts among 2,285 emergency department nurses. On average, shifts were 10.6±3.1 hours in duration. Researchers classified the shifts based on type: day, evening, night; and length: 12-hour, 8-hour, other. The preliminary results of the study found that unsupervised clustering methods may be a feasible approach for quickly identifying clinician shifts.
Citation: Moy AJ, Cato KD, Withall J . Using time series clustering to segment and infer emergency department nursing shifts from electronic health record log files. AMIA Annu Symp Proc 2023 Apr 29; 2022:805-14..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Emergency Department, Workforce