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
- Adverse Drug Events (ADE) (2)
- Adverse Events (3)
- Ambulatory Care and Surgery (1)
- Cardiovascular Conditions (3)
- Children/Adolescents (1)
- Clinician-Patient Communication (1)
- Clostridium difficile Infections (1)
- Communication (1)
- COVID-19 (1)
- Data (1)
- Diabetes (1)
- Diagnostic Safety and Quality (1)
- Elderly (3)
- (-) Electronic Health Records (EHRs) (32)
- Electronic Prescribing (E-Prescribing) (1)
- Emergency Department (4)
- Falls (2)
- Guidelines (1)
- Healthcare-Associated Infections (HAIs) (2)
- Healthcare Utilization (1)
- Health Information Technology (HIT) (24)
- Health Status (1)
- Health Systems (1)
- Heart Disease and Health (3)
- Home Healthcare (2)
- Hospitalization (6)
- Hospital Readmissions (4)
- Hospitals (2)
- Injuries and Wounds (3)
- Medical Errors (1)
- Medication (5)
- Medication: Safety (1)
- Mortality (3)
- Nursing Homes (1)
- Organizational Change (1)
- Osteoporosis (2)
- Outcomes (2)
- Patient-Centered Outcomes Research (2)
- Patient Adherence/Compliance (1)
- Patient Safety (9)
- Prevention (2)
- Primary Care (1)
- Provider (1)
- Provider: Clinician (1)
- (-) Risk (32)
- Sepsis (1)
- Social Determinants of Health (1)
- Surgery (3)
- Transitions of Care (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 32 Research Studies DisplayedLinfield GH, Patel S, Ko HJ
Evaluating the comparability of patient-level social risk data extracted from electronic health records: a systematic scoping review.
This study’s objective was to evaluate how and from where social risk data are extracted from electronic health records (EHRs) for research purposes, and how observed differences may impact study generalizability. A systematic scoping review was conducted of peer-reviewed literature that used patient-level EHR data to assess 1 ± 6 social risk domains: housing, transportation, food, utilities, safety, social support/isolation. The authors found 111 of 9022 identified articles met inclusion criteria. By domain, martial/partner status was most often included, predominantly defined by marital partner status, and extracted from structured sociodemographic data. Structured housing data was extracted most from billing codes and screening tools. Across domains, data were predominantly sourced from structured fields (n = 89/111) versus unstructured free text (n = 32/111).
AHRQ-funded; HS026383.
Citation: Linfield GH, Patel S, Ko HJ .
Evaluating the comparability of patient-level social risk data extracted from electronic health records: a systematic scoping review.
Health Informatics J 2023 Jul-Sep; 29(3):14604582231200300. doi: 10.1177/14604582231200300..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Social Determinants of Health, Risk
Hobensack M, Ojo M, Barrón Y
Documentation of hospitalization risk factors in electronic health records (EHRs): a qualitative study with home healthcare clinicians.
The objectives of this study were to identify risk factors that home healthcare clinicians associate with patient deterioration and to understand clinicians’ response to and documentation of these risk factors. The authors interviewed multidisciplinary home healthcare clinicians and used directed content analysis to identify risk factors for deterioration. A total of 79 risk factors were identified by the clinicians, who responded most often by communicating with the prescribing provider or following up with patients and caregivers. Clinicians also acknowledged that social factors played a role in deterioration risk. The authors noted that, since most risk factors were documented in clinical notes, methods such as natural language processing are needed to extract them. They concluded that by providing a comprehensive list of risk factors grounded in clinician expertise and mapped to standardized terminologies, the results of their study supported the development of an early warning system for patient deterioration.
AHRQ-funded; HS027742.
Citation: Hobensack M, Ojo M, Barrón Y .
Documentation of hospitalization risk factors in electronic health records (EHRs): a qualitative study with home healthcare clinicians.
J Am Med Inform Assoc 2022 Apr 13;29(5):805-12. doi: 10.1093/jamia/ocac023..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Home Healthcare, Risk, Hospitalization
Kamran F, Tang S, Otles E
Early identification of patients admitted to hospital for covid-19 at risk of clinical deterioration: model development and multisite external validation study.
The authors sought to create and validate a simple and transferable machine learning model from electronic health record data to accurately predict clinical deterioration in patients with COVID-19 across institutions, through use of a novel paradigm for model development and code sharing. They determined that a model to predict clinical deterioration was developed rapidly in response to the COVID-19 pandemic at a single hospital, was applied externally without the sharing of data, and performed well across multiple medical centers, patient subgroups, and time periods, showing its potential as a tool for use in optimizing healthcare resources.
AHRQ-funded; HS028038.
Citation: Kamran F, Tang S, Otles E .
Early identification of patients admitted to hospital for covid-19 at risk of clinical deterioration: model development and multisite external validation study.
BMJ 2022 Feb 17;376:e068576. doi: 10.1136/bmj-2021-068576..
Keywords: COVID-19, Hospitalization, Risk, Electronic Health Records (EHRs), Health Information Technology (HIT)
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)
Kandaswamy S, Pruitt Z, Kazi S
Clinician perceptions on the use of free-text communication orders.
The aim of this study was to investigate (1) why ordering clinicians use free-text orders to communicate medication information; (2) what risks physicians and nurses perceive when free-text orders are used for communicating medication information; and (3) how electronic health records (EHRs) could be improved to encourage the safe communication of medication information. The investigators concluded that clinicians' use of free-text orders as a workaround to insufficient structured order entry can create unintended patient safety risks.
AHRQ-funded; HS025136; HS024755.
Citation: Kandaswamy S, Pruitt Z, Kazi S .
Clinician perceptions on the use of free-text communication orders.
Appl Clin Inform 2021 May;12(3):484-94. doi: 10.1055/s-0041-1731002..
Keywords: Electronic Prescribing (E-Prescribing), Health Information Technology (HIT), Electronic Health Records (EHRs), Medication: Safety, Medication, Patient Safety, Communication, Provider: Clinician, Provider, Risk
Topaz M, Woo K, Ryvicker M
Home healthcare clinical notes predict patient hospitalization and emergency department visits.
About 30% of home healthcare patients are hospitalized or visit an emergency department (ED) during a home healthcare (HHC) episode. Novel data science methods are increasingly used to improve identification of patients at risk for negative outcomes. The aim of the study was to identify patients at heightened risk hospitalization or ED visits using HHC narrative data (clinical notes).
AHRQ-funded; HS027742.
Citation: Topaz M, Woo K, Ryvicker M .
Home healthcare clinical notes predict patient hospitalization and emergency department visits.
Nurs Res 2020 Nov/Dec;69(6):448-54. doi: 10.1097/nnr.0000000000000470..
Keywords: Elderly, Home Healthcare, Emergency Department, Hospitalization, Risk, Electronic Health Records (EHRs), Health Information Technology (HIT)
Saleh SN, Makam AN, Halm EA,
Can we predict early 7-day readmissions using a standard 30-day hospital readmission risk prediction model?
Despite focus on preventing 30-day readmissions, early readmissions (within 7 days of discharge) may be more preventable than later readmissions (8-30 days). In this study, the investigators assessed how well a previously validated 30-day EHR-based readmission model predicted 7-day readmissions and compared differences in strength of predictors. They suggested that improvements in predicting early 7-day readmissions will likely require new risk factors proximal to day of discharge.
AHRQ-funded; HS022418.
Citation: Saleh SN, Makam AN, Halm EA, .
Can we predict early 7-day readmissions using a standard 30-day hospital readmission risk prediction model?
BMC Med Inform Decis Mak 2020 Sep 15;20(1):227. doi: 10.1186/s12911-020-01248-1..
Keywords: Hospital Readmissions, Hospitals, Risk, Transitions of Care, Electronic Health Records (EHRs), Health Information Technology (HIT)
Scott HF, Colborn KL, Sevick CJ
Development and validation of a predictive model of the risk of pediatric septic shock using data known at the time of hospital arrival.
The purpose of this observational cohort study was to derive and validate a model of risk of septic shock among children with suspected sepsis, using data known in the electronic health record at hospital arrival. The investigators concluded that their model estimated the risk of septic shock in children at hospital arrival earlier than existing models. They indicate it leveraged the predictive value of routine electronic health record data through a modern predictive algorithm and suggest it has the potential to enhance clinical risk stratification in the critical moments before deterioration.
AHRQ-funded; HS025696.
Citation: Scott HF, Colborn KL, Sevick CJ .
Development and validation of a predictive model of the risk of pediatric septic shock using data known at the time of hospital arrival.
J Pediatr 2020 Feb;217:145-51.e6. doi: 10.1016/j.jpeds.2019.09.079..
Keywords: Children/Adolescents, Sepsis, Emergency Department, Hospitals, Risk, Electronic Health Records (EHRs), Health Information Technology (HIT)
Hannan EL, Barrett SC, Samadashvili Z
Retooling of paper-based outcome measures to electronic format: comparison of the NY State public risk model and EHR-derived risk models for CABG mortality.
This study assessed the feasibility of retooling the paper-based New York State coronary artery bypass graft (CABG) surgery statistical model for mortality and readmission into a model for electronic health records (EHRs). Researchers found that only 6 data elements could be extracted from the EHR, and outlier hospitals differed for readmission but was usable for mortality. They concluded that the EHR model was inferior to the NYS model, and that simplifying the EHR risk model couldn’t capture most of the risk factors in the NYS model.
AHRQ-funded; HS022647.
Citation: Hannan EL, Barrett SC, Samadashvili Z .
Retooling of paper-based outcome measures to electronic format: comparison of the NY State public risk model and EHR-derived risk models for CABG mortality.
Med Care 2019 May;57(5):377-84. doi: 10.1097/mlr.0000000000001104..
Keywords: Surgery, Electronic Health Records (EHRs), Health Information Technology (HIT), Mortality, Outcomes, Risk, Cardiovascular Conditions
Grundmeier RW, Xiao R, Ross RK
Grundmeier RW, Xiao R, Ross RK, Ramos MJ, Karavite DJ, Michel JJ, Gerber JS, et al. Identifying surgical site infections in electronic health data using predictive models,.
The objective of this study was to prospectively derive and validate a prediction rule for detecting cases warranting investigation for surgical site infections (SSI) after ambulatory surgery. The investigators concluded that electronic health record data can facilitate SSI surveillance with adequate sensitivity and positive predictive value.
AHRQ-funded; HS020921.
Citation: Grundmeier RW, Xiao R, Ross RK .
Grundmeier RW, Xiao R, Ross RK, Ramos MJ, Karavite DJ, Michel JJ, Gerber JS, et al. Identifying surgical site infections in electronic health data using predictive models,.
J Am Med Inform Assoc 2018 Sep;25(9):1160-66. doi: 10.1093/jamia/ocy075..
Keywords: Healthcare-Associated Infections (HAIs), Injuries and Wounds, Surgery, Electronic Health Records (EHRs), Health Information Technology (HIT), Risk, Patient Safety, Adverse Events, Ambulatory Care and Surgery
Flory JH, Keating SJ, Siscovick D
Identifying prevalence and risk factors for metformin non-persistence: a retrospective cohort study using an electronic health record.
Non-persistence may be a significant barrier to the use of metformin. The objective of this study was to assess reasons for metformin non-persistence, and whether initial metformin dosing or use of extended release (ER) formulations affect persistence to metformin therapy. The investigators concluded that their data supported the routine prescribing of low starting doses of metformin as a tool to improve persistence.
AHRQ-funded; HS023898.
Citation: Flory JH, Keating SJ, Siscovick D .
Identifying prevalence and risk factors for metformin non-persistence: a retrospective cohort study using an electronic health record.
BMJ Open 2018 Jul 23;8(7):e021505. doi: 10.1136/bmjopen-2018-021505..
Keywords: Diabetes, Electronic Health Records (EHRs), Health Information Technology (HIT), Medication, Patient Adherence/Compliance, Outcomes, Patient-Centered Outcomes Research, Risk
Skube SJ, Lindemann EA, Arsoniadis EG
Characterizing functional health status of surgical patients in clinical notes.
The researchers of this study hypothesize that important functional status data is contained in clinical notes. They found that several categories of phrases related to functional status including diagnoses, activity and care assessments, physical exam, functional scores, assistive equipment, symptoms, and surgical history were important factors. They conducted a chart review and compared functional health status level terms from the chart review to National Surgical Quality Improvement Program determinations.
AHRQ-funded; HS024532.
Citation: Skube SJ, Lindemann EA, Arsoniadis EG .
Characterizing functional health status of surgical patients in clinical notes.
AMIA Jt Summits Transl Sci Proc 2018 May 18;2017:379-88..
Keywords: Health Status, Patient Safety, Risk, Surgery, Electronic Health Records (EHRs)
Patterson BW, Repplinger MD, Pulia MS
Using the Hendrich II Inpatient Fall Risk Screen to predict outpatient falls after emergency department visits.
This study examined the utility of using the Hendrich II Inpatient Fall Risk Screen to predict outpatient falls in elderly patients after emergency department (ED) visits. Individuals aged 65 and older seen in the ED from January 2013 to September 30, 2015 participated in the study. The Hendrich II screen was found to correlate with outpatient falls, but it is likely it would have little utility as a stand-alone fall screen. When the screen was combined with other potential confounders or predictors, the screen performed much better.
AHRQ-funded; HS024558.
Citation: Patterson BW, Repplinger MD, Pulia MS .
Using the Hendrich II Inpatient Fall Risk Screen to predict outpatient falls after emergency department visits.
J Am Geriatr Soc 2018 Apr;66(4):760-65. doi: 10.1111/jgs.15299..
Keywords: Elderly, Falls, Risk, Emergency Department, Electronic Health Records (EHRs), Health Information Technology (HIT), Prevention, Patient Safety, Adverse Events
Howe JL, Adams KT, Hettinger AZ
Electronic health record usability issues and potential contribution to patient harm.
Researchers analyzed reports of possible patient harm that explicitly mentioned a major EHR vendor or product. They concluded that EHR usability may have been a contributing factor to some possible patient harm events. Only a small percentage of potential harm events were associated with EHR usability, but the analysis was conservative because safety reports only capture a small fraction of the actual number of safety incidents.
AHRQ-funded; HS023701.
Citation: Howe JL, Adams KT, Hettinger AZ .
Electronic health record usability issues and potential contribution to patient harm.
JAMA 2018 Mar 27;319(12):1276-78. doi: 10.1001/jama.2018.1171.
.
.
Keywords: Adverse Events, Electronic Health Records (EHRs), Medical Errors, Patient Safety, Risk
Rangachari P
Implementing a Social Knowledge Networking (SKN) system to enable meaningful use of an EHR medication reconciliation system.
The study examined user-engagement in the SKN system and associations between "SKN use" and "meaningful use" of electronic health record (EHR). The prospective implementation design is expected to generate context-sensitive strategies for meaningful use and successful implementation of EHR Medication Reconciliation (MedRec) and thereby make substantial contributions to the patient safety and risk management literature.
AHRQ-funded; HS024335.
Citation: Rangachari P .
Implementing a Social Knowledge Networking (SKN) system to enable meaningful use of an EHR medication reconciliation system.
Risk Manag Healthc Policy 2018 Mar 26;11:45-53. doi: 10.2147/rmhp.s152313.
.
.
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Medication, Patient Safety, Risk
Kan HJ, Kharrazi H, Leff B
Defining and assessing geriatric risk factors and associated health care utilization among older adults using claims and electronic health records.
This study used electronic health records (EHRs) to identify patients with factors associated with geriatric risk for hospitalization among older adults. Prevalence was estimated using claims, structured EHRs, and unstructured EHRs. Odds were calculated on the occurrence of hospitalizations for patients with 1 or 2 and greater risk factors.
AHRQ-funded; HS000029.
Citation: Kan HJ, Kharrazi H, Leff B .
Defining and assessing geriatric risk factors and associated health care utilization among older adults using claims and electronic health records.
Med Care 2018 Mar;56(3):233-39. doi: 10.1097/mlr.0000000000000865..
Keywords: Elderly, Hospitalization, Healthcare Utilization, Risk, Electronic Health Records (EHRs), Health Information Technology (HIT)
Harris AD, Sbarra AN, Leekha S
Electronically available comorbid conditions for risk prediction of healthcare-associated Clostridium difficile infection.
This study analyzed whether electronically available comorbid conditions are risk factors for Centers for Disease Control and Prevention (CDC)-defined, hospital-onset Clostridium difficile infection (CDI) after controlling for antibiotic and gastric acid suppression therapy use. It concluded that comorbid conditions are important risk factors for CDI.
AHRQ-funded; HS022291.
Citation: Harris AD, Sbarra AN, Leekha S .
Electronically available comorbid conditions for risk prediction of healthcare-associated Clostridium difficile infection.
Infect Control Hosp Epidemiol 2018 Mar;39(3):297-301. doi: 10.1017/ice.2018.10.
.
.
Keywords: Clostridium difficile Infections, Electronic Health Records (EHRs), Healthcare-Associated Infections (HAIs), Patient Safety, Risk
Sittig DF, Singh H
Toward more proactive approaches to safety in the electronic health record era.
This article discusses a proactive approach to safety in the electronic health record era. It discusses an updated health IT Sentinel Event Alert, released in March 2015 by the Joint Commission which took a broad, sociotechnical approach in exploring the factors involved in the safe use of health IT.
AHRQ-funded; HS023602; HS022087.
Citation: Sittig DF, Singh H .
Toward more proactive approaches to safety in the electronic health record era.
Jt Comm J Qual Patient Saf 2017 Oct;43(10):540-47. doi: 10.1016/j.jcjq.2017.06.005..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Patient Safety, Guidelines, Organizational Change, Risk
Blumenthal KG, Lai KH, Huang M
Adverse and hypersensitivity reactions to prescription nonsteroidal anti-inflammatory agents in a large health care system.
The researchers aimed to use electronic health record data to determine the incidence and predictors of hypersentivity reaction (HSR) to prescription nonsteroidal anti-inflammatory drugs (NSAIDs). They concluded that NSAID therapeutic use can be limited by adverse drug reactions (ADRs); about 1 in 5 NSAID ADRs is an hypersentivity reaction.
AHRQ-funded; HS022728.
Citation: Blumenthal KG, Lai KH, Huang M .
Adverse and hypersensitivity reactions to prescription nonsteroidal anti-inflammatory agents in a large health care system.
J Allergy Clin Immunol Pract 2017 May-Jun;5(3):737-43. doi: 10.1016/j.jaip.2016.12.006.
.
.
Keywords: Electronic Health Records (EHRs), Medication, Risk, Health Systems, Adverse Drug Events (ADE)
Banerji A, Blumenthal KG, Lai KH
Epidemiology of ACE inhibitor angioedema utilizing a large electronic health record.
The objective of this study was to identify the incidence of and risk factors for angioedema caused by angiotensin-converting enzyme inhibitors (ACEIs) using a large integrated electronic health record (EHR). It concluded that the incidence of ACEI angioedema within a large EHR is consistent with large clinical trial data. A history of nonsteroidal anti-inflammatory drug allergy was identified as a risk factor for patients with ACEI angioedema.
AHRQ-funded; HS022728.
Citation: Banerji A, Blumenthal KG, Lai KH .
Epidemiology of ACE inhibitor angioedema utilizing a large electronic health record.
J Allergy Clin Immunol Pract 2017 May - Jun;5(3):744-49. doi: 10.1016/j.jaip.2017.02.018.
.
.
Keywords: Electronic Health Records (EHRs), Medication, Risk, Health Information Technology (HIT), Adverse Drug Events (ADE)
Makam AN, Nguyen OK, Clark C
Incidence, predictors, and outcomes of hospital-acquired anemia.
This study examined the incidence, predictors, and postdischarge outcomes associated with hospital-acquired anemia (HAA). Most patients with severe HAA (85 percent) underwent a major procedure, had a discharge diagnosis of hemorrhage, and/or a discharge diagnosis of hemorrhagic disorder. Severe HAA is associated with increased odds for 30-day mortality and readmission after discharge; however, it is uncertain whether severe HAA is preventable.
AHRQ-funded; HS022418.
Citation: Makam AN, Nguyen OK, Clark C .
Incidence, predictors, and outcomes of hospital-acquired anemia.
J Hosp Med 2017 May;12(5):317-22. doi: 10.12788/jhm.2723
.
.
Keywords: Electronic Health Records (EHRs), Hospital Readmissions, Hospitalization, Patient-Centered Outcomes Research, Risk
Wang SV, Rogers JR, Jin Y
Use of electronic healthcare records to identify complex patients with atrial fibrillation for targeted intervention.
The researchers tested algorithms for identifying atrial fibrillation (AF) patients who also have known risk factors for stroke and major bleeding using electronic healthcare records (EHRs) data. The performance of candidate algorithms in 1000 bootstrap resamples was compared to a gold standard of manual chart review by experienced resident physicians of 480 patient charts. For 11 conditions, the median positive predictive value of the EHR-derived algorithms was greater than 0.90.
AHRQ-funded; HS022193.
Citation: Wang SV, Rogers JR, Jin Y .
Use of electronic healthcare records to identify complex patients with atrial fibrillation for targeted intervention.
J Am Med Inform Assoc 2017 Mar 1;24(2):339-44. doi: 10.1093/jamia/ocw082.
.
.
Keywords: Heart Disease and Health, Cardiovascular Conditions, Electronic Health Records (EHRs), Health Information Technology (HIT), Risk
Haas JS, Baer HJ, Eibensteiner K
A cluster randomized trial of a personalized multi-condition risk assessment in primary care.
This study evaluated whether collection of risk factors to generate electronic health record (EHR)-linked health risk appraisal (HRA) for coronary heart disease, diabetes, breast cancer, and colorectal cancer was associated with improved patient-provider communication, risk assessment, and plans for breast cancer screening. It concluded that patient-reported risk factors and EHR-linked multi-condition HRAs in primary care can modestly improve communication and promote accuracy of self-perceived risk.
AHRQ-funded; HS018644.
Citation: Haas JS, Baer HJ, Eibensteiner K .
A cluster randomized trial of a personalized multi-condition risk assessment in primary care.
Am J Prev Med 2017 Jan;52(1):100-05. doi: 10.1016/j.amepre.2016.07.013.
.
.
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Primary Care, Clinician-Patient Communication, Risk
Nguyen OK, Makam AN, Clark C
Predicting all-cause readmissions using electronic health record data from the entire hospitalization: model development and comparison.
The purpose of this study was to develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare "full-stay" model performance to a "first day" and 2 other validated models. It found that incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions.
AHRQ-funded; HS022418.
Citation: Nguyen OK, Makam AN, Clark C .
Predicting all-cause readmissions using electronic health record data from the entire hospitalization: model development and comparison.
J Hosp Med 2016 Jul;11(7):473-80. doi: 10.1002/jhm.2568.
.
.
Keywords: Electronic Health Records (EHRs), Hospital Readmissions, Hospitalization, Risk
Taslimitehrani V, Dong G, Pereira NL
Developing EHR-driven heart failure risk prediction models using CPXR(Log) with the probabilistic loss function.
The authors proposed to apply a classification algorithm, Contrast Pattern Aided Logistic Regression (CPXR(Log)) with the probabilistic loss function, to develop and validate prognostic risk models to predict 1, 2, and 5 year survival in heart failure (HF). They found that the new loss function used in the algorithm outperforms other functions used in previous studies and that HF is a highly heterogeneous disease (different subgroups of patients require different types of considerations with their diagnosis and treatment). They concluded that logistic risk models often make systematic prediction errors and that it is prudent to use subgroup based prediction models such as those given by CPXR(Log) when investigating heterogeneous diseases.
AHRQ-funded; HS023077.
Citation: Taslimitehrani V, Dong G, Pereira NL .
Developing EHR-driven heart failure risk prediction models using CPXR(Log) with the probabilistic loss function.
J Biomed Inform 2016 Apr;60:260-9. doi: 10.1016/j.jbi.2016.01.009.
.
.
Keywords: Electronic Health Records (EHRs), Heart Disease and Health, Health Information Technology (HIT), Risk