Predicting 30-Day Readmissions With Preadmission Electronic Health Record Data

Shadmi, Efrat; Flaks‐Manov, Natalie; Hoshen, Moshe; Goldman, Orit; Bitterman, Haim; Balicer, Ran D.

doi:10.1097/mlr.0000000000000315

Cited by 106 publications

(118 citation statements)

References 39 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…40 Using regression trees and logistic models, it found that 11 variables, including chronic conditions, prior health services use, body mass index, and geographic location weakly predicted increased readmission risk (odds ratios Ͻ2.00). Those results differ from ours in that they did not indicate increased risk from polypharmacy and Charlson scores, and the study's 11-factor model was less predictive than our 2-item model.…”

Section: Discussionmentioning

confidence: 99%

Admission Data Predict High Hospital Readmission Risk

Logue

Smucker

Regan

2016

The Journal of the American Board of Family Medicine

View full text Add to dashboard Cite

Purpose: The purpose of this study was to identify data available at the time of hospital admission that predict readmission risk.Methods: We performed a retrospective multiple regression analysis of 958 adult, nonpregnant patients admitted to the Family Medicine Service between June 2012 and October 2013. Data were abstracted from hospital administrative sources and electronic medical records. The outcome was 30-day hospital readmission. Candidate readmission predictors included polypharmacy (>6 medicines), Charlson comorbidity index, age, sex, insurance status, emergency department use, smoking, nursing report of cognitive issues, patient report of social support or financial issues, and a history of heart failure, pneumonia, or chronic obstructive pulmonary disease.Results: Patients at the Family Medicine Service had a 14% readmission risk. Bivariate analysis showed that high Charlson scores (>5), polypharmacy, heart failure, pneumonia, or chronic obstructive pulmonary disease each increased readmission risk (P < .05). A logistic model showed an estimated odds ratio for readmission for high Charlson scores of 1.7 (95% confidence interval, 1.1-2.6) and of 2.1 for polypharmacy (95% confidence interval,

show abstract

Section: Discussionmentioning

confidence: 99%

Admission Data Predict High Hospital Readmission Risk

Logue

Smucker

Regan

2016

The Journal of the American Board of Family Medicine

View full text Add to dashboard Cite

show abstract

“…Furthermore, VE can distinguish planned care referrals to a limited set of subspecialists ( The multivariate analysis confirms many previous studies showing age, comorbidities, length of stay, and number of previous hospitalizations or ED visits are associated with increased odds of readmission. [35][36][37][38][39][40][41][42][43] Marital status, which may be a marker of social determinants of health, and gender have had variable associations with readmission. 41,42,47 In this study, neither gender nor marital status was associated with readmission odds.…”

Section: Discussionmentioning

confidence: 99%

“…For each measure of continuity, a multivariate analysis using logistic regression was conducted to adjust for known readmission risk factors. 1,[35][36][37][38][39][40][41][42][43] Odds ratios with 95% confidence intervals were calculated. Direct comparison of the 4 non-nested models over the entire dataset using Akaike's Information Criterion was not valid due to the fact that the UPC, COC, and SECON models all excluded different data due to their inherent division-by-zero problem.…”

Section: Discussionmentioning

confidence: 99%

Visit Entropy Associated with Hospital Readmission Rates

et al. 2017

View full text Add to dashboard Cite

Purpose: The chronic disease model suggests continuity of care and team-based care can improve outcomes for multimorbidity patients and reduce hospitalizations. Continuity of care following admission has had mixed effects on readmission rates; however, its effect before admission has not been well studied. Increased outpatient care organization and continuity before admission is hypothesized to reduce the odds of readmission.Methods: In a cohort of 14,662 primary care patients from a Patient-Centered Medical Home (PCMH) practice, continuity of care in the 12 months before admission was assessed using 3 established metrics; usual provider continuity (UPC), dispersion continuity of care (COC), and sequence continuity (SECON). In addition, because these established metrics may not accurately reflect continuity in planned teambased care, a new metric called visit entropy (VE) was used to quantify the disorganization of visits. Multivariate logistic regression was performed to examine the relationship between readmission within 30 days and continuity while controlling for known readmission risk factors abstracted from an electronic medical record.Results: Higher VE was associated with readmission (odds ratio, 1.10; 95% confidence interval, 1.02 to 1.19). The continuity measures of UPC, COC, and SECON were not associated with readmission.

show abstract

“…[3][4][5] Research on characterizing revisit rates has many facets, ranging from the construction of risk indices 4,6 to examining statistical behavior 1,3,7-9 and constructing predictive models using machine learning principles. 10,11 Both 30 days 1,3,4,11 and 72 hours 7,8,10 have been used as cutoff points for whether a visit before a given ED encounter is considered a revisit. Such studies often treat insurance type as a factor; as such, there is not much information on the specific behavior of the space of Medicaid patients.…”

Section: Introductionmentioning

confidence: 99%

Understanding Emergency Department 72-Hour Revisits Among Medicaid Patients Using Electronic Healthcare Records

2015

View full text Add to dashboard Cite

Electronic Healthcare Records (EHRs) have the potential to improve healthcare quality and to decrease costs by providing quality metrics, discovering actionable insights, and supporting decision-making to improve future outcomes. Within the United States Medicaid Program, rates of recidivism among emergency department (ED) patients serve as metrics of hospital performance that help ensure efficient and effective treatment within the ED. We analyze ED Medicaid patient data from 1,149,738 EHRs provided by a hospital over a 2-year period to understand the characteristics of the ED return visits within a 72-hour time frame. Frequent flyer patients with multiple revisits account for 47% of Medicaid patient revisits over this period. ED encounters by frequent flyer patients with prior 72-hour revisits in the last 6 months are thrice more likely to result in a readmit than those of infrequent patients. Statistical L1-logistic regression and random forest analyses reveal distinct patterns of ED usage and patient diagnoses between frequent and infrequent patient encounters, suggesting distinct opportunities for interventions to improve efficacy of care and streamline ED workflow. This work forms a foundation for future development of predictive models, which could flag patients at high risk of revisiting.

show abstract

Predicting 30-Day Readmissions With Preadmission Electronic Health Record Data

Abstract: The PREADM is designed for use by health plans for early high-risk case identification, presenting discriminatory power better than or similar to that of previously reported models, most of which include data available only upon discharge.

Cited by 106 publications

References 39 publications

Admission Data Predict High Hospital Readmission Risk

Admission Data Predict High Hospital Readmission Risk

Visit Entropy Associated with Hospital Readmission Rates

Understanding Emergency Department 72-Hour Revisits Among Medicaid Patients Using Electronic Healthcare Records

Contact Info

Product

Resources

About