Literature DB >> 25182868

The effects of data sources, cohort selection, and outcome definition on a predictive model of risk of thirty-day hospital readmissions.

Colin Walsh1, George Hripcsak2.   

Abstract

BACKGROUND: Hospital readmission risk prediction remains a motivated area of investigation and operations in light of the hospital readmissions reduction program through CMS. Multiple models of risk have been reported with variable discriminatory performances, and it remains unclear how design factors affect performance.
OBJECTIVES: To study the effects of varying three factors of model development in the prediction of risk based on health record data: (1) reason for readmission (primary readmission diagnosis); (2) available data and data types (e.g. visit history, laboratory results, etc); (3) cohort selection.
METHODS: Regularized regression (LASSO) to generate predictions of readmissions risk using prevalence sampling. Support Vector Machine (SVM) used for comparison in cohort selection testing. Calibration by model refitting to outcome prevalence.
RESULTS: Predicting readmission risk across multiple reasons for readmission resulted in ROC areas ranging from 0.92 for readmission for congestive heart failure to 0.71 for syncope and 0.68 for all-cause readmission. Visit history and laboratory tests contributed the most predictive value; contributions varied by readmission diagnosis. Cohort definition affected performance for both parametric and nonparametric algorithms. Compared to all patients, limiting the cohort to patients whose index admission and readmission diagnoses matched resulted in a decrease in average ROC from 0.78 to 0.55 (difference in ROC 0.23, p value 0.01). Calibration plots demonstrate good calibration with low mean squared error.
CONCLUSION: Targeting reason for readmission in risk prediction impacted discriminatory performance. In general, laboratory data and visit history data contributed the most to prediction; data source contributions varied by reason for readmission. Cohort selection had a large impact on model performance, and these results demonstrate the difficulty of comparing results across different studies of predictive risk modeling.
Copyright © 2014 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Electronic health record; Predictive analytics; Readmissions; Regularized Logistic Regression; Risk modeling; Text mining

Mesh:

Year:  2014        PMID: 25182868      PMCID: PMC4261028          DOI: 10.1016/j.jbi.2014.08.006

Source DB:  PubMed          Journal:  J Biomed Inform        ISSN: 1532-0464            Impact factor:   6.317


  32 in total

1.  Validation and updating of predictive logistic regression models: a study on sample size and shrinkage.

Authors:  Ewout W Steyerberg; Gerard J J M Borsboom; Hans C van Houwelingen; Marinus J C Eijkemans; J Dik F Habbema
Journal:  Stat Med       Date:  2004-08-30       Impact factor: 2.373

Review 2.  Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors.

Authors:  F E Harrell; K L Lee; D B Mark
Journal:  Stat Med       Date:  1996-02-28       Impact factor: 2.373

3.  Hospital readmissions in patients with inflammatory bowel disease.

Authors:  Nyla Hazratjee; Markus Agito; Rocio Lopez; Bret Lashner; Maged K Rizk
Journal:  Am J Gastroenterol       Date:  2013-07       Impact factor: 10.864

4.  Regularization Paths for Generalized Linear Models via Coordinate Descent.

Authors:  Jerome Friedman; Trevor Hastie; Rob Tibshirani
Journal:  J Stat Softw       Date:  2010       Impact factor: 6.440

5.  Hospital strategies associated with 30-day readmission rates for patients with heart failure.

Authors:  Elizabeth H Bradley; Leslie Curry; Leora I Horwitz; Heather Sipsma; Yongfei Wang; Mary Norine Walsh; Don Goldmann; Neal White; Ileana L Piña; Harlan M Krumholz
Journal:  Circ Cardiovasc Qual Outcomes       Date:  2013-07

6.  Can readmissions to a geriatric medical unit be prevented?

Authors:  H Graham; B Livesley
Journal:  Lancet       Date:  1983-02-19       Impact factor: 79.321

7.  Predictors of 30-day readmission after subarachnoid hemorrhage.

Authors:  Mandeep Singh; James C Guth; Eric Liotta; Adam R Kosteva; Rebecca M Bauer; Shyam Prabhakaran; Neil Rosenberg; Bernard R Bendok; Matthew B Maas; Andrew M Naidech
Journal:  Neurocrit Care       Date:  2013-12       Impact factor: 3.210

8.  A multidisciplinary intervention to prevent the readmission of elderly patients with congestive heart failure.

Authors:  M W Rich; V Beckham; C Wittenberg; C L Leven; K E Freedland; R M Carney
Journal:  N Engl J Med       Date:  1995-11-02       Impact factor: 91.245

9.  Reasons for readmission after carotid endarterectomy.

Authors:  Aksharananda Rambachan; Timothy R Smith; Sujata Saha; Mark K Eskandari; Bernard R Bendok; John Y S Kim
Journal:  World Neurosurg       Date:  2013-08-20       Impact factor: 2.104

10.  Allocating scarce resources in real-time to reduce heart failure readmissions: a prospective, controlled study.

Authors:  Ruben Amarasingham; Parag C Patel; Kathleen Toto; Lauren L Nelson; Timothy S Swanson; Billy J Moore; Bin Xie; Song Zhang; Kristin S Alvarez; Ying Ma; Mark H Drazner; Usha Kollipara; Ethan A Halm
Journal:  BMJ Qual Saf       Date:  2013-07-31       Impact factor: 7.035

View more
  20 in total

1.  Implications of non-stationarity on predictive modeling using EHRs.

Authors:  Kenneth Jung; Nigam H Shah
Journal:  J Biomed Inform       Date:  2015-10-20       Impact factor: 6.317

2.  Augmenting community-level social determinants of health data with individual-level survey data.

Authors:  Min-Hyung Kim; Yiye Zhang; Jessica S Ancker
Journal:  AMIA Annu Symp Proc       Date:  2018-12-05

3.  Using Clinical Notes and Natural Language Processing for Automated HIV Risk Assessment.

Authors:  Daniel J Feller; Jason Zucker; Michael T Yin; Peter Gordon; Noémie Elhadad
Journal:  J Acquir Immune Defic Syndr       Date:  2018-02-01       Impact factor: 3.731

4.  How can Big Data Analytics Support People-Centred and Integrated Health Services: A Scoping Review.

Authors:  Timo Schulte; Sabine Bohnet-Joschko
Journal:  Int J Integr Care       Date:  2022-06-16       Impact factor: 2.913

5.  Grappling with the Future Use of Big Data for Translational Medicine and Clinical Care.

Authors:  S Murphy; V Castro; K Mandl
Journal:  Yearb Med Inform       Date:  2017-09-11

6.  Beyond discrimination: A comparison of calibration methods and clinical usefulness of predictive models of readmission risk.

Authors:  Colin G Walsh; Kavya Sharman; George Hripcsak
Journal:  J Biomed Inform       Date:  2017-10-24       Impact factor: 6.317

7.  Transition Networks in a Cohort of Patients with Congestive Heart Failure: A Novel Application of Informatics Methods to Inform Care Coordination.

Authors:  J A Merrill; B M Sheehan; K M Carley; P D Stetson
Journal:  Appl Clin Inform       Date:  2015-09-02       Impact factor: 2.342

8.  Person-centred pharmaceutical care reduces emergency readmissions.

Authors:  Julia Blagburn; Ben Kelly-Fatemi; Nasima Akhter; Andy Husband
Journal:  Eur J Hosp Pharm       Date:  2015-10-01

9.  An external validation of models to predict the onset of chronic kidney disease using population-based electronic health records from Salford, UK.

Authors:  Paolo Fraccaro; Sabine van der Veer; Benjamin Brown; Mattia Prosperi; Donal O'Donoghue; Gary S Collins; Iain Buchan; Niels Peek
Journal:  BMC Med       Date:  2016-07-12       Impact factor: 8.775

10.  Global Health and Visa Policy Reform to Address Dangers of Hajj during Summer Seasons.

Authors:  Mohanad Aleeban; Tim K Mackey
Journal:  Front Public Health       Date:  2016-12-22
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.