Prediction using a randomized evaluation of data collection integrated through connected technologies (PREDICT): Design and rationale of a randomized trial of patients discharged from the hospital to home

Chalanda N. Evans, Kevin G. Volpp, Daniel Polsky, Dylan S. Small, Edward H. Kennedy, Kelsey Karpink, Rachel Djaraher, Nicole Mansi, Charles A.L. Rareshide, Mitesh S. Patel

Research output: Contribution to journalArticle

Abstract

Background: Hospital readmission prediction models often perform poorly. A critical limitation is that they use data collected up until the time of discharge but do not leverage information on patient behaviors at home after discharge. Methods: PREDICT is a two-arm, randomized trial comparing ways to use remotely-monitored patient activity levels after hospital discharge to improve hospital readmission prediction models. Patients are randomly assigned to use a wearable device or smartphone application to track physical activity data. The study collects also validated assessments on patient characteristics as well as disparate data on credit scores and medication adherence. Patients are followed for 6 months. We evaluate whether these data sources can improve prediction compared to standard modelling approaches. Conclusion: The PREDICT Trial tests a novel method of remotely-monitoring patient behaviors after hospital discharge. Findings from the trial could inform new ways to improve the identification of patients at high-risk for hospital readmission. Trial Registration: Clinicaltrials.gov Identifier: NCT02983812

Original languageEnglish (US)
Pages (from-to)53-56
Number of pages4
JournalContemporary Clinical Trials
Volume83
DOIs
StatePublished - Aug 1 2019
Externally publishedYes

Fingerprint

Technology
Patient Readmission
Medication Adherence
Information Storage and Retrieval
Physiologic Monitoring
Exercise
Equipment and Supplies

Keywords

  • Health behaviors
  • Hospital readmission
  • Physical activity
  • Prediction models
  • Smartphones
  • Wearable devices

ASJC Scopus subject areas

  • Pharmacology (medical)

Cite this

Prediction using a randomized evaluation of data collection integrated through connected technologies (PREDICT) : Design and rationale of a randomized trial of patients discharged from the hospital to home. / Evans, Chalanda N.; Volpp, Kevin G.; Polsky, Daniel; Small, Dylan S.; Kennedy, Edward H.; Karpink, Kelsey; Djaraher, Rachel; Mansi, Nicole; Rareshide, Charles A.L.; Patel, Mitesh S.

In: Contemporary Clinical Trials, Vol. 83, 01.08.2019, p. 53-56.

Research output: Contribution to journalArticle

Evans, Chalanda N. ; Volpp, Kevin G. ; Polsky, Daniel ; Small, Dylan S. ; Kennedy, Edward H. ; Karpink, Kelsey ; Djaraher, Rachel ; Mansi, Nicole ; Rareshide, Charles A.L. ; Patel, Mitesh S. / Prediction using a randomized evaluation of data collection integrated through connected technologies (PREDICT) : Design and rationale of a randomized trial of patients discharged from the hospital to home. In: Contemporary Clinical Trials. 2019 ; Vol. 83. pp. 53-56.
@article{5c7a0a18133d49cb8098de6e258ea0bc,
title = "Prediction using a randomized evaluation of data collection integrated through connected technologies (PREDICT): Design and rationale of a randomized trial of patients discharged from the hospital to home",
abstract = "Background: Hospital readmission prediction models often perform poorly. A critical limitation is that they use data collected up until the time of discharge but do not leverage information on patient behaviors at home after discharge. Methods: PREDICT is a two-arm, randomized trial comparing ways to use remotely-monitored patient activity levels after hospital discharge to improve hospital readmission prediction models. Patients are randomly assigned to use a wearable device or smartphone application to track physical activity data. The study collects also validated assessments on patient characteristics as well as disparate data on credit scores and medication adherence. Patients are followed for 6 months. We evaluate whether these data sources can improve prediction compared to standard modelling approaches. Conclusion: The PREDICT Trial tests a novel method of remotely-monitoring patient behaviors after hospital discharge. Findings from the trial could inform new ways to improve the identification of patients at high-risk for hospital readmission. Trial Registration: Clinicaltrials.gov Identifier: NCT02983812",
keywords = "Health behaviors, Hospital readmission, Physical activity, Prediction models, Smartphones, Wearable devices",
author = "Evans, {Chalanda N.} and Volpp, {Kevin G.} and Daniel Polsky and Small, {Dylan S.} and Kennedy, {Edward H.} and Kelsey Karpink and Rachel Djaraher and Nicole Mansi and Rareshide, {Charles A.L.} and Patel, {Mitesh S.}",
year = "2019",
month = "8",
day = "1",
doi = "10.1016/j.cct.2019.06.018",
language = "English (US)",
volume = "83",
pages = "53--56",
journal = "Contemporary Clinical Trials",
issn = "1551-7144",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Prediction using a randomized evaluation of data collection integrated through connected technologies (PREDICT)

T2 - Design and rationale of a randomized trial of patients discharged from the hospital to home

AU - Evans, Chalanda N.

AU - Volpp, Kevin G.

AU - Polsky, Daniel

AU - Small, Dylan S.

AU - Kennedy, Edward H.

AU - Karpink, Kelsey

AU - Djaraher, Rachel

AU - Mansi, Nicole

AU - Rareshide, Charles A.L.

AU - Patel, Mitesh S.

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Background: Hospital readmission prediction models often perform poorly. A critical limitation is that they use data collected up until the time of discharge but do not leverage information on patient behaviors at home after discharge. Methods: PREDICT is a two-arm, randomized trial comparing ways to use remotely-monitored patient activity levels after hospital discharge to improve hospital readmission prediction models. Patients are randomly assigned to use a wearable device or smartphone application to track physical activity data. The study collects also validated assessments on patient characteristics as well as disparate data on credit scores and medication adherence. Patients are followed for 6 months. We evaluate whether these data sources can improve prediction compared to standard modelling approaches. Conclusion: The PREDICT Trial tests a novel method of remotely-monitoring patient behaviors after hospital discharge. Findings from the trial could inform new ways to improve the identification of patients at high-risk for hospital readmission. Trial Registration: Clinicaltrials.gov Identifier: NCT02983812

AB - Background: Hospital readmission prediction models often perform poorly. A critical limitation is that they use data collected up until the time of discharge but do not leverage information on patient behaviors at home after discharge. Methods: PREDICT is a two-arm, randomized trial comparing ways to use remotely-monitored patient activity levels after hospital discharge to improve hospital readmission prediction models. Patients are randomly assigned to use a wearable device or smartphone application to track physical activity data. The study collects also validated assessments on patient characteristics as well as disparate data on credit scores and medication adherence. Patients are followed for 6 months. We evaluate whether these data sources can improve prediction compared to standard modelling approaches. Conclusion: The PREDICT Trial tests a novel method of remotely-monitoring patient behaviors after hospital discharge. Findings from the trial could inform new ways to improve the identification of patients at high-risk for hospital readmission. Trial Registration: Clinicaltrials.gov Identifier: NCT02983812

KW - Health behaviors

KW - Hospital readmission

KW - Physical activity

KW - Prediction models

KW - Smartphones

KW - Wearable devices

UR - http://www.scopus.com/inward/record.url?scp=85068260888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068260888&partnerID=8YFLogxK

U2 - 10.1016/j.cct.2019.06.018

DO - 10.1016/j.cct.2019.06.018

M3 - Article

C2 - 31265915

AN - SCOPUS:85068260888

VL - 83

SP - 53

EP - 56

JO - Contemporary Clinical Trials

JF - Contemporary Clinical Trials

SN - 1551-7144

ER -