Prediction of 30-Day Readmission Using Machine Learning

Part of paid clinical trials in Boston, Massachusetts.

Sponsor
Brigham and Women's Hospital
Study ID
NCT04849312
Status
Completed

Conditions

Eligibility Criteria

Sex
ALL
Age
18 Years - N/A
Healthy Volunteers
Not accepted

Study Details

This is a retrospective observational study drawing on data from the Brigham and Women's Home Hospital database. Sociodemographic and clinic data from a training cohort were used to train a machine learning algorithm to predict the likelihood of 30-day readmission throughout a patient's admission. This algorithm was then validated in a validation cohort.

Key Dates

Start date
Jun 1, 2017
Status verified
Mar 2026
Primary completion
Oct 31, 2019
Completion
Nov 30, 2019

Study Design

Enrollment
372 participants (actual)

Arms

  • Arm: Training
    A subset of patients that are used to train the machine learning algorithm.
  • Arm: Validation
    A subset of patients that are "held back" and used to validate the algorithm's accuracy.

Primary Outcome Measure

30-Day Readmission [ yes / no ] [ Time Frame: From date of admission to 30-days post-discharge (31 to 54 days) ]

Locations (2)

FacilityCityStateZIPSite coordinators
Brigham and Women's Faulkner HospitalBostonMassachusetts02130-
Brigham and Women's HospitalBostonMassachusetts02115-

Find similar trials in Boston, MA

By condition
AsthmaCOPDHeart failure
By specialty
PulmonologyLung diseaseCardiologyHeart disease
By research site
Brigham and Women's Faulkner Hospital· Boston, MABrigham and Women's Hospital· Boston, MA

Related Studies