Prediction of Patient Deterioration Using Machine Learning

Mass General Brigham

Status: Unknown

Conditions: Chronic Kidney Diseases; Asthma; Infection; Anticoagulants; Increased; Chronic Obstructive Pulmonary Disease; Atrial Fibrillation Rapid; Hypertensive Urgency; Heart Failure; Gout Flare

Treatments: Other: Traditional vital sign alarms versus the BioVitals Index vs the National Early Warning Score 2

Study type: Observational

Funder types: Other; Industry

Identifiers

NCT05045742

2017P002583d

Details and patient eligibility

About

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 patient deterioration throughout a patient's admission. This algorithm was then validated in a validation cohort.

Enrollment: 500 estimated patients

Sex: All

Ages: 18+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

Cared for in the Brigham and Women's Home Hospital study

Exclusion criteria

Incomplete continuous monitoring data

Trial design

500 participants in 2 patient groups

Training

Description:

A subset of patients that are used to train the machine learning algorithm.

Treatment:

Other: Traditional vital sign alarms versus the BioVitals Index vs the National Early Warning Score 2

Validation

Description:

A subset of patients that are "held back" and used to validate the algorithm's accuracy.

Treatment:

Other: Traditional vital sign alarms versus the BioVitals Index vs the National Early Warning Score 2