NCT04005001

Brief Summary

Machine learning is a powerful method to create clinical decision support (CDS) tools, when training labels reflect the desired alert behavior. In our Phase I work for this project, we developed HindSight, an encoding software that was designed to examine discharged patients' electronic health records (EHRs), identify clinicians' sepsis treatment decisions and patient outcomes, and pass those labeled outcomes and treatment decisions to an online algorithm for retraining of our machine-learning-based CDS tool for real-time sepsis alert notification, InSight. HindSight improved the performance of InSight sepsis alerts in retrospective work. In this study, we propose to assess the clinical utility of HindSight by conducting a multicenter prospective randomized controlled trial (RCT) for more accurate sepsis alerts.

Trial Health

43
At Risk

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
37,986

participants targeted

Target at P75+ for phase_2 sepsis

Timeline
Completed

Started Sep 2021

Shorter than P25 for phase_2 sepsis

Geographic Reach
1 country

3 active sites

Status
unknown

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

First Submitted

Initial submission to the registry

June 28, 2019

Completed
4 days until next milestone

First Posted

Study publicly available on registry

July 2, 2019

Completed
2.2 years until next milestone

Study Start

First participant enrolled

September 25, 2021

Completed
11 months until next milestone

Primary Completion

Last participant's last visit for primary outcome

August 31, 2022

Completed
Same day until next milestone

Study Completion

Last participant's last visit for all outcomes

August 31, 2022

Completed
Last Updated

May 3, 2022

Status Verified

April 1, 2022

Enrollment Period

11 months

First QC Date

June 28, 2019

Last Update Submit

April 27, 2022

Conditions

SepsisSevere SepsisSeptic Shock

Keywords

SepsisMachine learning algorithmClinical decision support

Outcome Measures

Primary Outcomes (1)

  • Rate of reduction in false alerts

    The primary outcome measure of interest will be false alert reduction. Successful completion of Aim 1 will be demonstrated by a positive predictive value (PPV) in a live clinical setting for which the lower bound of the 95% confidence interval meets or exceeds the benchmark from prior retrospective studies. Meeting the retrospective PPV benchmark indicates that prospective CDS quality reflects retrospective CDS quality, and is sufficiently high to reduce alarm fatigue and improve clinical utility. Success of Aim 2 is contingent upon achieving a 15% relative reduction in false alerts when comparing between the two treatment arms (p \< 0.05; Fisher's Exact Test).

    Through study completion, human subjects involvement will occur for an average of eight months

Study Arms (2)

Experimental

EXPERIMENTAL

The experimental arm will involve patients monitored by HindSight.

Other: HindSight

Control

ACTIVE COMPARATOR

The control arm will involve patients monitored by InSight.

Other: InSight

Interventions

HindSightOTHER

HindSight will examine the dynamic trends of clinical measurements taken from a patient's EHR and analyzes correlations between vital signs to alert for the onset of sepsis.This machine learning based tool is optimized by encoder and utilizes periodic retraining to improve its performance over time.

Also known as: HindSight-Clinical decision support (CDS) system for sepsis alert notification
Experimental
InSightOTHER

Compared to the ability of the InSight software's recognition of sepsis onset to HindSight's performance. The study determines if the HindSight software has equivalent or better performance than the InSight software.

Control

Eligibility Criteria

Age18 Years+
Sexall
Healthy VolunteersYes
Age GroupsAdult (18-64), Older Adult (65+)

You may qualify if:

  • During the study period, all patients over the age of 18 presenting to the emergency department or admitted to an inpatient unit at the participating facilities will automatically be enrolled in the study, until the enrollment target for the study is met

You may not qualify if:

  • Patients under the age of 18
  • Prisoners

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (3)

Baystate Health

Springfield, Massachusetts, 01199, United States

RECRUITING

Cooper University Health Care

Camden, New Jersey, 08103, United States

RECRUITING

Cape Regional Medical Center

Cape May, New Jersey, 08210, United States

RECRUITING

Related Publications (5)

  • Desautels T, Calvert J, Hoffman J, Mao Q, Jay M, Fletcher G, Barton C, Chettipally U, Kerem Y, Das R. Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting. Biomed Inform Insights. 2017 Jun 12;9:1178222617712994. doi: 10.1177/1178222617712994. eCollection 2017.

    PMID: 28638239BACKGROUND

  • Calvert J, Mao Q, Rogers AJ, Barton C, Jay M, Desautels T, Mohamadlou H, Jan J, Das R. A computational approach to mortality prediction of alcohol use disorder inpatients. Comput Biol Med. 2016 Aug 1;75:74-9. doi: 10.1016/j.compbiomed.2016.05.015. Epub 2016 May 24.

    PMID: 27253619BACKGROUND

  • Calvert JS, Price DA, Barton CW, Chettipally UK, Das R. Discharge recommendation based on a novel technique of homeostatic analysis. J Am Med Inform Assoc. 2017 Jan;24(1):24-29. doi: 10.1093/jamia/ocw014. Epub 2016 Mar 28.

    PMID: 27026611BACKGROUND

  • Calvert J, Mao Q, Hoffman JL, Jay M, Desautels T, Mohamadlou H, Chettipally U, Das R. Using electronic health record collected clinical variables to predict medical intensive care unit mortality. Ann Med Surg (Lond). 2016 Sep 6;11:52-57. doi: 10.1016/j.amsu.2016.09.002. eCollection 2016 Nov.

    PMID: 27699003BACKGROUND

  • Shimabukuro DW, Barton CW, Feldman MD, Mataraso SJ, Das R. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res. 2017 Nov 9;4(1):e000234. doi: 10.1136/bmjresp-2017-000234. eCollection 2017.

    PMID: 29435343BACKGROUND

MeSH Terms

Conditions

SepsisShock, Septic

Interventions

peb protein, DrosophilaCompact DisksDrug Delivery Systems

Condition Hierarchy (Ancestors)

InfectionsSystemic Inflammatory Response SyndromeInflammationPathologic ProcessesPathological Conditions, Signs and SymptomsShock

Intervention Hierarchy (Ancestors)

Videodisc RecordingOptical Storage DevicesAudiovisual AidsEducational TechnologyTechnologyTechnology, Industry, and AgricultureTelevisionDrug TherapyTherapeutics

Study Officials

  • Jana Hoffman, PhD

    Dascena

    PRINCIPAL INVESTIGATOR

Central Study Contacts

Jana Hoffman, PhD

CONTACT

2158806619jana@dascena.com

Gina Barnes, MPH

CONTACT

2158806619gbarnes@dascena.com

Study Design

Study Type
interventional
Phase
phase 2
Allocation
RANDOMIZED
Masking
TRIPLE
Who Masked
PARTICIPANT, CARE PROVIDER, INVESTIGATOR
Purpose
OTHER
Intervention Model
PARALLEL
Sponsor Type
INDUSTRY
Responsible Party
SPONSOR

Study Record Dates

First Submitted

June 28, 2019

First Posted

July 2, 2019

Study Start

September 25, 2021

Primary Completion

August 31, 2022

Study Completion

August 31, 2022

Last Updated

May 3, 2022

Record last verified: 2022-04

Data Sharing

IPD Sharing
Will not share

Locations

US(3)