Back to results

Inpatient Mortality Prediction Algorithm Clinical Trial (IMPACT) (IMPACT)

Primary Purpose

Decompensation, Heart, Decompensation; Heart, Congestive, Death

Status

Withdrawn

Phase

Not Applicable

Locations

United States

Study Type

Interventional

Intervention

Patient mortality prediction

About this trial

This is an interventional diagnostic trial for Decompensation, Heart focused on measuring Dascena, patient mortality, machine learning, algorithm, diagnostic

Eligibility Criteria

18 Years - undefined (Adult, Older Adult)All SexesDoes not accept healthy volunteers

Inclusion Criteria:

All adult patients admitted to the participating units will be eligible.

Exclusion Criteria:

All patients younger than 18 years of age will be excluded.

Sites / Locations

UCSF Moffit-Long Hospital

Arms of the Study

Arm 1

Arm 2

Arm Type

Experimental

No Intervention

Arm Label

Prediction Algorithm

Control

Arm Description

Outcomes

Primary Outcome Measures

In-hospital mortality

Secondary Outcome Measures

Hospital length of stay

Full Information

NCT ID

NCT03212534

First Posted

July 6, 2017

Last Updated

September 20, 2021

Sponsor

Dascena

Collaborators

University of California, San Francisco

1. Study Identification

Unique Protocol Identification Number

NCT03212534

Brief Title

Inpatient Mortality Prediction Algorithm Clinical Trial (IMPACT)

Acronym

IMPACT

Official Title

A Randomized Clinical Trial of a Mortality Prediction Algorithm

Study Type

Interventional

2. Study Status

Record Verification Date

September 2021

Overall Recruitment Status

Withdrawn

Why Stopped

This trial did not start. No participants enrolled

Study Start Date

July 2017 (Anticipated)

Primary Completion Date

October 2017 (Anticipated)

Study Completion Date

October 2017 (Anticipated)

3. Sponsor/Collaborators

Responsible Party, by Official Title

Sponsor

Name of the Sponsor

Dascena

Collaborators

University of California, San Francisco

4. Oversight

Studies a U.S. FDA-regulated Drug Product

Studies a U.S. FDA-regulated Device Product

5. Study Description

Brief Summary

Through the mapping of retrospective patient data into a discrete multidimensional space, a novel algorithm for homeostatic analysis, was built to make outcome predictions. In this prospective study, the ability of the algorithm to predict patient mortality and influence clinical outcomes, will be investigated.

6. Conditions and Keywords

Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study

Decompensation, Heart, Decompensation; Heart, Congestive, Death

Keywords

Dascena, patient mortality, machine learning, algorithm, diagnostic

7. Study Design

Primary Purpose

Diagnostic

Study Phase

Not Applicable

Interventional Study Model

Parallel Assignment

Masking

None (Open Label)

Allocation

Randomized

Enrollment

0 (Actual)

8. Arms, Groups, and Interventions

Arm Title

Prediction Algorithm

Arm Type

Experimental

Arm Title

Control

Arm Type

No Intervention

Intervention Type

Other

Intervention Name(s)

Patient mortality prediction

Intervention Description

Healthcare provider is notified of patient mortality prediction.

Primary Outcome Measure Information:

Title

In-hospital mortality

Time Frame

Through study completion, an average of 30 days

Secondary Outcome Measure Information:

Title

Hospital length of stay

Time Frame

Through study completion, an average of 30 days

Other Pre-specified Outcome Measures:

Title

Hospital readmission

Time Frame

Through study completion, an average of 30 days

Title

ICU length of stay

Time Frame

Through study completion, an average of 30 days

10. Eligibility

Sex

All

Minimum Age & Unit of Time

18 Years

Accepts Healthy Volunteers

Eligibility Criteria

Inclusion Criteria: All adult patients admitted to the participating units will be eligible. Exclusion Criteria: All patients younger than 18 years of age will be excluded.

Overall Study Officials:

First Name & Middle Initial & Last Name & Degree

David Shimabukuro

Organizational Affiliation

University of California, San Francisco

Official's Role

Principal Investigator

Facility Information:

Facility Name

UCSF Moffit-Long Hospital

City

San Francisco

State/Province

California

ZIP/Postal Code

94143

Country

United States

12. IPD Sharing Statement

Citations:

PubMed Identifier

28638239

Citation

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.

Results Reference

background

PubMed Identifier

27253619

Citation

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.

Results Reference

background

PubMed Identifier

27026611

Citation

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.

Results Reference

background

PubMed Identifier

27699003

Citation

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.

Results Reference

background

Learn more about this trial

Inpatient Mortality Prediction Algorithm Clinical Trial (IMPACT)

We'll reach out to this number within 24 hrs