Back to results

Unsupervised Machine Learning for Clustering of Septic Patients to Determine Optimal Treatment

Primary Purpose

Sepsis, Severe Sepsis, Septic Shock

Status

Not yet recruiting

Phase

Phase 2

Locations

Study Type

Interventional

Intervention

Treatment-specific InSight

InSight

About this trial

This is an interventional diagnostic trial for Sepsis focused on measuring Dascena, machine learning, fluid administration, clustering algorithm, mortality, diagnostic

Eligibility Criteria

18 Years - undefined (Adult, Older Adult)All SexesAccepts Healthy Volunteers

Inclusion Criteria:

All adults above age 18 who are a member of one of the clinical subpopulations studied in this trial are eligible to participate in the study.

Exclusion Criteria:

Under age 18

Sites / Locations

Arms of the Study

Arm 1

Arm 2

Arm Type

Experimental

Active Comparator

Arm Label

Fluid treatment-specific algorithm

Standard InSight

Arm Description

The experimental arm will involve patients monitored by the fluid treatment-customized version of InSight.

The control arm will involve patients monitored with the standard, non-treatment specific version of InSight.

Outcomes

Primary Outcome Measures

In-hospital SIRS-based mortality

Mortality attributed to patients meeting two or more SIRS criteria at some point during their stay

Secondary Outcome Measures

Full Information

NCT ID

NCT03752489

First Posted

November 21, 2018

Last Updated

September 17, 2021

Sponsor

Dascena

1. Study Identification

Unique Protocol Identification Number

NCT03752489

Brief Title

Unsupervised Machine Learning for Clustering of Septic Patients to Determine Optimal Treatment

Official Title

Unsupervised Machine Learning for Clustering of Septic Patients to Determine Optimal Treatment

Study Type

Interventional

2. Study Status

Record Verification Date

September 2021

Overall Recruitment Status

Not yet recruiting

Study Start Date

April 1, 2022 (Anticipated)

Primary Completion Date

March 31, 2024 (Anticipated)

Study Completion Date

March 31, 2024 (Anticipated)

3. Sponsor/Collaborators

Responsible Party, by Official Title

Sponsor

Name of the Sponsor

Dascena

4. Oversight

Studies a U.S. FDA-regulated Drug Product

Studies a U.S. FDA-regulated Device Product

Data Monitoring Committee

Yes

5. Study Description

Brief Summary

The focus of this study will be to conduct a prospective, randomized controlled trial (RCT) at Cape Regional Medical Center (CRMC), Oroville Hospital (OH), and UCSF Medical Center (UCSF) in which a fluid treatment-specific algorithm will be applied to EHR data for the detection of severe sepsis. For patients determined to have a high risk of severe sepsis, the algorithm will generate automated voice, telephone notification to nursing staff at CRMC, OH, and UCSF. The algorithm's performance will be measured by analysis of the primary endpoint, reductions in in-hospital mortality.

6. Conditions and Keywords

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

Sepsis, Severe Sepsis, Septic Shock

Keywords

Dascena, machine learning, fluid administration, clustering algorithm, mortality, diagnostic

7. Study Design

Primary Purpose

Diagnostic

Study Phase

Phase 2

Interventional Study Model

Parallel Assignment

Masking

ParticipantCare ProviderInvestigator

Allocation

Randomized

Enrollment

51645 (Anticipated)

8. Arms, Groups, and Interventions

Arm Title

Fluid treatment-specific algorithm

Arm Type

Experimental

Arm Description

The experimental arm will involve patients monitored by the fluid treatment-customized version of InSight.

Arm Title

Standard InSight

Arm Type

Active Comparator

Arm Description

The control arm will involve patients monitored with the standard, non-treatment specific version of InSight.

Intervention Type

Diagnostic Test

Intervention Name(s)

Treatment-specific InSight

Intervention Description

The InSight algorithm which draws information from a patient's electronic health record (EHR) to predict the onset of severe sepsis, and in this study will be customized to differentiate between clusters of patients who respond similarly to fluids treatment according to the nature of their disease progression.

Intervention Type

Diagnostic Test

Intervention Name(s)

InSight

Intervention Description

The non-customized InSight algorithm which draws information from a patient's electronic health record (EHR) to predict the onset of severe sepsis.

Primary Outcome Measure Information:

Title

In-hospital SIRS-based mortality

Description

Mortality attributed to patients meeting two or more SIRS criteria at some point during their stay

Time Frame

Through study completion, an average of 8 months

10. Eligibility

Sex

All

Minimum Age & Unit of Time

18 Years

Accepts Healthy Volunteers

Eligibility Criteria

Inclusion Criteria: All adults above age 18 who are a member of one of the clinical subpopulations studied in this trial are eligible to participate in the study. Exclusion Criteria: Under age 18

Central Contact Person:

First Name & Middle Initial & Last Name or Official Title & Degree

Qingqing Mao, PhD

Phone

5108269508

qmao@dascena.com

Overall Study Officials:

First Name & Middle Initial & Last Name & Degree

Qingqing Mao, PhD

Organizational Affiliation

Dascena, Inc.

Official's Role

Principal Investigator

12. IPD Sharing Statement

Citations:

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

PubMed Identifier

29435343

Citation

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.

Results Reference

background

PubMed Identifier

29374661

Citation

Mao Q, Jay M, Hoffman JL, Calvert J, Barton C, Shimabukuro D, Shieh L, Chettipally U, Fletcher G, Kerem Y, Zhou Y, Das R. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ Open. 2018 Jan 26;8(1):e017833. doi: 10.1136/bmjopen-2017-017833.

Results Reference

background

Learn more about this trial

Unsupervised Machine Learning for Clustering of Septic Patients to Determine Optimal Treatment

We'll reach out to this number within 24 hrs