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

NCT03752489 | Unknown Phase 2 DMC

• 1 other identifier: 19-426246
• Study Type: interventional
• Target: 51,645
• Locations: 0 countries
• Sites: N/A

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.

Conditions

Sepsis; Severe Sepsis; Septic Shock

Keywords

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

Outcome Measures

Primary Outcomes (1)

• In-hospital SIRS-based mortality

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

  Through study completion, an average of 8 months

Study Arms (2)

Fluid treatment-specific algorithm

EXPERIMENTAL

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

Diagnostic Test: Treatment-specific InSight

Standard InSight

ACTIVE COMPARATOR

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

Diagnostic Test: InSight

Interventions

Treatment-specific InSight DIAGNOSTIC_TEST

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.

Fluid treatment-specific algorithm

InSight DIAGNOSTIC_TEST

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

Standard InSight

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• Under age 18

Sponsors & Collaborators

• Dascena: lead

Related Publications (3)

• 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: 27699003 BACKGROUND

• 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: 29435343 BACKGROUND

• 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.

  PMID: 29374661 BACKGROUND

MeSH Terms

Conditions

Sepsis; Shock, Septic; Disease

Condition Hierarchy (Ancestors)

Infections; Systemic Inflammatory Response Syndrome; Inflammation; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Shock

Study Officials

• Qingqing Mao, PhD

  Dascena, Inc.

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Qingqing Mao, PhD

CONTACT

5108269508; qmao@dascena.com

Study Design

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

Study Record Dates

• First Submitted: November 21, 2018
• First Posted: November 26, 2018
• Study Start: April 1, 2022
• Primary Completion: March 31, 2024
• Study Completion: March 31, 2024
• Last Updated: September 23, 2021

Record last verified: 2021-09