Predictive Analytics Monitoring for Clinical Deterioration in Cardiology

(PM-IMPACCT Trial)

Age: Any Age

Sex: Any

Trial Phase: Academic

Sponsor: Jamieson Bourque, MD

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to determine if a special computer display called CoMET can help doctors and nurses improve the health of hospitalized heart patients. The CoMET display provides predictions about a patient's health based on vital signs and other data, enabling the medical team to act quickly if issues arise. The trial will compare heart patients who receive this additional information with those receiving regular care. Patients in specific cardiology beds at UVa Hospital are eligible to participate. As an unphased trial, this study allows patients to contribute to innovative research that could enhance heart care for future patients.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this predictive analytics monitoring is safe for cardiology patients?

Research has shown that the CoMET Display, a tool for predicting health changes, has been integrated into hospitals to enhance patient care. This tool analyzes real-time patient information, such as vital signs and lab results, to predict potential condition deterioration. Studies have found that continuous monitoring benefits patients with heart problems, enabling healthcare teams to respond swiftly if necessary.

Currently, no specific evidence indicates harmful effects from using the CoMET Display. As a software tool that displays patient data, it does not interact with the body like drugs or surgery, suggesting a low risk of physical harm. The primary goal is to improve the speed and effectiveness with which healthcare teams address potential issues safely. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Most treatments for monitoring clinical deterioration in cardiology involve traditional observation and periodic checks. However, the CoMET Display is unique because it provides a continuous predictive monitoring score that forecasts potential events. This real-time display of risk scores can be shared daily with the care team during rounds, enhancing proactive decision-making. Researchers are excited about this approach because it could significantly improve patient outcomes by allowing timely interventions before clinical deterioration occurs.

What evidence suggests that the CoMET Display is effective for improving patient outcomes in cardiology?

In this trial, participants will join one of two groups. One group will use the CoMET Display, which studies have shown can predict when heart patients might worsen by using real-time data from bedside monitors. This system alerts doctors early, enabling quick action when treatments are most effective. Research indicates that CoMET could improve heart care outcomes by providing a visual tool that displays risk scores. In other settings, such as a children's intensive care unit, CoMET has effectively guided care decisions. The tool's ability to combine important health data into easy-to-understand scores makes it promising for enhancing heart patient care. The other group will receive standard CoMET device training but will not have access to the display or predictive monitoring scores. ^{1 2 3 6 7}

Who Is on the Research Team?

Jamieson M Bourque, MD

Principal Investigator

University of Virginia Health System

Are You a Good Fit for This Trial?

This trial is for adult patients staying in a specific cardiology and cardiovascular surgery ward at UVa Hospital. They must be assigned to a bed that's part of the study's randomized clusters. There are no exclusion criteria, so all eligible patients in these beds can participate.

Inclusion Criteria

Assigned for clinical purposes to a bed which is part of a randomized cluster

Exclusion Criteria

Not applicable.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Training

Clinicians receive standard CoMET device training

2 weeks

Intervention

Cluster-randomized control trial with intervention and control groups, using predictive display and standard monitoring

22 months

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• CoMET Display

Trial Overview The trial is testing if showing predictive analytics on monitors (CoMET Display) helps improve patient outcomes in acute care cardiology wards. It compares standard monitoring with and without the additional predictive display over a 22-month period.

How Is the Trial Designed?

Group I: CoMET Display Experimental Treatment 1 Intervention

Display of Continuous Monitoring of Event Trajectories (CoMET) predictive monitoring score, with standard CoMET device training.Risk scores will also be presented daily during rounds to members of the care team.

Group II: No Display Active Control 1 Intervention

Standard CoMET device training but no display or presentation of predictive monitoring score.

Who Is Running the Clinical Trial?

Jamieson Bourque, MD

Lead Sponsor

Trials

1

Recruited

10,400+

Advanced Medical Predictive Devices, Diagnostics and Displays, Inc.

Collaborator

Trials

1

Recruited

10,400+

Published Research Related to This Trial

The MEWS++ machine learning model can predict patient deterioration or death up to six hours in advance, significantly improving early detection compared to traditional methods, which rely on a limited set of variables.

In a study of 96,645 patients, the random forest model outperformed the traditional Modified Early Warning Score (MEWS) with a sensitivity increase of 37% and an AUC-ROC improvement of 14%, demonstrating its potential for timely clinical intervention.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model. Kia, A., Timsina, P., Joshi, HN., et al.[2020]

The Intensive care Warning Index (I-WIN) model, developed using machine learning on data from 488 infants with congenital heart disease, can predict clinical deterioration up to 8 hours in advance with high accuracy (AUC of 0.92 at 4 hours before deterioration).

This model represents a significant shift towards using data-driven approaches for risk prediction in critical care, potentially improving patient outcomes by allowing timely interventions based on routinely collected electronic health record data.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records. Ruiz, VM., Goldsmith, MP., Shi, L., et al.[2022]

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC8285742/

Predictive Monitoring–Impact in Acute Care Cardiology ... We present a dynamic, visual, predictive analytics monitoring tool that integrates real-time bedside telemetric physiologic data into robust clinical models.

2. digital.ahrq.gov digital.ahrq.gov/program-overview/research-stories/continuous-predictive-analytics-monitoring-improve-care-risk

Continuous Predictive Analytics Monitoring to Improve Care ... The monitoring system gives providers an earlier window of treatment when intervention is most effective. Drs. Keim-Malpass, Jamieson Bourque, and their ...

3. clinicaltrials.gov clinicaltrials.gov/study/NCT04359641

Predictive Monitoring - IMPact in Acute Care Cardiology Trial Hypothesis: display of predictive analytics monitoring on acute care cardiology wards improves patient outcomes and is cost-effective to the health system.

4. medrxiv.org medrxiv.org/content/10.1101/2022.06.03.22275909v1.full.pdf

the cumulative COMET score 8 In these settings, risk is displayed as the 'CoMET'. ('Continuous Monitoring of Event Trajectories') score. In addition to parameters ...

5. americandatanetwork.com americandatanetwork.com/clinical-data-abstraction/transforming-cardiology-programs-with-data-driven-decisions/

Transforming Cardiology Programs with Data-Driven ... Furthermore, in UVA's pediatric intensive care unit, the Continuous Monitoring of Event Trajectories (CoMET) system employs real-time data ...

6. digital.ahrq.gov digital.ahrq.gov/ahrq-funded-projects/predictive-monitoring-impact-real-time-predictive-monitoring-acute-care

IMPact of Real-Time Predictive Monitoring in Acute Care ... This research evaluates an artificial intelligence risk predictive tool called CoMET that uses visual outputs of patient data to serve as an early warning ...

7. sciencedirect.com sciencedirect.com/science/article/pii/S2666520424003138

Incidence of cardiac arrest following implementation of a ... Model risk estimates are calculated every 15 min and displayed using the Continuous Monitoring of Event Trajectories (CoMET®) (Nihon Kohden Digital Health ...