10424 Participants Needed

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 GroupAll trial participants will receive the active study treatment (no placebo)

Trial Summary

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 data supports the effectiveness of the treatment CoMET Display for predicting clinical deterioration in cardiology?

The CoMET Display uses real-time data to predict clinical deterioration, and studies show it can identify risk spikes that indicate a higher chance of needing intensive care. This predictive monitoring has been shown to improve early detection of patient decline, potentially allowing for timely interventions.12345

Is the CoMET Display safe for use in humans?

The CoMET Display, a predictive monitoring tool, has been used in studies to predict clinical deterioration in hospital settings. While these studies focus on its effectiveness in identifying high-risk patients, they do not report any specific safety concerns related to its use in humans.13467

How does the CoMET Display treatment differ from other treatments for predicting clinical deterioration in cardiology?

The CoMET Display treatment is unique because it uses continuous predictive analytics monitoring, which relies on real-time data from ECG and other clinical assessments to predict clinical deterioration, unlike traditional methods that use static or intermittent data inputs. This approach allows for more personalized alert thresholds based on individual patient baselines, potentially improving early detection of deterioration.12589

What is the purpose of this trial?

Hypothesis: display of predictive analytics monitoring on acute care cardiology wards improves patient outcomes and is cost-effective to the health system.The investigators have developed and validated computational models for predicting key outcomes in adults, and a useful display has been developed, implemented and iteratively optimized. These models estimate risk of imminent patient deterioration using trends in vital signs, labs and cardiorespiratory dynamics derived from readily available continuous bedside monitoring. They are presented on LCD monitors using software called CoMET (Continuous Monitoring of Event Trajectories; AMP3D, Advanced Medical Predictive Devices, Diagnostics, and Displays, Charlottesville, VA)To test the impact on patient outcomes, the investigators propose a 22-month cluster-randomized control trial on the 4th floor of UVa Hospital, a medical-surgical floor for cardiology and cardiovascular surgery patients. Clinicians will receive standard CoMET device training. Three- to five-bed clusters will be randomized to intervention (predictive display plus standard monitoring) or control (standard monitoring alone) for two months at a time. In addition, risk scores for patients in the intervention clusters will be presented daily during rounds to members of the care team of physicians, residents, nurses, and other clinicians. Data on outcomes will be statistically compared between intervention and control clusters.

Research Team

JM

Jamieson M Bourque, MD

Principal Investigator

University of Virginia Health System

Eligibility Criteria

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

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

Treatment Details

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.
Participant Groups
2Treatment groups
Experimental Treatment
Active Control
Group I: CoMET DisplayExperimental Treatment1 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 DisplayActive Control1 Intervention
Standard CoMET device training but no display or presentation of predictive monitoring score.

Find a Clinic Near You

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+

Findings from Research

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.
Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records.Ruiz, VM., Goldsmith, MP., Shi, L., et al.[2022]
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.
MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model.Kia, A., Timsina, P., Joshi, HN., et al.[2020]

References

Towards development of alert thresholds for clinical deterioration using continuous predictive analytics monitoring. [2021]
Developing Clinical Risk Prediction Models for Worsening Heart Failure Events and Death by Left Ventricular Ejection Fraction. [2023]
Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records. [2022]
Predictive Monitoring-Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial. [2021]
MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model. [2020]
Predicting acute clinical deterioration with interpretable machine learning to support emergency care decision making. [2023]
A Trend-Based Early Warning Score Can Be Implemented in a Hospital Electronic Medical Record to Effectively Predict Inpatient Deterioration. [2023]
Cardiorespiratory dynamics measured from continuous ECG monitoring improves detection of deterioration in acute care patients: A retrospective cohort study. [2020]
Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards. [2022]
Unbiased ResultsWe believe in providing patients with all the options.
Your Data Stays Your DataWe only share your information with the clinical trials you're trying to access.
Verified Trials OnlyAll of our trials are run by licensed doctors, researchers, and healthcare companies.
Back to top
Terms of Service·Privacy Policy·Cookies·Security