Clinical Validation of Vital-PICASO for Predicting Cardiac Arrest Within 24 Hours

NCT07742943 | Completed

• 1 other identifier: HA-PI-03
• Study Type: observational
• Target: 387
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this retrospective study is to evaluate the clinical performance of Vital-PICASO, an artificial intelligence-based biological signal analysis software designed to predict the risk of in-hospital cardiac arrest within 24 hours using vital-sign data collected from adult general ward inpatients. Electronic medical record data from patients aged 19 years or older who were admitted to a general ward at Seoul National University Hospital will be retrospectively reviewed. Vital-sign variables include systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, body temperature, and, when available, oxygen saturation. Eligible data will be classified as cardiac arrest-positive or cardiac arrest-negative according to predefined reference-standard criteria. The blinded datasets will then be analyzed using Vital-PICASO, and the software-generated risk scores will be compared with the reference-standard classifications. Predictive performance will be evaluated separately using models that include oxygen saturation and models that do not include oxygen saturation.

Conditions

Heart Arrest

Keywords

In-Hospital Cardiac Arrest; Cardiac Arrest Prediction; Vital-PICASO; Artificial Intelligence; Biological Signal Analysis Software; Early Warning System; Vital Signs; General Ward Inpatients; Oxygen Saturation

Outcome Measures

Primary Outcomes (2)

• AUROC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Including SpO2

  The area under the receiver operating characteristic curve (AUROC) will be calculated by comparing the cardiac arrest risk scores generated by Vital-PICASO using systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, body temperature, and oxygen saturation with the reference-standard classification of in-hospital cardiac arrest. AUROC values range from 0.5 to 1.0, with higher values indicating better discrimination. Clinical performance will be compared with the prespecified reference AUROC of 0.7647. The performance criterion will be met if the lower bound of the 95% confidence interval for the difference between the Vital-PICASO AUROC and the reference AUROC is greater than 0.

  Up to 72 hours before the cardiac arrest or matched index time

• AUROC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Excluding SpO2

  The area under the receiver operating characteristic curve (AUROC) will be calculated by comparing the cardiac arrest risk scores generated by Vital-PICASO using systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature, without oxygen saturation, with the reference-standard classification of in-hospital cardiac arrest. AUROC values range from 0.5 to 1.0, with higher values indicating better discrimination. Clinical performance will be compared with the prespecified reference AUROC of 0.7647. The performance criterion will be met if the lower bound of the 95% confidence interval for the difference between the Vital-PICASO AUROC and the reference AUROC is greater than 0.

  Up to 72 hours before the cardiac arrest or matched index time

Secondary Outcomes (6)

• AUPRC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Including SpO2

  Up to 72 hours before the cardiac arrest or matched index time

• AUPRC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Excluding SpO2

  Up to 72 hours before the cardiac arrest or matched index time

• Threshold-Specific Classification Performance of Vital-PICASO

  Up to 72 hours before the cardiac arrest or matched index time

• Cardiac Arrest Prediction Performance by Time Interval Before the Index Time

  Prespecified intervals within 24 hours before the cardiac arrest or matched index time

• Cumulative Cardiac Arrest Prediction Performance Before the Index Time

  Cumulative intervals up to 24 hours before the cardiac arrest or matched index time

Other Outcomes (1)

• Additional Diagnostic Performance Measures of Vital-PICASO

  Up to 72 hours before the cardiac arrest or matched index time

Study Arms (2)

Cardiac Arrest-Positive Group

General ward inpatients with an eligible in-hospital cardiac arrest documented in the electronic medical record and followed by resuscitation involving cardiopulmonary resuscitation, defibrillation, or advanced life support.

Cardiac Arrest-Negative Group

General ward inpatients without cardiac arrest or other predefined clinical deterioration during the selected hospitalization and observation period.

Eligibility Criteria

• Age: 19 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The study population consists of adult patients aged 19 years or older who were admitted to a general ward at Seoul National University Hospital and had at least 12 hours of electronic medical record data available between January 1, 2023, and May 31, 2025. The retrospective study dataset includes patients with an eligible in-hospital cardiac arrest occurring in a general ward and patients without cardiac arrest or other predefined clinical deterioration during the selected general ward admission period.

You may qualify if:

• General Criteria
• Male or female patient aged 19 years or older at the time the clinical data were recorded
• Electronic medical record data available between January 1, 2023, and May 31, 2025
• Admission to a general ward for at least 12 hours
• Availability of the required vital-sign data, including systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, body temperature, and oxygen saturation when available
• Clinical data not previously used in the development of Vital-PICASO
• Cardiac Arrest-Positive Group
• In-hospital cardiac arrest occurred in a general ward
• Cardiac arrest was documented in the electronic medical record and was followed by at least one of the following resuscitation procedures:
• High-quality cardiopulmonary resuscitation
• Defibrillation
• Advanced life support
• Vital-sign data were available for up to 72 hours before the cardiac arrest
• If cardiac arrest occurred within 24 hours after admission to the general ward, all available vital-sign data recorded before the event were included
• If a patient experienced multiple cardiac arrest events during the study period, only the first eligible event was included

You may not qualify if:

• Cardiac arrest occurred outside a general ward
• A do-not-resuscitate order was in effect at the time of data collection
• Pregnancy at the time of data collection or within 3 months after delivery
• The data were considered inappropriate for the study by the investigator

Sponsors & Collaborators

• Huinno AIM: lead

Study Sites (1)

Seoul National University Hospital

Seoul, South Korea

Location

MeSH Terms

Conditions

Heart Arrest

Condition Hierarchy (Ancestors)

Heart Diseases; Cardiovascular Diseases

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 29, 2026
• First Posted: August 3, 2026
• Study Start: August 20, 2025
• Primary Completion: December 19, 2025
• Study Completion: December 19, 2025
• Last Updated: August 3, 2026

Record last verified: 2026-07

Data Sharing

• IPD Sharing: Will not share

Locations

KR (1)