Clinical Validity of an AI-Based Biological Signal Analysis Software Vital-PICASO for Predicting the Risk of Cardiac Arrest Within 24hrs Using Vital Sign (SBP, DBP, HR, RR, BT, SpO2) From General Ward Inpatients; A Retrospective, Single-Center, Single-Arm, Superiority-Confirmatory Clinical Trial
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 387
- 试验地点
- 1
- 主要终点
- AUROC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Including SpO2
研究概览
简要总结
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.
详细描述
This study is a retrospective, single-center, single-arm, superiority-confirmatory clinical performance study conducted at Seoul National University Hospital.
Data Source and Study Population
Electronic medical records will be reviewed to identify patients aged 19 years or older who were admitted to a general ward for at least 12 hours between January 1, 2023, and May 31, 2025. Data previously used in the development of the investigational software will be excluded.
The clinical variables collected from eligible records include systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, body temperature, oxygen saturation when available, and the corresponding measurement times. Additional variables include the occurrence, timing, and location of in-hospital cardiac arrest, month and year of birth, sex, height and weight when available, do-not-resuscitate status, date of admission to the general ward, and clinical department.
Data Selection
研究设计
- 研究类型
- Observational
- 观察模型
- Case Control
- 时间视角
- Retrospective
入排标准
- 年龄范围
- 19 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •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
- •Cardiac Arrest-Negative Group
- •No cardiac arrest or other predefined clinical deterioration occurred during the selected general ward admission period
- •The patient was selected from the same general ward as patients in the cardiac arrest-positive group
- •Vital-sign data were available from a time period comparable with the cardiac arrest-positive group or within 72 hours after admission to the general ward
- •Only one eligible data segment was included per patient
- •The data were considered appropriate for inclusion in the cardiac arrest-negative group by the investigator
排除标准
- •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
结局指标
主要结局
AUROC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Including SpO2
时间窗: Up to 72 hours before the cardiac arrest or matched index time
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.
AUROC for 24-Hour Cardiac Arrest Prediction Using Vital Signs Excluding SpO2
时间窗: Up to 72 hours before the cardiac arrest or matched index time
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.
次要结局
- 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)
- F1 Score for 24-Hour Cardiac Arrest Prediction(Up to 72 hours before the cardiac arrest or matched index time)