This retrospective study evaluated the clinical performance of Vital-PICASO, an artificial intelligence-based biological signal analysis software designed to predict the risk of hypotension within 24 hours using vital-sign data 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 were retrospectively reviewed. Hypotension was defined as systolic blood pressure below 90 mmHg. Eligible data were classified as hypotension-positive or hypotension-negative according to predefined reference-standard criteria.
Vital-PICASO was applied to the selected vital-sign datasets, and the software-generated hypotension risk scores were compared with the reference-standard classifications. Predictive performance was evaluated separately using data that included oxygen saturation and data that excluded oxygen saturation. Because the study used previously collected medical records, there was no direct participant contact and the software results were not used to guide patient care.
Inclusion Criteria:
General Criteria
Hypotension-Positive Group
Hypotension-Negative Group
Exclusion Criteria:
Adult general ward inpatient data with an eligible hypotension event, defined as systolic blood pressure below 90 mmHg, occurring in the general ward. Vital-sign data collected for up to 72 hours before the first eligible hypotension event were included. If hypotension occurred within 24 hours after admission or transfer to the general ward, all available vital-sign data recorded before the event were included, provided that at least 12 hours of data were available.
Adult general ward inpatient data from patients who did not experience hypotension during the selected general ward admission. Data were randomly selected from the same general wards as the hypotension-positive group and from a time interval comparable with the hypotension event reference time or from up to 72 hours after admission to the general ward. Only one eligible data interval was selected per patient.
Seoul, South Korea
Early Prediction of ICU Hypotension Using Machine Learning
Artificial Intelligence - to Predict and Prevent Hypotension During Surgery
External Validation of Prediction Algorithm Using Non-invasive Monitoring Device for Intraoperative Hypotension
Hypotension Prediction During Cardiac Surgery Postoperative Period
Hypotension Prediction Index in Postoperative Surgical Patients
Hypotension Prediction 2 Study in Cardiac Surgery and Postoperative ICU Admission
Ability of Hypotension Prediction Index to Predict Hypotension Events in Thoracic Surgery
Hypotension Prediction Index for Blood Pressure Management