Clinical Validation of Vital-PICASO for Predicting Hypoxia Within 24 Hours in General Ward Inpatients

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 hypoxia 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 will be retrospectively reviewed. Hypoxia will be evaluated using two separate reference-standard criteria: oxygen saturation below 94% and administration of oxygen at 4 L/min or more. Eligible hypoxia-positive and hypoxia-negative datasets will be randomly selected. The selected vital-sign datasets will be analyzed using Vital-PICASO while the device operator is blinded to the reference-standard classification. The software-generated hypoxia risk scores will be compared with the reference-standard classifications to evaluate predictive performance. Because the study uses previously collected medical records, there is no direct participant contact and the software results will not affect patient care.

Inclusion Criteria: 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 * Clinical data not previously used in the development of Vital-PICASO SpO2-Based Hypoxia-Positive Group * Hypoxia occurred in a general ward * Hypoxia was defined as oxygen saturation below 94% * Vital-sign data were available for up to 72 hours before the hypoxia event * If hypoxia occurred within 24 hours after admission or transfer to the general ward, all available vital-sign data recorded before the event were included * If multiple eligible hypoxia events occurred during the data collection period, only the first eligible event was included for this criterion SpO2-Based Hypoxia-Negative Group * No hypoxia occurred during the selected general ward admission * Data were randomly selected from the same general wards as the corresponding hypoxia-positive group * Vital-sign data were available from a time interval comparable with the hypoxia-event reference time or for up to 72 hours after admission to the general ward * Only one eligible data interval was included per patient Oxygen-Treatment-Based Hypoxia-Positive Group * Hypoxia occurred in a general ward * Hypoxia was defined as oxygen administration at a flow rate of 4 L/min or more * Vital-sign data were available for up to 72 hours before the initiation of oxygen administration * If oxygen administration began within 24 hours after admission or transfer to the general ward, all available vital-sign data recorded before the event were included * If multiple eligible events occurred during the data collection period, only the first eligible event was included for this criterion Oxygen-Treatment-Based Hypoxia-Negative Group * No hypoxia occurred during the selected general ward admission * Data were randomly selected from the same general wards as the corresponding hypoxia-positive group * Vital-sign data were available from a time interval comparable with the hypoxia-event reference time or for up to 72 hours after admission to the general ward * Only one eligible data interval was included per patient Exclusion Criteria: * Hypoxia occurred outside a general ward * The patient had chronic obstructive pulmonary disease * A do-not-resuscitate order was in effect at the time the clinical data were recorded * The patient was pregnant or within 3 months after delivery at the time the clinical data were recorded * The data were considered inappropriate for the study by the principal investigator