A minority of symptomatic individuals (5-10%) develop severe disease characterised by a vascular leakage syndrome which can then lead to cardiovascular decompensation and death. Close monitoring of clinical status and vital signs allows for the identification of patients at an increased risk of progression.
In this prospective observational study, researcher investigated performance of a non-invasive wearable utilising photoplethysmography (PPG), to provide real-time risk prediction in hospitalised individuals. Using a multi-modal transformer approach, 10-min PPG waveform segments and basic clinical data (age, sex, clinical features on admission) were used as features to continuously forecast clinical state 2 h ahead.
Prediction of low-risk states, defined by NEWS2 and mSOFA < 6, was associated with an area under the precision-recall curve of 0.67 and an area under the receiver operator curve of 0.83. Implementation of such interventions could provide cost-effective triage and clinical care in dengue, offering opportunities for safe ambulatory patient management.
【MORE】