Applying Digital Technologies and AI in Virtual Hospitals: Exploring Global Innovative Models

Permanent URI for this collection

https://hdl.handle.net/10125/109916

Browse

Recent Submissions

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Remote Management of Atrial Fibrillation from a Virtual Ward
    (2025-01-07) Kazi, Saif-Ur-Rehman; Nunan, Joseph; Williams, Rob; Swinburn, Jon; Walden, Andrew P
    This retrospective case series analyses the effectiveness of the Virtual Acute Care Unit (VACU) in managing patients with atrial fibrillation (AF). Data from 50 patients admitted to the VACU is presented focusing on changes in clinical parameters, medication usage, and patient outcomes. The median age of the patients was 76.5 years, with a gender distribution of 21 males to 29 females. Heart rate (HR) and blood pressure measurements were recorded on admission and discharge. Results showed a significant reduction in HR (mean admission HR: 97 bpm, mean discharge HR: 88 bpm, p=0.039), with no significant changes in blood pressure. The majority of patients (41) were managed with Bisoprolol. With a readmission rate of 12%, which is in keeping with NHS improvement guidance on ambulatory pathways, the potential of the VACU to improve patient outcomes and reduce healthcare costs is convincing.
  • Thumbnail Image
    Item
    Enhancing Early Warning Systems: Predicting Next Vital Signs Using Recurrent Neural Networks and Attention Models
    (2025-01-07) Jehangir, Basra; Li, Weizi
    Vital signs are precise indicators of patient deterioration, and early warning scores have been introduced to identify high-risk patients in hospital wards. However, these scores often rely solely on current readings, ignoring trends over time. In this work, the prediction of vital signs—Diastolic Blood Pressure, Systolic Blood Pressure, Heart Rate, Respiratory Rate, Oxygen Saturation, and Temperature—is made using past vitals, demographics, and admission data from the MIMIC-III dataset. Deep learning models were trained for multi-task learning, with LSTM-Attention (LSTM-ATTN) outperforming others. It achieved a mean squared error of 0.0022, surpassing Long Short Term Memory (LSTM), Bidirectional Long Short Term Memory (BiLSTM), Multi-head Attention. This underscores its potential for deployment not only in hospital settings but also in the context of virtual ward management, where real-time prediction of patients’ next vital signs and early detection of deterioration can be invaluable.
  • Thumbnail Image
    Item