Digitally-enabled Blood Testing in Healthcare
Permanent URI for this collectionhttps://hdl.handle.net/10125/107482
Browse
Recent Submissions
Item type: Item , Risk Factors of Readmission of COVID-19 Patients Undergoing Remote Home Monitoring in Virtual Wards: A Retrospective Analysis(2024-01-03) Chan, Nicholas Berin; Tannetta, Dionne; Walden, Andrew PPatients with COVID-19 were admitted to a virtual ward (VW) for remote oximetry monitoring from the Emergency Department (ED), step down from inpatient wards and from the local primary care “Hot Hub”. To identify risk factors associated with 14-day readmission in COVID-19 patients, statistical analysis was performed to compare patients between the readmission group and the non-readmission group. A total of 356 patients were included in this study. Lower blood oxygen saturation in the first two days within the VW, referred from ED or inpatient wards, fewer days since symptom onset, and white cell count was associated with increased readmission risk. Our results indicate that blood oxygen saturation played a key role in determining clinical deterioration in COVID-19 patients, and other adjusting factors exist. This could be expanded to other pathways of VW and patients with other conditions to assess their clinical deterioration within the monitoring period in VW.Item type: Item , Early Detection of Inflammatory Arthritis to Improve Referrals Using Multimodal Machine Learning from Blood Testing, Semi-Structured and Unstructured Patient Records(2024-01-03) Wang, Bing; Li, Weizi; Bradlow, Anthony; Chan, Antoni T.Y.; Bazuaye, EghosaEarly detection of inflammatory arthritis (IA) is critical to efficient and accurate hospital referral triage for timely treatment and preventing the deterioration of the IA disease course, especially under limited healthcare resources. The manual assessment process is the most common approach in practice for the early detection of IA, but it is extremely labor-intensive and inefficient. A large amount of clinical information needs to be assessed for every referral from General Practice (GP) to the hospitals. Machine learning shows great potential in automating repetitive assessment tasks and providing decision support for the early detection of IA. However, most machine learning-based methods for IA detection rely on blood testing results. But in practice, blood testing data is not always available at the point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA. In this research, we present an ensemble learning-based method using multimodal data to assist decision-making in the early detection of IA. Experimental results show the precision, recall, F1-Score, accuracy, and G-Mean of 0.89, 0.85, 0.86, 0.85, and 0.88. To the best of our knowledge, our study is the first attempt to utilize multimodal data to support the early detection of IA from GP referrals.Item type: Item , Introduction to the Minitrack on Digitally-enabled Blood Testing in Healthcare(2024-01-03) Li, Weizi; Zenil, Hector; Ho, Kendall; Kanza, Samantha