Imperial College London (ICL)

ID 377

This project aims to explore the impacts of remote versus in-person consultation on type 2 diabetes (T2D) health outcomes. This will be achieved through a combination of approaches using real-world data from a diverse population in NWL.

The COVID 19 pandemic accelerated the adoption of digital health platforms, introducing virtual consultation as viable alternative to traditional in-person ones. While recent research indicates virtual consultation may improve attendance, reduce costs with better glycaemic control in T2D, other research shows better adherence to treatment and better patients understanding in face-to-face interactions. The analysis of EHR data utilizing machine learning to assess virtual consultations’ impact on T2D patient outcome will enhance personalisation of care through data-driven insights. This could result in more effective treatment regimens and improve convenience, as T2D required continuous monitoring, hence virtual consultation prevent the need for frequent in-person visit. The predictive approach of ML analysis will facilitate early risk detection enabling preventative care, potentially reducing complication rates of T2D. The extent to which virtual consultations can replace or complement traditional in-person care, without compromising quality and safety, remained unknown. Furthermore, the effectiveness of virtual interventions across diverse patient demographics and the long-term implications of such shifts remains to be comprehensively understood.

14/12/2023

TRE