Description
BackgroundFatty Liver Disease is a global liver pandemic and a leading cause of death and disability. A large contributing factor is the lack of accurate screening in primary care. Fatty Liver Disease is an asymptotic condition until it reaches end-stage, Cirrhosis. 3 out of 4 Cirrhosis cases in DK is first detected at this stage. Today, the patient pathway is characterized by inaccurate screening that leads to undiagnosed high-risk patients and redundant referral of healthy patients. This is mainly due to General Practitioners relying on outdated and inaccurate liver test to make their clinical decisions.
LiverPRO, is a clinical decision tool which enables timely detection of FLD patients at first point-of-contact (in primary care). Provides specialized liver knowledge and recommendation on demand for all clinicians. Utilises regular used blood samples and the existing test practice which ease implementation and increase scalability. LiverPRO is based on state-of-the-art algorithms that translate simple blood samples into an accurate risk assessment of the patient with 92% accuracy based on current testing.
The company behind the product (LTHealth) have developed a simplified version of the algorithm, which doesn’t require blood samples and can be done by the patient themselves. This project will focus on developing the self-test UX, to reach as many potential patients as possible.
Context
The project is focused on an application for the Danish market. All data collected throughout the process, and all resulting insights will be specific to this market. Some preliminary investigations have been carried out by the company to assess interest from potential users, with current results being promising. There are currently no existing solutions focused on increasing ease-of-access and improving diagnostic accuracy of liver health screenings using this type of algorithm.
Motivation and Contribution
This study will contribute by the development of a prototype for an app focusing on the interaction and user experience design factors. The app is expected take inputs on various physiological information like the documentation of clinical signs and symptoms, which will be analyzed based on the algorithm to provide a risk assessment report. Existing literature and apps on recommender systems in the broader research and practice on disease suspicion systems will inform and be contributed to through this project.
| Period | 22 Aug 2022 → 1 Feb 2023 |
|---|---|
| Examinee | Lasse Langendorf |
| Examination held at | |
| Degree of Recognition | National |