Business analysis and implementation of a platform to support management and prognosis of memory clinic patients using biomarkers, cognition and cerebrovascular data.

Abstract

The medicine of the future tends to be personalized, responding to the specific profile of each individual. Alzheimer’s disease is a complex and multifactorial neurodegenerative disease. Personalized prevention strategies, and potentially future personalized treatments, are the future for Alzheimer’s disease and will help reduce the global growing costs associated with this disease. A research team of Maastricht University is working towards this goal and aims to better understand the relationship between vascular factors and the main biomarkers of Alzheimer’s disease during the different stages of disease progression. At the end of this project, an algorithm will be created and implemented in a web platform that will allow practitioners to assess the risks and individual prognosis of their patient according to their specific profile, to offer them personalized preventive strategies and thus to evolve towards a more personalized medicine. The objective of this master thesis is to understand the expectations and needs of clinicians regarding the functionalities and design of the platform, as well as identifying other potential end users that could find an interest in this platform. To answer this question, a qualitative analysis using semi-structured in-depth interviews will be performed, as well as a competitive analysis and an analysis of the macro-environment. Some strategic and business elements will also be investigated. The clinicians definitely find an added value in the platform, especially if the outcome gave some preventive and therapeutic guidelines. The platform will need to be user-friendly and clear. The macro-environmental factors, as well as some internal factors, are in favor of the implementation of such a platform. Nonetheless, the opinion of the patients, as well as some ethical aspects, will need to be taken into consideration. Clinicians and patients need to be involved at all steps of the tool development. Validation is also indispensable to build a reliable platform. In conclusion, a machine learning-based platform establishing a prognosis and some therapeutical guidelines based on multiple data will be indispensable in the future in order to come up with a more personalized medicine and to reduce the global burden of Alzheimer’s disease.