Artificial intelligence in medicine
Artificial Intelligence (AI) refers to the ability of machines, usually computers, to perform tasks that require human intelligence. Machine Learning (ML) is the field of AI that allows computers to learn from experience (data). Although AI/ML has existed for decades, it has only very recently achieved adequate performance. This is mainly due to the availability of data, the recent advances in the parallel computing industry and the availability of public contribution libraries.
AI/ML is gradually changing the landscape of healthcare by enabling the extraction of information contained in clinical, medical, biological, lifestyle and other health-related data related to acute and chronic diseases. The goal is the prevention, early, faster, and more accurate diagnosis, improved and personalised treatment and disease management. Patient-specific and intelligent recommendation models based on Reinforcement Learning and Deep Learning could potentially automatise current clinical practices and make them more efficient and patient-friendly. However, the problems and challenges of AI/ML in medicine still exist, including insufficient data, interpretability, data privacy and heterogeneity. Ongoing research aims at mitigating such issues and deploying trustworthy, unbiased AI-tools and methods.
Artificial Intelligence in Diabetes Management
A trustworthy AI-based solutions along with innovative digital tools, as part of digitalization of health services, hold the potential to support and enable both health care providers and people with diabetes to attain and maintain glucose control, reduce the risk for severe complications, and ultimately improve the clinical outcomes and the quality of life. MELISSA aims to fill the gap between AI and its validated application in daily diabetes management with the world’s first fully automated holistic AI-driven treatment personalisation and optimisation platform supporting insulin-treated people with diabetes and their health care providers by providing personalized treatment and care recommendations.