Towards an adaptive decision-support system for Type I Diabetes treatment based on simulation and machine learning
Keyword(s):
Type I
◽
"Diabetes is one of the most prevalent chronic diseases in the world, especially in middle- and low-income countries. Inter- and intra-patient variability greatly hinders the establishment of effective treatments by clinicians, even among those most experienced. This variability also prevents health administrations to establish adequate controls that guarantee the application of the most cost-effective interventions. In this work, we propose a decision support system that uses simulation and machine learning as tools to provide the clinician with information adapted to the patient on the best intervention for a patient in terms of effectiveness and cost-effectiveness."