Artificial Intelligence & Big Data
Combating iatrogenism (adverse drug reactions) is a public health priority, which, when combined with therapeutic optimization, can reduce the risk of complications. These prevention strategies aim to prevent drug-related side effects before they occur and to better manage the patient with his treatment.
The current, validated methods for reducing these risks are time consuming and costly in terms of human resources. To prioritize these interventions, computerized decision support systems seem appropriate, theoretically allowing automated detection of risky situations. Despite the massive computerization of prescriptions, these tools are still not very functional due to a lack of reliability in the detection of iatrogenic risk situations and the lack of consideration of human factors (human-machine and interprofessional interactions).
Our objective is to develop iatrogenic prevention strategies using computerized decision support systems respecting two key stages: design of dynamic, reliable and specific rules for a given risk; a thoughtful and concerted integration of these alerts into the multi-professional care process, adapted to the care context.
Ultimately, the development of this project will make it possible to better detect and correct situations at iatrogenic risk and / or requiring therapeutic optimization in hospitalized diabetic patients, in conjunction with the outpatient sector and the patient.
Health data storage
The computerization of health data and the development of computer tools, including artificial intelligence (AI), offer major opportunities for the improvement of clinical research in diabetes. The Lille University Hospital has a health data warehouse (EDS) which has all the required authorizations and resources, and which collects routine care data for more than 230 000 stays per year and more than one million patients followed.
The objective is to develop pre-screening tools that can take advantage of the rich but heterogeneous data of the DHS. These tools will be based on first level AI (terminological alignment, automated annotation, etc.) and second level (supervised and unsupervised classification).
In the end, a detailed analysis of the data concerning diabetic patients hospitalized at the Lille University Hospital will make it possible to clarify the scope of certain clinical questions, to determine the recruitment capacities of diabetic patients at the Lille University Hospital, and to carry out pre-screening in view for inclusion in clinical trials. These essential functions will be able to meet the expectations of institutional and industrial research.
The Center d’Essais Thérapeutiques (Clinical Trial Unit) – PreciDIAB CTU aims to offer an integrated and adaptive organization according to the types of studies and the complexity of the research protocols. The objective of this new organization of clinical research is to pool and centralize the forces in place in order to develop research dynamics on the diabetic patient.
The first mission of this platform is to be a point of access, orientation, consultation and instruction for projects proposed by investigators, industrial and academic partners in relation to diabetic disease and its comorbidities in the context of by PreciDIAB.
The main objective of this platform, unique in France, is to increase the number of clinical research protocols carried out at the Lille University Hospital, to increase the number of recruitments of diabetic patients and to ensure the implementation of trials according to the standards in force.