Cohort profile for development of machine learning models to predict healthcare-related adverse events (Demeter): clinical objectives, data requirements for modelling and overview of data set for 2016-2018.

PURPOSE: In-hospital health-related adverse events (HAEs) are a major concern for hospitals worldwide. In high-income countries, approximately 1 in 10 patients experience HAEs associated with their hospital stay. Estimating the risk of an HAE at the individual patient level as accurately as possible is one of the first steps towards improving patient outcomes. Risk assessment can enable healthcare providers to target resources to patients in greatest need through adaptations in processes and procedures. Electronic health data facilitates the application of machine-learning methods for risk analysis. We aim, first to reveal correlations between HAE occurrence and patients' characteristics and/or the procedures they undergo during their hospitalisation, and second, to build models that allow the early identification of patients at an elevated risk of HAE. PARTICIPANTS: 143 865 adult patients hospitalised at Grenoble Alpes University Hospital (France) between 1 January 2016 and 31 December 2018. FINDINGS TO DATE: In this set-up phase of the project, we describe the preconditions for big data analysis using machine-learning methods. We present an overview of the retrospective de-identified multisource data for a 2-year period extracted from the hospital's Clinical Data Warehouse, along with social determinants of health data from the National Institute of Statistics and Economic Studies, to be used in machine learning (artificial intelligence) training and validation. No supplementary information or evaluation on the part of medical staff will be required by the information system for risk assessment. FUTURE PLANS: We are using this data set to develop predictive models for several general HAEs including secondary intensive care admission, prolonged hospital stay, 7-day and 30-day re-hospitalisation, nosocomial bacterial infection, hospital-acquired venous thromboembolism, and in-hospital mortality.

Cohort Creation and Visualization Using Graph Model in the PREDIMED Health Data Warehouse.

Grenoble Alpes University Hospital (CHUGA) is currently deploying a health data warehouse called PREDIMED [1], a platform designed to integrate and analyze for research, education and institutional management the data of patients treated at CHUGA. PREDIMED contains healthcare data, administrative data and, potentially, data from external databases. PREDIMED is hosted by the CHUGA Information Systems Department and benefits from its strict security rules. CHUGA's institutional project PREDIMED aims to collaborate with similar projects in France and worldwide. In this paper, we present how the data model defined to implement PREDIMED at CHUGA is useful for medical experts to interactively build a cohort of patients and to visualize this cohort.

E-learning for students in their first year: a French experimentation at the medical school of Grenoble.

A local study carried out in the Medical School of Grenoble shows that teaching in the first year in medicine studies satisfies neither the students, nor the teachers. The Faculty of Medicine of Grenoble decided to set up a reform in order to offer a high quality education. This reform leads to a complete reorganization of the curriculum and to the intensive use of new information and communication technologies of information, in particular, the use of multimedia documents. The communication and information technologies team of the Faculty of Medicine of Grenoble carried out an innovating and daring reform to start at the academic year 2006-2007. The new course is built on three activities: self learning on multi-media resources, meetings with teachers for questions-answers sessions and tutorials animated by older students. This article reports the first results for this successful project. In the academic year 2006-2007, are concerned 1290 students, 40 teachers and 8 disciplines.

[Towards a pedagogical e-learning approach to improve preparation for medical school curriculum in Grenoble: results over the 10 last years]. / Réforme pédagogique et « e-learning ¼ pour le concours de première année à la faculté de médecine de Grenoble : satisfaction des étudiants et des enseignants.

INTRODUCTION: Before 2005, at Grenoble, the teaching of the first year of medicine satisfied neither the students, nor the teachers anxious to exempt a correctly targeted effective teaching. METHODS: By 2006, the Grenoble-native teaching method was reformed in-depth with the introduction of information and communication technology (ICT) in education. Each sequence was over 4 weeks connecting: self- learning using multi-media resources, questions submitted online, meetings with teaching staff for interactive question-answer sessions in the presence of the teacher,) tutorials animated by older students for Multiple Choice Question (MCQ) training in preparation for the exams. The whole health formation was structured in 12 cycles of this same structured sequence. Since 2010, this method was extended from the faculty of medicine to the faculty of pharmacy and maieutic. Each year, more than 1600 students, 40 teachers and 140 tutors are concerned. The ICT laboratory was responsible for the production of the multi-media support, of the management of the questions online, the collection and the treatment of the evaluations of the lesson by the students. It also took part in the preparation of the MCQ trainings and after each sequence, delivered to students their personal ranking. RESULTS: Staffs between teachers and students are organized for the 12 cycles. The teachers' and students' opinions were analyzed to evaluate the reforms and allow teaching methods to be adapted accordingly. The expressed satisfaction' rate vary from 85% with more than 91% by students and teachers. The intensive use of new information and communication technologies is well accepted, by both sides: teachers and students. After each tutorial, students had their results and their rank, which are linked with the contest result. The mean of the 12 notes obtained during the tutorials is correlated with the note with the contest (R of Spearman=0.75). Student profiles at registration and success in the exams following the reform are described. The keys to success (e.g. social background, high school specialization) seem to be modified by the reform providing greater equality of opportunity between students. CONCLUSION: Since 2006, the teachers have adopted this teaching reform. All the returns from the students but also the staff and the teachers, allowed us to improve teachings quality. This teaching reform modified the profiles and the characteristics of the students received with the contest as well as the nature of the factors of this success.