The activities of the Clinical Data Science Laboratory are focused on the study and application of technologies for data collection and analysis in intensive care units. In this context, the Laboratory coordinates the GiViTI group - Gruppo Italiano per la Valutazione degli Interventi in Terapia Intensiva, a collaborative network of physicians and nurses established in 1991 and formed into an association in 2021, with the goal of carrying out continuous monitoring of the quality of care and conducting research projects.
Quality of care in the ICU
This line of research is aimed to evaluating the appropriateness of care provided by Italian Intensive Care Units (ICUs). The project, developed in collaboration with the GiViTI - Gruppo Italiano per la Valutazione degli Interventi in Terapia Intensiva network, allows the collection of clinical data from patients and information related to the organization of the hospitals and ICUs that are members of the group. The Laboratory, through a software with a modular structure called PROSAFE, analyzes data from more than 200 Italian ICU units. The goals of the project are to monitor, evaluate and improve the quality of care provided in this setting. Thanks to funding from the European Union, since 2011 the study has expanded to five other countries besides Italy: Cyprus, Greece, Israel, Slovenia and Hungary, becoming an international project.
Appropriateness of ICU admissions
ICU units are high-technology care settings in which the presence of highly qualified staff is required. These characteristics result in substantial management costs and special attention to the appropriate use of resources. The StART study (Study on the Appropriateness of ICU Admissions) active in Tuscany and Piedmont. The aim of the project is to evaluate the health care provided in the units with respect to the intensity and severity of services, taking into consideration the levels of care that can be delivered as a function of both available equipment and personnel. The goal of the project is to assess any factors of inappropriateness, identify the reasons for them, and set improvement goals.
Study of an intelligent medical record for the intensive care unit
The main objective of the project is to implement a permanent system for performance evaluation through the analysis of data entered into the MargheritaTre electronic medical record, currently used by about 70 units in Italy. The secondary objective is the creation of an anonymized database accessible to the scientific community. The project is being coordinated by a multidisciplinary study group with medical, nursing, statistical and IT expertise.
Pharmacokinetics of antibiotics in the critically ill patient
AbioKin is a prospective multicenter observational study with the objective of studying the pharmacokinetics of some of the most widely used antibiotics in the ICU. The study is carried out in centers adopting the MargheritaTre electronic medical record. The first phase of the project consists of collecting clinical information and plasma samples in critically ill patients undergoing antibiotic therapy under study. In the second phase, pharmacokinetic models will be developed to describe the evolution of plasma concentrations as a function of patients' clinical conditions. The third phase will involve the development of a simulator to be included in MargheritaTre, allowing the calculation and prediction of antibiotic plasma concentrations as a function of patients conditions, so as to support clinicians in choosing personalized therapies that achieve optimal therapeutic targets.
Data sharing
Availability of large and properly structured datasets provides significant benefits in healthcare research, allowing to improve clinical practice and support decision-making processes. In this context, sharing clinical data is fundamental to fully exploit the potential of those databases to validate and extend research findings and disseminate scientific knowledge. Sharing clinical data requires a multidisciplinary effort, addressing legal, ethical, technical, and scientific issues to ensure on the one hand patient privacy and data security, on the other hand data accessibility to researchers. Using data collected through the electronic health record MargheritaTre we have been preparing an anonymized, documented, and easily accessible version of this database to be shared through a in-house developed platform. In collaboration with Politecnico di Milano and Massachusetts Institute of Technology (MIT) we are organizing datathon events, contests where multidisciplinary teams will address challenging clinical questions by analyzing data from MargheritaTre database.
International Consensus on Cardiopulmonary Resuscitation.
