Collection of the technological, legal, and organizational requirements .
Collecting Evidence and Indicators within the pilots.
Identification and networking of local stakeholders: building a stakeholder platform.
End-users and stakeholders' engagement within the pilots .
Communication and dissemination .
Development and validation of predictions of bone fracture risk in fragile elders by using the Bologna Biomechanical Computed Tomography (BBCT), a digital twin technology that estimates non-invasively the biomechanical strength of any region of the skeleton starting from calibrated CT.
We plan to combine digital twin technology and muscle power analysis to explore how body weight, muscle conditioning, and neuromuscular control can contribute to the risk of joint overloading, a major determinant for the progression of osteoarthritis and failure of many joint replacements.
Comprehensive computer-based planning of High Tibial Osteotomy is possible through arthritic knee joint modeling; for a better outcome for this surgical intervention, able to slow down the progression of medial compartment osteoarthritis and delay joint replacement.
Patients with carcinoma are at high risk of bone fracture. This risk can be stratified by retrospective analyses of image series of patients from X-ray, CT, and MRI.
To establish a set of radiomics-based features from CT and MR to predict post-operative complications and adverse events after endo- and vascular surgery.
Correlations between traditional screening instruments and neuropsychological evaluations of motoric cognitive function using brain CT and MRI can reveal and predict sleep disorders.
We plan to develop personalized protocols for neurorehabilitation in children with cerebral palsy based on psychophysics, kinematic, kinetic, and electromyographic non-invasive analyses. These will also be exploited in individuals with type 2 diabetes and older adults at risk of falling.
The objective is to test the efficacy of AI to predict the risk of complications and treatment efficacy in a variety of non-communicable and communicable diseases in different ages
Data mining, artificial intelligence, and machine learning approaches to predict the risk of infections and acute CVD adverse events in a) "elderly frail frequent users" of the Emergency Department (ED), and b) to stratify response to vaccinations.
Data mining, artificial intelligence, and machine learning approach to identify subnetworks of cancer associated with early prediction, survival, metastasis, or phenotypes in cancer subtypes focusing on a) colon, b) lung, c) Myeloma, and d) AI predictions.
Prediction models based on omics, clinical scores, and electronic administrative claims will be applied to focus on subtasks such as a) diabetes complications; and b) Nonalcoholic Fatty Liver Disease, NAFLD.
Focuses on data mining, artificial intelligence, and machine learning approaches to focus on subtasks such as a) identifying subjects at risk for conversion from preclinical conditions to psychosis, and b) factors affecting progression to intellectual disability in genetic syndromes using Down Syndrome as a model.
This task focuses on assessing, validating and classifying instruments and tools for tracking and monitoring mobility and deformity of human joints and segments. Innovative custom prosthetics and orthotics will be designed and tested on patients.
This task aims to prevent diabetic foot complications via state-of-the-art biomechanical analyses based on state-of-the-art techniques using biomedical imaging (CT, WBCT, MRI), stereophotogrammetry, and baropodometry.
It focuses on validating a tool for the early detection of human papillomavirus (HPV) by using the Single-molecule bio-electronic smart system SIMOT Array that detects HPV biomarkers in body fluids.
Digital pathology and AI methods will be applied to solid organ transplant recipients (liver, kidney, heart, and lung) for prediction and stratification to prevent disease transmission. A new online platform will collect information related to post-transplantation biopsies.
AI and machine learning will be used to implement biomarkers and identify subjects at risk for conversion from preclinical conditions to Parkinson's and Alzheimer's disease progression and factors affecting progression to intellectual disability in Down Syndrome.
In oncology, supervised learning models are being defined to robustly discriminate among eubiosis and dysbiosis of the human microbiome to support the assessment of cancer therapy effectiveness and shed light on physiological processes and the etiopathogenesis of several NCDs.
Models are being developed to investigate molecular neurotransmission in healthy brain ageing and the alterations in accelerated ageing. The aim is to identify biomarkers from MRI and PET neuroimaging before the degeneration sets and cognition declines.
The Emilia-Romagna Inflammatory Bowel Disease (IBD) hub&spoke infrastructure will be developed further to allow for continuous quality of care assessment, research facilitation, timely alerting on clinical pathway management, benchmarking, and patient engagement.
The aim is to integrate an IoT infrastructure with digital, nutritional, and pharmacogenomics approaches based on healthy eating to improve patient care in relation to the risk of disease progression.
A family-centered tele-health approach leveraging wearable and easy-to-use medical devices will be designed to assist preterm and term infants cared for in neonatal intensive care units and to reduce chronic conditions, hospital stay, comorbidities, and nosocomial infections.
A decision support system, able to provide personalized insulin therapy suggestions and usable by non-specialized physicians will be validated. An integrated and scalable mobile platform leveraging continuous glucose monitoring, wearable devices, and innovative real-time personalized algorithms to reduce risks of adverse events will be developed and assessed.
Wearable devices will be used to reconstruct the biting activity and its relationship with food type and, eventually, estimate caloric intake in pathological individuals (obesity, T2DM) from children to the elderly.
The aim is to address multiple emergency department accesses (ED) by integrating hospital and community care services. To such a scope, an AI system, able to identify key factors related to frailty in ED users aged 65+, will be developed and used to monitor people at risk.