A5038706484- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Surgical Treatments
- Colorectal Cancer Screening and Detection
- Advanced X-ray and CT Imaging
- MRI in cancer diagnosis
- Colorectal and Anal Carcinomas
- COVID-19 Clinical Research Studies
- Gastric Cancer Management and Outcomes
- Biomedical Text Mining and Ontologies
- Advanced Radiotherapy Techniques
- AI in cancer detection
- Clinical practice guidelines implementation
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Sepsis Diagnosis and Treatment
- Colorectal Cancer Treatments and Studies
- Business Process Modeling and Analysis
- Sarcoma Diagnosis and Treatment
- Systemic Lupus Erythematosus Research
- Visual perception and processing mechanisms
- Medical Imaging Techniques and Applications
- Glioma Diagnosis and Treatment
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Privacy-Preserving Technologies in Data
- Heart Failure Treatment and Management
Agostino Gemelli University Polyclinic
2017-2025
Università Cattolica del Sacro Cuore
2016-2024
Istituti di Ricovero e Cura a Carattere Scientifico
2018-2023
Radboud University Nijmegen
2023
Radboud University Medical Center
2023
University Medical Center
2023
Maastricht University Medical Centre
2023
University of L'Aquila
2010-2021
Advanced Radiation Therapy (United States)
2020
Universidad Politécnica de Madrid
2019
Background and purposeAccess to healthcare data is indispensable for scientific progress innovation. Sharing time-consuming notoriously difficult due privacy regulatory concerns. The Personal Health Train (PHT) provides a privacy-by-design infrastructure connecting FAIR (Findable, Accessible, Interoperable, Reusable) sources allows distributed analysis machine learning. Patient never leaves institute.Materials methodsLung cancer patient-specific databases (tumor staging post-treatment...
The aim of this study was to evaluate the variation radiomics features, defined as "delta radiomics", in patients undergoing neoadjuvant radiochemotherapy (RCT) for rectal cancer treated with hybrid magnetic resonance (MR)-guided radiotherapy (MRgRT). delta features were then correlated clinical complete response (cCR) outcome, investigate their predictive power. A total 16 enrolled, and 5 (31%) showed cCR at restaging examinations. T2*/T1 MR images acquired a 0.35 T MRgRT unit considered...
Aim of this study was to develop a generalised radiomics model for predicting pathological complete response after neoadjuvant chemo-radiotherapy in locally advanced rectal cancer patients using pre-CRT T2-weighted images acquired at 1.5 T and 3 scanner.In two institutions, 195 were scanned: 136 scanned on MR scanner, 59 scanner. Gross tumour volumes delineated the 496 radiomic features extracted, applying intensity-based (IB) filter. Features standardised with Z-score normalisation an...
The aim of the study was to build a machine learning-based predictive model discriminate between hospitalized patients at low risk and high bloodstream infection (BSI). A Data Mart including all January 2016 December 2019 with suspected BSI built. Multivariate logistic regression applied develop clinically interpretable learning model. trained on 2016–2018 data tested data. feature selection based univariate first selected candidate predictors BSI. multivariate stepwise in five-fold...
Background Guidelines recommend using multiple drugs in patients with heart failure (HF) reduced ejection fraction, but there is a paucity of real-world data on the simultaneous initiation 4 pharmacological pillars at discharge after decompensation event. Methods and Results A retrospective mart, including diagnosed HF, was implemented. Consecutively admitted HF fraction were selected through an automated approach categorized according to number/type treatments prescribed discharge. The...
Most natural scenes are too complex to be perceived instantaneously in their entirety. Observers therefore have select parts of them and process these sequentially. We study how this selection prioritization is performed by humans at two different levels. One the overt attention mechanism saccadic eye movements a free-viewing paradigm. The second conscious decision which we asked observers points scene they considered most interesting. find very large participant population (more than one...
BackgroundTo retrospectively evaluate the difference in terms of pathologic complete response (pCR) according to time elapsed between chemoradiation (CRT) and total mesorectal excision (TME) on a large unselected real-life dataset locally advanced rectal cancer (LARC) patients.MethodsA multicentre retrospective cohort study LARC patients from 21 Italian Radiotherapy Institutions was performed. Patients were stratified into 3 different intervals CRT. The 1st group included 300 who underwent...
Purpose Distant metastases are currently the main cause of treatment failure in locally advanced rectal cancer (LARC) patients. The aim this research is to investigate a correlation between variation radiomics features using pre- and post-neoadjuvant chemoradiation (nCRT) magnetic resonance imaging (MRI) with 2 years distant metastasis (2yDM) rate LARC Methods Materials Diagnostic post- nCRT MRI patients, treated single institution from May 2008 June 2015 an adequate follow-up time, were...
The primary objective of the SKIN-COBRA (Consortium for Brachytherapy data Analysis) ontology is to define a specific terminological system standardize collection non-melanoma skin cancer patients treated with brachytherapy (BT, interventional radiotherapy). Through ontological characterization information, it possible find, isolate, organize, and integrate its meaning.SKIN-COBRA standardized consortium BT, including 8 centers. Its was firstly defined by multicentric multidisciplinary...
The problem of transforming Real World Data into Evidence is becoming increasingly important in the frameworks Digital Health and Personalized Medicine, especially with availability modern algorithms Artificial Intelligence high computing power, large storage facilities.Even where are well maintained a hospital data warehouse made available for research purposes, many aspects need to be addressed build an effective architecture enabling researchers extract knowledge from data.We describe...
Background: Cardiovascular sequelae after COVID-19 are frequent. However, the predictors for their occurrence still unknown. In this study, we aimed to assess whether myocardial injury during hospitalization is associated CV and death hospital discharge. Methods: prospective observational consecutive patients who were admitted in a metropolitan hub Italy, between March 2021 January 2022, with ≥ 1 assessment of high sensitivity cardiac troponin I (hs-cTnI) included if they alive at Myocardial...
To develop a predictive model and nomogram for maculopathy occurrence at 3 years after 106Ru/106Rh plaque brachytherapy in uveal melanoma.Clinical records of patients affected by choroidal melanoma treated with from December 2006 to 2014 were retrospectively reviewed. Inclusion criteria were: dome-shaped melanoma, distance the fovea > 1.5 mm, tumor thickness 2 follow-up 4 months. The delivered dose apex was 100 Gy. Primary endpoint this investigation radiation years. Analyzed factors as...
Abstract: Diagnosis and treatment of locally advanced rectal cancer is mainly based on multimodal approach for staging, planning treatment. The modern radiological imaging techniques offer, day after day, the possibility to characterize tumor lesions in a more precise prognostically valuable way. In cancer, extending often characterization colon literature offers some evidences that quantitative "radiomics" analysis images might improve prognostic evaluation patients' characterization....
The COVID-19 pandemic affected healthcare systems worldwide. Predictive models developed by Artificial Intelligence (AI) and based on timely, centralized standardized real world patient data could improve management of to achieve better clinical outcomes. objectives this manuscript are describe the structure technologies used construct a Data Mart architecture present how large hospital has tackled challenge supporting daily emergency, creating strong retrospective knowledge base, time...
Heart failure (HF) is a multifaceted clinical syndrome characterized by different etiologies, risk factors, comorbidities, and heterogeneous course. The current model, based on data from trials, limited the biases related to highly-selected sample in protected environment, constraining applicability of evidence real-world scenario. If properly leveraged, enormous amount may have groundbreaking impact care pathways. We present, here, development an HF DataMart framework for management...
Introduction. Cancer variability plus medical big data can be handled by artificial intelligence. Its models have different input types: images and many others (as numbers, predefined categories, free texts). The non image elements are as important images, per clinical practice literature. This article reviews such models, with component, applied use case to rectal cancer. Results Discussion. Secondary literature analysis shows all focusing on inputs only. Primary of interest include pure...