Matteo Leghissa

Mr. Matteo Leghissa


Research Focus & Metrics

Academic Career Length

34Years (1993-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 August 2023 in International Journal of Medical Informatics
Verified
Journal Article
Closed access
MLMatteo Leghissa
Matteo Leghissa
Álvaro CarreraÁlvaro Carrera
Álvaro Carrera
Carlos A. IglesiasCarlos A. Iglesias
Carlos A. Iglesias

19 August 2024 in International Journal of Medical Informatics
Verified
Journal Article
Open access
MLMatteo Leghissa
Matteo Leghissa
Álvaro CarreraÁlvaro Carrera
Álvaro Carrera
Carlos A. IglesiasCarlos A. Iglesias
Carlos A. Iglesias
Frailty is an age-related syndrome characterized by loss of strength and exhaustion and associated with multi-morbidity. Early detection and prediction of the appearance of frailty could help older people age better and prevent them from needing invasive and expensive treatments. Machine learning techniques show promising results in creating a medical support tool for such a task. This study aims to create a dataset for machine learning-based frailty studies, using Fried's Frailty Phenotype definition. Starting from a longitudinal study on aging in the UK population, we defined a frailty label for each subject. We evaluated the definition by training seven different models for detecting frailty with data that were contemporary to the ones used for the definition. We then integrated more data from two years before to obtain prediction models with a 24-month horizon. Features selection was performed using the MultiSURF algorithm, which ranks all features in order of relevance to the detection or prediction task. We present a new frailty dataset of 5303 subjects and more than 6500 available features. It is publicly available, provided one has access to the original English Longitudinal Study of Ageing dataset. The dataset is balanced after grouping frailty with pre-frailty, and it is suitable for multiclass or binary classification and prediction problems. The seven tested architectures performed similarly, forming a solid baseline that can be improved with future work. Linear regression achieved the best F-score and AUROC in detection and prediction tasks. Creating new frailty-annotated datasets of this size is necessary to develop and improve the frailty prediction techniques. We have shown that our dataset can be used to study and test machine learning models to detect and predict frailty. Future work should improve models' architecture and performance, consider explainability, and possibly enrich the dataset with older waves.

1 March 1993 in Radiation Effects and Defects in Solids
Verified
Journal Article
Closed access
MKM. Kraus
M. Kraus
PHP. Van Haßelt
P. Van Haßelt
JSJ. P. Ströbel
J. P. Ströbel
SPS. Peehs
S. Peehs
MLMatteo Leghissa
Matteo Leghissa
GSG. Saemann-Ischenko
G. Saemann-Ischenko
Many properties of HTSC's show a strong dependence on preparation induced defects as well as on the structure related anisotropy. The examination of the influence of artificially created defects on these properties can help to provide a better understanding of the relations between the structural and the superconducting parameters. In this contribution we present results of irradiation experiments performed on epitaxial YBa2Cu3O7-δ (Y-123) thin films (using various projectiles) to study effects on critical temperature T c, resistivity ϱ and critical current density jc , and on Bi2Sr2CaCu2O8+x (Bi-2212) single crystals (using 500 MeV I ions) to study effects on the behaviour of this compound in the mixed state.

17 December 2020 in Physics in Medicine & Biology
Verified
Journal Article
Open access
MDM Dehairs
M Dehairs
HBH Bosmans
H Bosmans
MLMatteo Leghissa
Matteo Leghissa
NMN W Marshall
N W Marshall
This study investigates the exposure parameters and required x-ray tube output when performing neurological procedures on a hybrid Angio-MR concept system proposed by Siemens Healthineers. The x-ray part of this system uses a longer source to detector distance than conventional (C-arm) systems and will have a fixed amount of filtration. Additionally, as the x-ray source is situated inside a magnetic field, the focal spot size and shape may be slightly distorted. In order to compare the Angio-MR system to a typical C-arm system, the exposure parameters of 60 thrombectomy procedures, performed in our hospital over the course of one year, were investigated in detail and a set of median values was determined. An analytical simulation platform was then developed to calculate the required tube voltage, tube current and pulse length to reach similar spatial frequency dependent signal difference to noise ratio (SDNR(u)) values as a conventional C-arm angiography system. These simulations were performed for a variety of focal spot sizes for the Angio-MR system. Results show that a standard current x-ray tube has sufficient power to reach similar SDNR(u) values as obtained in a conventional system if the focal spot size between both systems is comparable.

11 September 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MLMatteo Leghissa
Matteo Leghissa
Álvaro CarreraÁlvaro Carrera
Álvaro Carrera
Carlos A. IglesiasCarlos A. Iglesias
Carlos A. Iglesias
Traditionally, machine learning models in healthcare rely on centralized strategies using raw data. This poses limitations due to the amount of available data, which becomes hard to aggregate due to privacy concerns. Federated learning has been emerging as a new paradigm to improve model performance. It exploits information on the parameters from other clients while never sharing personal data from the patients. We present a proof-of-concept of federated learning techniques in the case of an automated screening tool for frailty in the older population. We used a frailty-specific dataset called FRELSA, with patients from nine regions of the UK used to simulate a scenario with regional hospitals. We compared three different strategies: separate regional training with no communication; federated averaging, the most widely used strategy for healthcare; and finally, global training on the full dataset for comparison. All three strategies were validated with two architectures: logistic regression and a neural network. Results show that federated strategies outperform local training and achieve global-like performance while preserving patient privacy. For Logistic Regression, the global validation F-score was 0.737 and the federated aggregated score was 0.735, offering improvement in seven of the nine regions. For Multi Layer Perceptron, the global validation F-score was 0.843 and the federated aggregated score was 0.834, improving in all nine regional models. The federated strategy is equivalent to pooling all the data together while avoiding all complications related to data privacy and sharing. The results of this study show that the proposed strategy is a viable method for improving frailty screening in healthcare systems.

30 June 2007
Verified
Book Chapter
Closed access
PDF file
MLMatteo Leghissa
Matteo Leghissa
MOM. Oomen
M. Oomen
JRJ. Rieger
J. Rieger
BFB. Fischer
B. Fischer
WHW. Häßler
W. Häßler