Antonio Lo Tito
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Antonio Lo Tito has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Chandra Bortolotto
Radiology Institute, Fondazione IRCCS Policlinico San Matteo, Pavia, 27100, Italy, Italy
4 shared publications - Gaia Messana
Diagnostic Imaging and Radiotherapy Unit, Department of Clinical, Surgical, Diagnostic, and Pediatric Sciences, University of Pavia, 27100 Pavia, Italy
4 shared publications - Giulia Maria Stella
Department of Internal Medicine and Medical Therapeutics, University of Pavia Medical School, 27100 Pavia, Italy
4 shared publications - Lorenzo Preda
Diagnostic Imaging and Radiotherapy Unit, Department of Clinical, Surgical, Diagnostic, and Pediatric Sciences, University of Pavia, 27100 Pavia, Italy
4 shared publications - Riccardo Bellazzi
Istituti Clinici Scientifici Maugeri IRCCS, Laboratory of Medical Informatics and Artificial Intelligence, Scientific Institute of Pavia, 27100 Pavia, Italy
4 shared publications - Giovanna Nicora
Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy
3 shared publications
Latest Publications
- Open Access
- 10 May 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (5) , 117
Bayesian Networks in the Management of Hospital Admissions: A Comparison between Explainable AI and Black Box AI during the Pandemic
Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffers from poor generalization ability in the presence of dataset shifts. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black box model (Random Forest), both studied with the aim of supporting clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.
- 10 May 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (5) , 117
Open AccessBayesian Networks in the Management of Hospital Admissions: A Comparison between Explainable AI and Black Box AI during the Pandemic
Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffers from poor generalization ability in the presence of dataset shifts. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black box model (Random Forest), both studied with the aim of supporting clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.
- Open Access
- 11 March 2024
- Published by MDPI AG in Preprints.org
Bayesian networks in the management of hospital admissions: a comparison between explainable AI and black box AI during the pandemics.
Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffer from poor generalization ability in presence of dataset shift. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black-box model (Random Forest), both studied with the aim to support clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.
- 11 March 2024
- Published by MDPI AG in Preprints.org
Open AccessBayesian networks in the management of hospital admissions: a comparison between explainable AI and black box AI during the pandemics.
Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffer from poor generalization ability in presence of dataset shift. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black-box model (Random Forest), both studied with the aim to support clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.
- Open Access
The Role of Native T1 and T2 Mapping Times in Identifying PD-L1 Expression and the Histological Subtype of NSCLCs
We investigated the association of T1/T2 mapping values with programmed death-ligand 1 protein (PD-L1) expression in lung cancer and their potential in distinguishing between different histological subtypes of non-small cell lung cancers (NSCLCs). Thirty-five patients diagnosed with stage III NSCLC from April 2021 to December 2022 were included. Conventional MRI sequences were acquired with a 1.5 T system. Mean T1 and T2 mapping values were computed for six manually traced ROIs on different areas of the tumor. Data were analyzed through RStudio. Correlation between T1/T2 mapping values and PD-L1 expression was studied with a Wilcoxon–Mann–Whitney test. A Kruskal–Wallis test with a post-hoc Dunn test was used to study the correlation between T1/T2 mapping values and the histological subtypes: squamocellular carcinoma (SCC), adenocarcinoma (ADK), and poorly differentiated NSCLC (PD). There was no statistically significant correlation between T1/T2 mapping values and PD-L1 expression in NSCLC. We found statistically significant differences in T1 mapping values between ADK and SCC for the periphery ROI (p-value 0.004), the core ROI (p-value 0.01), and the whole tumor ROI (p-value 0.02). No differences were found concerning the PD NSCLCs.
Open AccessThe Role of Native T1 and T2 Mapping Times in Identifying PD-L1 Expression and the Histological Subtype of NSCLCs
We investigated the association of T1/T2 mapping values with programmed death-ligand 1 protein (PD-L1) expression in lung cancer and their potential in distinguishing between different histological subtypes of non-small cell lung cancers (NSCLCs). Thirty-five patients diagnosed with stage III NSCLC from April 2021 to December 2022 were included. Conventional MRI sequences were acquired with a 1.5 T system. Mean T1 and T2 mapping values were computed for six manually traced ROIs on different areas of the tumor. Data were analyzed through RStudio. Correlation between T1/T2 mapping values and PD-L1 expression was studied with a Wilcoxon–Mann–Whitney test. A Kruskal–Wallis test with a post-hoc Dunn test was used to study the correlation between T1/T2 mapping values and the histological subtypes: squamocellular carcinoma (SCC), adenocarcinoma (ADK), and poorly differentiated NSCLC (PD). There was no statistically significant correlation between T1/T2 mapping values and PD-L1 expression in NSCLC. We found statistically significant differences in T1 mapping values between ADK and SCC for the periphery ROI (p-value 0.004), the core ROI (p-value 0.01), and the whole tumor ROI (p-value 0.02). No differences were found concerning the PD NSCLCs.
- Open Access
Correlation between PD-L1 Expression of Non-Small Cell Lung Cancer and Data from IVIM-DWI Acquired during Magnetic Resonance of the Thorax: Preliminary Results
This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (4 in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 104 in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC.
Open AccessCorrelation between PD-L1 Expression of Non-Small Cell Lung Cancer and Data from IVIM-DWI Acquired during Magnetic Resonance of the Thorax: Preliminary Results
This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (4 in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 104 in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC.