Publications by authors named "Alessio Luschi"
Microbiome data analysis is essential for understanding the role of microbial communities in human health. However, limited data availability often hinders research progress, and synthetic data generation could offer a promising solution to this problem. This study aims to explore the use of machine learning (ML) to enrich an unbalanced dataset consisting of microbial operational taxonomic unit (OTU) counts of 148 samples, belonging to 61 patients.
View Article and Find Full Text PDFArticle Synopsis
- Facial pigmented skin lesions are common, especially in South-European countries, and can be either malignant or benign; diagnosing them can be challenging, even for specialists like dermatologists.* -
- A study was conducted to assess the impact of a one-day dermoscopy training course on ophthalmologists, focusing on their ability to evaluate periorbital pigmented lesions through clinical and dermoscopic analysis.* -
- Results showed that before the training, ophthalmologists had an accuracy of 63.7%, but after the course, their sensitivity improved, indicating a positive effect of the training on their diagnostic skills.*
Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis.
Bioengineering (Basel)
October 2024
Article Synopsis
- Diagnosing atypical pigmented facial lesions (aPFLs) is difficult for dermatologists and crucial for patient care, as incorrect diagnoses can lead to mismanagement and delays in treatment.
- The study compared machine learning and deep learning models to improve diagnostic accuracy of aPFLs using 1197 dermoscopic images classified into seven categories, focusing on the potential role of AI in supporting clinicians.
- Results showed that while dermatologists were 71.2% accurate in identifying malignant versus benign lesions, their accuracy dropped to 42.9% when distinguishing among specific lesions, highlighting the complexity of aPFL evaluations.
There has been growing scientific interest in the research field of deep learning techniques applied to skin cancer diagnosis in the last decade. Though encouraging data have been globally reported, several discrepancies have been observed in terms of study methodology, result presentations and validation in clinical settings. The present review aimed to screen the scientific literature on the application of DL techniques to dermoscopic melanoma/nevi differential diagnosis and extrapolate those original studies adequately by reporting on a DL model, comparing them among clinicians and/or another DL architecture.
View Article and Find Full Text PDFThe primary goal of this project is to create a framework to extract Real-World Evidence to support Health Technology Assessment, Health Technology Management, Evidence-Based Maintenance, and Post Market Surveillance (as outlined in the EU Medical Device Regulation 2017/745) of medical devices using Natural Language Processing (NLP) and Artificial Intelligence. An initial literature review on Spontaneous Reporting System databases, Health Information Technologies (HIT) fault classification, and Natural Language Processing has been conducted, from which it clearly emerges that adverse events related to HIT are increasing over time. The proposed framework uses NLP techniques and Explainable Artificial Intelligence models to automatically identify HIT-related adverse event reports.
View Article and Find Full Text PDFBackground: Navigation portable applications have largely grown during the last years. However, the majority of them works just for outdoor positioning and routing, due to their architecture based upon Global Positioning System signals. Real-Time Positioning System intended to provide position estimation inside buildings is known as Indoor Positioning System (IPS).
View Article and Find Full Text PDF