WARE: Wet AMD Risk-Evaluation Tool as a Clinical Decision-Support System Integrating Genetic and Non-Genetic Factors

Abstract

Given the multifactorial features characterizing age-related macular degeneration (AMD), the availability of a tool able to provide the individual risk profile is extremely helpful for personalizing the follow-up and treatment protocols of patients. To this purpose, we developed an open-source computational tool named WARE (Wet AMD Risk Evaluation), able to assess the individual risk profile for wet AMD based on genetic and non-genetic factors. In particular, the tool uses genetic risk measures normalized for their relative frequencies in the general population and disease prevalence. WARE is characterized by a user-friendly web page interface that is intended to assist clinicians in reporting risk assessment upon patient evaluation. When using the tool, plots of population risk distribution highlight a “low-risk zone” and a “high-risk zone” into which subjects can fall depending on their risk-assessment result. WARE represents a reliable population-specific computational system for wet AMD risk evaluation that can be exploited to promote preventive actions and personalized medicine approach for affected patients or at-risk individuals. This tool can be suitable to compute the disease risk adjusted to different populations considering their specific genetic factors and related frequencies, non-genetic factors, and the disease prevalence.

D4Z4 Methylation Levels Combined with a Machine Learning Pipeline Highlight Single CpG Sites as Discriminating Biomarkers for FSHD Patients

“…In conclusion, the application of methylation analysis and ML was able to successfully distinguish FSHD patients from controls, providing additional evidence for DNA methylation as a powerful disease biomarker to be exploited for a rapid and reliable prioritization of FSHD subjects to be confirmed by standard testing ( D4Z4 sizing, research for FSHD-associated variants). Moreover, our study is in line with the recent application of ML for enhancing the clinical diagnosis and decision-making performance in several medical fields, including oncology, cardiology, ophthalmology and neurology [ 35 , 36 , 37 , 38 ]. In addition, ML-based methods have also been tested for fostering the research of molecular disease biomarkers in different diseases and phenotypes, including neuromuscular disorders [ 25 , 39 , 40 ].…”

A Splicing Variant in RDH8 Is Associated with Autosomal Recessive Stargardt Macular Dystrophy

“…During the last century there has been an improvement in sequencing technologies, and, presently, the rapid improvement in artificial intelligence (AI) can support the development of tools and algorithms for medical and genetic purposes. Many multifactorial disorders yet benefit from the computational evaluation of individualized risk (i.e., age-related macular dystrophy) [ 33 ]. The application of AI to Mendelian disease is more difficult due to the frequent absence of family data.…”