Machine learning in metastatic uveal melanoma
Research type
Research Study
Full title
Machine learning to identify predictors of outcome and survival in the treatment of mUM (metastatic uveal melanoma) with M-PHP (melphalan percutaneous hepatic perfusion).
IRAS ID
304900
Contact name
Ganesh Vigneswaran
Contact email
Sponsor organisation
University of Southampton
Duration of Study in the UK
2 years, 0 months, 1 days
Research summary
Uveal melanoma, the most common primary eye tumour in adults, has a terrible prognosis; half of patients acquire metastatic or distant disease, and only one out of every ten patients are alive after one year. Immunotherapy (medication), surgery, or, more recently, chemotherapy directly focused at the liver known as melphalan percutaneous hepatic perfusion are all options for patients (M-PHP). The latter has shown promise and has the added benefit of being delivered through a small hole via the groin and neck. However, there is still a large discrepancy in survival, with four out of every ten patients failing to respond to therapy. We cannot foresee who they will be, and being able to find which patients are likely to respond and which treatments are likely to be useful will improve decision making and save patients from ineffective treatment and side effects. Machine learning is a type of artificial intelligence that is used to find complicated patterns in big datasets, such as treatment response or patient survival outcomes. A computerised tomography (CT) scan creates detailed images of the inside of the body using X-rays and computed reconstruction. We know that these scans contain information that is currently hidden, and our goal is to employ artificial intelligence to extract and uncover this information to help predict treatment responses. Finally, we plan to develop a tool to aid in shared decision-making for metastatic uveal melanoma patients to improve current treatment paths.
REC name
London - Central Research Ethics Committee
REC reference
22/PR/0466
Date of REC Opinion
14 Apr 2022
REC opinion
Favourable Opinion