UPMC, Helomics Join to Develop Predictive Models of Ovarian Cancer Outcomes

UPMC, Helomics Join to Develop Predictive Models of Ovarian Cancer Outcomes

Researchers from the University of Pittsburgh Medical Center (UPMC) have teamed up with Helomics — a subsidiary of Predictive Oncology — to explore the use of artificial intelligence as a way to improve the treatment decision process for ovarian cancer.

Despite the advances made to improve diagnosis and treatment, few prognostic tools are accurate enough to predict outcomes in these patients. This results in high recurrence rates and poor overall survival.

The collaborative study is taking advantage of Helomics’ artificial intelligence (AI) D-CHIP platform to predict patients’ responses to therapy and build a roadmap for personalized treatment.

“We believe that this effort will enhance our understanding of the molecular profiles of women with ovarian cancer by using the power of artificial intelligence to create predictive models of therapeutic success,” Robert Edwards, MD, professor and chair of the department of obstetrics, gynecology and reproductive sciences at the University of Pittsburgh School of Medicine, said in a press release.

“We are excited about the potential for AI-powered, evidence-based decision making to increase our ability to bring about successful outcomes,” said Edwards, who is also co-leader of the Breast and Ovarian Cancer Program at the UPMC Hillman Cancer Center.

The AI approach will combine genetic information from each patient with their responses to therapy, building individualized clinical profiles. This compiled information is then compared with the company’s D-CHIP knowledge base, which contains anonymized molecular and treatment response profiles from about 150,000 cancer cases.

The information collected is thought to provide additional evidence that could help clinicians make educated decisions about targeted therapies for women with ovarian cancer.

“We [at Helomics] believe that by linking both the drug response profile and the genomic profile of the patient’s tumor using a machine learning approach, we can provide ‘multi-omic’ predictive models that will have greater decision-making impact than just genomics alone, which in turn will positively benefit oncologists and their patients,” said Mark Collins, PhD, chief innovation officer at Helomics. “Working alongside [UPMC] provides us with the unique opportunity to potentially make a direct impact on how medicine is practiced at one of the leading women’s medical facilities in the country.”