Image source: Geneva University Hospitals (HUG)

News • Watson on the case

Personalised cancer care through AI

The Geneva University Hospitals (HUG) is the first European university hospital to utilize IBM’s artificial intelligence (AI) technology to help uncover therapeutic options for cancer patients.

HUG will use the IBM Watson Health’s precision oncology offering, Watson for Genomics, an AI tool that enables oncologists to provide patients with more personalized, evidence-based cancer care. Using information extracted from peer-reviewed articles and validated by experts, Watson for Genomics produces a report for physicians classifying genetic alterations in a patient’s tumor and providing associated therapies and clinical trials for the actionable ones. By implementing this tool, physicians at HUG are able to more quickly categorize massive bodies of genomic data for various cancer types and scale precision oncology for their patients.

Recommended article


Article • A look into the crystal ball

Experts debate predictive potential of AI

‘Hello, John? You are about to suffer a heart attack – please come to the hospital immediately!’ Will we, one day, be collected by emergency doctors even before we’re ill? If it was up to some AI experts at Medica, this could be the case – soon. Some obstacles must yet be overcome to achieve perfect AI predictions. Yet, during Medica, some IT experts ventured to gaze into a crystal ball.

This technology provides clinicians the ability to find actionable genomic insights that manual interpretation may miss while also saving clinician time

Nathan Levitan

“As the first European hospital to adopt Watson for Genomics we will further help our physicians provide more personalized cancer care and streamline variability for genomic reporting, which we believe may improve outcomes for our patients,” said Rodolphe Meyer M.D., Deputy Chief Information Officer at HUG. “We remain very committed to the fight against cancer, including utilizing the best technological advances in medicine, such as AI, and participating in ongoing, quality academic research”. With 18 million diagnoses each year (according to the WHO cancer fact sheet), cancer has a heavy human toll, as well as a high health system cost. Patients can face exhausting, lengthy and confusing treatment regimens, while oncologists are responsible for staying up to date on an ever-growing body of medical literature and genomic data to identify the best care plan for each individual patient. “We are pleased to partner with Geneva University Hospitals, and we are pleased to work with HUG to help their physicians focus on what matters most – their patients – and help them make more informed decisions that aid in their treatment and care, says Nathan Levitan, M.D., Chief Medical Officer Oncology & Genomics, IBM Watson Health. “This technology provides clinicians the ability to find actionable genomic insights that manual interpretation [Kim et al., Journal of Clinical Oncology 2019] may miss while also saving clinician time – completing classification of gene and RNA-sequencing results in ten minutes compared to what would take 160 hours manually.” [Wrzeszczynski et al, Neurology Genetics 2017]

Source: Geneva University Hospitals (HUG)


Related articles


News • Appeal for better approval conditions

AI in personalised cancer medicine: “A fundamental change is needed”

AI technology holds promise for personalised cancer therapies. However, rigid and slow approval requirements impede its introduction, say experts – and point out how this might be changed.


News • Precision oncology

Genomic sequencing benefits only 5% of cancer patients

Genomic sequencing panels as part of personalised cancer treatment have been found to only benefit one in 20 patients they are currently used for, according to a study by CNIO.


Article • Interpreter of maladies

Will AI help realize the promise of precision medicine?

Machine learning and artificial intelligence (AI) have the potential to transform cancer treatment management worldwide. Their ability to rapidly analyse and integrate routinely acquired diverse data…

Related products

Subscribe to Newsletter