THANK YOU FOR SUBSCRIBING
Pharma Tech Outlook | Monday, August 16, 2021
Even though advanced analytics can add value at every stage of the product life cycle, from research and early development to market access and commercialization, most pharmaceutical companies still do not systematically apply it to their oncology work.
FREMONT, CA: Due to the power of advanced analytics, hundreds of huge enterprises and digital start-ups have revealed plans to supply self-driving automobiles by 2020. Nonetheless, while no firm is currently creating self-driving cars on their assembly lines (owing to the constant postponement of planned delivery dates), it is only a matter of time before they do. Newer models already contained semiautonomous functions like adaptive cruise control and driver-assist parking, which felt like a lofty but achievable purpose. But, over time, it was known how difficult it is to construct a completely autonomous vehicle, thanks to the vast volumes of data, machine-learning models, and skilled engineers necessary.
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
[vendor_logo_first]The situation is similar in oncology. One has seen the compelling headlines promising that big data and sophisticated analytics would revolutionize cancer care and research and that all patients will soon receive tailored treatment plans owing to machine learning. However, it is arguable that progress has been slower than anticipated.
Without a doubt, significant progress is being made. Using radiomics, a machine-learning technique that can help identify, classify, and monitor solid tumors from CT, MRI, or PET scans rather than relying solely on radiographers and often-painful biopsies, researchers have developed a model that can accurately predict molecular subtypes in head and neck cancers. Machine-learning models have also outperformed board-certified dermatologists in detecting melanoma through picture identification in other studies.
Even though advanced analytics can add value at every stage of the product life cycle, from research and early development to market access and commercialization, most pharmaceutical companies still do not systematically apply it to their oncology work. They do not, for example, frequently assess real-world evidence to establish new indications for existing therapies—an analysis that could be especially useful in treating rare tumors where finding patients for a study is difficult and time-consuming.
They also cannot use data to understand the entire network of a patient's care team, including specialists, primary-care doctors, and care sites. Consider the advancements that could be made if companies could use such data to help oncologists keep up with the often-confusing array of new combination therapies and targeted treatments, ensuring that patients receive the best standard of care based on their history, genetics, and biomarkers at a time when the COVID-19 pandemic has hampered cancer care so severely.
The largest roadblock, though, is a culture that is wary of the kind of experimentation required to create advanced analytics capabilities. Pharmaceutical companies are not making greater success with advanced analytics in cancer because of a scarcity of data scientists with experience in the field. Data scarcity is also a problem. As a result, many businesses are simply deferring a high learning curve. However, advanced analytics will undoubtedly play a significant part in cancer research and care and pharmaceutical companies' oncology success.
See Also: Top Machine Learning Solution Companies
More in News