Ashwin Oberoi, MChem, Oncology Analyst
The recent surge in artificial intelligence (AI) development has highlighted the potential of data to conquer some of the greatest challenges in healthcare, but has also raised questions about what role this wave will play across oncology indications. Oncologists have historically struggled in trying to define small subsets of patients that may benefit from a specific treatment, as ween with immunotherapies. As such, developers require better tools to help combat this need. Considering the rising cost of drug development and the timelines involved in oncology indications, AI may find its niche in significantly reducing the time taken and costs associated in matching patients with the most relevant clinical trials. Many large pharma companies, including Roche, Pfizer, and Johnson & Johnson (J&J), have launched novel AI initiatives; however, it remains to be seen how their novel AI initiatives will facilitate the development and implementation of new agents into the oncology space.
AI holds a large potential for precision medicine. Approximately 100 start-ups have begun to use AI as a drug discovery tool to identify synergistic combinations of drug targets. Roche, a key leader in the oncology space, has jumped on the bandwagon with its acquisition of Flatiron Health and its partnership with GNS Healthcare. Flatiron Health is an Alphabet-backed oncology-driven digital health analytics start up. Flatiron’s value is derived from its partnership with the National Institutes of Health (NIH) in a collaboration that sought to enhance clinical trial development by collecting patient data at the point of care. Flatiron’s interface gives physicians access to datasets that can be used to decipher useful insight from inconsequential statistical noise. Genentech’s alliance with GNS Healthcare will provide the company with the ability to isolate and validate both novel therapeutic agents and tumor biomarkers via its lexicon of genomic and patient data. This is specifically focused in oncology, and is intended to pinpoint the intrinsic drivers behind some of the most devastating tumor types. Additionally, BenevolentAI, a UK-based start-up, has entered into a partnership with J&J’s Janssen, which has continued to enhance its AI-powered platform that mines data in order to gain insights for designing new drugs.
It is available to find low cialis cost out treatment alternatives of ED. Due to its aphrodisiac properties, it can improve libido level buy line viagra in men and women. Emotional instability gets to be obvious levitra pills for sale deeprootsmag.org in changes in one’s reasoning, discernments, temperament and judgment that consequently bring about changes in discourse and conduct. This herbal supplement offers effective treatment for low libido and weak erection. cost levitra
Lowering clinical trial development costs is another key challenge that AI may be able to meet. Patient recruitment plays a major part in clinical trial costs. Speeding up the recruitment process by using AI to match cancer patients with the most relevant clinical trials could significantly reduce the associated time and costs by making sure that the patients have all the necessary eligibility requirements for a particular clinical trial. Pfizer formed a collaboration with IBM Watson to improve the clinical trial development process. IBM Watson, however, has encountered many potential challenges in optimizing the necessary software; as such, the technology remains in its infancy. Nevertheless, the Mayo Clinic recently noted that it observed an 80% increase in clinical trial enrolment for breast cancer patients by using IBM Watson’s AI platform to effectively match patients with their respective clinical trials.
Although these AI initiatives are still at an early stage, companies in the oncology space that add AI as an essential part of their drug development process will be equipped with the tools necessary to gain a significant advantage over their competitors. These companies will have lower costs for their drug development timelines, more efficient identification of drug targets, and enhanced patient stratification methods, all of which will ultimately lead to larger earnings growth and more effective therapies being introduced more quickly to the oncology market the years to come.