Philadelphia-based analytics company, Clarivate Analytics has released an advanced predictive analytics tool, named Cortellis Analytics – Drug Timeline and Success Rates (DTSR) that is a part of the Cortellis suite of intelligence solutions for drug development and commercialization. Cortellis Analytics – Drug Timeline and Success Rates employ Machine Learning to predict the timeline and possibility of success for a drug, enabling incessant and drastic improvements in pipeline prediction and research and development (R&D) investment decisions.
Pharmaceutical R&D investment outpaces that of almost every other industry; however, returns have repeatedly fallen over the past few years. The CMR’s (Centre for Medicines Research) recent analysis noted that the possibility of effectively shifting a new drug entrant from phase I to market was less than 10 percent across all therapy sectors, with roughly one-third of R&D costs invested in phase 3 alone. The CMR’s analysis, in addition, revealed that the value to bring a drug to market is around USD 3.2 billion that an all-time high. Unlike traditional prediction models that depend on customary benchmarks, fixed template-based algorithms, and inadequate data inputs, the patent-pending Cortellis model brings a totally diverse approach to forecasting success. To utilizing traditional data from Cortellis, with 15 years of pharmaceutical intelligence spanning 70,000 drug programs and drug development trends analyses, the model looks at the target’s upcoming trial milestones as well as the exclusive key traits that may impact success or failure to create possibilities of success at each stage of development. When experimented against customary industry benchmarking approaches, Cortellis Analytics – DTSR outperformed those by 25 percent, offering superior confidence to decision-makers.
President of Life Sciences at Clarivate Analytics, Mukhtar Ahmed stated that current approaches to pipeline predictions fall well short of meeting the industry’s requirements. The Cortellis Analytics tool employs an improved statistical algorithm based on data science and Machine Learning to make anticipations that are incessantly updated based on the latest existing data. Ahmed further noted that researchers, through this dynamic approach, can more confidently and competently generate grave decisions related to pipeline forecasting and portfolio planning all through the development lifecycle.