Innovations in advanced analytics are redefining businesses across industries. Although advanced analytics are currently most widely used in the automation of repetitive and labour intensive tasks, the increasing complexity of algorithms and prevalence of data are leading to tangible changes to how businesses strategise and plan, as well as operate. The pharma industry is no different.
Artificial intelligence (AI), machine learning (ML), natural language processing (NLP) and predictive analytics (PA) are gaining significant traction and interest across the pharma value chain. AI driven drug discovery is rapidly becoming mainstream and the pharma industry is increasingly relying on emerging technologies to revolutionise science. For example, Benevolent AI, a leader in AI and ML driven drug discovery, identified a potential treatment for COVID-19, which in combination with an existing treatment for patients with severe symptoms has been proven to reduce the time to recovery of hospitalised COVID-19 patients. Due to its data-rich nature, healthcare is also an exciting frontier for the adoption of AI in the fields of diagnosis and pathology. Similarly, AI is emerging as an innovative tool to inform commercial strategy and drive top-line growth, for example by providing a comprehensive evidence-based approach to predicting the impact of different stimuli on customer decision making.
Data is the foundation
Rigorous data collection has become the norm, and the abundance of robust, well defined data has increased significantly in the past decade. Data and data collection techniques are the foundation for advanced analytics. Sales and marketing channels have access to large volumes of data, such as customer interaction data from customer relationship management (CRM) systems, prescription data, physician profile data and patient behavioural data.
Behavioural data analytics tools, such as PwC’s Behaviour Predictor, can be used to predict patient behaviours based on digital-twin technology and diverse, integrated data sources, that drive health outcomes and enable the identification and development of tailored interventions. In the same vein, patient social media sentiment data is increasingly being analysed using NLP tools to detect medical abnormalities, such as adverse drug reactions, and improve patient outcomes. This abundance of data presents a distinct opportunity to ‘develop’, ‘train’ and ‘feed’ advanced analytics platforms that can also support and improve the performance of the pharma commercial teams.
Data-driven insights drive sales and marketing optimisation
Commercial operations teams can use this data with optimised advanced analytics to enhance decision making and improve the effectiveness of sales and marketing. Sales interaction data with Healthcare Practitioners (HCPs) captured on CRMs can supply rich data to use with tools, such as reinforcement learning and decision tree analysis. These tools can inform future sales engagement strategy and maximise the value of interactions with HCPs, which are often short and hard to obtain.
The COVID-19 pandemic has sharpened the value of having a fully integrated customer interaction approach that allows for remote communication that can be flexibly provided across digital platforms. The pandemic has also resulted in a change to the way HCPs interact with patients, for example through remote monitoring or digital telemedicine platforms, which has sparked an increase in data that can be used to improve and enhance relationships between HCPs and patients. We expect these changes to persist for the foreseeable future. Pharma companies should capitalise on the surge in data resulting from the pandemic and the increase in acceptance and use of digital communication platforms, which can support the development of more personalised HCP engagement strategies dictated by data-driven insights from advanced analytics.
Improving market access and pricing efforts
Advanced analytics could also be deployed to improve market access, pricing and reimbursement efforts. For instance, predictive analytics can inform global and local pricing strategies, determine appropriate launch sequences, and help to model and optimise discounts and rebates in complex payer environments while minimising the impact on net price. An AI platform could be created to automate the development of payer communication and health technology assessments (HTAs). For example, an AI tool could be trained to automate the bulk of health economics and outcomes research (HEOR) analysis and subsequent dossier preparation by automating activities such as analysis of clinical trial data, cost data and real world data (RWD) to build a dossier based on a product profile, desired product positioning, pricing goals and the needs of specific groups of payers.
As the application of advanced analytics continues to evolve across functions in the pharma value chain, the commercial function is on the cusp of becoming even more highly data driven through which specific drivers and barriers to successful engagement of individual HCPs are automatically evaluated and used to inform an optimal commercial strategy.
In our next article in this series, we’ll feature a case study of a revolutionary tool that is enhancing HCP interaction, discuss the use of data collected from HCP interactions and present five areas of focus for developing leading advanced analytics capabilities in the commercial function.
Related content
Contact us
Follow us
