Inderpreet Kambo, Associate Director and Jeremy Carter, Senior Director at Axtria explain how data analytics has now become main-stream within the pharma-biotech space as companies, payers, and regulators attempt to store data and make data-driven decisions
Data has touched multiple aspects of the pharma value chain, from drug discovery to clinical development to patient finding, and drug dosing and adherence for patients. Adoption of data in pharmaceutics has brought better outcomes for patients and the whole healthcare ecosystem: lower cost of healthcare delivery, better patient access to quality healthcare, and data-backed delivery of healthcare. Looking back, pharma companies have traditionally lacked on digital innovation and the adoption of data in the pharma mainstream. This is partly due to strict healthcare privacy regulations but also due to a lack of skilled resources and nascent infrastructure for many of the pharma firms. However, there has been a rapid growth of digital adoption in the last decade itself. Data analytics has now become main-stream within the pharma-biotech space as companies, payers, and regulators attempt to store data and make data-driven decisions.
Data-analytics and machine learning (ML) algorithms to drive innovation and value. Pharma manufacturers can link data to analyse data from various sources: payer claims, electronic medical records (EMRs), lab tests, smartwatches, apps, social media, and much more, to make informed day-to-day decisions. Companies are using AI/ML algorithms in several ways to streamline their processes and improve patient care.
Manufacturers are making use of customised ML algorithms to understand the impact of drug dosing. Take the example of Zenith Epigenetics, which leverages AI algorithms to identify continuously the optimal dose for its cancer drug ZEN-3694. The algorithms calibrated patients’ unique response to treatment using their own clinical data. This calibration was then used to create a customised patient profile, ultimately resulting in reduced adverse events and overall patient discontinuations.
Pharma companies are partnering among themselves, and with public organisations, to share and contribute to a common goal of improved patient care using advanced analytics. Manufacturers are also using advanced analytics to predict the binding of molecules to the target protein. This enables chemists to pursue hit discovery, lead optimisation, and make beforehand toxicity predictions. An example of this is Axtria’s Decision Science and HEOR teams, which are helping pharmaceutical manufacturers improve clinical outcomes, ultimately influencing treatment guidelines.
Providing quality care has become one of the major objectives of healthcare value-chain. Value-based care comprises models that incentivise healthcare care providers to offer high-quality care at an affordable cost. Previously, fee-for-service has been the dominant reimbursement model. However, there is a paradigm shift in providing care that frees providers from documenting the quantity of drugs prescribed or the number of various tests ordered. This enabling of value-based-care revolves around long-term tracking of patients through mutual collaboration between payers, providers, and manufacturers.
Under value-based care, pharma manufacturers, as well as payers, are leveraging analytics to segment patient population who are at a higher likelihood for contracting diseases, especially those that come with a higher cost of treatment. The stakeholders are pre-emptively taking to avoid these costly clinical events. Patients and organisations are similarly doing pattern recognition to gain visibility into inappropriate use of higher-cost services, such as emergency room (ER) visits when a primary care physician could deliver the same care, or the visit could be avoided altogether.
Pharma manufacturers are enabling end-to-end patient management by creating data engines to feed data from various sources: paid claims, hospital admissions, drug adherence, side effects, or reasons for discontinuations. However, until now, pharma companies have had little visibility in the patient’s engagement at the delivery of care with even less information on the patient’s progress. With gene therapies and other innovative drugs in the pipeline, trustworthy pharma-payer relationships and effective data capture through multi-stakeholder collaborations have become even more important to implement these outcome-based care.
- Use of data to build a comprehensive picture of customers. Omnichannel engagement revolves around a central essence that our target audiences in pharma, e.g., physicians, hospitals, and patients, are not tethered to just a single channel, platform, or medium for communication. The healthcare ecosystem is facilitating this engagement by utilising data in a methodical process.
- Correlating needs with capabilities. It is critical to pinpoint attributions and align business needs with the current data capabilities. The first step in defining digital adoption for pharma marketing is understanding business priorities and setting up a roadmap. A cogent view is much needed to level-set manufacturers’ journey of digital adoption – from segmenting top customers to defining measurable key performance indicators (KPIs).
- Creating a single source of truth. There has