By Emily May, Assistant Manager, Deloitte Centre for Health Solutions

This week we launched our report, Intelligent post-launch patient support: Enhancing patient safety with AI. This is the sixth and final report in our Intelligent biopharma series that highlights the impact of artificial intelligence (AI) across the biopharma value chain, and explores the role of AI in the final step in the value chain, post-market pharmacovigilance (PV) and patient support programmes (PSP). Our focus is on how AI can increase safety, improve equity and enhance patient engagement and experience. In this week’s blog we discuss the key takeaways from the report including how companies who embrace a bold digitally powered vision can achieve a predictive, personalised, preventative and participatory future for biopharma which ultimately creates a safer future for patients.

Why patient safety strategies need to change

Ensuring the quality and safety of a medicinal product is a moral and regulatory requirement. Post-launch PV is crucial in providing evidence to the industry and regulators of the long-term safety profile of medicines; while PSPs can help patients manage their medication and disease outcomes more effectively. PSPs can also improve equitable access and provide early safety signals. A rising incidence of post-launch adverse event reports (AERs), and the move to more personalised, preventative, predictive and participatory (4P) medicine, has coincided with advances in AI technologies and data analytics. This conjunction increases the potential for post-launch strategies to increase safety, improve equity and enhance patient engagement and experience.

The rational for transforming biopharma’s pharmacovigilance strategies

Monitoring adverse events reports is becoming increasingly challenging

PV is a fundamental activity across the biopharma value chain but is particularly relevant in providing the mechanisms needed to monitor the safety and efficacy of medicines post-launch. However, monitoring adverse events (AE) to ensure patient safety post-launch is becoming especially challenging, driven by the complexity of product portfolios, the higher volume and variety of products and increased public awareness and scrutiny. Despite the volume of individual case safety reports (ICSRs) increasing year-on-year, estimates suggest that more than 90 per cent of AEs go unreported, further demonstrating the need for more sensitive methods of AE monitoring.

Patient health data is increasing in complexity and variety

Social media is increasingly used by patients as a platform to share personal experiences of taking medication, however the terms used for medical concepts are often inconsistent and difficult to extract. This heterogeneity also adds to the difficulties in identifying a signal and defining a relationship between the drug and expressed effect. Furthermore, connected medical devices, such as wearables, are additionally increasing the volume of data that can be integrated into PV. The rise in real-time data from such sources relies on mature processing systems with the capacity to perform advanced multimodal analysis to derive value. Moreover, the adoption of automation and advanced analytics to improve transparency across reporting methods can help build trust in PV systems, increase efficiency and improve the cost-effectiveness of generating richer insights on product quality and patient safety.

How can AI augment pharmacovigilance?

AE reporting is a critical and time-consuming part of ensuring the safe and effective use of medicines. AI provides a scalable and adaptable solution for handling the growing case volume and diverse types of incoming data formats effectively. Machine learning (ML) algorithms can be trained datasets and then applied to extract information from incoming AERs (adverse event reports), continually learning and improving the algorithms each time to increase consistency and reduce human error. Natural language processing (NLP) enables end-to-end analysis of multi-formatted AERs, including mass unstructured data littered with colloquialisms and non-technical terminology to deliver comprehensive yet interpretable sentiment analysis. This augmented intelligence delivers a significant efficiency boost to the current PV operating model and enables better regulatory compliance by ensuring the timeliness and accuracy of submissions.

How patient support programmes can improve patient outcomes

A PSP is a data collection system where the marketing authorisation holder (MAH) exchanges information about the use of its medicinal products with health care practitioners (HCPs) and patients, including direct interactions with patients to help manage medication and disease outcomes. PSPs can help to:

• increase the volume of data captured and detect AEs that would otherwise be undetected,
• offer more personalised and preventative disease management services, especially where chronic conditions involve a wide range of HCPS and interventions
• improve therapy and treatment adherence and subsequent efficacy by enabling HCPs to modify disease progression via earlier intervention.

Digital approaches offer new opportunities to design and deliver PSPs in novel, impactful and cost-effective ways. The advent of AI-enabled devices can reduce the need to manually input data and help patients understand and manage their health more effectively through continuous monitoring. A PSP that integrates and harmonises treatment timings, in-person care and complicated schedules, while providing continued support and education, will enable patients to self-manage more effectively. Increasingly, PSPs are being outsourced to access the operational expertise and technology required to continually scale as the amount of data increases.

How AI can transform PSPs

Reliable, interactive, and personalised PSPs can improve adherence to medication prescriptions and help manage complex and long-term conditions more effectively. As the industry pivots towards outcome-based reimbursement models, the importance of PSPs will continue to grow, AI can help provide flexible solutions that are scalable and adaptable with fast roll-out capabilities. We have identified seven post-launch activities where AI-enabled PSPs can significantly influence patient outcomes (Figure 1).

Figure 1. How AI can improve patient-support programmes and the key criteria for success

Source: Anita Osborn, “10 steps to a successful patient support programme.” Pharmaphorum, 25 February 2016, Deloitte analysis, 2022.

Examples of AI-enabled solutions

Wearables, apps and remote patient monitoring (RPM) enable patients to self-manage more effectively while providing HCPs and biopharma companies with real-time data and information on the progress of an individual’s condition. Biopharma’s adoption of AI-enabled technologies alongside PSPs, means the wealth of objective and longitudinal data can be analysed quickly and processed to provide personalised health insights, facilitate increased patient engagement, anticipate deteriorating health, and decrease the costs of care for patients and HCPs. However, pharma companies should have clear and transparent policies around how to access and manage this wealth of data which complies with the regulations and legal frameworks in each country.

Medication adherence is critical in effective disease management, but engaging patient to self-track their medication is challenging and often wanes over time, with approximately half of all patients not taking medication as prescribed. AI can be deployed across a population of PSP participants to predict patients at higher risk of non-adherence. If a patient is identified as having a high risk of non-adherence, they can be targeted for proactive, tailored interventions. For example, gamification within a PSP can be used to positively reinforce and improve the management of the patient’s condition and help adherence to medication become a habit. AI can identify when patients begin to disengage and recalibrate to the patient’s gaming style or change the challenge to retain and/or reignite their interest.

Chatbots within a PSP can deliver a bespoke experience to help patients stay on track with their health management. From answering questions relating to medication to addressing reasons for non-adherence, AI-enabled chatbots can provide personalised information to benefit the patient. A chatbot can cover a multitude of concerns, including emotional issues such as fear surrounding mediations and the concern of side effects to build trust with the patient. This cannot fully replace HCP interaction but supports the patient across many aspects of their disease management.

Delivering an AI-powered, safe, patient-centric future

There are several challenges to realising the patient-centric future enabled by adopting AI-enabled PV and PSPs. We have identified multiple steps that can be taken to turn these challenges into opportunities (Figure 2).

Figure 2. Necessary steps to delivering an AI-powered future

Source: Deloitte analysis, 2022

Over the next few years, patient-centric support services provide an opportunity to make patients equal partners in decision-making and help biopharma companies deliver safer, more personalised health outcomes. AI-enabled PSPs will transform biopharma’s relationship with patients improving enrolment, adherence, and retention. Implemented alongside an AI-supported PV system that enables patients to identify and report AEs directly and the rise of end-to-end advanced visibility will improve the safety of medications across the biopharma industry, ultimately delivering improved patient outcomes.

 

Emily May, Assistant Manager, UK Centre for Health Solutions

Emily is an assistant manager in the Centre for Health Solutions where she applies her background in both scientific research and pharmaceutical analytics to produce supported insights for the Life Sciences and Healthcare practice. Emily leads the research and publication of the life sciences insights, performing thorough analysis to find solutions for the challenges impacting the industry and generating predictions for the future. Prior to joining the centre, Emily worked as an Analytical Scientist conducting physical chemistry analysis on early stage drug compounds and previously lived in Antwerp, Belgium where she researched and developed water-based adhesive films.

Email | LinkedIn