Achieving patient insights is no cakewalk. The process is riddled with numerous challenges including difficulty managing the high volume, variety, and velocity of siloed real-world data; the absence of reusable and modularized analytical solutions; and the lack of capabilities to unlock an integrated patient journey. To overcome these challenges and harness the full potential of patient insights, life sciences companies must invest in the right data management tools and analytical techniques. A deep understanding of the data and insights required is also vital to unravel hidden patient patterns, uncover valuable correlations, and derive actionable intelligence from the vast sea of data at their disposal. This article highlights the critical importance of efficient data management and the role of advanced analytical approaches in unleashing the transformative power of patient insights.
Navigating the complex world of patients, physicians, and payers can be a challenging journey for drug manufacturers. Regardless of their size, they consistently face obstacles in marketing and distributing their products while meeting the diverse needs of healthcare stakeholders. It's no wonder that these companies often grapple with complicated questions that keep them up at night.
That’s where patient insights come in. They empower manufacturers to design personalized drug strategies, ensuring that each medication reaches the patients who can benefit the most. By shedding light on patient journeys and physician preferences, patient analytics helps identify optimal distribution channels, maximizing the reach and impact of therapies.
This detailed understanding of the payer landscape also facilitates streamlined reimbursement and market access for better outcomes. With patient analytics as their compass, organizations can break free from uncertainty and embark on a confident, data-driven journey toward success.
Figure 1: Key business questions that patient insights can help answer
How can we effectively communicate the benefits and risks of the drug to patients?
What strategies can be implemented to promote patient adherence to the prescribed treatment?
How can we help patients overcome potential barriers to adherence, such as cost or complexity of the regimen?
What are the preferences and unmet needs of the target patient population?
What clinical data and evidence can we provide to physicians to support the use of the drug in their practice?
How can we engage influential physicians and key opinion leaders in the field to advocate for the use of the drug?
How can we demonstrate the value and cost effectiveness of the drug to payers?
How can we secure favourable formulary placement and reimbursement coverage for the drug?
What steps can we take to improve the accuracy of our forecasts and predictions, ensuring they align more closely with actual outcomes?
How can we evaluate the reactions of patients, physicians, and payers towards our brand quickly enough to act on them?
There exists enough data in the industry that can provide answers to these questions. This data comes from various sources, such as electronic health records, disease registries, claims data, patient surveys, clinical trial results, prescription information, social media conversations, historical engagement patterns, etc. Together, these sources serve as the foundation for generating meaningful patient insights that can drive smarter decisions across the life sciences value chain.
We’re talking about millions of lost, disparate, and disconnected datasets across different departments, systems, and formats. Companies often struggle with limited ability to understand how to gather all this data, inadequate analytical expertise to stitch that data into a single story, and outdated processes and systems that just don’t move fast enough.
All of this affects their ability to truly (and quickly) to generate accurate patient insights and understand patients and their experiences, as well as the viewpoints, requirements, and preferences of physicians and payers – slowing them in their journey to answering the key business questions discussed above.
What will it take to piece this data puzzle together and achieve what we call a super-integrated intelligence of the entire customer ecosystem?
A top 5 global life sciences company had a similar question. Looking for a way to create one holistic picture of its entire data estate, the organization decided to partner with Indegene.
The company wanted to craft an effective brand strategy to drive growth for its portfolio of products across indications such as rheumatoid arthritis, skin disorders, cancer, and others. However, managing the explosive amount of information flowing in for each product became extremely challenging. On top of that, the data sources were highly fragmented and unstructured, and the company lacked the necessary analytical infrastructure to tackle this effectively. This resulted in difficulties and inconsistencies during data analysis. It felt like trying to navigate through a dense, uncharted forest of data without a compass.
They were clearly at risk of missing out on valuable physician and patient insights that were extremely essential to drive brand growth and distinctively lead the market.
This challenge is far more common than we realize.
Figure 2: Study shows that lifesciences leaders struggle to extract insights from data
48%
48%
Of life sciences leaders admit their competitiveness is suffering because they cannot extract or use insights from data they already have within their business.1
An equal percentage admit they do not use their own data for business decisions as well as they could. These challenges are also amplified for companies planning new launches but are stuck in what feels like an endless loop-hole of unorganized data from everywhere.
Figure 3: Study shows that lifesciences leaders struggle to use data to improve time to market
48%
49%
Of life sciences leaders also admit that their companies struggle to use data effectively to improve time to market1
In fact, drug launches have fallen short of expectations set by companies and analysts. Even with promising projections, some highly anticipated blockbuster drugs have experienced bitter disappointments when payers express reluctance and meticulously crafted sales plans fail to materialize.
Figure 4: Drug launches missing Wall Street Estimates
50%
50%
Of drugs launched in the last 15 years underperformed analysts’ sales estimates by more than 20%2
Figure 5: Newly-launched drugs struggle to rake in high revenue
Only one-fifth
of new meds reached $1 billion in U.S. sales, and more than half failed to hit even $250 million3
Nitin Raizada
Vice President of Enterprise Commercial Solutions at Indegene
The gap in patient engagement within life sciences is evident, as half of the patients express a desire for companies to understand more about their lives, and one in three seeks increased engagement. Industry research reveals that only 21% of marketers believe they are effectively utilizing patient insights, and just 15% find them relevant3. It's no surprise that only 6% of patients feel life sciences companies are genuinely on their side3.
Bridging this gap is crucial, and it requires prioritizing patients, involving them in drug development, and gaining a true understanding of their lives and their treatment journey to create truly patient-centered healthcare solutions.
Indegene's collaboration with the global drugmaker mentioned above involved a three-step approach to tackle their data challenges, such as managing siloed real-world data, addressing the lack of reusable analytics, and unlocking an integrated patient journey to harness the full potential of patient insights.
The journey began with a deep exploration into the diverse insights required throughout the entire brand lifecycle. This comprehensive understanding enabled them to craft highly impactful strategies that were customized to accomplish specific objectives, taking into account the brand’s position in the lifecycle, including late-stage phases, pre-launch, launch, post-launch, and market maturity.
Here’s a visual representation of some of the key insights generally needed for each stage:
In addition to the above, companies would also need insights related to forecasting, such as sales projections, demand forecasting, and supply chain optimization. They would require brand insights to track brand perception, awareness, and customer satisfaction. Moreover, understanding HCP insights, including their treatment patterns, preferences, and educational needs, is crucial for effective engagement and support.
Once the list of insights required was ready, the next step was to map them to the available data sets. This process involves understanding the data sources available, gathering relevant data, and organizing it to extract actionable insights.
Here are a few examples:
Clinical Trial Data:
Clinical trial databases:
Access and analyze data from clinical trial databases to gather insights on efficacy, safety, and patient outcomes
Electronic Health Records (EHRs):
Leverage anonymized patient data from EHRs to understand real-world treatment patterns and patient demographics
Case report forms (CRFs):
Analyze CRFs to extract valuable clinical and patient-related information
Market Research Data:
Patient surveys:
Conduct surveys to capture patient preferences, unmet needs, and satisfaction levels
Physician surveys:
Gather insights from healthcare providers regarding treatment practices, perceptions, and preferences
Focus groups and interviews:
Conduct qualitative research to gain in-depth insights into patient and healthcare provider experiences
Real-World Data (RWD) Sources:
Claims and reimbursement data:
Utilize data from insurance claims and reimbursement systems to understand treatment patterns, costs, and utilization
Disease registries:
Access disease-specific registries to analyze long term patient outcomes and real-world treatment effectiveness
Pharmacy data:
Obtain pharmacy sales data to track prescription volume, market share, and patient adherence
Digital and Social Media Data:
Social media platforms:
Monitor social media channels for patient sentiment, discussions, and feedback related to the brand and disease area
Online forums and communities:
Analyze discussions on patient forums and online communities to understand patient experiences, challenges, and treatment preferences
Website analytics:
Track website traffic, user engagement, and conversion rates to assess the effectiveness of online marketing efforts
Sales and Marketing Data:
Sales data:
Collect sales data from internal systems or external sources to monitor product performance, market share, and sales trends
Promotion and marketing data:
Capture data from marketing campaigns, detailing activities, and promotional channels to evaluate their impact on brand perception and awareness
Customer relationship management (CRM) data:
Analyze CRM data to track interactions with healthcare providers, key opinion leaders, and other stakeholders
Other Data Sources:
Health economic data:
Gather data on health economic outcomes, cost effectiveness, and payer perspectives
Adverse event reporting systems:
Monitor adverse event reporting databases to identify safety signals and assess product safety
The final step involved establishing a scalable analytical infrastructure which was crucial for harmonizing and synthesizing data to generate accelerated patient insights in record time. The infrastructure included the following:
Common Data Models: To overcome the siloed nature of data sources, the company built common data models. These models standardized data formats, definitions, and structures across various sources, enabling seamless integration and analysis. This standardization facilitated data aggregation and ensured consistency in insights across different indications and products.
Analytics-Ready Data Sets: The company invested in building analytics-ready data sets. They developed data pipelines and processes to transform raw data into structured, clean, and validated data sets. These data sets were specifically designed to enable brand teams to focus on analysis rather than data wrangling.
Standard Re-usable Code Repositories: To enhance efficiency and consistency in analysis, the company established standard re-usable code repositories. These repositories contained pre-built scripts, algorithms, and analytical models that could be easily adapted and reused across different projects. This approach saved time and effort in analysis, while also ensuring consistency in methodologies and results.
Predictive Modeling: By analyzing historical data and incorporating relevant variables, they developed models to forecast patient and physician behaviors, identify potential market opportunities, and optimize brand strategies. Predictive modeling provided valuable insights to guide decision-making and drive brand growth.
Dashboards: The company also implemented automated plug-and-play dashboards to provide easy access to insights and facilitate data-driven decision-making. These dashboards were designed to be user-friendly and customizable, allowing users to interact with the data and visualize key metrics.
Watch this video to learn about the Indegene’s NEXT platform for integrated patient insights to simplify the task of managing an overwhelming volume of patient data. It equips life sciences teams with powerful analytical tools to conquer data complexity, access clinically valuable patient insights faster, and drive impactful outcomes throughout the patient journey.
Apart from the steps included above, companies may also consider scaling their advanced analytics infrastructure across other use cases for greater impact. By extending these capabilities, organizations can unlock new insights that drive innovation and efficiency beyond a single brand or therapy area.
Here are a few examples:
Patient-focused
Understand the drivers behind patients’ treatment choices between two drugs.
Create patient profiles with a high probability of responding positively to a specific treatment
Predict drug side effects and disease progression based on patient characteristics and treatment data
Predict the likelihood of patient hospitalization and re-admission based on historical data
HCP-focused
Identify HCPs who are likely to be early adopters of new treatments or therapies
Assess HCP brand loyalty and identify influential HCPs who can advocate for the brand
Predict HCP prescription behaviors, including their willingness to write prescriptions and their likelihood to change prescriptions
Analyze HCP referral patterns and identify key influencers within professional networks
Payer-focused
Predict factors influencing payer decisions, such as efficacy, safety, cost effectiveness, and real world evidence. This helps in understanding the drivers behind payer approvals or rejections
Score payers based on their likelihood to include a specific drug in their formulary. This insight guides market access strategies, negotiations, and resource allocation
This approach helped the company’s stakeholders swiftly filter, sort, analyze and visualize complex data seamlessly, without involving the organization’s IT team. In addition, they achieved the following outcomes.
30%
Reduction in cost from FTE models
20+
Re-usable components in 80% of the use cases
80%
Faster insights across high-impact use cases
Vikas Mahajan
Senior Director of Data and Analytics at Indegene
Now more than ever, life sciences companies must prioritize building an integrated data environment like the one discussed above. The true power lies in connecting the dots and creating a comprehensive, 360-degree view of patient data. With the right data management tools and analytical techniques, coupled with a clear understanding of the required patient insights, companies can uncover hidden patterns, identify valuable correlations, and extract actionable intelligence from the vast sea of information at their disposal.
It is time for organizations to embrace their own prescription for success, apply the steps outlined above, and use patient insights to position their brands for sustainable, long-term impact.
1. Weintraub A. Half of drugs rolled out since 2004 didn't live up to sales forecasts [Internet]. Fierce Pharma; 2021 Jan 20. Available from: https://www.fiercepharma.com/pharma/half-drugs-launched-last-15-years-failed-to-meet-wall-street-s-expectations-report
2. RBC Capital Markets. The healthcare data explosion [Internet]. RBC Capital Markets;. Available from: https://www.rbccm.com/en/gib/healthcare/episode/the_healthcare_data_explosion
3. Clear M&C Saatchi. Why patient insight is critical to improve patient outcomes [Internet]. Clear Strategy. Available from: https://clearstrategy.com/thinking/why-patient-insight-is-critical-to-improve-patient-outcomes/