Case Study: Incorporating Patient Voice into Forecasting Models for Better Peak Sales Predictions

Thought Leadership and Case Studies

Patient voice has become a more and more valuable part of pharmaceutical forecasting. Traditional peak sales models rely on historical market data, epidemiology, prescribing patterns, competitive intelligence, and pricing assumptions. These inputs remain important, but they don’t always include the real-world patient experiences, preferences, and treatment decisions that drive product adoption. Pharmaceutical organisations that include patient perspectives in their forecasting models can develop more realistic peak sales projections, improve launch planning, and create patient-centric commercial strategies. This case study demonstrates how patient insights can improve forecasting accuracy and produce better business and healthcare outcomes.

The Challenge

A mid-sized pharmaceutical company was about to launch a speciality therapy for a chronic disease. Early predictive models relied on clinical trial results, physician interest, and market size estimates to project high market uptake.

But commercial leaders weren’t sure that the assumptions made in traditional forecasting adequately reflected patient behaviour outside of controlled clinical settings. The current model did not adequately capture factors such as convenience of treatment, financial considerations, adherence, and quality-of-life expectations.

The group elected to include structured patient insights before completing its commercial outlook.

What the Patient Voice Means

Patient voice is information collected directly from patients about their experiences, preferences, expectations, and treatment journeys.

Common sources are:

Interviews with patients
Questionnaires
Advisory boards
Patient advocacy groups
Real-world evidence studies
Online patient communities
Patient-reported outcome measures

Such insights can help organisations better understand how patients make treatment decisions beyond clinical efficacy.

Building a Better Forecasting Model

The forecasting team worked with market research, medical affairs, commercial strategy, and patient engagement specialists to improve the existing forecasting framework.

Additional new variables were added.

Treatment Convenience

Research showed that the frequency of administration was an important factor in treatment adoption. Patients were very clear that they wanted treatments that reduced the need for clinic visits and that made long-term management of the disease easier.

This data reset forecast penetration rates for several patient segments.

Financial Considerations

Qualitative patient interviews identified affordability concerns, insurance complexity, and out-of-pocket costs as important barriers to treatment adoption.

Forecast assumptions were revised to reflect more realistic patient access scenarios.

Quality of Life Priorities

Beyond clinical outcomes, patients consistently prioritised improvements in daily functioning, symptom control, and treatment flexibility.

By understanding these priorities, the team was able to better estimate long-term treatment persistence and adherence.

Patient Education

Research showed that patients who were well-informed were more likely to ask their healthcare providers about new therapies and to stay engaged in their treatment.

The forecast model included expected gains from planned patient education efforts.

Results

Including patient perspectives, the revised forecast model yielded more balanced peak sales projections.

The revised model had several advantages:

More realistic timelines for adoption
Better segmentation of patient populations
Improved estimates of long-term treatment adherence
More realistic commercial planning assumptions
Better alignment of patient needs with launch strategy

The predicted peak sales were somewhat lower than the original estimate, but leadership gained more confidence in the forecast because it reflected real-world patient behaviour more closely.

Key Takeaways

Several important lessons were learned from the project.

Traditional Data Needs Patient Insights

While clinical outcomes and physician research remain critical, patient perspectives add another layer of context that strengthens forecasting assumptions.

Cross-Functional Collaboration Improves Accuracy

Collaboration among commercial, medical, market research, and patient engagement teams throughout the project improved forecasting accuracy.

Continuous Validation Is Required

Patient preferences change over time. Forecasting models need constant refreshes with new market research, real-world evidence, and commercial performance data.

A Patient-Centric View of Forecasting Leads to Better Decisions

By understanding patient priorities, organisations can develop more effective launch strategies, educational programs, and commercial investments while improving long-term forecasting accuracy.

Future Outlook

As pharmaceutical organisations increasingly adopt patient-centric healthcare, forecasting models will continue moving beyond traditional market assumptions. Artificial intelligence, real-world evidence, digital health technologies, and advanced analytics will provide better access to patient perspectives in commercial planning.

Companies that successfully combine quantitative market data with qualitative patient insights will be better positioned to generate more accurate peak sales projections, allocate resources more efficiently, and develop therapies that meet both commercial objectives and patient needs.

About Pharma Insights Conference

Pharma Insights Conference convenes pharmaceutical executives, market researchers, forecasting specialists, patient engagement leaders, healthcare professionals, and technology innovators to explore the latest developments in life sciences. Through keynote presentations, expert panel discussions, networking opportunities, and educational sessions, the conference examines forecasting methodologies, patient-centric research, artificial intelligence, market access, commercial strategy, and healthcare innovation. It provides valuable opportunities for professionals seeking to improve forecasting accuracy and strengthen patient-focused decision-making.