Hemal Somaiya, Chief Strategy Officer, PharmaForceIQ
KEY TAKEAWAYS:
• Real-time clinical triggers enable engagement at precise treatment decision moments
• Publisher-level affinity data eliminates digital media waste across 7 million physicians
• AML case study achieved 47% target share within five months
• Machine learning automatically optimizes spend at individual physician level
• Trigger-based targeting identified 400 previously invisible high-value prescribers
The pharma industry's embrace of omnichannel marketing has created a paradox: more channels, more data, more spend, but diminishing returns on prescription outcomes. Hemal Somaiya, Chief Strategy Officer at PharmaForceIQ, argues the industry has stopped short of true transformation.
"We really believe that just connecting the dots across these channels is not sufficient because that's really what omnichannel means," Somaiya explained. "But you have to take it to the next level where you are connecting the dots across the entire ecosystem from data to deployment to measurement."
Her company's "optichannel" approach moves beyond channel coordination to ecosystem integration, delivering what most pharma marketers claim is impossible: improved prescription lift with reduced marketing spend. The difference lies in real-time personalization powered by daily data feeds and machine learning optimization, capabilities that transform when and how brands engage physicians at moments of clinical decision-making.
The Real-Time Data Imperative
Traditional pharma data infrastructure delivers prescription insights six or more weeks after prescribing events, a latency that renders targeting decisions ineffective, particularly for rare diseases where patient encounters are sporadic. Somaiya's platform addresses this temporal mismatch with daily and weekly data feeds across clinical triggers, prescription behavior, and physician engagement patterns.
The foundation is PharmaForceIQ's proprietary affinity dataset covering over 7 million physicians, dynamically profiling where individual doctors engage across channels and publishers. "At PharmaForceIQ what we have done is build this proprietary affinity data set which is on 7 million+ NPIs, both Type 1 and Type 2," Somaiya noted, "and for each of these NPIs we have profiled them to understand where are they going in a dynamic manner, what are they most engaging with."
But data scale alone doesn't solve the timing problem. The critical innovation is connecting real-time clinical signals, patient diagnoses, prior authorizations, prescription fills, to automated engagement triggers. "Understanding that a physician has diagnosed an eligible patient on a weekly or daily manner is important," Somaiya emphasized. "Similarly for physician prescriptions for your brand, competitor brand, knowing that mostly six weeks later is a moot point. But if you know that on a daily or weekly basis, that's critical."
For specialty brands, this timing precision is existential. Community oncologists may encounter eligible patients only once every six to twelve months. Traditional reach-and-frequency campaigns waste resources engaging physicians with no current patient need while simultaneously missing the narrow window between diagnosis and treatment selection. "If that patient opportunity is not going to present till November, then you've engaged at the wrong time," Somaiya explained. "The physician is not going to remember in November that email that you sent in the month of January."
This approach inverts the traditional targeting model. Instead of maintaining constant physician touchpoints regardless of clinical context, trigger-based engagement activates only when real-time signals indicate an imminent treatment decision. The result is higher relevance, reduced physician fatigue, and improved conversion, all while decreasing total brand touchpoints.
Publisher-Level Precision and Hidden Digital Waste
The pharma industry's adoption of affinity-based targeting has been superficial, according to Somaiya. Most vendors provide only channel-level insights, identifying that a physician has "affinity for banner ads" without specifying which of 500 possible websites justify media investment. This granularity gap represents significant hidden waste in digital budgets. PharmaForceIQ's dataset provides dynamic, publisher-specific affinity data, enabling precise media placement decisions.
But precision in targeting must connect to precision in measurement and optimization. The platform measures impact at the individual physician level in real time, then uses machine learning to automatically route media dollars toward high-performing channel, publisher, and content combinations. "If you are measuring in real time at one-to-one physician level, you need to be able to have an engine that's going to continue to route your dollars in a very impactful manner," Somaiya stated, "where you're going to continue to evolve the campaign and reduce your media spend."
This continuous optimization loop is what Somaiya calls "agile media", a departure from traditional agency models where annual plans lock in media allocations with limited flexibility. The pharma industry has grown accustomed to justifying digital investments through leading indicators: email open rates, website visits, click-through rates. Somaiya argues these engagement metrics no longer justify budgets in an environment of intensifying ROI scrutiny.
"We are guiding our clients to spend less from overall media spend perspective, but increase their impact by reducing the media spend significantly," she noted. "The email engagement rates or banner ads and so on is not enough anymore." Her approach shifts accountability to lagging indicators, new prescription lift, total prescription volume, revenue impact. This measurement philosophy reflects a broader maturation in pharma marketing, where finance and executive leadership increasingly demand clear connections between marketing activities and commercial outcomes.
The specificity challenge becomes clear in Somaiya's pointed example: "If I'm going to go to a client and tell them Dr. John Smith has affinity to a banner ad, they can deploy that banner ad on 500 different websites. Where should a client spend the media dollars to deploy that ad?" The efficiency model is counterintuitive: use machine learning not to increase performance through additional spend, but to eliminate waste and reduce total investment while maintaining or improving outcomes.
The 400 Hidden Prescribers
PharmaForceIQ's AML case study revealed a striking blind spot in traditional pharma targeting: 400 physicians who were generating prescriptions despite being absent from the brand's target list, sales force call plans, and all promotional activities including speaker programs and advisory boards. These "hidden prescribers" were identified through trigger-based signals, clinical decision data points, prior authorizations, and online behavior patterns that indicated imminent treatment decisions.
The brand faced significant challenges: second to market with a slightly inferior clinical profile, limited to second-line relapsed/refractory indication while the leading competitor held broad indication rights, and operating in a rare disease space where community oncologists encounter eligible patients only once or twice annually. "This is a brand in the AML space, second to market, slightly inferior overall clinical profile versus the leading brand in the market," Somaiya explained.
The results validated the approach with remarkable speed and scale.
Don't just read about it, be in the room at Pharma USA 2026 (March 17-18, Philadelphia). Visit the website here.
"There was a 24% uptake from NRX," Somaiya reported. "More meaningfully if we continue to dig deeper, these results were achieved just within five months. We already saw the engagement rate go up by that measure and then NRX go up just for their target list from 38% to 47%."
The 400 newly identified physicians represented net incremental opportunity that would have remained invisible under historical prescribing-based targeting models. "We were able to drive prescriptions meaningfully from these 400 HCPs which otherwise may likely have not prescribed to that brand," Somaiya emphasized. "These 400 HCPs were not called upon by the rep. They were not being targeted in any way, shape or form."
For specialty and rare disease brands, these emerging prescribers, physicians new to a therapeutic area, those in non-traditional practice settings, or doctors whose patient mix is shifting, may represent twenty to forty percent of total market opportunity. Pharma targeting methodologies built on decile analysis and historical prescription data systematically exclude these high-value segments.
Four Pillars of Optichannel Success
Somaiya outlined four essential elements that distinguish optichannel from traditional omnichannel approaches. The first is real-world data-driven engagement that operates on clinically relevant timelines rather than marketing calendar schedules. "Real-world real-time data feeds are critical as one of the guiding principles of optichannel essentials," she stated.
The second pillar is continuous optimization powered by machine learning. "It's not just getting the real-time insights, but how are those insights feeding into your real-time deployment, real-time measurement and evolution of your campaigns on an ongoing basis," Somaiya explained. "And you need a technology machine learning driven platform that is going to allow you to do that because manually you're just not going to get there."
The third element is strategic focus on efficiency over volume. "Less is more," Somaiya emphasized. "We are guiding our clients to spend less from overall media spend perspective, but increase their impact by reducing the media spend significantly."
The fourth pillar is one-to-one personalization at scale. "It's the world of personalization and when we all talk big game about AI and machine learning, you have to truly reach every customer where they are and do that one-to-one targeting versus the good old target list segmentation approach," she noted. The platform flags results at the individual physician level, enabling both automated optimization and transparent accountability. "You knew what is working and what is not working, not just overall for the campaign but at individual HCP levels."
From Omnichannel Hype to Optichannel Accountability
The pharma industry's omnichannel journey has produced mixed results: significant infrastructure investment, proliferation of digital channels, and growing data complexity, but inconsistent commercial impact. Somaiya's critique cuts to the core issue: connecting channels without integrating the entire ecosystem from data through deployment to measurement leaves fundamental problems unsolved.
"We work across several clients today. Small biotech, mid-size biotech and across every single client, when we first engage with them, they'll tell us we're doing omnichannel and we're not seeing measurable output," Somaiya observed. "There are very, very few clients who will say yes omnichannel is working and we've figured it all out."
Her company's value proposition directly addresses the efficiency imperative dominating pharma commercial strategy. "We help clients achieve those lagging indicators while concurrently reducing their overall spend for marketing," Somaiya stated. "So we're not going to come to the table and tell our clients increase your spend and that'll help you increase your impact. That's easy to do. We reduce your spend and maintain your impact."
PharmaForceIQ's 100% client renewal rate suggests the optichannel model addresses pain points traditional approaches miss: the timing mismatch between data availability and clinical decisions, the waste in channel-level versus publisher-level targeting, the accountability gap between engagement metrics and prescription outcomes, and the cost pressure requiring efficiency gains rather than incremental investment.
The broader implications extend beyond any single platform. As pharma portfolios shift toward specialty and rare disease assets with sporadic patient encounters and narrow treatment windows, marketing playbooks built on primary care and chronic disease models will increasingly underperform. The maturation of real-time data infrastructure and machine learning capabilities raises the bar for what constitutes acceptable targeting precision and measurement rigor.
Commercial organizations face a strategic choice: continue optimizing omnichannel approaches that connect channels while accepting delayed data, superficial affinity, and engagement-based measurement, or redesign around trigger-based engagement, publisher-level precision, and prescription-level accountability. "AI just overall came along the journey of our platform because we wanted precision and we wanted that real-time ability to continue to update how we are responding to what the customer is engaging with and not engaging with," Somaiya explained.
The efficiency imperative, doing more with less in an environment of margin pressure and budget scrutiny, will likely accelerate this evolution. The question is whether pharma organizations can move fast enough to capture the opportunity before more agile competitors establish advantages that prove difficult to overcome.
To get you highlights of Pharma Customer Engagement USA faster, we are using generative AI technology to summarise the transcripts of the sessions. If you have any feedback about the summary, please contact lucy.fisher@thomsonreuters.com.
Discover more on this topic at Pharma USA 2026 (March 17-18, Philadelphia) - North America's largest cross-functional pharma gathering. Visit the website here.
