Some of the most powerful breakthroughs happen when methods built for one discipline get turned on another. In this episode, Dr Andree Bates interviews Dr Irina Babina, CEO of Concr, on how computational techniques originally developed in astrophysics are being applied to oncology, helping predict how individual cancer patients will respond to treatment.

Irina shares her journey from genetics and targeted cancer therapy into building applied solutions, driven by a frustration many scientists recognise: good science doesn’t always reach patients fast enough. A pivotal patient experience reinforced her focus on personalised biology, because behind every dataset is a person, and oncology cannot be solved purely through averages.

Concr’s approach is built around Bayesian computation and uncertainty-aware modelling. Instead of assuming clean, complete datasets, the system is designed to work with missingness and fragmentation, updating predictions as new evidence comes in. Irina explains how Concr connects mechanistic biological modelling and preclinical drug perturbation data to patient multi-omics, imaging, treatment response, and outcomes data from both clinical trials and real-world settings.

A key application is Concr’s patient-level digital twin (“Farsight Twin”), which simulates an individual’s probability of response across therapies, estimates likely benefit, and helps stratify patients earlier in development. Irina shares a use case where Concr supported indication ranking from cell line data, then helped interpret phase 1 signal by estimating which patients benefited from the novel drug versus standard of care, enabling sharper inclusion and expansion planning.

Looking ahead, Irina argues we’re moving toward personalised oncology where population-level protocols fade, and decision-making becomes confidence-based, adaptive, and informed by longitudinal monitoring as tumours evolve over time.

Topics Covered

• Applying astrophysics-inspired methods to cancer biology

• Bayesian computation and modelling uncertainty

• Integrating multi-omics, imaging, trials, and real-world evidence

• Translational modelling from preclinical to clinical outcomes

• Patient-level digital twins and therapy response simulation

• Stratification, enrichment, and reducing early-stage uncertainty

• Pan-cancer modelling to improve rare cancer prediction

• The future of personalised oncology and dynamic monitoring

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan. Details at eularis.com.

If this episode described your situation, send me a LinkedIn DM starting with ‘SENSECHECK’ and two things: the question you’re trying to answer internally, and what’s currently in flight. I’ll reply with what I’d need to see to turn that activity into a defensible plan, and the next step.

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

Pharma doesn’t have an AI experimentation problem. It has an AI execution, scaling, and ROI justification problem. In this solo episode, Dr Andree Bates names one of the most expensive failure patterns in the industry: pilot purgatory.

A key theme is misdiagnosis. When AI stalls, organisations often blame platforms, data science capability, training, vendor selection, or “resistance to change”. Dr Andree argues these explanations are usually incomplete because they ignore the structural constraints that determine whether AI gets trusted, governed, adopted, and tied to real decisions at scale.

She outlines the core blockers she sees repeatedly: governance ambiguity, unresolved decision rights between global and local teams, data ownership disputes, incentive misalignment across functions, and adoption friction caused by tools that were never designed around real workflows. Treating adoption as a comms issue or solving with yet another pilot simply keeps the constraint untouched.

Finally, Dr Andree explains what breaking out of pilot purgatory actually takes: clear executive ownership of business outcomes (not just technical delivery), defined decision points where AI changes action, governance that accelerates scale rather than blocking it, cross functional stewardship models, and defensible value logic that survives board scrutiny. The organisations pulling ahead aren’t running the most pilots. They’re confronting what’s structurally broken early, then building a strategy and sequencing plan that makes scale inevitable.

Topics Covered

• What “pilot purgatory” is and why it’s so costly

• The tell tale signs: pilots, duplication, uneven adoption, decorative AI

• Why more pilots can make the stall worse

• Common misdiagnoses: tools, training, vendors, “resistance”

• The real blockers: governance, decision rights, data ownership, incentives

• Why adoption is a downstream symptom, not the core problem

• Rebuilding defensible ROI logic and board ready financial models

• What “good” looks like when organisations break out of purgatory

• Why delay compounds scepticism and weakens transformation capacity

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan.Details at eularis.com.

If this episode described your situation, send me a LinkedIn DM starting with ‘SENSECHECK’ and two things: the question you’re trying to answer internally, and what’s currently in flight. I’ll reply with what I’d need to see to turn that activity into a defensible plan, and the next step. 

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how the use of AI-based technologies can save them time and grow their brands and improve company results.This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

If you want, I can also pull 3 “quote graphic” alternates that are shorter and sharper from this solo transcript (there are loads of killer lines in here).

Dr. Andree Bates LinkedIn | Facebook | X

Cell therapies have huge potential, but cost, complexity, and centralised manufacturing have kept many of them confined to last-line use. In this episode, Dr Andree Bates speaks with Armon Sharei, Founder and CEO of Portal Biotechnologies, about what happens when AI meets cell engineering, and why point-of-care delivery could make personalised cell programming more practical, scalable, and safer.

Armon explains Portal’s core idea: cells are programmable machines. If you can reliably deliver multiple cargoes into cells, you can instruct new behaviours. Portal’s method briefly “squishes” cells through precision pores to disrupt the membrane so external material can enter, opening the door to complex cell engineering without permanent genome edits.

They explore where AI fits in: modelling cell behaviour. By combining perturbation experiments, rich readouts, and phenotypic screening, AI can help generate “virtual cell models” that suggest which RNA instructions to deliver to drive specific outcomes. The bottleneck is data at the right complexity, because many effects only appear when multiple pathways are changed at once.

A key takeaway is the safety and flexibility of transient RNA reprogramming. Unlike irreversible genetic modification, RNA fades within days, reducing long-term risk and making earlier-line use more realistic. Armon also discusses how point-of-care workflows may be regulated differently, with the machine treated as a device and the cargo as the drug.

Looking ahead, he paints a vision of infusion-centre cell programming: a compact system that takes blood, delivers tailored RNA instructions to immune cells, and returns them within hours, potentially bringing costs closer to mainstream biologics and expanding access.

Topics Covered

• Why delivery is the unlock for programmable cell therapies
• How Portal’s “cell squishing” delivery works
• Using AI to model cells and generate functional programmes
• The data bottleneck and why multi-perturbation datasets matter
• Phenotypic screening and lab-to-clinic feedback loops
• Transient RNA reprogramming vs permanent genetic modification
• Regulatory implications of point-of-care engineering
• Economics and scalability of point-of-care approaches
• Near-term opportunities in oncology and autoimmunity
• The future vision for infusion-centre personalised therapies

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan.Details at eularis.com.

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

AI platforms and tools solve specific problems. Strategy makes sure you’re solving the right ones, in the right order. If you want help mapping priorities as you evaluate what to roll out next, send me a LinkedIn DM starting with ‘PRIORITIES’ and two lines: what’s already in flight, and the decision you’re trying to make next.

Dr. Andree Bates LinkedIn | Facebook | X

Clinical trial site selection is one of the biggest hidden bottlenecks in drug development, and it’s still often driven by legacy relationships, spreadsheets, and habit. In this episode, Dr Andree Bates interviews Simon Arkell, founder of Ryght, Inc, about “AI Site Twins” and why the next era of site selection shifts from institutional memory to predictive, real-time analytics.

Simon explains why the current model produces terrible outcomes at scale: too many activated sites under-enrol, competition at sites is poorly understood, and sponsors often don’t see the failure until timelines have already slipped. He argues this is primarily a site selection problem, because “the easy button” of re-using familiar sites reduces data-driven decision making, even as trials get more complex and patient competition intensifies.

Ryght’s approach is to build AI-powered digital replicas of research sites, creating a unique identifier and a dynamic “twin” profile that continuously improves as new data arrives. Simon walks through how protocols can be matched to sites across countries, then enriched using harmonised public data, competitive trial context, and automated outreach that dramatically increases engagement. He also describes how different AI agents help fill missing information, find the right contacts, and capture context across email, portals, and voice interactions to improve future matching.

The upside is massive: faster feasibility, better site choices, shorter time-to-activation, earlier first-patient-in, and ultimately faster time-to-market. Simon links these operational gains to commercial reality: every month saved can mean earlier revenue, longer effective patent runway, and more lives impacted by getting therapies to patients sooner.

Topics Covered

• Why site selection is still a major bottleneck in clinical trials

• The true cost of underperforming sites and enrolment failure

• What an AI Site Twin is and how it differs from legacy databases

• Global protocol-to-site matching and competitive trial context

• Data harmonisation from messy public sources

• Agent workflows: enrichment, outreach, contact finding, and context capture

• Engagement rates and accelerating feasibility timelines

• Enrolment curve modelling and predicting site performance

• Security, HIPAA/GDPR compliance, and sponsor data integration

• Time-to-activation, first-patient-in, and time-to-last-patient-in KPIs

• Why “execution speed” and flywheels create a moat in AI applications

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan.Details at eularis.com.

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

For many life sciences teams, the first wave of AI has looked like copilots: smart search, quick answers, and help on demand. Useful, but passive. In this episode, Dr Andree Bates is joined by Parth Khanna, CEO and co-founder of ACTO, to explore what comes next: moving beyond copilots into role-based AI agents that proactively close knowledge gaps, improve field readiness, and operate safely inside regulated environments.

Parth shares his path into life sciences and tech, including founding an early NLP company in 2012 and then building ACTO after speaking with over 100 life science companies about field force effectiveness. Today, ACTO supports tens of thousands of professionals and hundreds of brand launches, and Parth argues the industry is now entering the “agentic era” where the real differentiator is not just model access, but how organisations build context, control, and change management around AI.

A key theme is why generic AI tools often fail inside enterprises. Parth outlines four requirements for agent success: context (role and job-specific personalisation), connection (stitching data sources and agent-to-agent workflows), control (testing, monitoring, observability), and change management (reducing fear and driving adoption). Without these, he says, many copilots and assistants end up underused, with people quietly reverting to old workflows.

Parth then introduces ACTO’s concept of role-based “super agents”, designed around a real job description (for example an MSL). Rather than a disconnected swarm of task bots, a “queen bee” orchestrator agent delegates to worker agents, checks outputs against compliance guardrails, and can be assessed with exams to quantify risk before deployment. This approach, he argues, makes AI both more powerful and safer for regulated field teams.

Finally, the conversation looks ahead. Parth believes the future of work depends on pairing AI capability with distinctly human strengths: strategy, judgement, and human connection. The winners won’t be those who automate the most tasks, but those who redesign roles so humans and agents amplify each other.

Topics Covered

• Why copilots are useful but fundamentally passive

• The shift from AI that responds to AI that acts

• Why generic tools fail: context, connection, control, change management

• Adoption reality: why many AI assistants go unused

• Quantifying risk and moving from black box to observable AI

• Role-based super agents and the “queen bee” orchestrator model

• Testing agents with exams before field deployment

• Guardrails, compliance, and agent-to-agent quality checks

• Human skills AI can’t replace: strategy, judgement, connection

• The future of MSL and field excellence in an agentic era

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan.

Details at eularis.com.

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Many pharma and life science organisations have been investing in AI for years: pilots across commercial, medical, regulatory, and R&D, innovation labs, steering committees, vendor spend, and genuine effort from smart teams. And yet the same story keeps showing up in boardrooms: ROI is unclear, adoption is patchy, and leaders struggle to explain how all the AI activity connects to strategic goals.

In this solo episode, Dr Andree Bates steps into “The Diagnostic Room” to explain why this happens, and why it’s usually not a technology, talent, or speed issue. It’s a diagnosis issue: organisations often haven’t identified what is actually constraining value, so they end up executing hard on the wrong problem.

Dr Andree shares a real example from a mid-sized pharma company that believed its AI programme was failing due to lack of velocity. On the surface, it was a reasonable hypothesis. But a focused diagnostic revealed three hidden structural blockers: unclear decision rights for scaling pilots into production, fragmented data ownership preventing access to the best datasets, and incentive misalignment where the people expected to adopt AI tools were not rewarded for the behaviours those tools required.

She then clarifies what a diagnostic is and is not. A diagnostic is not a strategy, roadmap, vendor shortlist, financial model, or implementation plan. Instead, it provides evidence-based clarity: what’s broken, how you compare to peers, what’s at stake, and what questions have been opened that cannot responsibly be answered in ten days. That clarity creates a shared language for leadership, replacing vague frustration with a precise problem statement.

The organisations pulling ahead are not simply those with the biggest budgets, but those willing to find what’s actually broken before trying to fix it.

Topics Covered

• Why AI initiatives can grow without creating measurable ROI

• The gap between pilots and a true AI strategy

• Misdiagnosis: executing brilliantly on the wrong problem

• What a diagnostic sprint is (and what it is not)

• Three hidden blockers

• Why working groups can’t fix structural AI constraints

• What a full strategic AI blueprint includes

• Why many AI business cases are untested projections

• How to improve board confidence with evidence, governance, and measurement

• Why diagnostics create speed by creating shared clarity

Eularis helps pharma and biotech leaders turn AI activity into board-defensible strategy and measurable commercial outcomes.

If your organisation has plenty of AI in motion but very little that moves the commercial needle in a way the board can see, start with our 10-Day AI Diagnostic Sprint. It’s a focused diagnostic that surfaces what’s actually broken and what’s blocking results, before you invest in a larger strategy effort.

The Sprint diagnoses the problem. The AI Strategic Blueprint that follows is where we build the board-defensible strategy and plan.

Details at eularis.com.

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

If this episode described your situation, send me a LinkedIn DM starting with ‘SENSECHECK’ and two things: the question you’re trying to answer internally, and what’s currently in flight. I’ll reply with what I’d need to see to turn that activity into a defensible plan, and the next step.

Dr. Andree Bates LinkedIn | Facebook | X

AI ethics has moved from theory to urgent necessity, especially as AI systems become embedded in healthcare, business decisions, and society at large. In this episode, Dr Andree Bates is joined by Dr Nadia Morozova, founder of Enriched Insights, to unpack what ethical AI really means in practice, and how organisations can innovate quickly without creating risk, bias, or governance failures.

Nadia shares insights from the global conversation on AI ethics, including discussions at Davos, and explains why trust is becoming the true competitive advantage. She argues that organisations should use AI to build stronger, more open relationships with customers and stakeholders, where technology acts as an enabler rather than the centrepiece.

The conversation then gets practical. Nadia outlines a human-centric framework for high-quality AI outcomes, covering accurate sampling, futureproofing (because models are trained on the past), data connectivity across sources, and responsible blending of human and synthetic data. She warns that leadership teams often treat AI as “magic”, assuming tools will solve complex problems like data harmonisation without the hard work of ontology, governance, and expert oversight.

A real-world example brings this to life: the Zillow case, where initial success collapsed as market dynamics shifted and the model failed to adapt in time, leading to huge losses. For Nadia, the lesson is clear: ethical responsibility is not a checkbox at launch, it requires ongoing monitoring, review, and culture change.

Nadia closes with a strategic message for leaders: start with business goals and targeted use cases, involve data experts early, build governance upfront, and keep humans in the loop throughout the AI lifecycle. Done properly, ethical AI is not a constraint on innovation, it is how you protect long-term value and trust.

Topics Covered

• Why AI ethics is now an urgent business and societal issue

• Trust, transparency, and accountability in AI deployment

• Human centricity as the foundation of high data quality

• Accurate sampling and avoiding “biased reality” in models

• Why futureproofing matters when algorithms learn from the past

• Data connectivity, governance, and the ontology problem

• Responsible blending of human and synthetic data

• Dangerous leadership assumptions about AI “magic”

• The Zillow case and what happens without ongoing oversight

• Strategy first: KPIs, targeted use cases, and right-sized models

• Skills gaps: technical roles, business acumen, and cross-functional teams

• Culture change and post-deployment monitoring

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

Digital biomarkers are turning everyday movement into clinically useful data, giving doctors a clearer picture of what’s happening between appointments, and giving pharma new ways to measure drug impact earlier and more precisely. In this episode, Dr Andree Bates interviews Dr Quique Llaudet, CEO and co-founder of Ephion Health, about precision monitoring and how AI-driven mobility analysis is changing both clinical care and drug development.

Quique shares his journey from academic research into entrepreneurship, driven by a desire to turn science into real products that help patients. Ephion Health grew out of early work with paediatric hospitals in Barcelona, where sensor technology used in rehabilitation and exoskeleton projects revealed a bigger opportunity: objective, high-sensitivity gait and movement analysis that can detect disease signatures and track progression over time.

The conversation breaks down what a digital biomarker actually is: a measurable signal of health captured via connected devices and analysed with digital methods. Ephion’s platform integrates multiple validated, off-the-shelf sensors to capture rich movement data in a short test, replacing blunt measures like the six-minute walk test with something both more sensitive and less stressful for patients. The system then combines key parameters into a single composite score to track progression and treatment response.

Quique also tackles the “black box” concern head on. He explains how their models are developed alongside clinicians, with clinical relevance checked throughout, and how doctors can inspect the underlying parameters behind the biomarker score in a dashboard. For rare diseases with limited data, he highlights deep collaboration with clinicians and patient associations, and the use of synthetic data to support modelling and testing.

Finally, Quique outlines the economics: reducing specialist assessment time, enabling more frequent remote monitoring, supporting earlier treatment adjustments, and helping pharma generate evidence in real-world settings. The long-term vision is continuous monitoring that helps clinicians act earlier, plus AI-assisted diagnosis and eventually prevention.

Topics Covered

• What digital biomarkers are and how they differ from traditional biomarkers

• Turning mobility data into clinically meaningful signals

• Multi-sensor monitoring: IMUs, pressure insoles, and EMG

• Why short tests can beat the six-minute walk test

• Composite biomarker scoring and tracking treatment response

• AI patterns clinicians may sense but cannot quantify

• Explainability and building models “hand in hand” with doctors

• Data challenges in rare disease and the role of patient associations

• Synthetic data for modelling and validation

• Economic impact: time savings, remote monitoring, and better treatment adjustment

• Pharma use cases: real-world evidence and earlier efficacy signals in trials

About the PodcastAI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

Digital twins have become one of the most promising tools in Alzheimer’s research, but the bigger story is what happens when they scale across disease areas. In this episode, Dr Andree Bates interviews Aaron Smith, Founder and Head of Machine Learning at Unlearn AI, about how “digital twin generators” can transform trial design by modelling realistic patient progression and improving statistical power without compromising the fundamentals of randomised controlled trials.

Aaron shares his journey from academic mathematics into computer vision and machine learning, then into biopharma, where Unlearn began by building generative models that learn the joint distribution of clinical variables. In practice, that means the model can take baseline patient measurements and generate likely future progressions that are as indistinguishable from real clinical records as possible.

The conversation dives into a key misconception: digital twins are not only about replacing control arms. Aaron explains a regulatory friendly approach where you keep standard trial structure, but add counterfactual information for every patient into the analysis. Unlearn’s best known method, ProCOVA (prognostic covariate adjustment), summarises a predicted control outcome per patient and uses it for covariate adjustment, creating more efficient treatment effect estimates. The headline result is simple: you can increase power, or reduce recruitment burden while maintaining power, potentially speeding time to results.

Finally, Aaron explains why scaling across diseases is genuinely hard. Data structures differ wildly by indication, missingness can block transfer learning, and areas like oncology require modelling complex treatment histories. He also highlights that combining sources is not just “more data”, it demands careful harmonisation and context modelling to avoid biased predictions, especially when bringing in real world evidence.

Topics Covered

• What “digital twin generators” are in clinical trials

• Generative modelling of clinical records and disease progression

• Counterfactual prediction under standard of care

• Why replacing control arms is not the only use case

• ProCOVA and prognostic covariate adjustment

• Getting more statistical power and reducing trial size

• FDA openness to digital twins in trials and what it enables

• Why scaling across disease areas is not just parameter tuning

• Missing data, confounding context, and data harmonisation

• CNS versus oncology modelling challenges

• Real world evidence and how to validate digital twin models

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

AI in drug development is moving beyond “failure prevention” into something much bigger: redesigning how we discover, develop, and deliver medicines. In this episode, Dr Andree Bates speaks with Vitalay Fomin of Numenos about biomarker discovery, patient stratification, and why the next breakthroughs come from breaking down data silos across diseases, modalities, and even species.

Vitalay shares his background across biotech and pharma, including work in biomarker discovery, translational medicine, and data science, and how frustration with existing approaches led her to build a new architecture for clinical genomic insights. A core theme is that traditional methods often oversimplify biology by forcing outcomes into binary labels and treating each disease area as an isolated box, even when the available data is too limited to answer meaningful questions well.

The conversation explores how foundation model approaches can unify clinical, genomic, transcriptomic, proteomic and imaging signals to create a fuller “biological fingerprint” of each patient. Vitalay explains how this can enable earlier insight from single-arm trials by effectively benchmarking against standard-of-care cohorts, helping teams enrich later-stage trials with the right subpopulations sooner, and reducing time and cost.

They also discuss the real blockers to adoption: not only scientific conservatism, but commercial uncertainty around how Big Pharma structures deals with tech-bio companies that bring platforms rather than single assets. Vitalay argues that explainability is non-negotiable in this space, because clinicians, scientists, patients, and regulators will not trust black-box predictions.

Topics Covered

• Why AI is shifting from failure prevention to pipeline redesign

• Biomarker discovery beyond binary responder vs non-responder labels

• Breaking disease silos to learn across indications

• Multimodal integration: DNA, RNA, protein, imaging, and clinical data

• Using foundation models to bridge trial data and real-world data

• Patient stratification and trial enrichment from early studies

• Reverse translation and identifying unmet need before target hunting

• Explainability, trust, and regulatory readiness

• Adoption barriers: culture, champions, and deal structures for tech-bio

• Misconceptions about AI in drug development and why “press a button” is a myth

About the Podcast

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

Enterprise AI is shifting from experiments to infrastructure, and that changes everything. In this episode, Dr Andree Bates interviews Jocelyn Houle, Senior Director of Product Management at Securiti.ai, to explore the future of enterprise AI, agents, automation, and the single biggest blocker to scale: trust.

Jocelyn shares what she is seeing across highly regulated industries as organisations move beyond proof of concept into production. She explains why the agent era raises the stakes: when you add LLMs into workflows, systems become non-deterministic and harder to trace end to end. In her words, once the data goes in, you cannot easily untangle it, so organisations need stronger controls around permissions, auditing, and policy enforcement.

A major theme is that data foundations matter more than ever. Jocelyn warns that agents will not magically repair messy data, they will expose weak data quality immediately. From there, she outlines how trust can be won or lost at the prompt layer, both outbound (what the model says to customers) and inbound (what users share with the organisation). She also discusses “toxic combinations”, where overlapping access can accidentally leak sensitive information, plus the growing need for prompt screening and tracking to reduce risk.

The conversation also digs into explainability and auditability, with Jocelyn being refreshingly honest that the perfect solution is not here yet. Instead, enterprises are using practical approaches like benchmarking releases side by side, cataloguing AI agents in use, and building governance that is starting to look more like modern cybersecurity: baked in from the start, not added as an afterthought.

Jocelyn closes with clear advice for leaders: start “left” with raw data controls, build a truly cross-functional team, and begin setting up auditability even with imperfect tools, because regulators are catching up and they will expect responsible behaviour.

Topics Covered

• Where enterprise AI adoption really stands today

• What makes AI agents different from traditional automation

• Non-determinism, traceability, and why permissions matter

• Data mapping, policy controls, and reducing sensitive data leakage

• Prompt security: outbound and inbound trust risks

• “Toxic combinations” and exposure through agent workflows

• Explainability, benchmarking, and parallel release testing

• AI governance becoming as essential as cybersecurity

• Top 3 pieces of advice for CTOs starting their AI journey

• Why enterprise AI will become so embedded we stop talking about it

AI For Pharma Growth is the podcast from pioneering Pharma Artificial Intelligence entrepreneur Dr Andree Bates, created to help pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands, and improve company results.

This show blends deep sector experience with practical conversations that demystify AI for biopharma leaders, from start-up biotech right through to Big Pharma. Each episode features experts building AI-powered tools that are driving real-world results across discovery, R&D, clinical trials, medical affairs, market access, regulatory, insights, sales, marketing, and more.

Dr. Andree Bates LinkedIn | Facebook | X

About the Podcast