Menu

HEOR Strategy

Using AI in HEOR

Discover how artificial intelligence is reshaping health economics and outcomes research.

The Course Course Content Next Session

About the course

AI is no longer just a future possibility for health economics and outcomes research (HEOR) — it is already changing how evidence is synthesised, how economic models are built and how real-world evidence is analysed. Tools that were experimental two years ago are now embedded in the workflows of leading consultancies, contract research orgasnisations (CROs) and life science companies. Yet adoption remains uneven, and the gap between organisations that are using AI effectively and those that are still watching from the sidelines is widening. For professionals who commission, oversee, undertake or evaluate HEOR work, understanding what these tools can and cannot do is now a core competency — not a technical curiosity.

This course provides a structured, critical introduction to AI across the major HEOR disciplines. Over six modules, participants move from the current landscape through evidence synthesis, health economic modelling, real-world evidence and governance — with a consistent emphasis on practical application, validation and the limitations that matter when AI-assisted outputs feed into health technology assessments (HTAs) and reimbursement decisions. The course will be refreshed annually as the technology and regulatory environment evolves, ensuring that participants are learning what is, rather than what was current.

Delivered via IHLM’s online learning platform and through live interactive virtual tutorials this course will enable you to harness the possibility of AI in your own HEOR or market access practice.

What you’ll learn

On completion of this course you’ll be able to:

  • evaluate AI tools critically and distinguish genuine efficiency gains from hype
  • commission, oversee or undertake AI-augmented evidence reviews with confidence, knowing where human judgement remains essential
  • identify where AI can add immediate value across your organisation’s modelling, evidence synthesis and real-world evidence workflows
  • assess the quality and regulatory acceptability of AI-assisted outputs against HTA body and journal expectations
  • build a proportionate AI adoption strategy covering tool selection, validation, training and governance

How you’ll learn

This course is broken down into six manageable weekly modules:

  • work at your own speed through a carefully curated collection of self-paced online learning materials that include video lectures, podcasts, interviews and real-world case studies
  • evidence-based research from peer-reviewed publications will help you dig more deeply into topics that really interest you
  • you are not alone – you will interact with other course members, collaborate on learning activities and get direct feedback and coaching from the course leader during weekly virtual tutorials
  • earn professional certification by completing weekly learning activities and mini-projects

This course should take approximately 6 – 8 hours per week. You can expect to devote about 2 – 3 hours per week to self-paced learning, about 2 hours per week preparing for and participating in the virtual tutorial and 2 – 3 hours per week applying your knowledge through learning activities and mini-projects. Every tutorial is recorded so you can rewatch it at any time.

Who should take this course?

This course is designed for market access, medical affairs and HEOR professionals in life science companies, consultancies and CROs who need to understand how AI is changing the way HEOR work is planned, commissioned and delivered. It is equally relevant for regulatory affairs professionals evaluating AI-assisted submissions and for HTA or procurement professionals encountering AI-generated evidence with increasing frequency. No technical background in AI, machine learning or programming is required — the course is built around practical application and critical appraisal rather than technical implementation.

About the certificates

Upon successful completion of the course you’ll receive an:

  • IHLM Certificate of CPD Completion – This may be useful for course members who belong to professional bodies that have Continuing Professional Development requirements. The course has an estimated 60 hours of guided learning.
  • IHLM Professional Certificate in Using AI in HEOR – This is evidence of the competencies and capabilities you’ve developed during the course. The award of a professional certificate requires completion of learning activities and mini-projects during each module.

How to register

Ready to start? Just click the ‘Register now’ button at the top of this page or use the ‘Ask us a question’ button if you’d like to talk to one of our course facilitators. The fee for this course is £745 per person. If you’d like to pay in instalments you can arrange this by contacting us at: registration@heorinstitute.com.

All registrations are subject to our terms and conditions which are available here. By registering for an IHLM course you are accepting these terms and conditions and agreeing to be bound by them.

 

 

Module 1: The AI Landscape in HEOR — What Has Changed and Why It Matters

Artificial intelligence has moved from theoretical prospect to working reality across multiple health economics and outcomes research (HEOR) disciplines. This module maps the current landscape — where AI tools are genuinely useful today, where they are promising but immature and where the claims outrun the evidence.

  • the shift from manual to augmented workflows — how large language models, machine learning and natural language processing are being applied across HEOR disciplines
  • a practical framework for evaluating whether a new AI tool delivers genuine efficiency gains or simply automates the wrong things faster
  • how health technology assessment (HTA) bodies, journals and professional organisations are responding to AI-generated evidence
  • the commercial and competitive implications of AI adoption for organisations that commission or conduct HEOR work

Module 2: AI in Evidence Synthesis — From Screening to Synthesis

Evidence synthesis is where AI is most mature, most practically useful and most likely to change how work is commissioned and delivered. This module goes deeper than any other in the course, covering the specific tools, workflows and validation approaches already reshaping how reviews are conducted.

  • AI-assisted screening and study selection — how tools like ASReview, Rayyan and LLM-based classifiers reduce screening workload and what validation is needed before relying on their outputs
  • automated data extraction — using AI to extract study characteristics, outcomes and risk-of-bias judgements from full-text articles, and the quality assurance steps required
  • AI-assisted search strategy development and grey literature identification — how language models accelerate search string construction and source identification
  • the emerging frontier of AI-generated narrative summaries and evidence maps, and why human oversight of the interpretive layer remains non-negotiable

Module 3: AI in Health Economic Modelling

Health economic models have historically been built by hand in spreadsheets — a process that is time-consuming, error-prone and difficult to audit. This module examines how AI is beginning to change the modelling workflow while being candid about the current limitations.

  • using large language models to draft VBA macros, R scripts and Python code for decision trees, Markov models and partitioned survival models
  • automated error checking — how AI tools can identify formula errors, logical inconsistencies and structural problems faster than manual review
  • AI for parameter estimation and literature scanning — accelerating the identification and extraction of model inputs from published evidence
  • why model conceptualisation, structural assumptions and clinical plausibility still require expert human judgement and are unlikely to be automated soon

Module 4: AI in Real-World Evidence and Outcomes Research

Real-world evidence generation involves large, messy datasets and complex analytical decisions. AI and machine learning methods are increasingly applied to tasks that were previously impractical — but their adoption in HTA-grade research requires careful attention to transparency and reproducibility.

  • natural language processing for unstructured clinical data — extracting outcomes, adverse events and treatment patterns from electronic health records and registry narratives
  • machine learning for predictive modelling and patient stratification — identifying subgroups, predicting treatment response and modelling disease progression
  • automated coding and data linkage — standardising and harmonising data across registries, claims databases and hospital information systems
  • why “black box” methods face resistance from HTA bodies and what is needed for machine learning-derived evidence to gain acceptance

Module 5: Quality, Governance and Validation of AI in HEOR

Adopting AI without governance is a risk. This module addresses the quality assurance, ethical and regulatory considerations that organisations must navigate when integrating AI into HEOR workflows.

  • validation frameworks — how to design and document quality checks that provide confidence in AI-generated screening decisions, data extractions and model code
  • reporting and transparency standards — emerging guidelines on disclosing AI use in systematic reviews, economic evaluations and HTA submissions
  • bias, hallucination and reproducibility — the specific failure modes of large language models in HEOR and the practical safeguards that mitigate them
  • organisational governance — building internal policies for AI tool selection, data security, intellectual property and accountability

Module 6: Strategic Adoption — Building an AI-Enabled HEOR Capability

Understanding what AI can do is the starting point. This final module addresses how to adopt AI tools strategically — without overcommitting to tools that may not last or underinvesting in capabilities already delivering returns.

  • assessing readiness — evaluating current workflows, data infrastructure and team skills to identify where AI will deliver the most immediate value
  • build, buy or commission — deciding between in-house capability, commercial platforms and external consultants using AI-augmented methods
  • managing the transition — change management, training and workflow redesign for teams integrating AI into established processes
  • staying current — monitoring a rapidly evolving landscape, evaluating new tools critically and refreshing your AI strategy as technology and regulation mature

 

Course Leader

Benedict Stanberry

Course Factfile

  • Next session: 26 February 2027
  • Duration: 6 weeks
  • Commitment: 6-8 hours a week
  • Qualification: Certificate
  • Cost: £745
  • Location: Online

Related programmes

  • Strategic Evidence Generation for Market Access and HTA

    • Find out more about Using AI in HEOR

    Enquiry

    More courses

    All courses

    Insights

    • Hello My Name Is…

      February 13, 2026

      Introducing yourself properly is surely a basic necessity if we’re to be a respectful and trusted caregiver?

    • Caesarean deliveries and value-based care

      May 9, 2025

      Can glove change help reduce the costs and improve the outcomes of caesarean sections – enabling obstetric teams to deliver more value-based care?

    Upcoming Courses

    Enquiry