Tag: ISPOR25

What to look for at ISPOR25 – Artificial Intelligence

After Modelling and Regulations & Pricing, and just a few days before ISPOR25, here is my take on the potentially interesting sessions on Artificial Intelligence (AI, which generally means: the use of Generative AI, or GenAI, in HEOR).

First, Sven Klijn, William Rawlinson, and Tim Reason are again offering their introductory course on Applied Generative AI for HEOR. Last year, I followed it in Barcelona, and it was nice. In my opinion, “nice” means that although I didn’t learn much more than previous presentations by the authors and my own experience, it was a great course for beginners because it struck the right balance between theory (which too many sessions end up only covering) and practical examples. Don’t expect hands-on exercises (that would be too long, and the course synopsis doesn’t mention that either). But “nice” to me means that the presenters dared to show actual working code, with all the humility that it implies. This year, they mention they’ll cover Retrieval-Augmented Generation (RAG) and agents. Hopefully, their coverage of these aspects will be as good as last year’s on the other topics.

Note that there is another course on AI and its use in Real-World Evidence (RWE) Research. I never attended this one, but I hope the instructors will give the audience practical instructions, independent of the AI tool their company is selling.

ISPOR’s key areas of focus for AI in HEOR (source)

Now on to the sessions! After several ISPOR sessions filled with hype from AI-enthusiasts and AI-deniers, we are slowly coming to some “âge de raison.” However, GenAI is still relatively new, and sessions reflect the need to cater to all audiences.

For the beginners (in AI), a few sessions will introduce GenAI and its use in HEOR. Even if hidden (intentionally or not), GenAI relies on prompt and prompt engineering; one session will present an overview of this technique. A second session will present an overview of progress and challenges brought by GenAI.

For the more advanced AI users, most sessions will talk about the newest tools. One session will talk about reliability in LLMs and prompting (as a side note, I will be interested in the Aide solutions that were teased for some time now). From another session’s title, advances in GenAI should be presented; however, the abstract lacks the latest trends, like agents and functions. For these, one should probably attend the session specifically on agents or this other session on RAG (both with one of the same presenters).

Another approach is from the perspective of AI applications. Literature reviews and AI will be covered in two sessions (AI-Assisted Literature Reviews: Requirements and Advances and Leveraging Automated Tools for Literature Reviews in Health Economics and Outcomes Research: Opportunities, Challenges, and Best Practices). RWD/RWE will be covered in three sessions: Identifying Gaps and Establishing a Development Plan for Consensus Real-World Data Standards and two commercial sessions (054 and 048; disclaimer: this last session is from my current employer). Health Preferences and AI have their own sessions, as do rare diseases and AI (with no less than three pharma companies as presenters!).

Finally, the most practical sessions, IMHO, will be the Research Podiums, as they should marry the technological approaches with the domain approaches. Interestingly, the first of these sessions, The Power and Pitfalls of AI in Health Data Analysis, only presents posters using NLP and Machine Learning (i.e. no GenAI per se). The second session, AI-Assisted Literature Reviews: Requirements and Advances, is focused on literature reviews. This year, it looks like there will be no sessions specifically focused on Modelling; my opinion is that either no significant progress was made (compared to previous ISPOR conferences) or this progress is now kept internally (for pharma’s own use or for consultants’ clients’ use).

Did I miss any important sessions? Do you have another take on sessions at this ISPOR conference or AI in HEOR? Although I enjoy a good quasi-philosophical debate on the good and evil of AI in HEOR, I’m happy to see practical applications being presented and discussed 🙂

What to look for at ISPOR 2025 – Regulations & pricing

ISPOR 2025 is now in about two weeks and in this second post about sessions to look for, I’ll talk about regulations and pricing (this is part of a series: last week, I wrote about Modelling; next week, I will write about AI).

IRA letters on a pile of scientific papers with a view of an American city at night

As the main edition of ISPOR is held in North America, the Inflation Reduction Act (IRA) will naturally attract considerable attention. It will start with the very first Plenary Session, promising to explore the impact of price limits on innovation and provide real-world examples.

The lessons learnt or (unintended) consequences-type of sessions are in vogue, with sessions like “Year 1 learnings“, “Implications for Providers“, “Did the IRA spook the industry” (from the perspective of rare diseases), “Unintended consequences“, and a discussion “Beyond Drug Negotiation“.

Here is one session to remind you that timing is essential … The IRA was introduced in 2022, under US President Biden, but the first Maximum Fair Prices will be implemented in 2026, under US President Trump. The latter has already introduced sweeping changes in the pharmaceutical research landscape in the US. But I found one interesting issue panel somewhat prophetic: “IRA Under Trump: What Is Next?“. Given the timelines for panel submission for ISPOR (before the 2024 elections), I have so many scenarios in my head about the authors trying to write the abstract broad enough to encompass potential futures while navigating the possible sensitivity of the situation, even before it happens. It will be an interesting panel to attend …

A panel also takes another perspective, wondering if the IRA became the US HTA. From the abstract, I understand the authors’ perspective, but I don’t agree: although the IRA will impact millions of Americans, it still lacks a direct impact on commercial plans. But it’s obviously a broader discussion than a terse comment in a blog post.

JCA letters on a pile of scientific papers with a view of an European countryside in the afternoon

It will also be the first ISPOR conference after the European Joint Clinical Assessment (JCA) process started in Europe. Therefore, it is a bit early to draw conclusions and look at lessons learnt. However, two interesting sessions will examine it from the outside: one will examine the global (i.e. ex-EU) impact of JCA, and another will consider JCA as an enabler of cross-border collaborations.

Finally, because I recently contributed to projects supporting investors with health economics tools and assessments, I will be interested in the Input/Output Modelling panel: it will look at the broader impact of investments in health and pharmaceutical products. Their abstract reminded me of some early work published by a former boss on the societal impact of vaccination (I wonder if vaccines will be mentioned, by the way). The last workshop (the last one mentioned here) is titled “HEOR meets investing“, and it is precisely what we recently did: early health economics modelling can greatly help secure investments by reassuring about the potential cost-effectiveness of a drug, and justifying studies to fill crucial input data gaps.

I missed some panels in this short helicopter view. Do you have any other suggestions?

Next week, I will look at AI’s potential progress in health economics. Stay tuned!

What to look for at ISPOR25 – Modelling

ISPOR25, the annual North American conference for the International Society for Pharmacoeconomics and Outcomes Research, is in three weeks. As usual, I’m planning for it by browsing its program. This time, I decided to share a few of my interests on my blog. ISPOR usually covers many topics, from “hardcore” statistical methods to top-level overviews of some issues, so I will focus on only a few topics. Feel free to connect with me if you want to discuss anything at or around the conference (or virtually). (And before we start, full disclaimer: I’m currently working for Parexel, but opinions shared here are only mine; otherwise, I would have written them on the company blog.)

Notes from Jep preparing the ISPOR25 conference with its program on a laptop screen in the background — As usual, browsing the ISPOR conference program brings pages of potentially interesting topics

This first post will be about my primary interest: HEOR modelling, what input data we use, the impact of broader frameworks and regulations, and how it is used. Stay tuned for the next posts: they will be about higher-level regulations and pricing, and one specific to AI.

Despite a huge number of posters (as usual) and a somewhat inefficient official search engine, we can still find interesting posters by following poster tours. For instance, the HEOR impact case poster tour (027) on Wednesday is presenting two takes on managed-entry agreements: Zemplenyi et al. will look at three outcome-based agreement models for sickle-cell disease while Arcand will argue that the epidemiological approach is still more valid than RWD for the re-evaluation of CAR T-cell therapies in Quebec. The Methodology Research in HEOR Poster Tour (55), the Cost-Effectiveness Evaluation of Medical Therapies (100) and the session on Novel Concepts and Frameworks in Health Economic Evaluations (131) will have some interesting presentation of real use of (sometimes new) modelling methods.

One aspect of HEOR Modelling that has not yet become mainstream (i.e. required by HTA agencies or taught before basic cost-effectiveness modelling) is the Generalized Cost-Effectiveness Analysis (GCEA) and other frameworks looking at incorporating other elements of value (other than costs and effects, broadly speaking). These frameworks are great and necessary to study the value of a healthcare intervention in a broader perspective than “just” the reimbursement perspective. However, in my opinion, some issues hinder their wider adoption: a wide agreement on their definition (and their usefulness, for a start) and established methods to collect input data. Two panels will be revisiting this: Challenges in the Implementation of Generalized Cost-Effectiveness Analysis (GCEA): Debating a Path Forward (059) and Global Guidance for Evidence-Based Value Assessment of Innovative Health Technologies: Feasible Reality or Idealistic Dream? (138).

Somewhat related, three other panels will explore specific value elements: cost of inequality, family spillover, and financial risk protection. And one session revisits the societal perspective and one the cost-benefit analysis.

From a tools perspective, one session will explore New Tools Facilitating Health Economics and Outcomes (078). It contains 4 interesting posters:

One will seemingly introduce a benchmark to assess a Large Language Model (LLM) performance at extracting information from models and literature reviews. I wrote “seemingly” because, if the intent is great, the rest of the abstract is not clear about how this system will assess the next model (not only the ones currently contained in the LLM database). And I am a bit doubtful about the use of the number of tokens as a measure of quality. Hopefully, the presentation will clarify these points.
One will present a review of the literature on the use of AI in health economics models. From the abstract, it looks a bit like the first review I presented with my previous boss, last year at WorldEPA 2024. Note I will present some interesting sessions on AI in HEOR in a following post.
Two posters/presentations will show tools to improve efficiencies: a VBA/R automator (I wonder about the sustainability of maintaining this type of program) and the use of metamodels.

This last poster is interesting because we will also present a poster about visual programming and try to convince the audience that this way of programming has many benefits for specific uses of modelling: brainstorming, early modelling, strategy (and introducing newcomers to complex topics in modelling).
In a real geek way, it is interesting to note that most of these sessions still rely on MS Excel and venture, from time to time, with R. Our poster introduces Typescript, but it’s more a side effect (due to the framework used). In addition, our solution can be extended to any programming language, including Python, for instance (a programming language used a lot in data science; besides the use of LLMs for HEOR, Python is not used very much in our domain).

To end this post, I will also follow with interest the session asking to Flip (to) the Script: Is It Time to Rethink Health Economic Modeling for HTAs? (073). It has been a decade since R was tested for modelling. There are now great packages, videos tutorials (example) and advanced training, a fast-growing group and a recently created HTA working group within the R Consortium. Still, modellers are mainly using MS Excel …

I didn’t mention sessions on causal inference, survival analysis, surrogate endpoints, … They are all worth attending. In your opinion, what session(s) did I miss in this brief overview?