Brindha Chandrasekaran’s Post

Replicating an Economic Model ≠ Evaluating an AI Model Many early GenAI use cases in health economics (HE) focus on replicating existing models. But replication isn’t evaluation. Some GenAI tools can replicate existing health economic models with results that perfectly align with human-built models in terms of outputs like ICERs. Sounds impressive — but is it enough? Or is this really the direction we should take when evaluating AI-assisted HE models? Is it feasible or realistic that every time in real HTA submissions we build two models (AI vs. human) just to compare? ✅ Replication may test a single model’s performance, but it doesn’t advance the evaluation framework that’s needed to assess trustworthy and transparent AI-assisted modelling. Let me ask a simple question to my HEOR and HTA colleagues: If there’s an AI tool that replicates a model in disease area X, producing exactly the same outputs (Cost, QALYs, ICER) as an existing human-built model — does that alone remove your concerns about its transparency and reliability? And if you use that same AI tool to build a de novo model from scratch, how can you guarantee it will still be 100% aligned with a hypothetical human-built model (if one exists)? ✅ Also — let’s be fair. Humans make errors too. Models are built with uncertainty, and decisions are probabilistic, influenced by evolving evidence. Deviation between AI-built and human-built models does not necessarily mean AI is wrong. Maybe new data is emerging. Maybe AI uses different statistical methods that are actually better than Excel. Maybe it applies updated assumptions. As the classic quote says: “All models are wrong, but some are useful.” ✅ When we talk about “evaluating AI-built HE models”, we’re actually talking about two layers of evaluation: Evaluating the HE model itself — calculations, parameters, assumptions, settings, as highlighted in the NICE HTA Lab report. Evaluating the AI tool that builds the model — its trustworthiness, transparency, and reproducibility. This second layer is foundational. Every pharma, biotech, consultancy can build their own AI tool. There’s no single “universal” AI tool for HE modelling — nor should there be. For trust to be earned, we must evaluate the AI itself: What AI architecture is being used? If it’s RAG, what knowledge base is feeding it? If it’s an Agentic model, what supporting evidence does it output (e.g., R/Python survival analysis code, documentation of decision steps)? Replication and comparison are useful starting points. But it’s time for the HEOR community to move beyond replication and build robust evaluation frameworks tailored to GenAI’s strengths and risks — especially around transparency, documentation, and human oversight. 👉 NICE HTA Lab project: https://lnkd.in/e7rXkcVH Curious how others in #HEOR and #HTA are approaching this. Let’s discuss. #GenAI #HTA #Transparency #AgenticAI # #HTAinnovation

IMPACT ASSESSMENT 2.0? 👋🏼This Funding the Frontier might be an interesting tool for health research funders and policy makers! 👇🏼 In international health research, funding agencies could analyse their portfolios and benchmark against each other, to assess how impactful are their grants (e.g. citations in clinical trials, downstream patents, new legislation or clinical guidelines based on them, etc). Another interesting study hypothesis could be to compare across domains (e.g. disease areas) to identify emerging trends, gaps and underexploited opportunities. All this information could guide investments and help shape better policies, for the benefit of people worldwide. And yes there will be correlations rather than causality relations, incomplete data, a myriad confounding factors to weed out, and a myriad of other complex issues to factor in before reaching any conclusion … but that’s part of the excitement of testing new tools and methods. What do you think? 🤔 #healthresearch #researchfunding #fundingagencies #grants #impact #impactassessment #researchpolicy European Commission European Parliamentary Research Service Panel for the Future of Science and Technology (STOA) Joanna Drake Maria Pilar AGUAR FERNANDEZ Signe Ratso Marina Zanchi Stéphane Hogan Sandra Gallina

🔍 Harmonizing Health Technology Assessments Across Europe The new EU Joint Clinical Assessment (JCA) framework marks a pivotal shift toward a unified approach in evaluating the clinical effectiveness and safety of new health technologies. Introduced under Regulation (EU) 2021/2282, it aims to streamline national health technology assessments (HTAs), reduce duplication, and improve patient access to innovative therapies across member states. While JCA focuses on clinical evidence and safety, national systems still handle economic evaluations such as cost-effectiveness analyses. The article underscores the need for early alignment between Health Technology Developers (HTDs) and national HTA bodies—particularly around PICO parameters (Population, Intervention, Comparator, Outcome)—to ensure efficient integration of clinical and economic evidence. Key recommendations include: Sharing national PICOs early to align evidence generation. Selecting populations and comparators based on clinical—not economic—criteria. Leveraging patient-reported outcomes to inform quality-of-life assumptions in economic models. Using pragmatic approaches to safety and surrogate data. Embracing innovation in modelling, including AI and large language models, for faster, more adaptable evaluations. Ultimately, the JCA offers an opportunity to enhance transparency, efficiency, and equity in access to healthcare innovation across Europe—if paired with strong collaboration and methodological innovation among regulators, HTAs, and industry stakeholders. Adam Johns André Andrade, MBA Sukhvinder (Sukhi) Johal

🟤UK is redefining the future of clinical research - twice as fast, powered by AI. Last week, the UK announced that the average time to approve a clinical trial has dropped from 91 to just 41 days. That’s twice as fast - achieved not by cutting corners, but by rethinking how regulation and technology can work together. The Medicines and Healthcare products Regulatory Agency (MHRA) implemented a risk-proportionate approach in 2023 - assessing over 4,600 applications in the first year. The result? ✅ 99% of initial applications reviewed within 30 days ✅ 99.9% of amendments processed within 35 days ✅ Faster access to life-saving therapies for patients Behind these numbers - AI is the silent accelerator. MHRA introduced bespoke AI tools such as The Knowledge Hub (to flag issues in past submissions and provide clearer guidance to sponsors) and The GMP Compliance Checker (to verify manufacturing documentation in seconds instead of hours). Together, they freed experts to focus on what truly matters - complex safety and scientific assessment. But this is only the beginning. In April 2026, new legislation will make these reforms permanent: • All UK trials will have to be publicly registered and publish results, including plain-language summaries for patients. • Sponsors will get more flexibility - 60 days to respond to regulator feedback (instead of 14). • Patients will be able to search and join trials directly through the NHS app. Transparency. Speed. Predictability. These are not buzzwords anymore - they’re becoming regulatory standards. The UK is positioning itself as a global leader in clinical research, balancing speed and safety with technological precision. This moment matters - because when someone is fighting for their life, every day counts. https://lnkd.in/dPRrWm5E #ClinicalResearch #AIinHealthcare #MHRA #Innovation #RegulatoryScience #FutureofTrials #Leadership #LifeSciences

The World Health Organization is pioneering a transformative shift in medical research by integrating climate and environmental outcomes into clinical trials. 🌍🩺 This initiative enhances the sustainability of healthcare interventions while strengthening global health security amid evolving environmental challenges. Building on established frameworks, the new guidelines—SPIRIT-ICE and CONSORT-ICE—specifically target randomized trials to standardize reporting on climate impacts. The development process employs a rigorous, multi-stage methodology including comprehensive literature reviews, expert Delphi surveys, and consensus meetings with key stakeholders. Ethical approval is anticipated by September 2025, marking a significant step toward global adoption. By embracing these enhanced reporting standards, the medical research community will achieve greater accuracy, transparency, and a holistic view of health interventions that align with environmental sustainability. This landmark advancement embodies the essential collaboration needed to address public health in the face of climate change with foresight and precision. #ClimateAction #ClinicalResearches #ClinicalTrials #GlobalHealth #HealthcareInnovation #MedicalResearch #PublicHealth #Publications #RegulatoryAgencies #Sustainability #WHO #MarketAccess #MarketAccessToday

At our third webinar on 𝐄𝐪𝐮𝐢𝐭𝐚𝐛𝐥𝐞 𝐃𝐚𝐭𝐚 𝐏𝐫𝐨𝐜𝐮𝐫𝐞𝐦𝐞𝐧𝐭 & 𝐆𝐨𝐯𝐞𝐫𝐧𝐚𝐧𝐜𝐞, hosted by the World Health Organization South Africa and the Koita Centre for Digital Health at Ashoka University (KCDH-A), the focus was on a simple but profound question: how do we ensure that health data serves everyone, not just a few? In her keynote, Prof. Ilona Kickbusch, (Director, Digital Transformations for Health Lab), emphasized the idea of data solidarity, reminding us that equitable health data systems are built when governance and procurement practices foster collective benefit rather than fragmented silos. The panel explored these challenges from multiple vantage points: 🔹 Prof. Gautam Menon discussed systemic risks of fragmented data ecosystems. 🔹 Dr. Sanghamitra Bandyopadhyay highlighted the scientific hurdles of bias in heterogeneous health datasets. 🔹Dr. Boonchai Kijsanayotin shared grounded lessons from Thailand on ensuring rural and smaller facilities are not excluded from data-sharing benefits. The Sri Lanka spotlight, with Mr. Jayantha Fernando, demonstrated how robust data protection laws can provide the trust backbone for responsible AI in health. The message was clear: responsible AI begins long before algorithms; it starts with the fairness of data collection, the solidarity of governance, and the inclusiveness of access. We thank all speakers and participants for a thought-provoking and practical discussion. Watch here: https://lnkd.in/gBfPvVDk Ashoka University | World Health Organization South-East Asia | Soumya Swaminathan | Rizwan Koita | Anurag Agrawal | Aradhita Baral | Dr. Sangita Reddy | Suvrankar Datta | Lipika Dey | Dr. Partha Pratim Das (PPD) | Mayank Garg | Digital Transformations for Health Lab | Indian Statistical Institute, Kolkata #ResponsibleAI #DigitalHealth #HealthEquity #WHO #AIforHealth

🔬 Clinical Trials in Israel: H1 2025 Highlights At the intersection of science and innovation, #Israel is accelerating research with streamlined approvals, AI-ready oversight, and strong sector resilience. Key highlights: ✔ 175 clinical trials registered Jan–Jun 2025 (ClinicalTrials.gov) ✔ Drug registration reform live 23 Mar 2025: reliance tracks with target timelines of 70 or 120 working days (Ministry of Health Israel; U.S. International Trade Administration) ✔ AI principles published in late 2024 now shaping 2025 ethics reviews, with added focus on transparency, data governance, and risk (Ministry of Health Israel) Israel’s life-science and health-tech sector continues to expand, with sustained funding boosting site capacity, vendor depth, and the creation of new companies, further strengthening its global role in clinical development. 📍 At PVR (People. Value. Research), we are proud to support sponsors and sites in Israel, navigating evolving regulatory pathways to advance science, patient access, and integrity.

Proud to share our latest editorial in Value in Health – An HEOR Publication: “Methodological Challenges With Conducting Health Economic Evaluations in the Critical-Care Context.” 👉 https://lnkd.in/gTDVFFtA Critical care is one of the most resource-intensive and high-stakes areas in medicine. Yet despite its importance, health economic evaluations in intensive care units (ICUs) remain surprisingly rare and often methodologically inconsistent. In this piece, Stavros Petrou and I explore why conducting cost-effectiveness and value assessments in critical care is so difficult — and why getting it right matters for improving hospital efficiency and patient outcomes. We discuss: 💡 The massive heterogeneity among ICU patients that complicates study design 💡 The data gaps that make it hard to capture long-term outcomes or costs 💡 How better measurement and modeling can help hospitals eliminate “defects in value” and move toward zero waste in care delivery Even small methodological improvements can make a real dent in the trillion-dollar problem of wasteful care. I’m grateful to the ISPOR—The Professional Society for Health Economics and Outcomes Research Value in Health editorial team for highlighting this issue and to colleagues advancing economic evaluation in hospital medicine. Peter Pronovost MD, PhD, FCCM Patricia Davidson Mary Beth Makic USC Schaeffer Institute USC Alfred E. Mann School of Pharmacy and Pharmaceutical Sciences #healtheconomics #valueinhealth #criticalcare #costeffectiveness #healthpolicy #hospitalquality

Important paper highlighting solutions like public private mix and diagnostic network optimisation for #TB #UHC #PHC Having served as a primary care doctor in rural India, I have seen the impact we can have with building capabilities at primary care level, often the first line of service access and delivery for communities. Thanks Yogan Pillay Madhukar Pai, MD, PhD for bringing attention and sharing key insights and solutions for integrating TB services within primary health care

Prevalent Bad Statistical Practices in Preclinical Studies ‼️ This is a critical issue — and one that has major ripple effects in biotech and medtech. Bad statistical practices in preclinical research do not just affect the science; they shape business, regulatory trust, and ultimately patient outcomes. 1. Poor Study Design: Use of pseudo replication (technical replicates instead of biological replicates), lack of randomisation/blinding, underpowered studies, trying to control sources of variation too much, ... 2. Inadequate Data Analysis: Overreliance of t-tests, ignore repeated measures, no correction for multiple testing, etc. 3. Selective Reporting: P-hacking / data dredging, selective outcome reporting, dropping outliers without justification,... 4. Misinterpretation of Results: Equating “non-significant” with “no effect”, overstating effect size,... 5.  Lack of Transparency: No preregistration → hypotheses, endpoints, and analysis plans are often flexible and changed post hoc. Incomplete reporting of methods and data → prevents reproducibility. Explore scientific publications and you will notice that there methodological errors are still prevalent in 2025!!! Why Do These Bad Practices Persist in 2025? ◽ Tradition (“this is how labs have always done it”). ◽ Pressure to publish “positive” results quickly. ◽ Lack of statistical expertise in preclinical teams. ◽ Journals and funders historically not enforcing rigorous standards. 💡 Early involvement of a statistician turns good research into reliable, publishable, and decision-ready evidence. This is why we have developed our mentoring program on good statistical practices. Contact Natalie Rodrigue to enroll. #stop #bad #statistical #practices #better #science