Having worked with pharma clients, healthcare providers, and digital platforms across the Asia-Pacific region, I’ve seen the challenges first-hand—data in silos, limited trial diversity, and lengthy timelines. But I’ve also seen growing momentum. The region is now poised to take a leadership role by combining real-world data (RWD) with AI-powered analysis to improve how clinical research is conducted and applied.

Why RWE Is Critical for Asia

Traditional clinical trials are the norm, but they often leave out a large section of the real-world patient population—especially in Asia with the assumption that patients and providers here may not have enough technology access when compared to its peers. Whether it’s older adults with comorbidities, rural patients, or those with irregular access to care, the truth is that trial participants don’t always reflect the people actually taking the medicine.

This is where real-world evidence becomes so valuable. It allows us to understand how treatments are working across diverse populations and care settings. RWD comes from electronic health records, health insurance claims, wearables, mobile health apps, pharmacy records, and more. It shows us how patients respond to treatment in real life—not just under ideal clinical trial conditions.

In a region as complex and varied as Asia, we need that visibility to make better decisions, faster.

How AI Changes the Game

We’ve had access to real-world data for years. Making sense of the data at hand is the real challenge.

This is where AI brings real value—especially machine learning and natural language processing (NLP). These technologies help us organise, clean, and analyse large volumes of structured and unstructured data. For instance:

• Standardising messy datasets: AI can pull together data from hospitals, clinics, and labs—even if it’s recorded in different formats or languages.
• Predicting outcomes: We can use AI to identify patients at higher risk of side effects, non-response, or hospital readmission.
• Synthetic control arms: Historical patient data can be used to create virtual control groups, reducing the number of patients who need to be enrolled in new trials.
• Subgroup discovery: AI can help uncover which patients benefit most (or least) from a treatment—something we often miss with a one-size-fits-all trial design.

Why Asia Has an Advantage

What makes Asia unique is also what makes it powerful in the RWE-AI landscape. We’re sitting on huge volumes of data, often underused. Our population diversity—genetic, environmental, economic—offers a goldmine of insights that could lead to more tailored therapies.

Also, cost-efficiency plays in our favour. Conducting clinical studies in Asia is much more affordable when compared to the West considering resource and per patient costs. When AI is added to low cost studies to streamline the process, the return on investment is bound to be higher.

Another advantage with Asia is that many countries within Asia are investing hugely in digital health infrastructure. India’s Ayushman Bharat Digital Mission (ABDM), for example, aims to connect health data across providers and states. Singapore and South Korea have already established national-level health data systems. These foundations are opening up new opportunities to do smarter clinical research.

Real-World Case: AI-Powered Oncology Insights in South Korea

One of the most inspiring examples is from South Korea. A leading hospital collaborated with an AI company to process thousands of cancer patient records using NLP. The system extracted key information from pathology reports, doctor notes, and lab data to identify how patients were responding to immunotherapy drugs in real time.

The AI helped doctors make better treatment choices and also contributed to evidence that supported label expansion for a cancer drug. This is a great example of how real-world data, when powered by AI, can accelerate decision-making—not just for doctors, but for regulators and pharma companies too.

Challenges We Still Need to Solve

While the potential is huge, there are still some real barriers we need to overcome to scale this across the region.

• Data fragmentation: Many hospitals and clinics still don’t follow standardised formats or coding. Thus it is difficult to do efficient data merger and analysis.
• Regulatory uncertainty: While regulators are becoming more open to RWE, there’s still lack of clarity on how AI-generated evidence will be reviewed and accepted.
• Talent shortage: We need more professionals who understand both domains—clinical research and data science. Right now, that overlap is limited.
• Ethical and privacy concerns: Data protection laws are evolving across Asia. Ensuring patient privacy, especially in large-scale AI models, must be a priority.

What Needs to Happen Next

To make AI + RWE a mainstream part of clinical development in Asia, we need a collaborative, ecosystem-wide push. Here are four practical steps:

1. Clearer regulatory guidance: Authorities should publish RWE and AI frameworks with defined use cases and evidence thresholds.
2. Interoperable data systems: More investment is needed in health IT platforms that allow different systems to talk to each other—especially in public hospitals.
3. Upskilling the workforce: We need to create hybrid roles—clinical data scientists, RWE strategists, and AI validators—who can work across silos.
4. Patient-centric governance: Consent, transparency, and trust must be embedded in how we collect and use real-world data.

Asia’s Time to Lead

The convergence of RWE and AI offers a major leap forward for clinical research—not just in efficiency, but in impact. In Asia, we’re in a unique position to lead this change. We have the patients, the data, the tech capacity, and increasingly, the policy momentum.

Now is the time to bring all of this together and reimagine clinical research to be more inclusive, responsive, and evidence-based. The future isn’t about replacing clinical trials—it’s about complementing them with insights from the real world.

The adaptation of RWE and AI will not only accelerate drug development but also ensure that therapies developed are relevant to the people who need it the most.

References

1. Makady A, et al. Real-World Evidence for Regulatory Decision Making: Challenges and Solutions in Europe. Clin Pharmacol Ther. 2017;101(5):599–601.
2. Krumholz HM. Big Data and New Knowledge in Medicine: Learning Health Systems. Health Aff (Millwood). 2014;33(7):1163–70.
3. India Ministry of Health. Ayushman Bharat Digital Mission. https://abdm.gov.in
4. Korean Society of Medical Informatics. AI in Cancer Care: Real-World Implementation. 2021.
5. U.S. Food & Drug Administration. Framework for FDA’s Real-World Evidence Program. 2021.
6. Deloitte. AI in Clinical Trials: Transforming Evidence Generation. 2020.
7. Lee CH, et al. Real-World Data in Oncology: South Korean Experience and Regulatory Trends. J Glob Oncol. 2023.