Researchers at the National University of Singapore (NUS) have successfully used an innovative artificial intelligence (AI) platform, CURATE.AI, to treat a patient with Waldenström macroglobulinemia, a rare blood disorder affecting approximately three in a million people annually. The AI platform optimizes treatment strategies for rare diseases, which individually affect fewer than 1 in 2,000 people but collectively impact over 7,000 different types globally.
CURATE.AI: Personalizing Treatment with Small Data
CURATE.AI distinguishes itself from traditional AI systems by leveraging small data sets to personalize treatments. The platform dynamically adjusts dosages based on a patient’s responses, allowing for more precise and tailored care. This is particularly crucial in the Asia-Pacific region, where approximately 258 million people live with rare diseases, facing unique challenges in healthcare access and treatment development.
Professor Dean Ho, Director of the Institute for Digital Medicine (WisDM) at NUS Medicine, co-led the clinical trial. According to Prof Ho, "No two patients are alike, and even the same patient can change over time as well. It is essential for treatment to evolve alongside the patient."
Clinical Trial Results
Since the trial began in October 2021, the patient experienced significant improvements in red blood cell levels, eliminating the need for blood transfusions. Furthermore, the patient had fewer hospital admissions and reported no serious side effects while maintaining durable disease control.
The research team collaborated with clinicians from the National University Cancer Institute, Singapore (NCIS), to guide drug dosage decisions based on real-time patient responses. This personalized approach led to lower and well-tolerated drug doses, saving the patient approximately USD 8,000 (around SGD 10,500) in medication costs over the first two years of treatment.
Expert Commentary
Dr. Sanjay de Mel, Senior Consultant at NCIS, emphasized the importance of personalized approaches: "Achieving a good treatment response while minimising side effects is crucial when treating patients with Waldenström macroglobulinemia. Patients may differ significantly in how their bodies handle the treatment and the types of side effects they experience. A personalised approach to medication dosing is therefore required to address this inter-individual variability."
Implications and Future Directions
The ongoing clinical trial is now open for recruiting more patients suitable for this AI-guided treatment. Initial results, published in NPJ Digital Medicine, highlight the potential of AI in revolutionizing care for patients with rare diseases. CURATE.AI's ability to work with single-patient data addresses the limitations of large-scale trials, which are often impractical for rare diseases due to limited patient populations. This approach offers a practical solution for the urgent need to develop personalized strategies for rare diseases.
