CURATE.AI: How Digital Twins Are Revolutionizing Precision Dosing

May 22, 2025

By Bio-IT World Staff 

May 22, 2025 | Singapore researchers have developed an innovative artificial intelligence platform that creates personalized “digital twins” of patients to optimize drug dosing on an individual basis. The CURATE.AI platform, developed by Dr. Dean Ho and his team at the National University of Singapore's Institute for Digital Medicine (WisDM), represents a significant advancement in precision medicine by dynamically adjusting treatment regimens based on real-time patient responses. 

In a groundbreaking feasibility study conducted across two Singapore hospitals, researchers used CURATE.AI to monitor two blood biomarkers—carcinoembryonic antigen (CEA) and cancer antigen 125 (CA125)—in ten patients with advanced solid tumors. What makes this study particularly noteworthy is its prospective nature: rather than analyzing historical data retrospectively, the platform provided forward-looking treatment recommendations that clinicians could immediately implement. 

The study revealed that CURATE.AI often recommended lower doses than standard maximum-tolerated-dose protocols while maintaining efficacy and improving tolerability. This “small data” approach represents a paradigm shift from conventional AI applications that typically require massive datasets. 

“This early finding suggests that this platform may be effective at pinpointing the optimal dose that a patient should receive at any given time, and that this optimal dose... can change over time for each patient,” explained Dr. Ho, who serves as both director of WisDM and head of NUS's biomedical engineering department. 

CURATE.AI has already demonstrated success in several clinical applications: 

  • Guiding treatment for a rare blood cancer patient, resulting in lower, well-tolerated doses and $8,000 in savings over two years 
  • Reducing an investigational inhibitor drug dose by 50% for a prostate cancer patient, enabling him to resume an active lifestyle
  • Recommending reduced chemotherapy (nab-paclitaxel) dosing for a patient whose lung tumor subsequently shrank 

The platform's versatility extends beyond oncology, with trials underway or completed for hypertension management, immunotherapy optimization, and even cognitive training adjustment. What distinguishes WisDM's approach is its comprehensive methodology, which considers not only clinical validation but also user acceptability and behavioral economics to overcome adoption barriers. 

As Dr. Ho and his team prepare to expand into larger randomized controlled trials, they’re exploring potential industry partnerships and international collaborations. Their pioneering work challenges traditional clinical trial design by recognizing that patients evolve over time, so it is “critical to evolve treatment alongside them and to adjust where necessary and possible.” 

Read the full story by Deborah Borfitz at Clinical Research News.