Right Patient, Right Dose, Right Time

While artificial intelligence (AI) has shown promising potential, much of its use has remained theoretical or retrospective. Turning its potential into real-world healthcare outcomes, researchers at the Yong Loo Lin School of Medicine, National University of Singapore (NUS Medicine) have successfully utilised an AI platform to make precise recommendations for dose adjustments in 10 patients at the National University Cancer Institute, Singapore (NCIS) in Singapore.

Led by Professor Dean Ho, Director of the Institute for Digital Medicine (WisDM), NUS Medicine, the team tracked the cancer biomarkers, CEA and CA125, of 10 patients in Singapore who were diagnosed with advanced solid tumours, to create personalised ‘digital twins’ for each patient.

By analysing the changes in biomarkers in response to different drug doses, precise recommendations were made to adjust each patient's treatment plan. Over the period from the first dosing in August 2020 to the last dosing in September 2022, clinicians accepted 97.2 per cent of the recommended doses, with some patients receiving optimal doses that were approximately 20 per cent lower on average. The research trial marks a potential shift towards personalised oncology, where drug doses are dynamically adjusted for each patient during treatment, potentially reducing costs, rather than adhering to a standard, one-size-fits-all treatment regimen.

This approach to patient care is enabled by the CURATE.AI platform - developed by Prof Ho and team - an optimisation platform which harnesses a patient's clinical data, such as drug type, drug dose and cancer biomarkers, to generate an individualised digital profile to determine a customised optimal dose during chemotherapy treatment.

Prof Ho said, "Our team is among the few in precision medicine that have taken AI-driven treatment into real-world clinical settings. The results from our study represent a meaningful milestone in healthcare - demonstrating prospective, real-time optimisation of treatment based on an individual's own data. Currently, the collection of data is still mainly population driven - specifically, many patients’ data is collected, but they are largely snapshots. However, patients evolve over time, yet their treatment is guided based on population data that does not capture how each patient’s status changes during the course of therapy. By leveraging AI to adjust drug doses based on biomarkers and patient data, we have unlocked a new frontier in personalised medicine." Prof Ho is also Head of the Department of Biomedical Engineering at the College of Design and Engineering (CDE) at NUS, and Director of the NUS N.1 Institute for Health.

The clinical lead of the study, Associate Professor Raghav Sundar, who was from the Department of Medicine, NUS Medicine, and the NUS N.1 Institute for Health at the time of the research, said, "These are important first steps that we have made in personalising chemotherapy drug dosing for our cancer patients. This is something that many of us as clinicians have hoped to have for our patients, but has been extremely challenging to translate from idea to implementation. The data from this research trial forms the basis for the next steps in the field of precision drug dosing in oncology." Assoc Prof Raghav was also a Senior Consultant in the Department of Haematology-Oncology, NCIS at the time of the research. He is currently an Associate Professor of Internal Medicine (Medical Oncology & Hematology) at the Yale School of Medicine.

As the field of AI-powered personalised medicine continues to advance, this work sets the stage for transforming clinical care by integrating data-driven approaches that are not only more precise but also adapted to each patient's treatment needs. Published in Nature Partner Journals (NPJ) Precision Oncology, the study is poised to expand into larger, randomised controlled trials with further refinements in design to validate the effectiveness of the CURATE.AI platform against traditional treatment regimens. The potential applications of the platform extend beyond oncology - it is already being adapted for use in other therapeutic areas, including immunotherapy, hypertension, and healthspan medicine within the longevity space.

Nigel Foo, co-author of the study, and PhD candidate from Prof Ho’s research team at WisDM, NUS Medicine, and the NUS N.1 Institute for Health, added, "It's not always about how much data is collected; in the context of therapy, it's about how the data is collected. By pairing drug dose changes with how cancer markers change, we can better understand how different drugs interact over time. Our method of using digital twins to guide individualised patient care is a key advance, especially as the field has traditionally focused on the retrospective use of data for diagnosis or prediction." He is also from the Department of Biomedical Engineering at NUS CDE.

Blasiak A, Truong ATL, Foo N, Tan LWJ, Kumar KS, Tan SB, Teo CB, Tan BKJ, Tadeo X, Tan HL, Chee CE, Yong WP, Ho D, Sundar R.
Personalized dose selection platform for patients with solid tumors in the PRECISE CURATE.AI feasibility trial.
NPJ Precis Oncol. 2025 Feb 21;9(1):49. doi: 10.1038/s41698-025-00835-7

Most Popular Now

AI also Assesses Dutch Mammograms Better…

AI is detecting tumors more often and earlier in the Dutch breast cancer screening program. Those tumors can then be treated at an earlier stage. This has been demonstrated by...

Unlocking the 10 Year Health Plan

The government's plan for the NHS is a huge document. Jane Stephenson, chief executive of SPARK TSL, argues the key to unlocking its digital ambitions is to consider what it...

AI can Find Cancer Pathologists Miss

Men assessed as healthy after a pathologist analyses their tissue sample may still have an early form of prostate cancer. Using AI, researchers at Uppsala University have been able to...

Alcidion Grows Top Talent in the UK, wit…

Alcidion has today announced the addition of three new appointments to their UK-based team, with one internal promotion and two external recruits. Dr Paul Deffley has been announced as the...

How AI could Speed the Development of RN…

Using artificial intelligence (AI), MIT researchers have come up with a new way to design nanoparticles that can more efficiently deliver RNA vaccines and other types of RNA therapies. After training...

AI, Full Automation could Expand Artific…

Automated insulin delivery (AID) systems such as the UVA Health-developed artificial pancreas could help more type 1 diabetes patients if the devices become fully automated, according to a new review...

MIT Researchers Use Generative AI to Des…

With help from artificial intelligence, MIT researchers have designed novel antibiotics that can combat two hard-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). Using generative AI algorithms, the research...

Penn Developed AI Tools and Datasets Hel…

Doctors treating kidney disease have long depended on trial-and-error to find the best therapies for individual patients. Now, new artificial intelligence (AI) tools developed by researchers in the Perelman School...

AI Hybrid Strategy Improves Mammogram In…

A hybrid reading strategy for screening mammography, developed by Dutch researchers and deployed retrospectively to more than 40,000 exams, reduced radiologist workload by 38% without changing recall or cancer detection...

New Training Year Starts at Siemens Heal…

In September, 197 school graduates will start their vocational training or dual studies in Germany at Siemens Healthineers. 117 apprentices and 80 dual students will begin their careers at Siemens...

Routine AI Assistance may Lead to Loss o…

The introduction of artificial intelligence (AI) to assist colonoscopies is linked to a reduction in the ability of endoscopists (health professionals who perform colonoscopies) to detect precancerous growths (adenomas) in...

New AI Tool Addresses Accuracy and Fairn…

A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms...