A research team led by National Taiwan University Hospital (NTUH) developed Artificial Intelligence (AI) system that speeds up leukemia diagnosis after completing trials at four medical institutions in Taiwan and the United States.
The trials have conducted assessments and differential counting of bone marrow smears which are used for leukemia diagnosis. A total of 254 patients were involved in the trials. The diagnosis results using the AI system reached a matching rate of 70-90% with those by a human doctor. The AI system has received approval from Taiwan’s Ministry of Health and Welfare and the European Union for marketing as an AI medical device.
– Chou Wen-chien, Director, Department of Laboratory Medicine, NTUH
The number of patients with leukemia or myeloproliferative neoplasm (MPN) in Taiwan has risen in recent years from 2,168 in 2016 to 2,550 in 2018, with about 1,100 deaths from leukemia reported each year, according to MOHW statistics.
Bone marrow aspirate Differential Cell Counts (DCCs) are critical for diagnosing leukemia, a cancer of the blood and bone marrow, Chou said. DCCs are typically obtained by clinical laboratory scientists conducting bone marrow smears.
However, manual counts are labour intensive due to the enormous amounts of blood cells and the inherent complexity of bone marrow specimens, while the precision and accuracy of the results can also be affected by the examiners’ personal experiences and eyesight. A human examination of blood and bone marrow aspirate smears takes about 20-30 minutes and can take 40-60 minutes if DCCs are obtained on two separate smears.
NTUH has partnered with an AI Taipei-based company to develop an AI system that is designed to automate the procedure of bone marrow smear differential counting. The company is dedicated to providing solutions for digital pathology and AI-powered diagnostic support. Trained on nearly 600,000 carefully curated cells, the AI system can provide 15 subtypes of differential count and generate a bone marrow aspirate smear analysis in five minutes.
NTUH is also committed to promoting international cooperation. Through such cooperation, the hospital leverages the experience and knowledge from advanced countries and boost the development of Taiwan’s own medical technology.
NTUH believes that the future of our medicine will be built mainly around holistic and personalised healthcare. On the basis of humanistic care of better quality, NTUH will be able to appropriately utilise electronic information and biotechnology to form the foundation of our management and raise their service quality to international standards. NTUH has been adapting in the past to the changing times and shifts in the environment by carrying out a series of organisational reconstruction and R&D programs.
As reported by OpenGov Asia, Taipei City-based research organisation is promoting the use of Artificial Intelligence (AI) in academic institutions, nongovernmental groups and enterprises through data exchanges and open-source projects. Taiwan’s leading role in the global supply of semiconductors means the country is ideally placed to integrate the latest and greatest technologies into the biotech and medical sectors.
Healthcare is the ideal field to expand the use of AI given the technology’s ability to quickly conduct big data analyses and modelling. Taiwan’s National Health Insurance (NHI) Research Database contains over two decades worth of data and images to assist in this process.
With access to such a rich resource, Taiwan researchers are looking to put their combined expertise to good use in the field of precision medicine, providing customised treatment plans tailored to individual patients. This is achieved by combining NHI data with information from wearable sensors recording heartbeat, blood pressure, blood sugar and oxygen saturation. This approach of preventive medicine ensures people are aware of the warning signs before they get ill. The research organisation’ goal is to utilise the power of AI to relieve the burden on hospitals resulting from avoidable conditions.