Taiwan’s Food and Drug Administration (FDA) has approved the use of artificial intelligence (AI) system that will help doctors to read chest X-rays and thus more quickly detect COVID-19 infections. The AI-based diagnostic system can be used, alongside PCR testing and rapid antigen tests, as a fast diagnostic tool to detect COVID-19 cases by pinpointing a suspected chest infection on X-ray images. The AI system was developed jointly by a Taiwanese startup and some medical institutions.
The FDA approved the AI on a special case basis for commercialisation in light of the current COVID-19 situation in Taiwan. The technology will be particularly useful in cases where an undiagnosed asymptomatic COVID-19 patient visits a doctor with some other ailment. The AI system instantly provides clinicians with reliable values on the location of a particular illness such as pneumonia and lung infection. Then it can be used to read the chest X-ray images of the person and issue an alert if it detects a possible COVID-19 infection.
Taipei Medical University (TMU) comments that putting suspected cases who were admitted into the hospital through the AI real-time screening helps reduce the number of screening tests and medical costs and further accelerate the hospital’s existing treatment procedure. Through an AI machine training model that differs from the past, the specificity of the AI model can be emphasised. Based on the prediction, doctors can focus on treating high-risk patients immediately to avoid missing the critical treatment time.
The AI system can also be used as a fast detection tool among medical personnel if a COVID-19 case emerges in a hospital. With the use of the AI system, there will be no immediate need for the entire hospital staff to be tested, in such a situation. By taking chest X-rays of those with suspicious symptoms and having the AI system read the images, doctors will be able to identify those who have contracted COVID-19.
In addition to the advantages of speeding up COVID-19 diagnosis and saving manpower, the AI system can also help reduce the incidence of errors among overworked radiologists. In the clinical trials, the AI system had an 80% accuracy rate for the detection of COVID-19.
In Taiwan, the digital health trend is attracting the growing attention of businesses and new start-ups operating at the intersection of technology and medical science. Renowned hi-tech companies aim to transform not only Taiwan’s healthcare system, but also the world’s. The focus is on integrating advanced technologies with the latest medical applications to enable connected and smart healthcare. This development is expected to have a synergistic impact on Taiwan’s emerging biomedical industry.
One of Taiwan’s digital healthcare collaborations is a study about the adoption of machine learning (ML) to detect medication errors, as reported by OpenGov Asia. Reducing medication errors at the source is crucial. However, to help physicians be better informed and make better decisions, they need more accurate suggestions and alerts.
Hence, ML can provide insights on patterns and predictions to help doctors make data-driven decisions. For technology to assist in solving these problems, ML must understand these variables. For this to be successful, data must be properly collected, organised, and maintained.
Data-driven medicine demands huge and diverse medical data sets. The biggest challenge is successfully implementing data-driven applications in clinical practice, from local to global, without compromising patient safety and privacy.
The AI model for medication safety has been trained by one of the world’s largest prescription databases, 1.5 billion well-coded prescriptions from the U.S. and Taiwan, to learn the association between diagnosis, medication, and complex prescribing behaviour of doctors from different countries. The study has shown the model trained by federated learning (FL) achieves remarkable performance comparable to the other two models trained by individual data sets.
The result is a breakthrough in the international transferability of medical AI. It demonstrates a way to provide practical data-driven prescribing support to improve patient safety even though it could be challenging to obtain data to develop these systems locally.
