National Taiwan University Hospital (NTUH) on Thursday presented its newly developed telecare system that uses artificial intelligence (AI) to predict the occurrence of patient-related emergency events by analyzing text conversations between patients and their live-in caregivers.
The “Intelligent Voice Emergency Prediction System of the Fourth-Generation Real-Time Synchronous Telehealth Care Platform” developed by NTUH and Chunghwa Telecom won the “21st National Innovation Award-Clinical Innovation Award” in November last year.
At a news conference, Ho Yi-lwun (何奕倫), director of the Department of Internal Medicine and Telecare Center at NTUH, said the system converts conversations between patients and caregivers into text, and could analyze keywords in conversations, such as blood pressure and other physiological data, for earlier predictions for emergency treatment, thereby reducing unnecessary complications in patient care.
Photo: Chiu Chih-jou, Taipei Times
Taking people with acute myocardial infarction as an example, Ho said if intervention occurs within the golden six hours for treatment, there is a chance occluded blood vessels could be recanalized.
The intelligent voice emergency prediction system could accurately identify people with emergency needs, distinguish between high and low-risk patients, and allow those with greatest need to receive necessary treatment quicker, he added.
This system would not only help reduce emergency room visit rates, but also the length of hospital stays and the risk of death, due to immediate medical responses, Ho added.
Hung Chi-sheng (洪啟盛), a doctor from NTUH’s Telehealth Center, said that since its establishment in August 2009, the Telecare Center has handled 540,000 phone calls and cared for more than 7,000 patients.
It cooperated with Chunghwa Telecom to introduce the telecom’s multi-language, medical speech recognition technology and conduct AI model training, which could recognize speech in Mandarin, English and Hoklo (also known as Taiwanese), Mandarin accents of migrant caregivers, medical terms, Chinese and English names of drugs, and convert the speech into text.
Through language processing and analysis of integrated nursing records, the AI system could monitor and predict the probability of people experiencing emergency events within two weeks of analysis, Hung said.
The system’s predictive accuracy rate is roughly 90 percent, he said.
Telecare could improve patients’ blood pressure, reduce mortality, reduce emergency room visits, and the number and length of hospital stays, Hung added.
Home-based telecare has become an important tool to address healthcare needs in Taiwan’s aging society, particularly during the COVID-19 pandemic, he said.
A magnitude 4.9 earthquake struck off Tainan at 11:47am today, the Central Weather Administration (CWA) said. The hypocenter was 32.3km northeast of Tainan City Hall at a depth of 7.3km, CWA data showed. The intensity of the quake, which gauges the actual effect of a seismic event, measured 4 in Tainan and Chiayi County on Taiwan's seven-tier intensity scale, the data showed. The quake had an intensity of 3 in Chiayi City and County, and Yunlin County, while it was measured as 2 in Kaohsiung, Nantou County, Changhua County, Taitung County and offshore Penghu County, the data showed. There were no immediate reports of
Weather conditions across Taiwan are expected to remain stable today, but cloudy to rainy skies are expected from tomorrow onward due to increasing moisture in the atmosphere, according to the Central Weather Administration (CWA). Daytime highs today are expected to hit 25-27°C in western Taiwan and 22-24°C in the eastern counties of Yilan, Hualien, and Taitung, data on the CWA website indicated. After sunset, temperatures could drop to 16-17°C in most parts of Taiwan. For tomorrow, precipitation is likely in northern Taiwan as a cloud system moves in from China. Daytime temperatures are expected to hover around 25°C, the CWA said. Starting Monday, areas
Taiwan has recorded its first fatal case of Coxsackie B5 enterovirus in 10 years after a one-year-old boy from southern Taiwan died from complications early last month, the Centers for Disease Control (CDC) said yesterday. CDC spokesman Lo Yi-chun (羅一鈞) told a news conference that the child initially developed a fever and respiratory symptoms before experiencing seizures and loss of consciousness. The boy was diagnosed with acute encephalitis and admitted to intensive care, but his condition deteriorated rapidly, and he passed away on the sixth day of illness, Lo said. This also marks Taiwan’s third enterovirus-related death this year and the first severe
A Taiwanese software developer has created a generative artificial intelligence (AI) model to help people use AI without exposing sensitive data, project head Huang Chung-hsiao (黃崇校) said yesterday. Huang, a 55-year-old coder leading a US-based team, said that concerns over data privacy and security in popular generative AIs such as ChatGPT and DeepSeek motivated him to develop a personal AI assistant named “Mei.” One of the biggest security flaws with cloud-based algorithms is that users are required to hand over personal information to access the service, giving developers the opportunity to mine user data, he said. For this reason, many government agencies and