• Directory of Taiwan

Taiwan develops emergency room GIS system to detect infectious diseases

System analyzes patient, geographic data to alert about occurrence of epidemic, predict spread, trace source

Emergency rooms are the first place to detect epidemics, says NTU professor Wen Tzai-hung.

Emergency rooms are the first place to detect epidemics, says NTU professor Wen Tzai-hung. (CNA photo)

TAIPEI (Taiwan News) — National Taiwan University Hospital (NTUH) has partnered with National Taiwan University's (NTU) Department of Geography to develop a geographic information system (GIS) based on emergency room (ER) patient data that actively detects the spread of infectious diseases early on.

During an online press conference, NTU Department of Geography professor Wen Tzai-hung (溫在弘) announced the project and said ERs are the first place to detect epidemics when they happen, CNA reported. By detecting abnormal ER traffic and combining the information with patients’ symptoms, disease onset times, and location of residence, one would be able to actively analyze features of infectious diseases, predict spread patterns, or even trace the origin of the diseases before large-scale outbreaks occur.

According to Wen, the latest GIS includes syndromic and pathogen information so that one can cross-reference medical and spatial data, which helps public health authorities pinpoint the source of epidemics and take preventative measures as soon as possible.

NTHU Center of Intelligence Healthcare Vice Director Lee Chien-chang (李建璋) was cited as saying that traditionally, infectious disease detection is passive and relies on frontline physicians’ alertness. This tends to lead to a delay in taking action to curb the diseases’ spread.

The GIS developers have analyzed historical data from 2018’s respiratory and gastrointestinal syndromes with the system and plan to better train its prediction abilities by actively detecting and analyzing data from the current COVID pandemic next, Lee said. CNA also cited Wen as saying the team hopes to test the system in hospital ERs this year and deploy it to detect COVID-19 infection clusters in 2022.