Wiwik Anggraeni and Mauridhi Hery Purnomo (360info)
Wed 3 Aug 2022
Dengue fever outbreaks in Indonesia are becoming more frequent. Artificial intelligence can help predict where the next hotspot will be.
With 390 million dengue virus infections per year, researchers need all the help they can get to track infections. Recently machine learning, a subset of artificial intelligence, has been used make predictions on where the next outbreak will occur.
Dengue epidemics occurred approximately every five years. Now in Indonesia, as in other parts of the world, they occur more frequently. The number of dengue cases actually reported to WHO has increased more than tenfold over the past two decades, from 505,430 cases in 2000, to 5.2 million in 2019. Some 4,032 people, mostly children, died of dengue fever in 2019.
Forecasting dengue outbreaks can help authorities take action to prevent an epidemic Where better fight against the epidemic.
The machine learning studies data on past outbreaks, seeing how many cases there were at that time, when and what the weather conditions were like in the area at that time. In Indonesia, dengue usually occurs during the rainy season. No cases of dengue were noted during certain periods of the dry season.
The Intermittency of Indonesian Data makes finding a trend more difficult. Using machine learning techniques, the model can dynamically change based on the number of new cases entering the system. The chance of producing future predictions that match reality is improved.
Other studies on dengue tried approaches ranging from statistical techniques to time series. Some combine models and strategies in the hope that they can increase the accuracy of predictions. Machine learning, especially deep learning in the context of AI, has performed better than these approaches in predicting the spread of dengue caseloads.
Machine learning can also be used to identify relationships between dengue patients and find events or individuals that are spreading.
AI groups patients based on climate and geographic variables. Then an analysis of their interactions, known as social network analysis (SNA), is used to find the qualities and centrality of the relationships. AI combined with SNA is used to dig deeper into where and when substantial spread is possible. AI with SNA provides an accurate and rapid understanding of dengue in a particular region. The approach can find areas that need special attention for medical intervention.
AI technology, including machine learning, offers an alternative way to deal with many national issues, especially dengue fever. Such technology could be used in Indonesia to support government programs to meet international commitments to prevent dengue outbreaks.
Wiwik Anggraeni is a Lecturer in the Department of Information Systems, Faculty of Intelligent Electrical and Computer Technologies (F-ELECTICS), Institute Teknologi Sepuluh Nopember, Surabaya, Indonesia.
Mauridhi Hery Purnomo is a Lecturer in the Department of Computer Engineering, Faculty of Electrical Technology and Intelligent Computing (F-ELECTICS), Teknologi Sepuluh Nopember Institute, Surabaya, Indonesia. He is President of the Laboratory of Multimedia Computing and Artificial Intelligence
Originally published under Creative Commons by 360info™.