{"665707":{"#nid":"665707","#data":{"type":"news","title":"New Hybrid Machine Learning Framework Extends Range of Accurate Epidemic Forecasting","body":[{"value":"\u003Cp\u003ECommunity leaders and public health officials may soon have more time to plan for Covid and flu outbreaks thanks to a new machine learning (ML) framework that is improving the accuracy of long-range epidemic forecasting.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThat is exactly what researchers at Georgia Tech\u0026rsquo;s School of Computational Science and Engineering (CSE) have developed through EINNs,\u0026nbsp;\u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2202.10446\u0022\u003EEpidemiologically-Informed Neural Networks\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAlong with proving its ability to improve accuracy in long-term epidemic forecasting, EINNs has implications in artificial intelligence (AI) by leading a path toward optimization for current models based on neural networks and differential equations to follow.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;To generate trustworthy epidemic forecasts, more than just data may be required,\u0026rdquo; said\u0026nbsp;\u003Cstrong\u003EAlexander Rodr\u0026iacute;guez\u003C\/strong\u003E, a CSE Ph.D. student and EINNs researcher. \u0026ldquo;In our paper, we tackle this challenge by introducing a methodology to enable better integration of epidemiological knowledge and deep neural networks. This integration can help neural networks predict farther into the future.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EJoining Rodr\u0026iacute;guez on the EINNs team from the School of CSE are Ph.D. student\u0026nbsp;\u003Cstrong\u003EJiaming Cui\u003C\/strong\u003E\u0026nbsp;and Associate Professor\u0026nbsp;\u003Cstrong\u003EB. Aditya Prakash\u003C\/strong\u003E. The trio partnered with Virginia Tech Professor\u0026nbsp;\u003Cstrong\u003ENaren Ramakrishnan\u003C\/strong\u003E\u0026nbsp;and\u0026nbsp;\u003Cstrong\u003EBijaya Adhikari\u003C\/strong\u003E, an assistant professor at the University of Iowa, to develop EINNs.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn their study, all models, including EINNs, made eight-week forecasts for Covid-19 and flu, in two time periods. The team\u0026rsquo;s testing period for Covid-19 forecasting spanned Sept. 2020 to March 2021, which encompassed the entire Delta variant wave. For flu, the period lasted from Dec. 2017 to May 2018.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EWhen testing EINNs in forecasting Covid-19 and flu, the framework resulted in improved accuracy of up to 55% of recurrent neural network models, while also increasing correlation with epidemic trends. EINNs also demonstrated 77% less error in comparison to traditional mechanistic epidemiological models based on ordinary differential equations.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThese results show promise in forecasting multiple diseases at the same time from a longer perspective. This could prevent future hardships, like the 2022 \u0026ldquo;tripledemic\u0026rdquo; of COVID-19, flu, and respiratory syncytial virus (RSV).\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAs a result of the success of the framework\u0026rsquo;s design, and its potential for improving epidemic forecasting, the research team presented EINNs at the\u0026nbsp;\u003Ca href=\u0022https:\/\/aaai-23.aaai.org\/\u0022\u003E37th Association for the Advancement of Artificial Intelligence (AAAI) 2023 conference\u003C\/a\u003E\u0026nbsp;in Washington, D.C. Here, the conference committee assigned EINNs to the AI for Social Impact track.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Predicting and preventing epidemics are major challenges for the World Health Organization and the Centers for Disease Control and Prevention, with far-reaching effects on health, economy, and social well-being,\u0026rdquo; Rodr\u0026iacute;guez said. \u0026ldquo;Forecasting with EINNs allows us to see further into the future, which it critical to planning and decision-making in public health.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EPart of the beauty of EINNs is its incorporation of the best aspects from neural networks and mechanistic models, an idea borrowed from physics-informed neural networks. The team mentions in their study that the goal was not to compete with the models, but rather to develop a method for consistently good performance in accuracy and correlation.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECurrent neural network models are good at short-term forecasting, typically one to four weeks, but do not have any knowledge on epidemic dynamics. As a result, they often lose accuracy in long-term forecasting.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMechanistic models, on the other hand, contain this knowledge, making them a welcomed addition to deep neural networks for long-term epidemic forecasting. At the same time, mechanistic models have difficulty ingesting some datasets, like social media data. EINNs enables such models to incorporate these datasets better through neural networks.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn total, the research team made 5,696 predictions per tested model, including EINNs. This required training each model more than 700 times. Though computationally expensive, this developed the AI that ultimately led the team\u0026rsquo;s success.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETo accomplish this, the team tested models on four Intel Xeon E7-4850 CPUs, boosted by four NVDIA Tesla V100 DGXS 32GB GPUs. With code written in PyTorch, the GPUs completed training of each predictive task in about 30 minutes.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Current ML modes don\u0026rsquo;t utilize domain knowledge embedded in epidemiological models and we wanted to bridge that gap,\u0026rdquo; Rodr\u0026iacute;guez said. \u0026ldquo;To accomplish this, we took inspiration from recent work in scientific AI and developed new techniques. We incorporate this mechanistic knowledge by carefully matching so-called gradients of epidemic variable through transfer learning.\u0026rdquo;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Researchers at Georgia Tech\u2019s School of Computational Science and Engineering (CSE) have developed EINNs, Epidemiologically-Informed Neural Networks"}],"uid":"36319","created_gmt":"2023-02-10 17:57:57","changed_gmt":"2023-02-10 19:59:00","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2023-02-10T00:00:00-05:00","iso_date":"2023-02-10T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"665705":{"id":"665705","type":"image","title":"EINNs Charts","body":null,"created":"1676051479","gmt_created":"2023-02-10 17:51:19","changed":"1676051479","gmt_changed":"2023-02-10 17:51:19","alt":"EINNs at AAAI 2023","file":{"fid":"251753","name":"EINNs Charts.png","image_path":"\/sites\/default\/files\/images\/EINNs%20Charts.png","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/EINNs%20Charts.png","mime":"image\/png","size":134615,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/EINNs%20Charts.png?itok=itasvOYa"}}},"media_ids":["665705"],"groups":[{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"},{"id":"135","name":"Research"},{"id":"138","name":"Biotechnology, Health, Bioengineering, Genetics"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"146","name":"Life Sciences and Biology"}],"keywords":[{"id":"166983","name":"School of Computational Science and Engineering"}],"core_research_areas":[{"id":"39441","name":"Bioengineering and Bioscience"},{"id":"39431","name":"Data Engineering and Science"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr \/\u003E\r\nbryant.wine@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}