A machine learning method to monitor China’s AIDS epidemics with data from Baidu trends

Abstract

BackgroundAIDS is a worrying public health issue in China and lacks timely and effective surveillance. With the diffusion and adoption of the Internet, the ‘big data’ aggregated from Internet search engines, which contain users’ information on the concern or reality of their health status, provide a new opportunity for AIDS surveillance. This paper uses search engine data to monitor and forecast AIDS in China.MethodsA machine learning method, artificial neural networks (ANNs), is used to forecast AIDS incidences and deaths. Search trend data related to AIDS from the largest Chinese search engine, Baidu.com, are collected and selected as the input variables of ANNs, and officially reported actual AIDS incidences and deaths are used as the output variable. Three criteria, the mean absolute percentage error, the root mean squared percentage error, and the index of agreement, are used to test the forecasting performance of the ANN method.ResultsBased on the monthly time series data from January 2011 to June 2017, this article finds that, under the three criteria, the ANN method can lead to satisfactory forecasting of AIDS incidences and deaths, regardless of the change in the number of search queries.ConclusionsDespite the inability to self-detect HIV/AIDS through online searching, Internet-based data should be adopted as a timely, cost-effective complement to a traditional AIDS surveillance system.

Search trends and prediction of human brucellosis using Baidu index data from 2011 to 2018 in China

“…This study nevertheless has some deficiencies: First, China is a country with a wide range of cultures ethnicities, geographies, and population distributions 26 . Due to the scarcity of data at the provincial and municipal levels, it is not possible to predict the incidence trend in individual provinces and cities through this model.…”

Algorithmic prediction of HIV status using nation-wide electronic registry data

“…Thus, it has been used to predict progression of HIV and ART resistance and for ART optimization [10], [11], [12]. Recent studies have also shown that machine learning algorithms may be used for surveillance, including prediction of new HIV diagnoses and AIDS incidence based on internet search data [29,30], and there is early evidence that social media data may be used to study parameters such as HIV prevention, testing, and treatment efforts [31]. Our study adds to this growing field.…”

“…This may include exploring other machine learning techniques, redefining or including new predictors and exploring interactions in the present models. Previous studies have suggested that behavioral information such as sexual preference and illicit drug use is useful for HIV prediction[30] and may improve performance of these models further. Future studies should try and make such extensions.…”

Digital Public Health Surveillance Tools for Alcohol Use and HIV Risk Behaviors

“…HIV studies have already shown promise using internet search data to predict HIV diagnoses in the US and China [19,41,49]. Though it has its limitations, modeling using internet search trend data may be a cost-effective HIV surveillance method [50]. These methods might be especially relevant and immediately implementable in low resource areas that lack surveillance tools [18,45].…”