Dataset Information

Using Baidu search index to monitor and predict newly diagnosed cases of HIV/AIDS, syphilis and gonorrhea in China: estimates from a vector autoregressive (VAR) model.

ABSTRACT:

Objectives

Internet search engine data have been widely used to monitor and predict infectious diseases. Existing studies have found correlations between search data and HIV/AIDS epidemics. We aimed to extend the literature through exploring the feasibility of using search data to monitor and predict the number of newly diagnosed cases of HIV/AIDS, syphilis and gonorrhoea in China.

Methods

This paper used vector autoregressive model to combine the number of newly diagnosed cases with Baidu search index to predict monthly newly diagnosed cases of HIV/AIDS, syphilis and gonorrhoea in China. The procedures included: (1) keywords selection and filtering; (2) construction of composite search index; (3) modelling with training data from January 2011 to October 2016 and calculating the prediction performance with validation data from November 2016 to October 2017.

Results

The analysis showed that there was a close correlation between the monthly number of newly diagnosed cases and the composite search index (the Spearman's rank correlation coefficients were 0.777 for HIV/AIDS, 0.590 for syphilis and 0.633 for gonorrhoea, p<0.05 for all). The R² were all more than 85% and the mean absolute percentage errors were less than 11%, showing the good fitting effect and prediction performance of vector autoregressive model in this field.

Conclusions

Our study indicated the potential feasibility of using Baidu search data to monitor and predict the number of newly diagnosed cases of HIV/AIDS, syphilis and gonorrhoea in China.

SUBMITTER: Huang R

PROVIDER: S-EPMC7202716 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Baidu search index to monitor and predict newly diagnosed cases of HIV/AIDS, syphilis and gonorrhea in China: estimates from a vector autoregressive (VAR) model.

Huang Ruonan R Luo Ganfeng G Duan Qibin Q Zhang Lei L Zhang Qingpeng Q Tang Weiming W Smith M Kumi MK Li Jinghua J Zou Huachun H

BMJ open 20200324 3

<h4>Objectives</h4>Internet search engine data have been widely used to monitor and predict infectious diseases. Existing studies have found correlations between search data and HIV/AIDS epidemics. We aimed to extend the literature through exploring the feasibility of using search data to monitor and predict the number of newly diagnosed cases of HIV/AIDS, syphilis and gonorrhoea in China.<h4>Methods</h4>This paper used vector autoregressive model to combine the number of newly diagnosed cases w ...[more]

PMID: 32209633

Similar Datasets

Project description:BackgroundAccurate incidence prediction of sexually transmitted diseases (STDs) is critical for early prevention and better government strategic planning. In this paper, four different forecasting models were presented to predict the incidence of AIDS, gonorrhea, and syphilis.MethodsThe annual percentage changes in the incidence of AIDS, gonorrhea, and syphilis were estimated by using joinpoint regression. The performance of four methods, namely, the autoregressive integrated moving average (ARIMA) model, Elman neural network (ERNN) model, ARIMA-ERNN hybrid model and long short-term memory (LSTM) model, were assessed and compared. For 1-year prediction, the collected data from 2011 to 2020 were used for modeling to predict the incidence in 2021. For 5-year prediction, the collected data from 2011 to 2016 were used for modeling to predict the incidence from 2017 to 2021. The performance was evaluated based on four indices: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).ResultsThe morbidities of AIDS and syphilis are on the rise, and the morbidity of gonorrhea has declined in recent years. The optimal ARIMA models were determined: ARIMA(2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(3,1,2)(1,1,2)12 for AIDS, gonorrhea, and syphilis 1-year prediction, respectively; ARIMA (2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(2,1,1)(0,1,0)12 for AIDS, gonorrhea and syphilis 5-year prediction, respectively. For 1-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 23.26, 20.24, 18.34, and 18.63, respectively; For gonorrhea, the MAPEs are 19.44, 18.03, 17.77, and 5.09, respectively; For syphilis, the MAPEs are 9.80, 9.55, 8.67, and 5.79, respectively. For 5-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 12.86, 23.54, 14.74, and 25.43, respectively; For gonorrhea, the MAPEs are 17.07, 17.95, 16.46, and 15.13, respectively; For syphilis, the MAPEs are 21.88, 24.00, 20.18 and 11.20, respectively. In general, the performance ranking of the four models from high to low is LSTM, ARIMA-ERNN, ERNN, and ARIMA.ConclusionThe time series predictive models show their powerful performance in forecasting STDs incidence and can be applied by relevant authorities in the prevention and control of STDs.

Project description:BackgroundSyphilis and gonorrhea reached an all-time high in 2018. The resurgence of syphilis and gonorrhea requires innovative methods of sexual contact tracing that encourage disclosure of same-sex sexual contacts that might otherwise be suppressed. Over 75% of Grindr mobile phone application users report seeking "friendship," so this study asked people diagnosed with syphilis and gonorrhea to identify their friends.MethodsPatients at the two Baltimore sexually transmitted infection (STI) clinics and the Baltimore City Health Department were asked 12 questions to elicit members of their friendship networks before eliciting sexual networks. The study included 353 index cases and 172 friendship contacts, yielding a friendship network of 331 non-isolates (n = 331) and sexual-only network of 140 non-isolates. The data were plotted and analyzed using exponential family random graph analysis.ResultsEliciting respondents' in-person social contacts yielded 12 syphilis cases and 6 gonorrhea cases in addition to the 16 syphilis cases and 4 gonorrhea cases that would have been found with sexual contacts alone. Syphilis is clustered within sexual (odds ratio = 2.2, 95% confidence interval (1.36, 3.66)) and social contacts (OR = 1.31, 95% CI (1.02, 1.68)). Gonorrhea is clustered within reported social (OR = 1.56, 95% CI (1.22, 2.00)) but not sexual contacts (OR = 0.98, 95% CI (0.62, 1.53)).ConclusionsEliciting friendship networks of people diagnosed with syphilis and gonorrhea may find members of their sexual networks, drug use networks, or people of similar STI risk. Friendship networks include more diagnosed cases of syphilis and gonorrhea than sexual networks alone, especially among populations with many non-disclosing men who have sex with men (MSM) and women who have sex with women (WSW). Future research should evaluate whether this friendship network method of contact tracing can be implemented by adapting automated mobile phone COVID-19 contact tracing protocols, if these COVID-19 contact tracing methods are able to maintain anonymity and public trust.

Project description:BackgroundChina implemented a nationwide lockdown to contain COVID-19 from an early stage. Previous studies of the impact of COVID-19 on sexually transmitted diseases (STDs) and diseases caused by blood-borne viruses (BBVs) in China have yielded widely disparate results, and studies on deaths attributable to STDs and BBVs are scarce.ObjectiveWe aimed to elucidate the impact of COVID-19 lockdown on cases, deaths, and case-fatality ratios of STDs and BBVs.MethodsWe extracted monthly data on cases and deaths for AIDS, gonorrhea, syphilis, hepatitis B, and hepatitis C between January 2015 and December 2021 from the notifiable disease reporting database on the official website of the National Health Commission of China. We used descriptive statistics to summarize the number of cases and deaths and calculated incidence and case-fatality ratios before and after the implementation of a nationwide lockdown (in January 2020). We used negative binominal segmented regression models to estimate the immediate and long-term impacts of lockdown on cases, deaths, and case-fatality ratios in January 2020 and December 2021, respectively.ResultsA total of 14,800,330 cases of and 127,030 deaths from AIDS, gonorrhea, syphilis, hepatitis B, and hepatitis C were reported from January 2015 to December 2021, with an incidence of 149.11/100,000 before lockdown and 151.41/100,000 after lockdown and a case-fatality ratio of 8.21/1000 before lockdown and 9.50/1000 after lockdown. The negative binominal model showed significant decreases in January 2020 in AIDS cases (-23.4%; incidence rate ratio [IRR] 0.766, 95% CI 0.626-0.939) and deaths (-23.9%; IRR 0.761, 95% CI 0.647-0.896), gonorrhea cases (-34.3%; IRR 0.657, 95% CI 0.524-0.823), syphilis cases (-15.4%; IRR 0.846, 95% CI 0.763-0.937), hepatitis B cases (-17.5%; IRR 0.825, 95% CI 0.726-0.937), and hepatitis C cases (-19.6%; IRR 0.804, 95% CI 0.693-0.933). Gonorrhea, syphilis, and hepatitis C showed small increases in the number of deaths and case-fatality ratios in January 2020. By December 2021, the cases, deaths, and case-fatality ratios for each disease had either reached or remained below expected levels.ConclusionsCOVID-19 lockdown may have contributed to fewer reported cases of AIDS, gonorrhea, syphilis, hepatitis B, and hepatitis C and more reported deaths and case-fatality ratios of gonorrhea, syphilis, and hepatitis C in China.

Dataset Information

Using Baidu search index to monitor and predict newly diagnosed cases of HIV/AIDS, syphilis and gonorrhea in China: estimates from a vector autoregressive (VAR) model.

Objectives

Methods

Results

Conclusions

Publications

Using Baidu search index to monitor and predict newly diagnosed cases of HIV/AIDS, syphilis and gonorrhea in China: estimates from a vector autoregressive (VAR) model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets