Early Detection Of Outbreaks Research Articles

Tracking dynamics change parameters of chaotic infectious disease outbreak with bifurcated time-series long short-term memory model

In the dire need to develop a robust epidemiological surveillance model, this study aimed to determine if the dynamics change parameters of past infectious disease outbreaks would enable early accurate detection of future outbreaks. An optimized regular LSTM could not accurately learn the non-linear relationship of the epidemiological data in the peak stage of the pre-vaccination era measles outbreak, which hence influenced the decrease predictability at increasing time series. The result of this study shows that Pitchfork bifurcation of LSTM at 1.5 bifurcation point matches the dynamic change inherent in California's pre-vaccination era measles outbreak at the improved prediction performances of root mean squared error (RMSE) = 0.1684 for the 1962 outbreak, and root mean squared error (RMSE)= 0.2776 for 1964 outbreak. In conclusion, it was observed that the dynamics change parameters are dependent on the stochastic nature of the optimization algorithm engaged, and the chaotic nature of epidemiological data.

Malaria elimination and the need for intensive inter-country cooperation: a critical evaluation of regional technical co-operation in Southern Africa

BackgroundMalaria elimination requires closely co-ordinated action between neighbouring countries. In Southern Africa several countries have reduced malaria to low levels, but the goal of elimination has eluded them thus far. The Southern Africa Development Community (SADC) Malaria Elimination Eight (E8) initiative was established in 2009 between Angola, Botswana, Eswatini, Mozambique, Namibia, South Africa, Zambia, and Zimbabwe to coordinate malaria interventions aiming to eliminate malaria by 2030. Cross-border coordination is important in malaria elimination settings as it strengthens surveillance, joint planning and implementation, knowledge exchange and optimal use of resources. This paper describes how this collaboration is realized in practice, its achievements and challenges, and its significance for malaria elimination prospects.MethodsThe ministers of health of the E8 countries oversee an intergovernmental technical committee supported by specialist working groups consisting of technical personnel from member countries and partner institutions. These technical working groups are responsible for malaria elimination initiatives in key focus areas such as surveillance, vector control, diagnosis, case management, behaviour change and applied research. The technical working groups have initiated and guided several collaborative projects which lay essential groundwork for malaria elimination.ResultsThe E8 collaboration has yielded achievements in the following key areas. (1) Establishment and evaluation of malaria border health posts to improve malaria services in border areas and reduce malaria among resident and, mobile and migrant populations. (2) The development of a regional malaria microscopy slide bank providing materials for diagnostic training and proficiency testing. (3) A facility for regional external competency assessment and training of malaria microscopy trainers in collaboration with the World Health Organization. (4) Entomology fellowships that improved capacity in entomological surveillance; an indoor residual spraying (IRS) training of trainers’ scheme to enhance the quality of this core intervention in the region. (5) Capacity development for regional malaria parasite genomic surveillance. (6) A mechanism for early detection of malaria outbreak through near real time reporting and a quarterly bulletins of malaria incidence in border districts.ConclusionsThe E8 technical working groups system embodies inter-country collaboration of malaria control and elimination activities. It facilitates sustained interaction between countries through a regional approach. The groundwork for elimination has been laid, but the challenge will be to maintain funding for collaboration at this level whilst reducing reliance on international donors and to build capacities necessary to prepare for malaria elimination.

Modelling climate change impacts on the spatial distribution of anthrax in Zimbabwe

BackgroundIn Zimbabwe, anthrax is endemic with outbreaks being reported almost annually in livestock, wildlife, and humans over the past 40 years. Accurate modelling of its spatial distribution is key in formulating effective control strategies. In this study, an Ensemble Species Distribution Model was used to model the current and future distribution of anthrax occurrence in Zimbabwe.MethodsBioclimatic variables derived from the Beijing Climate Centre Climate System Model were used to model the disease. Collinearity testing was conducted on the 19 bioclimatic variables and elevation to remove redundancy. Variables that had no collinearity were used for anthrax habitat suitability modelling. Two future climate change scenarios for different Representative Concentration Pathways (RCP), RCP4.5 and RCP8.5 were used. Model evaluation was done using true skill, Kappa statistics and receiver operating characteristics.ResultsThe results showed that under current bioclimatic conditions, eastern and western districts of Zimbabwe were modelled as highly suitable, central districts moderately suitable and southern parts marginally suitable for anthrax occurrence. Future predictions demonstrated that the suitable (8%) and highly suitable (7%) areas for anthrax occurrence would increase under RCP4.5 scenario. In contrast, a respective decrease (11%) and marginal increase (0.6%) of suitable and highly suitable areas for anthrax occurrence were predicted under the RCP8.5 scenario. The percentage contribution of the predictors varied for the different scenarios; Bio6 and Bio18 for the current scenario, Bio2, Bio4 and Bio9 for the RCP4.5 and Bio3 and Bio15 for the RCP8.5 scenarios.ConclusionsThe study revealed that areas currently suitable for anthrax should be targeted for surveillance and prevention. The predicted future anthrax distribution can be used to guide and prioritise surveillance and control activities and optimise allocation of limited resources. In the marginally to moderately suitable areas, effective disease surveillance systems and awareness need to be put in place for early detection of outbreaks. Targeted vaccinations and other control measures including collaborative ‘One Health’ strategies need to be implemented in the predicted highly suitable areas. In the southern part where a high decrease in suitability was predicted, continued monitoring would be necessary to detect incursions early.

Real-Time On-Site Monitoring of Viruses in Wastewater Using Nanotrap® Particles and RICCA Technologies.

Wastewater-based epidemiology (WBE) is an effective and efficient tool for the early detection of infectious disease outbreaks in a community. However, currently available methods are laborious, costly, and time-consuming due to the low concentration of viruses and the presence of matrix chemicals in wastewater that may interfere with molecular analyses. In the present study, we designed a highly sensitive "Quick Poop (wastewater with fecal waste) Sensor" (termed, QPsor) using a joint approach of Nanotrap microbiome particles and RICCA (RNA Isothermal Co-Assisted and Coupled Amplification). Using QPsor, the WBE study showed a strong correlation with standard PEG concentrations and the qPCR technique. Using a closed format for a paper-based lateral flow assay, we were able to demonstrate the potential of our assay as a real-time, point-of-care test by detecting the heat-inactivated SARS-CoV-2 virus in wastewater at concentrations of 100 copies/mL and within one hour. As a proof-of-concept demonstration, we analyzed the presence of viral RNA of the SARS-CoV-2 virus and PMMoV in raw wastewater samples from wastewater treatment plants on-site and within 60 min. The results show that the QPsor method can be an effective tool for disease outbreak detection by combining an AI-enabled case detection model with real-time on-site viral RNA extraction and amplification, especially in the absence of intensive clinical laboratory facilities. The lab-free, lab-quality test capabilities of QPsor for viral prevalence and transmission in the community can contribute to the efficient management of pandemic situations.

A New Statistical Method to Detect Disease Outbreaks from Hospital Emergency Department Data.

Early detection and prediction of disease outbreaks are crucial for public health service delivery, containment response, saving patient lives, and reducing costs. We propose a new data-driven statistical methodology for outbreak detection and prediction based on routinely collected hospital Emergency Department data. The time between consecutive ED presentations matching a diagnosis of interest forms the basis of a novel index measure to signal that an outbreak has occurred. We validate the method using historical presentations of influenza-like illness made to a large sample of public hospital EDs in 2020 and compare outbreaks identified by the method with the start of the first wave of COVID-19. The method shows promise within the field of disease outbreak detection.

COVID-19 cases, vaccination, and SARS-CoV-2 in wastewater: insights from a Brazilian municipality.

Vaccines combatting COVID-19 demonstrate the ability to protect against disease and hospitalization, and reduce the likelihood of death caused by SARS-CoV-2. In addition, monitoring viral loads in sewage emerges as another crucial strategy in the epidemiological context, enabling early and collective detection of outbreaks. The study aimed to monitor the viral concentration of SARS-CoV-2 in untreated sewage in a Brazilian municipality. Also, it attempted to correlate these measurements with the number of clinical cases and deaths resulting from COVID-19 between July 2021 and July 2022. SARS-CoV-2 viral RNA was quantified by RT-qPCR. Pearson's correlation was performed to analyze the variables' relationship using the number of cases, deaths, vaccinated individuals, and viral concentration of SARS-CoV-2. The results revealed a significant negative correlation (p < 0.05) between the number of vaccinated individuals and the viral concentration of SARS-CoV-2, suggesting that after vaccination, the RNA viral load concentration was reduced in the sample population by the circulating concentration of wastewater. Consequently, wastewater monitoring, in addition to functioning as an early warning system for the circulation of SARS-CoV-2 and other pathogens, can offer a novel perspective that enhances decision-making, strengthens vaccination campaigns, and contributes to authorities establishing systematic networks for monitoring SARS-CoV-2.

Correspondence of SARS-CoV-2 genomic sequences obtained from wastewater samples and COVID-19 patient at long-term care facilities

Wastewater-based epidemiology (WBE) has been in the spotlight because of applicability of early detection of virus outbreak and new variants at the catchment area. However, there has been a notable absence of research directly confirming the association between SARS-CoV-2 in wastewater and patient specimens. In this study, we performed a quantitative and qualitative investigation with a genetic-level comparison of SARS-CoV-2 between COVID-19 patients and SARS-CoV-2 positive wastewater samples at long-term care facilities. Wastewater samples were collected via passive sampling from manholes, and SARS-CoV-2 load in wastewater was determined by qPCR. We performed correlation analysis between SARS-CoV-2 load and COVID-19 case number, which suggested that SARS-CoV-2 was detected from wastewater earlier than ascertainment of COVID-19 case. Six and six RNA samples from COVID-19 positive cases and wastewater, respectively, from two facilities were then applied for amplicon sequencing analysis. Mutation analysis revealed high sequence similarity of SARS-CoV-2 variants between wastewater and patient samples (>99 %). To the best of our knowledge, this is the first study demonstrating that WBE is also effective in predicting predominant SARS-CoV-2 variant at facility-level, which is helpful to develop early-warning system for outbreak occurrence with predominant variant.

Optimal Selection of Sampling Points within Sewer Networks for Wastewater-Based Epidemiology Applications.

Wastewater-based epidemiology (WBE) has great potential to monitor community public health, especially during pandemics. However, it faces substantial hurdles in pathogen surveillance through WBE, encompassing data representativeness, spatiotemporal variability, population estimates, pathogen decay, and environmental factors. This paper aims to enhance the reliability of WBE data, especially for early outbreak detection and improved sampling strategies within sewer networks. The tool implemented in this paper combines a monitoring model and an optimization model to facilitate the optimal selection of sampling points within sewer networks. The monitoring model utilizes parameters such as feces density and average water consumption to define the detectability of the virus that needs to be monitored. This allows for standardization and simplicity in the process of moving from the analysis of wastewater samples to the identification of infection in the source area. The entropy-based model can select optimal sampling points in a sewer network to obtain the most specific information at a minimum cost. The practicality of our tool is validated using data from Hildesheim, Germany, employing SARS-CoV-2 as a pilot pathogen. It is important to note that the tool's versatility empowers its extension to monitor other pathogens in the future.

A Novel Protocol for the Early Detection of COVID-19 at a Skilled Nursing Facility

Accurate measurement of vital signs are important at skilled nursing facilities (SNF). Recent technological advancements now enable automated vital sign measurements. This overcomes the limitations of traditional manual vital sign measurement, which is time-consuming and error-prone. We present a novel case where continuous vital sign measurement was used to detect meaningful vital sign changes that led to early detection of a COVID-19 outbreak at a SNF. Residents were continuously monitored for changes to baseline respiratory rate and heart rate and with a Probability of Change (POC). Variations in baseline respiratory rate and heart rate occurred in 66% and 42%, respectively, of COVID-19 positive individuals; 83% of participants had statistically significant variations in either vital sign. Clinical investigations are typically triggered by vital signs outside normal ranges. We present a novel methodology to detect subtle vital sign changes that can lead to earlier diagnosis, treatment, and recovery from infections, like COVID-19.

Early Detection of PRRSV Outbreaks in Breeding Herds by Monitoring Productivity and Electronic Sow Feed Data Using Univariate and Multivariate Statistical Process Control Methods

Early Detection of PRRSV Outbreaks in Breeding Herds by Monitoring Productivity and Electronic Sow Feed Data Using Univariate and Multivariate Statistical Process Control Methods

A Comprehensive Review on Optimizing Machine Learning Models for Early Detection and Forecasting of Monkeypox Outbreaks

This is a significant problem in diagnosing zoonotic opportunistic 'emerging' diseases like Monkeypox, which require not only better diagnostics but also efficient, effective, and affordable diagnostics. This paper considers the possibilities of machine learning (ML), deep learning (DL), and optimization algorithms for diagnosing and predicting Monkeypox. The presently employed strategies can be enhanced because clinical and imaging data can be harnessed to drive these technologies for early detection and subsequent containment activities. Generally, in a review, the authors offer information on how the diagnostic processes using ML and DL result in enhanced accuracy, specificity, and sensitivity of models, thus reducing design reliabilities. Furthermore, outbreak data is subjected to predictive modeling analysis to establish patterns useful in helping risk managers and policymakers prepare to manage future outbreaks. This system poses a new diagnostic model for Monkeypox and other zoonotic diseases by incorporating these complex computational tools into the present healthcare systems. This advancement not only strengthens the diagnostic arsenal of zoonotic diseases but also expands the possibilities for the interception and prevention of such diseases in the future at the world level.

The Intelligent Infectious Disease Active Surveillance and early warning system in China: An application of dengue prevention and control

Utilizing advanced information technologies such as big data and artificial intelligence (AI), China has established and implemented the Intelligent Infectious Disease Active Surveillance and Early Warning System. It provides new tools for the surveillance, early warning, and response to infectious diseases, enhancing the timeliness, scientific basis, and efficiency of epidemic control efforts. The system comprises four functional modules including multi-channel active surveillance, intelligent early warning, data-driven risk assessment, and smart emergency response. This paper provides a detailed overview of the structure and functions of the Intelligent Infectious Disease Active Surveillance and Early Warning System in China, with a specific focus on its application in dengue prevention and control in Hainan Province from February to May 2024. Firstly, the system can proactively capture and integrate heterogeneous surveillance data from multiple sources. Based on these multi-channel data, users can select appropriate warning indicators and AI models to automatically trigger early warnings. Using vast amounts of surveillance data, the system can construct machine learning models to accurately assess the transmission risk of infectious diseases. In terms of emergency response, the system offers powerful tools for early diagnosis, smart epidemiological investigation, digital contact tracing, vaccine and drug development, and evaluation of intervention measures. This system facilitates early detection, reporting, and management of outbreaks, serving as a valuable reference for other countries and regions. Nevertheless, continuous efforts are needed to strengthen scientific research and multidisciplinary collaboration, establish reliable data collection mechanisms, enhance continuous model monitoring and adjustments, and leverage the latest large language models. In the future, the system will be further optimized to help control emerging and major infectious diseases more effectively.

Exposure dynamics of Ross River virus in horses - Horses as potential sentinels (a One Health approach).

Ross River virus (RRV), the most medically and economically important arbovirus in Australia, has been the most prevalent arbovirus infections in humans for many years. Infected humans and horses often suffer similar clinical symptoms. We conducted a prospective longitudinal study over a 3.5-year period to investigate the exposure dynamics of RRV in three foal cohorts (n=32) born in a subtropical region of South East Queensland, Australia, between 2020 and 2022. RRV-specific seroconversion was detected in 56% (n=18) of foals with a median time to seroconversion, after waning of maternal antibodies, of 429days (95% CI: 294-582). The median age at seroconversion was 69weeks (95% CI: 53-57). Seroconversion events were only detected between December and March (Southern Hemisphere summer) over the entire study period. Cox proportion hazards regression analyses revealed that seroconversions were significantly (p<0.05) associated with air temperature in the month of seroconversion. Time-lags in meteorological variables were not significantly (p>0.05) associated with seroconversion, except for relative humidity (p=0.036 at 2-month time-lag). This is in contrast to research results of RRV infection in humans, which peaked between March and May (Autumn) and with a 0-3month time-lag for various meteorological risk factors. Therefore, horses may be suitable sentinels for monitoring active arbovirus circulation and could be used for early arbovirus outbreak detection in human populations.

Surveillance of SARS-CoV-2 RNA in wastewater matrix: a review.

SARS-CoV-2 is the agent responsible for the global pandemic sickness, COVID-19. It is an enveloped virus that belongs to the family Coronaviridae. Recent studies have revealed the fecal shedding of the virus and have been found to enter wastewater and aquatic systems. Prolonged viral presence in fecal samples is a common observation in the reported literature. Survival of the virus in the recipient environment could be a crucial factor that influences its fecal-oral transmission. The detection of a novel coronavirus in wastewater opportunity has potential for environmental surveillance at the community or population level. Such a surveillance system can enable the early detection of disease outbreaks in zones with pre-symptomatic/asymptomatic patients and act as a complementary tool for continuous monitoring of quarantine zones. In contrast to developed regions, resource constraints in underdeveloped communities coupled with different sanitation settings may pose a challenge to wastewater sampling and surveillance. To begin, this review summarizes the literature on the presence of SARS-CoV-2 in feces. The approaches for viral extraction, concentration, and detection in wastewater matrices are then highlighted. Finally, investigations on wastewater-based epidemiology for SARS-CoV-2 surveillance are reviewed.

Vancomycin-resistant Enterococcus faecium in Japan, 2007-2015: a molecular epidemiology analysis focused on examining strain characteristics over time.

Our study emphasizes the efficacy of whole-genome sequencing (WGS) in addressing outbreaks of vancomycin-resistant enterococci. WGS enables the identification and tracking of resistant bacterial strains, early detection and management of novel infectious disease outbreaks, and the appropriate selection and use of antibiotics. Furthermore, our approach deepens our understanding of how resistant bacteria transfer genes and adapt to their environments or hosts. For modern medicine, these insights have significant implications for controlling infections and effectively managing antibiotic use in the current era, where antibiotic resistance is progressing.

Challenges and proposed solutions for optical reading on point-of-need testing systems

A broad spectrum of application fields, including human and animal health, food safety and environmental monitoring, require performing real time, on-field chemical determinations, a concept known as point-of-need testing (PONT). In the case of infectious diseases, it allows for early diagnosis, which usually enables better treatment options for the patient, and permits early outbreak detection and intervention with proper control measures. PONT solutions are usually developed on microfluidic chips, preferably with no extra equipment, as to lower their cost, ease their delivery and portability. However, equipment-free PONT is not always feasible, since off-chip operations (e.g., pumping or heating) might be required and provided by the so-called analyzers. A typical example is the hardware for optical reading, which is the subject of this perspective article. Firstly, the state-of-the-art is briefly analyzed considering the solutions provided by both academy and industry. Special emphasis is made on the smartphone-based approaches that use no additional hardware (add-ons) for optical reading. Smartphones are the straightforward option, since they can replace a number of operations typically done by analyzers. The issues arising from using smartphones without add-ons are classified into variability sources and technical challenges. Finally, a set of methods for dealing with these challenges is proposed and briefly discussed. Simpler systems will be more easily adopted by more users, for a broader range of application cases, and will let PONT be a more powerful tool for improving disease diagnosis and outbreak management.

Emerging Zoonotic Diseases among Pastoral Communities of Caia and Búzi Districts, Sofala, Mozambique: Evidence of Antibodies against Brucella, Leptospira, Rickettsia, and Crimean-Congo Hemorrhagic Fever Virus.

Emerging zoonotic diseases are an increasing threat to public health. There is little data on the seroprevalence of zoonotic diseases among pastoralists in the country. We aim to carry out a cross-sectional study on the prevalence of major zoonotic diseases among pastoral communities in the Caia and Búzi districts. Between January and December 2018, a questionnaire was used to solicit socio-demographic data from consenting pastoralists with the collection of blood samples in the Caia and Búzi districts of the Sofala province. All samples were tested using ELISA commercial reagents for the detection of IgM antibodies against Brucella and Leptospira. Likewise, IgM and IgG antibodies against Rickettsia and CCHFV were determined using ELISA kits. A total of 218 samples were tested, of which 43.5% (95/218) were from the district of Caia and 56.4% (123/218) from the Búzi district. Results from both districts showed that the seroprevalence of IgM antibodies against Brucella and Leptospira was 2.7% (6/218) and 30.3% (67/218), respectively. Positivity rates for IgM and IgG anti-Rickettsia and CCHFV were 8.7% (19/218), 2.7% (6/218), 4.1% (9/218), and 0.9% (2/218), respectively. Results from our study showed evidence of antibodies due to exposure to Brucella, Leptospira, Rickettsia, and CCHFV with antibodies against Leptospira and Rickettsia being the most prevalent. Hence, laboratory diagnosis of zoonotic diseases is essential in the early detection of outbreaks, the identification of silent transmission, and the etiology of non-febrile illness in a pastoral community. There is a need to develop public health interventions that will reduce the risk of transmission.

Mhealth tools for community-based infectious disease surveillance in Africa: a scoping review protocol

IntroductionCountries in the WHO’s African region have found community-based surveillance useful in ensuring the effectiveness of the Integrated Disease Surveillance and Response strategy. This approach encourages community participation in the...

Detection of SARS-CoV-2 in aerosols in long term care facilities and other indoor spaces with known COVID-19 outbreaks

Coronavirus outbreaks are likely to occur in crowded and congregate indoor spaces, and their effects are most severe in vulnerable long term care facilities (LTCFs) residents. Public health officers benefit from tools that allow them to control COVID-19 outbreaks in vulnerable settings such as LTCFs, but which could be translated in the future to control other known and future virus outbreaks. This study aims to develop and test a methodology based on detection of SARS-CoV-2 in aerosol samples collected with personal pumps that could be easily implemented by public health officers. The proposed methodology was used to investigate the levels of SARS-CoV-2 in aerosol in indoor settings, mainly focusing on LTCFs, suffering COVID-19 outbreaks, or in the presence of known COVID-19 cases, and targeting the initial days after diagnosis.Aerosol samples (N = 18) were collected between November 2020 and March 2022 in Castelló (Spain) from LTCFs, merchant ships and a private home with recently infected COVID-19 cases. Sampling was performed for 24-h, onto 47 mm polytetrafluoroethylene (PTFE) and quartz filters, connected to personal pumps at 2 and 4 L/min respectively. RNA from filters was extracted and SARS-CoV-2 was determined by detection of regions N1 and N2 of the nucleocapsid gene alongside the E gene using RT-PCR technique.SARS-CoV-2 genetic material was detected in 87.5% samples. Concentrations ranged ND-19,525 gc/m3 (gene E). No genetic traces were detected in rooms from contacts that were isolated as a preventative measure. Very high levels were also measured at locations with poor ventilation. Aerosol measurement conducted with the proposed methodology provided useful information to public health officers and contributed to manage and control 12 different COVID-19 outbreaks.SARS-CoV-2 was detected in aerosol samples collected during outbreaks in congregate spaces. Indoor aerosol sampling is a useful tool in the early detection and management of COVID-19 outbreaks and supports epidemiological investigations.

Search-engine-based surveillance using artificial intelligence for early detection of coronavirus disease outbreak

The search-engine-based surveillance methods for the early warning and prediction of infectious diseases cannot achieve search engine keywords automatic filtering and real-time updating, lead to powerless for the early warning of emerging infectious diseases. The aim of this study is to develop an artificial intelligence (AI) method for search-engine-based surveillance to improve the early warning ability for emerging infectious diseases. The 32 keywords (444 million search queries) that may be related to the coronavirus disease (COVID-19) outbreak was collected from December 18, 2019 to February 11, 2020 from Baidu’s search engine database. The graph convolution network (GCN) model was used to select search engine keywords automatically, and then, multiple linear regression was performed to explore the relationship between the daily query frequencies of keywords and daily new cases. The GCN model was used to automatically select keywords. The prediction trend of the GCN model was highly consistent with the true curve with a mean absolute error of 81.65. Three keywords including “epidemic”, “mask” and “coronavirus” were selected. The selection keywords in the search queries were highly correlated with the daily number of confirmed cases (r = 0.96, 0.94, and 0.89; P < 0.01). An abnormal initial peak (3.05 times the normal volume) in queries appeared on December 31, 2019, which could have served as an early warning signal for an outbreak. Of particular concern, 17.5% of query volume originated from the Hubei Province, 51.15% of which was from Wuhan City. The coefficients of determination (R2) of our constructed model were 0.88, 0.88, 0.84, 0.77, 0.77, 0.75, 0.73, and 0.73 for a time lag of 0–7 days, respectively, using selection keywords. The model we constructed was used in the Beijing Xinfadi outbreak as an independent test dataset, which successfully predicted the daily numbers of cases for the following days and detected an early signal during the Beijing Xinfadi outbreak (R2 = 0.79). In this paper search-engine-based surveillance based on the AI method was established for the early detection of the COVID-19 epidemic for the first time. The model achieves automatic filtering and real-time updating of search engine keywords and can effectively detect the early signals of emerging infectious diseases.