Surveillance of communicable diseases using social media: A systematic review

Early warning system using primary health care data in the post-COVID-19 pandemic era: Brazil nationwide case-study

Syndromic surveillance using primary health care (PHC) data is a valuable tool for early outbreak detection, as demonstrated by the potential to identify COVID-19 outbreaks. However, the potential of such an early warning system in the post-COVID-19 era remains largely unexplored. We analyzed PHC encounter counter of respiratory complaints registered in the database of the Brazilian Unified National Health System from October 2022 to July 2023. We applied EARS (variations C1/C2/C3) and EVI to estimate the weekly thresholds. An alarm was determined when the number of encounters exceeded the week-specific threshold. We used data on hospitalization due to respiratory disease to classify as anomalies the weeks in which the number of cases surpassed predetermined thresholds. We compared EARS and EVI efficacy in anticipating anomalies. A total of 119 anomalies were identified across 116 immediate regions during the study period. The EARS-C2 presented the highest early alarm rate, with 81/119 (68%) early alarms, and C1 the lowest, with 71 (60%) early alarms. The lowest true positivity was the EARS-C1 118/1,354 (8.7%) and the highest was EARS-C3 99/856 (11.6%). Routinely collected PHC data can be successfully used to detect respiratory disease outbreaks in Brazil. Syndromic surveillance enhances timeliness in surveillance strategies, albeit with lower specificity. A combined approach with other strategies is essential to strengthen accuracy, offering a proactive and effective public health response against future outbreaks.

Innovating health prevention models in detecting infectious disease outbreaks through social media data: an umbrella review of the evidence

Introduction and objective

The number of literature reviews examining the use of social media in detecting emerging infectious diseases has recently experienced an unprecedented growth. Yet, a higher-level integration of the evidence is still lacking. This study aimed to synthesize existing systematic literature reviews published on this topic, offering an overview that can help policymakers and public health authorities to select appropriate policies and guidelines.

Methods

We conducted an umbrella review: a review of systematic reviews published between 2011 and 2023 following the PRISMA statement guidelines. The review protocol was registered in the PROSPERO database (CRD42021254568). As part of the search strategy, three database searches were conducted, specifically in PubMed, Web of Science, and Google Scholar. The quality of the included reviews was determined using A Measurement Tool to Assess Systematic Reviews 2.

Results

Synthesis included 32 systematic reviews and 3,704 primary studies that investigated how the social media listening could improve the healthcare system's efficiency in terms of a timely response to treat epidemic situations. Most of the included systematic reviews concluded showing positive outcomes when using social media data for infectious disease surveillance.

Conclusion

Systematic reviews showed the important role of social media in predicting and detecting disease outbreaks, potentially reducing morbidity and mortality through swift public health action. The policy interventions strongly benefit from the continued use of online data in public health surveillance systems because they can help in recognizing important patterns for disease surveillance and significantly improve the disease prediction abilities of the traditional surveillance systems.

Systematic Review Registration

http://www.crd.york.ac.uk/PROSPERO, identifier [CRD42021254568].

Targeting COVID-19 and Human Resources for Health News Information Extraction: Algorithm Development and Validation

BACKGROUND

Global pandemics like COVID-19 put a high amount of strain on health care systems and health workers worldwide. These crises generate a vast amount of news information published online across the globe. This extensive corpus of articles has the potential to provide valuable insights into the nature of ongoing events and guide interventions and policies. However, the sheer volume of information is beyond the capacity of human experts to process and analyze effectively.

OBJECTIVE

The aim of this study was to explore how natural language processing (NLP) can be leveraged to build a system that allows for quick analysis of a high volume of news articles. Along with this, the objective was to create a workflow comprising human-computer symbiosis to derive valuable insights to support health workforce strategic policy dialogue, advocacy, and decision-making.

METHODS

We conducted a review of open-source news coverage from January 2020 to June 2022 on COVID-19 and its impacts on the health workforce from the World Health Organization (WHO) Epidemic Intelligence from Open Sources (EIOS) by synergizing NLP models, including classification and extractive summarization, and human-generated analyses. Our DeepCovid system was trained on 2.8 million news articles in English from more than 3000 internet sources across hundreds of jurisdictions.

RESULTS

Rules-based classification with hand-designed rules narrowed the data set to 8508 articles with high relevancy confirmed in the human-led evaluation. DeepCovid's automated information targeting component reached a very strong binary classification performance of 98.98 for the area under the receiver operating characteristic curve (ROC-AUC) and 47.21 for the area under the precision recall curve (PR-AUC). Its information extraction component attained good performance in automatic extractive summarization with a mean Recall-Oriented Understudy for Gisting Evaluation (ROUGE) score of 47.76. DeepCovid's final summaries were used by human experts to write reports on the COVID-19 pandemic.

CONCLUSIONS

It is feasible to synergize high-performing NLP models and human-generated analyses to benefit open-source health workforce intelligence. The DeepCovid approach can contribute to an agile and timely global view, providing complementary information to scientific literature.

Online spaces and the control of communicable diseases: implications for nursing practice

The digital revolution has significantly altered healthcare, including communicable disease control, with online spaces emerging as vital tools in preventing, identifying and controlling the spread of diseases. However, healthcare professionals, including nurses, need to find a balance between harnessing the benefits of mass communication and mitigating the potentially harmful effects of online misinformation. This article explores the benefits and challenges of using online spaces such as social media platforms in the control of communicable diseases and discusses the potential use of telehealth in reducing the risk of healthcare-associated infection and antimicrobial resistance. The author also describes a framework that nurses can use to explore potential roles and practice in the context of communicable disease control in online spaces.

Use of Large Language Models to Assess the Likelihood of Epidemics From the Content of Tweets: Infodemiology Study

BACKGROUND

Previous work suggests that Google searches could be useful in identifying conjunctivitis epidemics. Content-based assessment of social media content may provide additional value in serving as early indicators of conjunctivitis and other systemic infectious diseases.

OBJECTIVE

We investigated whether large language models, specifically GPT-3.5 and GPT-4 (OpenAI), can provide probabilistic assessments of whether social media posts about conjunctivitis could indicate a regional outbreak.

METHODS

A total of 12,194 conjunctivitis-related tweets were obtained using a targeted Boolean search in multiple languages from India, Guam (United States), Martinique (France), the Philippines, American Samoa (United States), Fiji, Costa Rica, Haiti, and the Bahamas, covering the time frame from January 1, 2012, to March 13, 2023. By providing these tweets via prompts to GPT-3.5 and GPT-4, we obtained probabilistic assessments that were validated by 2 human raters. We then calculated Pearson correlations of these time series with tweet volume and the occurrence of known outbreaks in these 9 locations, with time series bootstrap used to compute CIs.

RESULTS

Probabilistic assessments derived from GPT-3.5 showed correlations of 0.60 (95% CI 0.47-0.70) and 0.53 (95% CI 0.40-0.65) with the 2 human raters, with higher results for GPT-4. The weekly averages of GPT-3.5 probabilities showed substantial correlations with weekly tweet volume for 44% (4/9) of the countries, with correlations ranging from 0.10 (95% CI 0.0-0.29) to 0.53 (95% CI 0.39-0.89), with larger correlations for GPT-4. More modest correlations were found for correlation with known epidemics, with substantial correlation only in American Samoa (0.40, 95% CI 0.16-0.81).

CONCLUSIONS

These findings suggest that GPT prompting can efficiently assess the content of social media posts and indicate possible disease outbreaks to a degree of accuracy comparable to that of humans. Furthermore, we found that automated content analysis of tweets is related to tweet volume for conjunctivitis-related posts in some locations and to the occurrence of actual epidemics. Future work may improve the sensitivity and specificity of these methods for disease outbreak detection.

Sentiment analysis of epidemiological surveillance reports on COVID-19 in Greece using machine learning models

The present research deals with sentiment analysis performed with Microsoft Azure Machine Learning Studio to classify Facebook posts on the Greek National Public Health Organization (EODY) from November 2021 to January 2022 during the pandemic. Positive, negative and neutral sentiments were included after processing 300 reviews. This approach involved analyzing the words appearing in the comments and exploring the sentiments related to daily surveillance reports of COVID-19 published on the EODY Facebook page. Moreover, machine learning algorithms were implemented to predict the classification of sentiments. This research assesses the efficiency of a few popular machine learning models, which is one of the initial efforts in Greece in this domain. People have negative sentiments toward COVID surveillance reports. Words with the highest frequency of occurrence include government, vaccinated people, unvaccinated, telephone communication, health measures, virus, COVID-19 rapid/molecular tests, and of course, COVID-19. The experimental results disclose additionally that two classifiers, namely two class Neural Network and two class Bayes Point Machine, achieved high sentiment analysis accuracy and F1 score, particularly 87% and over 35%. A significant limitation of this study may be the need for more comparison with other research attempts that identified the sentiments of the EODY surveillance reports of COVID in Greece. Machine learning models can provide critical information combating public health hazards and enrich communication strategies and proactive actions in public health issues and opinion management during the COVID-19 pandemic.