MaltSci 麦伴科研

Appearance

Popular Reports / Public Health

This report is written by MaltSci based on the latest literature and research findings

How does AI predict epidemics? ​

Abstract ​

The emergence of infectious diseases and their rapid global spread underscore the need for effective epidemic prediction methodologies. Traditional forecasting approaches, reliant on historical data and statistical models, often fall short, particularly in unprecedented outbreaks like COVID-19. This review highlights the transformative role of artificial intelligence (AI) in enhancing epidemic prediction accuracy through the integration of diverse data sources such as social media, climate data, and health records. AI technologies, particularly machine learning and natural language processing, enable the analysis of vast datasets to identify emerging disease trends and facilitate timely public health interventions. The review outlines the current state of research in AI-driven epidemic prediction, showcasing successful applications during the COVID-19 pandemic and dengue fever outbreaks. However, challenges such as data quality, ethical considerations, and integration with public health infrastructures remain. Future directions emphasize the need for improved AI techniques, collaboration between AI researchers and public health officials, and the development of resilient health systems. This comprehensive analysis aims to provide insights for enhancing epidemic preparedness and response, ultimately contributing to better global health outcomes.

Outline ​

This report will discuss the following questions.

  • 1 Introduction
  • 2 Overview of Epidemic Prediction
    • 2.1 Definition and Importance of Epidemic Prediction
    • 2.2 Traditional Methods of Epidemic Prediction
  • 3 AI Technologies in Epidemic Prediction
    • 3.1 Machine Learning Approaches
    • 3.2 Natural Language Processing Applications
    • 3.3 Data Sources Utilized in AI Predictions
  • 4 Case Studies of AI in Epidemic Prediction
    • 4.1 Successful Applications during COVID-19
    • 4.2 Predicting Dengue Fever Outbreaks
    • 4.3 Other Notable Examples
  • 5 Challenges and Limitations
    • 5.1 Data Quality and Availability
    • 5.2 Ethical Considerations in AI Applications
    • 5.3 Integration with Public Health Systems
  • 6 Future Directions
    • 6.1 Advancements in AI Techniques
    • 6.2 Enhancing Collaboration between AI Researchers and Public Health Officials
    • 6.3 Building Resilient Health Infrastructure
  • 7 Conclusion

1 Introduction ​

The emergence of infectious diseases and their rapid global spread pose profound challenges to public health systems, highlighting the critical need for effective epidemic prediction methodologies. Traditional approaches to epidemic forecasting have largely relied on historical data, expert opinions, and statistical models. However, the limitations of these methods, particularly in the face of unprecedented outbreaks such as COVID-19, have underscored the necessity for innovative solutions that can enhance our predictive capabilities. In this context, artificial intelligence (AI) has emerged as a transformative force, enabling researchers to harness vast amounts of data from diverse sources, including social media, climate data, and health records, to improve epidemic prediction accuracy [1][2].

The significance of epidemic prediction cannot be overstated. Accurate forecasting is essential for timely public health interventions, resource allocation, and outbreak management. As the frequency and severity of infectious disease outbreaks increase due to factors such as globalization, urbanization, and climate change, the need for robust predictive models becomes ever more pressing [3]. AI technologies, particularly machine learning and natural language processing, offer new avenues for understanding and forecasting epidemic outbreaks, thereby potentially revolutionizing the field of epidemiology [4][5].

Current research demonstrates a growing interest in integrating AI methodologies into epidemic prediction frameworks. Various studies have highlighted the potential of AI to process heterogeneous datasets, enabling earlier detection of outbreaks and improved predictions of disease transmission [2][6]. For instance, machine learning algorithms can analyze patterns in large datasets to identify emerging infectious disease trends, while natural language processing can extract relevant information from unstructured data sources such as news articles and social media posts [1][7]. These advancements not only enhance the accuracy of epidemic forecasts but also facilitate a more proactive approach to public health surveillance and response [8].

This review is organized as follows: Section 2 provides an overview of epidemic prediction, including its definition and importance, as well as a discussion of traditional methods used in this domain. Section 3 delves into the specific AI technologies employed in epidemic prediction, with subsections focusing on machine learning approaches, natural language processing applications, and the diverse data sources utilized in AI predictions. Section 4 presents case studies illustrating successful applications of AI in predicting epidemics, including notable examples from the COVID-19 pandemic and other infectious diseases such as dengue fever. In Section 5, we address the challenges and limitations associated with AI in epidemic prediction, including data quality, ethical considerations, and the integration of AI systems with existing public health infrastructures. Section 6 outlines future directions for research in this field, emphasizing the need for advancements in AI techniques, enhanced collaboration between AI researchers and public health officials, and the development of resilient health infrastructures. Finally, Section 7 concludes the review by summarizing key insights and implications for public health interventions.

By synthesizing current literature and highlighting case studies, this report aims to provide a comprehensive understanding of the role of AI in epidemic prediction, assessing its strengths and limitations while offering a framework for future research and practical applications in public health. The insights garnered from this review will contribute to a more robust approach to epidemic preparedness and response, ultimately enhancing our ability to mitigate the impacts of infectious diseases on global health systems.

2 Overview of Epidemic Prediction ​

2.1 Definition and Importance of Epidemic Prediction ​

Epidemic prediction involves the use of various methodologies and technologies to anticipate the emergence and spread of infectious diseases. This predictive capability is crucial for public health as it allows for timely interventions that can mitigate the impacts of epidemics on populations and healthcare systems. Artificial Intelligence (AI) has emerged as a transformative tool in this domain, enhancing the accuracy and efficiency of epidemic predictions.

AI's role in epidemic prediction is multifaceted. It utilizes machine learning algorithms and data analytics to analyze vast amounts of data from diverse sources, including healthcare records, social media, environmental data, and historical epidemic patterns. This analysis can identify trends and correlations that may not be immediately apparent through traditional epidemiological methods. For instance, AI systems can detect anomalies in health data, forecast potential outbreaks, and predict the geographic spread of diseases based on real-time information[9].

The importance of epidemic prediction cannot be overstated. It enables public health authorities to implement preventive measures, allocate resources effectively, and develop response strategies that can save lives and reduce economic burdens. Rapid epidemic intelligence, facilitated by AI, allows for earlier detection and rapid response, which is essential in mitigating the health and economic impacts of serious epidemics and pandemics[10]. The AI-driven EPIWATCH system, for example, has demonstrated its capability to provide early signals of epidemics before official detection by health authorities, showcasing the potential of AI in enhancing public health surveillance[10].

Moreover, the integration of AI in epidemic prediction is supported by advancements in data science and computational methods, which have significantly improved the modeling of infectious disease dynamics. These AI systems can process and analyze structured and unstructured data, allowing for more comprehensive surveillance and predictive modeling. The ability to correlate cross-source data, optimize healthcare resource allocation, and support informed outbreak response further enhances the effectiveness of epidemic prediction efforts[2].

In summary, AI significantly advances epidemic prediction by enabling the analysis of large datasets, improving the accuracy of forecasts, and facilitating timely public health responses. This predictive capability is vital for managing public health threats and preparing for future epidemics, ultimately contributing to better health outcomes and enhanced epidemic preparedness[1][11].

2.2 Traditional Methods of Epidemic Prediction ​

Artificial Intelligence (AI) has emerged as a transformative tool in predicting epidemics, significantly enhancing traditional methods of epidemic prediction. The integration of AI technologies facilitates improved accuracy and efficiency in forecasting disease outbreaks, allowing for proactive public health measures.

Traditional methods of epidemic prediction primarily rely on statistical models and historical data to forecast disease spread. These approaches, such as the SIR (Susceptible-Infectious-Recovered) and SIS (Susceptible-Infectious-Susceptible) models, utilize deterministic equations to estimate the dynamics of disease transmission. However, these traditional models often face limitations in their ability to account for complex and nonlinear interactions among various factors influencing disease spread, such as population density, mobility patterns, and environmental variables [7].

In contrast, AI-driven methodologies leverage machine learning (ML) and deep learning (DL) techniques to analyze vast amounts of heterogeneous data from diverse sources, including electronic health records, social media, and environmental data. This capability allows AI to identify patterns and correlations that may not be apparent through traditional methods. For instance, AI models can process real-time data to enhance forecasting accuracy and provide timely alerts about potential outbreaks [6].

One significant advantage of AI in epidemic prediction is its ability to integrate various data types, enabling a more comprehensive understanding of disease dynamics. By employing predictive analytics, AI can improve the accuracy of outbreak predictions and assist public health officials in implementing effective response strategies. AI systems can analyze data on social behavior, climate changes, and healthcare infrastructure to create a more nuanced risk assessment, identifying geographic hotspots and high-risk populations [12].

Moreover, AI applications in epidemic prediction extend to the use of natural language processing (NLP) and big data analytics, allowing for the synthesis of information from news reports and social media, which can serve as early indicators of emerging health threats [5]. This capability enhances the early warning systems that are crucial for timely public health interventions.

Despite the potential of AI to revolutionize epidemic prediction, challenges remain. Issues such as data privacy, model transparency, and the need for rigorous validation of AI models across different epidemiological contexts must be addressed to fully realize the benefits of AI in this field [3]. Furthermore, the "black box" nature of many AI algorithms can hinder trust and acceptance among public health practitioners [13].

In conclusion, AI significantly enhances epidemic prediction by integrating diverse data sources and employing advanced analytical techniques. This advancement allows for more accurate forecasting and better preparedness for future epidemics, marking a substantial evolution from traditional predictive methods. Continued research and development in AI methodologies are essential to overcome existing challenges and improve epidemic response strategies [8].

3 AI Technologies in Epidemic Prediction ​

3.1 Machine Learning Approaches ​

Artificial Intelligence (AI), particularly through machine learning (ML) approaches, has significantly advanced the prediction of epidemics by enhancing our ability to analyze complex data patterns and forecast disease outbreaks. Several studies have demonstrated the effectiveness of these technologies in epidemic prediction.

Machine learning methods, such as multi-layer perceptrons, convolutional neural networks (CNNs), and long-short term memory networks (LSTMs), are employed to estimate critical epidemiological parameters, including the basic reproduction number (R0). These models learn from historical epidemiological data to identify patterns that can indicate potential outbreaks. For instance, in a comparative study, it was found that machine learning approaches can be verified and tested faster than traditional methods like approximate Bayesian computation, which are more robust across different datasets (Tessmer et al., 2018) [14].

AI-driven epidemiological models, such as the Susceptible-Infectious-Recovered (SIR) and Susceptible-Infectious-Susceptible (SIS) frameworks, leverage data to predict the spread of diseases. These models integrate various data sources, including climate, demographic, and health data, to improve the accuracy of outbreak predictions. The integration of machine learning algorithms and predictive analytics enhances our understanding of disease propagation patterns, which is crucial for timely public health interventions (Gawande et al., 2025) [7].

Furthermore, AI technologies have been instrumental in developing early warning systems for infectious disease surveillance. These systems utilize diverse data sources, such as epidemiological data, web data, and climate data, to detect outbreaks earlier and improve prediction accuracy. Challenges remain, particularly concerning data quality and ethical considerations, but the potential for AI to strengthen epidemic prediction capabilities is substantial (Villanueva-Miranda et al., 2025) [3].

In summary, AI and machine learning approaches are transforming epidemic prediction by enabling faster data processing, improved pattern recognition, and enhanced forecasting capabilities. These technologies are essential for developing robust public health responses to emerging infectious diseases, ultimately aiming to mitigate their impact on global health.

3.2 Natural Language Processing Applications ​

Artificial Intelligence (AI), particularly through the application of Natural Language Processing (NLP), plays a significant role in predicting epidemics by enhancing the speed and accuracy of disease surveillance and outbreak detection. The integration of various AI techniques, including machine learning (ML), deep learning (DL), and NLP, allows for the processing and analysis of vast amounts of data from diverse sources, which is critical for early warning systems (EWS) in public health.

NLP specifically enables the extraction of valuable information from unstructured data, such as social media posts, news articles, and medical reports. This capability is essential for identifying emerging health threats and trends that may not be captured through traditional surveillance methods. For instance, AI-driven epidemic intelligence systems leverage NLP to analyze real-time data, correlating information from multiple sources to detect potential outbreaks more swiftly and accurately than manual reporting systems could allow (Kaur & Butt, 2025) [2].

The systematic review by Villanueva-Miranda et al. (2025) highlights the benefits of using AI in early warning systems, noting that machine learning and NLP can significantly enhance outbreak prediction accuracy and enable earlier detection of potential epidemics. The study underscores the integration of various data types, including epidemiological data, climate data, and even wastewater analysis, to improve predictive models [3].

Challenges persist, such as ensuring data quality, addressing biases in AI models, and enhancing model transparency to mitigate the "black box" issue. Ethical considerations, including privacy and equity in data usage, are also paramount as AI technologies become more integrated into public health strategies (Villanueva-Miranda et al., 2025) [3]. Moreover, the implementation of AI-driven systems must align with public health policies to ensure effective communication and response to identified threats (Kaur & Butt, 2025) [2].

AI's transformative potential is particularly evident in the context of the COVID-19 pandemic, where NLP was utilized to process vast amounts of literature and data, aiding in the identification of critical information needs and trends. Chen et al. (2021) conducted a comprehensive review of NLP applications during the pandemic, demonstrating how these technologies can support various tasks, including information retrieval, sentiment analysis, and misinformation detection, all of which are vital for timely epidemic response [15].

In summary, AI, through the lens of NLP, significantly enhances epidemic prediction capabilities by enabling the analysis of diverse data sources, improving outbreak detection accuracy, and supporting informed public health responses. However, to fully realize these benefits, it is essential to address existing challenges and ensure ethical implementation.

3.3 Data Sources Utilized in AI Predictions ​

Artificial Intelligence (AI) has emerged as a transformative tool in predicting epidemics by integrating diverse data sources and employing advanced analytical techniques. The predictive capabilities of AI in epidemic forecasting are underpinned by its ability to process large volumes of heterogeneous data, enabling timely and accurate predictions.

One of the primary data sources utilized in AI predictions includes electronic health records, which provide real-time insights into patient health and disease trends. Additionally, social media platforms serve as a valuable resource for outbreak prediction, allowing for the analysis of public sentiment and behaviors that may indicate emerging health threats. AI algorithms can sift through vast amounts of data from these platforms to identify patterns that precede outbreaks, thereby facilitating earlier intervention strategies[6].

Furthermore, spatiotemporal data plays a critical role in AI-driven epidemic predictions. This type of data encompasses geographic information systems (GIS) and environmental data, which help in tracking the spread of diseases over time and across different regions. By integrating these data sources, AI can enhance the accuracy of disease transmission predictions and identify geographic hotspots that are at higher risk for outbreaks[16].

Wearable technologies are another innovative data source that AI leverages for early infection detection. These devices can monitor physiological parameters in real-time, providing crucial information about potential disease outbreaks. The continuous stream of data from wearables enables AI systems to analyze trends and anomalies that may indicate the onset of an epidemic[6].

Moreover, AI applications also incorporate open-source data from news reports and public health announcements, which can generate valid early warning signals of emerging epidemics. This approach not only supplements traditional surveillance methods but also serves as a catalyst for earlier investigation and diagnostics, potentially leading to quicker pathogen characterization and vaccine development[16].

AI techniques such as machine learning (ML), deep learning (DL), and natural language processing (NLP) are pivotal in synthesizing these diverse datasets. These technologies enable AI systems to learn from historical data, improving their predictive accuracy over time. For instance, AI-driven models have shown significant promise in enhancing influenza forecasting accuracy by integrating social media data with epidemiological information[3].

However, despite the advantages, the implementation of AI in epidemic prediction faces challenges, including data privacy concerns, the need for robust model validation, and the requirement for external testing across various epidemiological contexts. Addressing these challenges is crucial for the effective application of AI in public health strategies[2].

In conclusion, AI predicts epidemics by utilizing a multitude of data sources, including electronic health records, social media, spatiotemporal data, and wearable technologies. Through advanced analytical techniques, AI enhances the capacity for early detection and response, ultimately strengthening public health initiatives against infectious diseases.

4 Case Studies of AI in Epidemic Prediction ​

4.1 Successful Applications during COVID-19 ​

Artificial Intelligence (AI) has emerged as a powerful tool in predicting epidemics, particularly during the COVID-19 pandemic. The ability of AI to analyze vast amounts of data and identify patterns has led to significant advancements in epidemic prediction and management. Several case studies illustrate the successful applications of AI in this domain.

One of the critical applications of AI during the COVID-19 pandemic has been in predicting outbreaks and identifying high-risk areas. AI systems utilize machine learning algorithms to analyze various data sources, including epidemiological data, social media trends, and mobility patterns. For instance, the use of AI for tracking and tracing infected individuals has been instrumental in mitigating the spread of the virus. AI can process real-time data to predict potential hotspots, thereby allowing health authorities to implement timely interventions [8].

Moreover, AI has facilitated the development of predictive models that can forecast the number of COVID-19 cases. Techniques such as deep learning and time series analysis have been employed to model the spread of the virus. A study utilizing deep learning models, including Long Short-Term Memory (LSTM) networks, demonstrated the effectiveness of these approaches in forecasting COVID-19 cases. The Stacked LSTM algorithm, in particular, yielded high accuracy with an error rate of less than 2%, proving its reliability for short-term and medium-term predictions [17].

In addition to direct predictions, AI has been applied to enhance epidemiological modeling. Traditional epidemiological models have been complemented by AI-driven systems that improve pattern recognition and outbreak predictions. AI-based model systems can analyze minimal and variable data, enhancing the accuracy of disease diagnosis and identifying potential drug targets [18]. The integration of AI with big data analytics has further empowered public health officials to select better response strategies, optimizing preparedness measures against COVID-19 [19].

AI's role in vaccine development during the pandemic also highlights its predictive capabilities. Machine learning algorithms have been utilized to analyze genomic data, which aids in identifying potential vaccine candidates. By simulating various scenarios and outcomes, AI can expedite the vaccine development process, which is crucial during an outbreak [20].

Furthermore, AI has been instrumental in managing healthcare resources effectively. By analyzing data related to healthcare infrastructure and patient demographics, AI can predict the demand for medical resources, ensuring that healthcare systems are adequately prepared for surges in cases [21].

Despite these advancements, challenges remain in the widespread implementation of AI for epidemic prediction. Issues such as data quality, privacy concerns, and the need for standardized reporting protocols must be addressed to maximize the potential of AI in public health [19].

In conclusion, AI has proven to be a transformative force in predicting epidemics, particularly during the COVID-19 pandemic. Its applications in outbreak prediction, healthcare resource management, and vaccine development demonstrate the significant impact of AI on global health. Continued research and development in this field are essential for enhancing epidemic preparedness and response in the future.

4.2 Predicting Dengue Fever Outbreaks ​

Artificial intelligence (AI) has emerged as a powerful tool in predicting epidemics, particularly in the context of dengue fever outbreaks. Various studies illustrate the application of AI techniques, including machine learning algorithms, to enhance the accuracy of outbreak predictions. The following case studies highlight how AI has been utilized to forecast dengue fever incidences effectively.

One notable study by Nurul Azam Mohd Salim et al. (2021) employed machine learning techniques to predict dengue outbreaks in Selangor, Malaysia. The researchers analyzed data from five districts with the highest incidence of dengue fever from 2013 to 2017, utilizing climate variables such as temperature, wind speed, humidity, and rainfall. Among the various models tested, the Support Vector Machine (SVM) with a linear kernel demonstrated the best performance, achieving an accuracy of 70%, a sensitivity of 14%, and a specificity of 95%. Notably, the sensitivity of the SVM model increased significantly when applied to a balanced testing sample, highlighting the importance of data handling in predictive modeling. The study concluded that machine learning holds considerable promise for dengue outbreak predictions, suggesting future research should explore boosting techniques or nature-inspired algorithms for further improvements [22].

In another investigation by Chien-Hung Lee et al. (2021), a dual-parameter estimation algorithm was developed to predict dengue fever epidemics using a vector compartment model combined with the Markov Chain Monte Carlo method. This study incorporated meteorological and mosquito-related factors to model the dynamics of dengue transmission. By analyzing time series data from 2000 to 2016 across three cities, the model effectively estimated the periodicity of dengue outbreaks and suggested optimal intervention timing to control epidemic spread. The researchers found that the estimated dengue report rate was approximately 20%, closely aligning with official statistics, indicating the model's potential for practical application in public health [23].

Reham Abdallah et al. (2024) took a different approach by leveraging transfer learning and the Analytic Hierarchy Process (AHP) in machine learning to enhance predictions of dengue, chikungunya, and Zika outbreaks. Utilizing a comprehensive dataset that included climate and socioeconomic data from 2007 to 2017, the study employed multiple machine learning algorithms, with an ensemble model achieving the highest accuracy of 96.80% for predicting Zika outbreaks. This research underscores the effectiveness of combining advanced algorithms and feature selection methods to improve predictive accuracy for infectious diseases [24].

Moreover, Sarah F. McGough et al. (2021) presented a dynamic ensemble learning approach that incorporated weather and population susceptibility data to forecast dengue epidemics in Brazil. This model identified local patterns in environmental factors and population immunity, enabling predictions months in advance. The incorporation of population susceptibility into the forecasting process marked a significant advancement, as traditional models often overlooked this critical variable [25].

These studies collectively demonstrate that AI, particularly through machine learning and ensemble modeling techniques, plays a crucial role in enhancing the predictive capabilities for dengue fever outbreaks. By integrating diverse datasets, including climatic, environmental, and socioeconomic factors, AI models can provide timely and actionable insights for public health officials, thereby facilitating more effective epidemic management and control strategies. The ongoing research in this field suggests a promising future for AI applications in epidemic prediction, particularly as methodologies continue to evolve and improve.

4.3 Other Notable Examples ​

Artificial Intelligence (AI) has emerged as a transformative tool in predicting epidemics by leveraging various methodologies, including machine learning (ML) and data integration from diverse sources. The application of AI in epidemic prediction can be illustrated through several notable case studies and examples.

One prominent use case is the integration of AI into epidemiological modeling, which has significantly enhanced our ability to forecast disease dynamics. For instance, AI-driven models, such as the SIR (Susceptible-Infectious-Recovered) and SIS (Susceptible-Infectious-Susceptible) models, are employed to predict the spread of infectious diseases. These models utilize machine learning algorithms and predictive analytics to improve understanding of disease propagation patterns, which aids in outbreak prevention and vaccine distribution optimization (Gawande et al. 2025) [7].

In the context of COVID-19, AI played a critical role in monitoring and predicting outbreaks. The utilization of AI technologies allowed for the tracking of infected individuals, identification of high-risk areas, and prediction of potential hotspots. Machine learning algorithms processed vast datasets, including epidemiological data and social media trends, to provide real-time insights into infection dynamics (Siddig et al. 2023) [8]. Moreover, AI's ability to analyze heterogeneous datasets, such as electronic health records and wearable technologies, facilitated earlier detection of outbreaks and improved disease transmission predictions (Li et al. 2025) [6].

Another notable example is the application of AI in the development of early warning systems (EWS) for infectious disease surveillance. A systematic review highlighted the effectiveness of AI in enhancing outbreak detection and prediction accuracy through the integration of diverse data sources, including climate data, web-based information, and wastewater analysis. The challenges faced in this domain, such as data quality and ethical considerations, underscore the need for improved model transparency and collaboration between AI developers and public health experts (Villanueva-Miranda et al. 2025) [3].

AI's predictive capabilities are further exemplified in the context of climate-sensitive infectious diseases. Advanced spatio-temporal models and machine learning techniques have been utilized to understand the intricate relationships between climatic factors and disease transmission, enabling timely responses to potential outbreaks (Haque et al. 2024) [26]. These models are crucial for anticipating the impacts of climate change on public health and improving epidemic preparedness.

Overall, AI's contributions to epidemic prediction are multifaceted, encompassing advancements in modeling techniques, data integration, and the development of innovative surveillance systems. The ongoing research and application of AI in this field hold significant promise for enhancing public health responses to future epidemics and pandemics.

5 Challenges and Limitations ​

5.1 Data Quality and Availability ​

Artificial intelligence (AI) plays a pivotal role in predicting epidemics by utilizing advanced algorithms to analyze vast amounts of data from various sources. However, the effectiveness of these AI applications is significantly influenced by challenges related to data quality and availability.

One of the primary challenges in AI-driven epidemic prediction is data quality. AI systems rely on accurate and comprehensive datasets to train their models effectively. In many cases, the data used may be incomplete, biased, or of low quality, which can lead to erroneous predictions and potentially catastrophic outcomes in public health management. For instance, data may be affected by reporting delays, inaccuracies in manual data entry, or insufficient coverage of certain populations or geographic areas. These issues can create gaps in the information needed for AI systems to function optimally, as highlighted in the systematic review conducted by Villanueva-Miranda et al. (2025), which notes that significant challenges persist regarding data quality and bias[3].

Furthermore, the availability of relevant data poses another significant hurdle. AI models require diverse datasets to enhance their predictive capabilities, including epidemiological data, climate data, and social media inputs. However, in many regions, particularly low-income and middle-income countries, there is often a lack of infrastructure to collect and maintain such data. This limitation not only hampers the development of robust AI models but also exacerbates existing disparities in health outcomes. The review by Kaur and Butt (2025) emphasizes that the growing frequency of emerging infectious diseases necessitates rapid and accurate surveillance methods, yet many regions lack the necessary data to implement these systems effectively[2].

Additionally, ethical considerations surrounding data privacy and equity further complicate the landscape of AI in epidemic prediction. The use of personal data, particularly in health contexts, raises concerns about consent and the potential for misuse. Ensuring that AI applications do not reinforce existing inequalities in health access and outcomes is crucial, as pointed out by Trump et al. (2025), who discuss the ethical challenges of implementing AI in pandemic response[27].

In summary, while AI holds considerable promise for predicting epidemics, its success is heavily contingent upon the quality and availability of data. Addressing these challenges requires a concerted effort to improve data collection methods, ensure data integrity, and develop ethical frameworks that promote equitable access to health information. Only through such measures can AI effectively contribute to enhanced epidemic preparedness and response.

5.2 Ethical Considerations in AI Applications ​

Artificial intelligence (AI) is increasingly being applied to the modeling and prediction of infectious disease epidemics, leveraging advanced methodologies such as machine learning and computational statistics. However, the deployment of AI in this context presents various challenges and limitations, particularly concerning ethical considerations.

AI has the potential to transform infectious disease epidemiology by enhancing the ability to analyze vast amounts of surveillance data, thereby facilitating more accurate predictions of disease outbreaks. AI systems can integrate various data sources, including real-time health data, social media, and environmental factors, to improve epidemiological modeling. For instance, recent advances in AI have been shown to accelerate breakthroughs in answering critical epidemiological questions, such as the dynamics of disease spread and the effectiveness of interventions[1].

Despite these advancements, there are significant challenges associated with AI applications in epidemic prediction. One major challenge is the quality and representativeness of the data used to train AI models. Poor data quality can lead to biased predictions, which may exacerbate existing health disparities. The concept of "data poverty" highlights the difficulties faced by low- and middle-income countries (LMICs) in accessing high-quality data necessary for effective AI deployment[28]. Furthermore, AI models can be limited by their inability to account for complex social and environmental contexts, which are crucial for understanding disease dynamics[1].

Ethical considerations also play a critical role in the application of AI for epidemic prediction. The use of AI raises concerns regarding privacy, particularly in how personal health data is collected, processed, and utilized. There is a risk of violating individuals' privacy rights, especially when using data sourced from social media or other public platforms. The ethical frameworks of utilitarianism and deontology have been employed to analyze these challenges, suggesting that the deployment of AI should prioritize public benefit while respecting individual rights[29].

Moreover, there is a pressing need for transparency and accountability in AI-driven predictions. Stakeholders must ensure that AI models are explainable and that their decision-making processes are transparent to maintain public trust. The potential for "model hallucinations," where AI generates inaccurate or misleading outputs, poses additional ethical dilemmas, particularly in high-stakes environments such as public health[30].

In summary, while AI offers promising tools for predicting epidemics, the challenges of data quality, the complexities of contextual factors, and ethical considerations regarding privacy and transparency must be carefully addressed. Ongoing discussions among researchers, policymakers, and healthcare professionals are essential to navigate these challenges and ensure that AI contributes positively to public health outcomes[1][28][30].

5.3 Integration with Public Health Systems ​

Artificial intelligence (AI) plays a pivotal role in predicting epidemics through the utilization of advanced data analytics and machine learning techniques. By analyzing vast amounts of data from diverse sources, AI can identify patterns and trends that may indicate the emergence of infectious diseases. For instance, AI systems can process real-time surveillance data, historical health records, and even social media trends to forecast potential outbreaks. This capability is especially crucial given the increasing frequency of emerging infectious diseases, necessitating rapid and accurate surveillance methods (Kaur & Butt, 2025) [2].

However, the integration of AI into public health systems faces significant challenges and limitations. One primary concern is the fragmentation of data across different health systems, which can hinder the effectiveness of AI algorithms that rely on comprehensive datasets. In many cases, data is siloed within specific institutions, leading to incomplete datasets that AI cannot utilize fully (Miglietta et al., 2025) [31]. Additionally, there are issues related to data quality, including biases stemming from unequal representation of populations in the datasets used for training AI models. Such biases can exacerbate existing health disparities and lead to inaccurate predictions (Panteli et al., 2025) [32].

Furthermore, ethical considerations present another layer of complexity. AI systems must navigate concerns regarding privacy, accountability, and the potential for unintended consequences. For instance, the use of AI in public health must ensure that it does not reinforce inequities in health access or outcomes (Del Rey Puech et al., 2025) [33]. This necessitates the development of robust regulatory frameworks and ethical guidelines to govern AI applications in public health (Kraemer et al., 2025) [1].

In addition to these challenges, there is also the need for public health professionals to be adequately trained in AI technologies to leverage their full potential effectively. This includes understanding how to interpret AI-generated insights and integrate them into public health decision-making processes (Morgenstern et al., 2021) [34]. The lack of workforce readiness can limit the adoption and implementation of AI-driven solutions in public health.

In conclusion, while AI has the potential to revolutionize epidemic prediction and response, its integration into public health systems is fraught with challenges. Addressing data fragmentation, ensuring ethical use, and equipping public health professionals with the necessary skills are critical steps that must be taken to harness the transformative potential of AI in predicting and managing epidemics effectively.

6 Future Directions ​

6.1 Advancements in AI Techniques ​

Artificial Intelligence (AI) has emerged as a transformative tool in predicting epidemics, leveraging advancements in machine learning (ML), natural language processing (NLP), and data integration techniques. The capacity of AI to analyze vast amounts of data from diverse sources significantly enhances the accuracy and timeliness of epidemic predictions.

One of the primary methodologies employed by AI in epidemic prediction involves the integration of heterogeneous datasets, which include electronic health records, social media, climate data, and spatiotemporal information. This integration allows for the real-time monitoring of disease spread and the identification of potential outbreaks before they escalate. For instance, AI-driven models can utilize social media data to predict influenza outbreaks by analyzing public discussions and search trends, thereby improving forecasting accuracy[6].

Moreover, AI techniques such as machine learning enable the development of predictive models that can analyze patterns in historical epidemiological data. These models, including Susceptible-Infectious-Recovered (SIR) and Susceptible-Infectious-Susceptible (SIS) frameworks, are utilized to simulate disease dynamics and forecast the potential trajectory of infectious diseases[7]. The application of these models has been instrumental in optimizing public health responses, including vaccination strategies and resource allocation.

In addition to predictive modeling, AI enhances epidemic intelligence through the automation of data collection and analysis processes. This automation facilitates faster responses to emerging threats, as traditional methods often suffer from delays due to manual reporting and analysis. AI systems can process real-time data, enabling timely alerts and intervention strategies[2].

Looking ahead, future directions in AI for epidemic prediction involve refining algorithms to improve adaptability and robustness. The integration of advanced AI techniques, such as deep learning, holds promise for enhancing model performance and reducing biases associated with data quality[3]. Furthermore, addressing ethical considerations and ensuring transparency in AI applications will be critical to gaining trust from public health officials and the general population.

Overall, the evolution of AI technologies continues to shape the landscape of epidemic prediction, promising more effective public health strategies and improved outcomes in infectious disease management. Continued research and development in this field are essential for harnessing AI's full potential in combating future epidemics[1][35][36].

6.2 Enhancing Collaboration between AI Researchers and Public Health Officials ​

Artificial Intelligence (AI) plays a pivotal role in predicting epidemics through various methodologies and data integration techniques. The utilization of AI in epidemic prediction encompasses a multitude of approaches, which are crucial for enhancing the capabilities of public health surveillance systems.

AI technologies enable the integration of diverse data sources, including electronic health records, social media, spatiotemporal data, and wearable technologies. This integration facilitates earlier detection of outbreaks and real-time monitoring of disease transmission dynamics. For instance, AI can analyze social media trends to predict outbreaks, leveraging public sentiment and reported symptoms to forecast disease spread more accurately. Additionally, wearable sensors provide critical data for early infection detection, contributing to timely interventions [6].

Moreover, AI-driven epidemiological models, such as the Susceptible-Infectious-Recovered (SIR) and Susceptible-Infectious-Susceptible (SIS) models, utilize machine learning algorithms to simulate and predict the spread of infectious diseases. These models enable public health officials to optimize resource allocation, manage vaccine distribution, and implement effective mitigation strategies [7]. The ability of AI to process large datasets allows for improved risk assessment by identifying high-risk individuals and geographic hotspots, thus enhancing public health strategies [6].

Collaboration between AI researchers and public health officials is essential for maximizing the effectiveness of AI in epidemic prediction. This collaboration can facilitate the development of robust AI models that are adaptable to various epidemiological settings and ensure that AI applications are grounded in real-world public health needs. It is crucial for researchers to engage with public health practitioners to understand the specific challenges they face, allowing for the design of AI solutions that are not only innovative but also practical and applicable in real-time scenarios [32].

In conclusion, AI's predictive capabilities in epidemic forecasting hinge on its ability to synthesize and analyze diverse data streams, thereby enhancing the accuracy of outbreak predictions and public health responses. Future directions should focus on fostering collaborative frameworks that unite AI expertise with public health knowledge, ensuring that AI technologies are effectively utilized to bolster epidemic preparedness and response efforts [11].

6.3 Building Resilient Health Infrastructure ​

Artificial Intelligence (AI) has emerged as a pivotal tool in predicting epidemics and enhancing public health infrastructure resilience. Its applications in epidemic prediction leverage advanced methodologies, such as machine learning (ML), deep learning (DL), and natural language processing (NLP), which can process vast amounts of data from diverse sources to forecast disease outbreaks and inform timely responses.

AI predicts epidemics by utilizing various models and techniques. For instance, AI-driven epidemiological models like SIR (Susceptible-Infectious-Recovered) and SIS (Susceptible-Infectious-Susceptible) have been instrumental in simulating disease spread, allowing for the anticipation of outbreaks and optimization of vaccine distribution strategies[7]. These models integrate data from multiple domains, including historical disease incidence, demographic information, climate data, and even social media trends, to improve the accuracy of predictions[6].

The integration of AI into early warning systems (EWS) significantly enhances the capacity for outbreak detection. Machine learning algorithms analyze real-time data from various sources, including epidemiological reports, environmental data, and human mobility patterns, to identify potential outbreaks before they escalate[3]. This proactive approach not only facilitates early detection but also aids in resource allocation and response planning, thus building a more resilient health infrastructure.

Moreover, AI applications extend to improving the quality and timeliness of data used in epidemic prediction. By utilizing NLP, AI can mine vast amounts of unstructured data from medical literature and online resources, identifying emerging trends and patterns that might signal an impending outbreak[37]. This capability is crucial in the context of infectious diseases, where rapid changes in transmission dynamics can occur.

Future directions for AI in epidemic prediction emphasize the need for continuous research and development to refine predictive models and address challenges related to data quality, bias, and ethical considerations. For instance, ensuring the transparency of AI models and improving their explainability will be vital in gaining trust among public health officials and the general population[38]. Additionally, enhancing collaboration between AI developers and public health experts is essential to create integrated systems that can adapt to the complexities of infectious disease dynamics[2].

In summary, AI's role in predicting epidemics is characterized by its ability to analyze diverse data sources, model disease transmission dynamics, and enhance early warning systems. As the field evolves, it will be crucial to address existing challenges while leveraging AI's transformative potential to strengthen public health infrastructure and improve epidemic preparedness and response strategies.

7 Conclusion ​

The integration of artificial intelligence (AI) into epidemic prediction represents a significant advancement in public health preparedness and response strategies. Key findings indicate that AI enhances the accuracy and efficiency of epidemic forecasting by utilizing diverse data sources and advanced analytical techniques. Traditional epidemic prediction methods, while foundational, often fall short in the face of complex, rapidly evolving infectious diseases. AI's ability to process large datasets, identify patterns, and predict disease transmission dynamics is critical for timely public health interventions. Case studies, particularly those involving COVID-19 and dengue fever, highlight the transformative potential of AI in outbreak detection and management. However, challenges remain, including data quality, ethical considerations, and the need for integration with existing public health systems. Future research should focus on refining AI methodologies, enhancing collaboration between AI researchers and public health officials, and building resilient health infrastructures to better prepare for and respond to future epidemics. As the landscape of infectious disease continues to evolve, the role of AI in epidemic prediction will be increasingly vital, necessitating ongoing innovation and adaptation in public health strategies.

References ​

  • [1] Moritz U G Kraemer;Joseph L-H Tsui;Serina Y Chang;Spyros Lytras;Mark P Khurana;Samantha Vanderslott;Sumali Bajaj;Neil Scheidwasser;Jacob Liam Curran-Sebastian;Elizaveta Semenova;Mengyan Zhang;H Juliette T Unwin;Oliver J Watson;Cathal Mills;Abhishek Dasgupta;Luca Ferretti;Samuel V Scarpino;Etien Koua;Oliver Morgan;Houriiyah Tegally;Ulrich Paquet;Loukas Moutsianas;Christophe Fraser;Neil M Ferguson;Eric J Topol;David A Duchêne;Tanja Stadler;Patricia Kingori;Michael J Parker;Francesca Dominici;Nigel Shadbolt;Marc A Suchard;Oliver Ratmann;Seth Flaxman;Edward C Holmes;Manuel Gomez-Rodriguez;Bernhard Schölkopf;Christl A Donnelly;Oliver G Pybus;Simon Cauchemez;Samir Bhatt. Artificial intelligence for modelling infectious disease epidemics.. Nature(IF=48.5). 2025. PMID:39972226. DOI: 10.1038/s41586-024-08564-w.
  • [2] Jasleen Kaur;Zahid Ahmad Butt. AI-driven epidemic intelligence: the future of outbreak detection and response.. Frontiers in artificial intelligence(IF=4.7). 2025. PMID:40810005. DOI: 10.3389/frai.2025.1645467.
  • [3] Ismael Villanueva-Miranda;Guanghua Xiao;Yang Xie. Artificial intelligence in early warning systems for infectious disease surveillance: a systematic review.. Frontiers in public health(IF=3.4). 2025. PMID:40626156. DOI: 10.3389/fpubh.2025.1609615.
  • [4] Parveen Kumar;Benu Chaudhary;Preeti Arya;Rupali Chauhan;Sushma Devi;Punit B Parejiya;Madan Mohan Gupta. Advanced Artificial Intelligence Technologies Transforming Contemporary Pharmaceutical Research.. Bioengineering (Basel, Switzerland)(IF=3.7). 2025. PMID:40281723. DOI: 10.3390/bioengineering12040363.
  • [5] Sergio Consoli;Pietro Coletti;Peter V Markov;Lia Orfei;Indaco Biazzo;Lea Schuh;Nicolas Stefanovitch;Lorenzo Bertolini;Mario Ceresa;Nikolaos I Stilianakis. An epidemiological knowledge graph extracted from the World Health Organization's Disease Outbreak News.. Scientific data(IF=6.9). 2025. PMID:40494870. DOI: 10.1038/s41597-025-05276-2.
  • [6] Jin-Hua Li;Yi-Ju Tseng;Shu-Hui Chen;Kuan-Fu Chen. Artificial Intelligence in Infection Surveillance: Data Integration, Applications and Future Directions.. Biomedical journal(IF=4.4). 2025. PMID:41205676. DOI: 10.1016/j.bj.2025.100929.
  • [7] Mayur Suresh Gawande;Nikita Zade;Praveen Kumar;Swapnil Gundewar;Induni Nayodhara Weerarathna;Prateek Verma. The role of artificial intelligence in pandemic responses: from epidemiological modeling to vaccine development.. Molecular biomedicine(IF=10.1). 2025. PMID:39747786. DOI: 10.1186/s43556-024-00238-3.
  • [8] Emmanuel Edwar Siddig;Hala Fathi Eltigani;Ayman Ahmed. The Rise of AI: How Artificial Intelligence is Revolutionizing Infectious Disease Control.. Annals of biomedical engineering(IF=5.4). 2023. PMID:37335374. DOI: 10.1007/s10439-023-03280-4.
  • [9] David B Olawade;Ojima J Wada;Aanuoluwapo Clement David-Olawade;Edward Kunonga;Olawale Abaire;Jonathan Ling. Using artificial intelligence to improve public health: a narrative review.. Frontiers in public health(IF=3.4). 2023. PMID:37954052. DOI: 10.3389/fpubh.2023.1196397.
  • [10] C Raina MacIntyre;Samsung Lim;Ashley Quigley. Preventing the next pandemic: Use of artificial intelligence for epidemic monitoring and alerts.. Cell reports. Medicine(IF=10.6). 2022. PMID:36543103. DOI: 10.1016/j.xcrm.2022.100867.
  • [11] Vanessa I S Mendes;Beatriz M F Mendes;Rui Pedro Moura;Inês M Lourenço;Mariana F A Oliveira;Kim Lee Ng;Cátia S Pinto. Harnessing artificial intelligence for enhanced public health surveillance: a narrative review.. Frontiers in public health(IF=3.4). 2025. PMID:40809756. DOI: 10.3389/fpubh.2025.1601151.
  • [12] Suzanne D van der Werff;Stephanie M van Rooden;Aron Henriksson;Michael Behnke;Seven J S Aghdassi;Maaike S M van Mourik;Pontus Nauclér. The future of healthcare-associated infection surveillance: Automated surveillance and using the potential of artificial intelligence.. Journal of internal medicine(IF=9.2). 2025. PMID:40469046. DOI: 10.1111/joim.20100.
  • [13] Hamed Khalili;Maria A Wimmer. Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic.. Life (Basel, Switzerland)(IF=3.4). 2024. PMID:39063538. DOI: 10.3390/life14070783.
  • [14] Heidi L Tessmer;Kimihito Ito;Ryosuke Omori. Can Machines Learn Respiratory Virus Epidemiology?: A Comparative Study of Likelihood-Free Methods for the Estimation of Epidemiological Dynamics.. Frontiers in microbiology(IF=4.5). 2018. PMID:29552000. DOI: 10.3389/fmicb.2018.00343.
  • [15] Qingyu Chen;Robert Leaman;Alexis Allot;Ling Luo;Chih-Hsuan Wei;Shankai Yan;Zhiyong Lu. Artificial Intelligence in Action: Addressing the COVID-19 Pandemic with Natural Language Processing.. Annual review of biomedical data science(IF=6.0). 2021. PMID:34465169. DOI: 10.1146/annurev-biodatasci-021821-061045.
  • [16] C Raina MacIntyre;Samsung Lim;Deepti Gurdasani;Miguel Miranda;David Metcalf;Ashley Quigley;Danielle Hutchinson;Allan Burr;David J Heslop. Early detection of emerging infectious diseases - implications for vaccine development.. Vaccine(IF=3.5). 2024. PMID:37271702. DOI: 10.1016/j.vaccine.2023.05.069.
  • [17] Jayanthi Devaraj;Rajvikram Madurai Elavarasan;Rishi Pugazhendhi;G M Shafiullah;Sumathi Ganesan;Ajay Kaarthic Jeysree;Irfan Ahmad Khan;Eklas Hossain. Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?. Results in physics(IF=4.6). 2021. PMID:33462560. DOI: 10.1016/j.rinp.2021.103817.
  • [18] Yashpal Singh Malik;Shubhankar Sircar;Sudipta Bhat;Mohd Ikram Ansari;Tripti Pande;Prashant Kumar;Basavaraj Mathapati;Ganesh Balasubramanian;Rahul Kaushik;Senthilkumar Natesan;Sayeh Ezzikouri;Mohamed E El Zowalaty;Kuldeep Dhama. How artificial intelligence may help the Covid-19 pandemic: Pitfalls and lessons for the future.. Reviews in medical virology(IF=6.6). 2021. PMID:33476063. DOI: 10.1002/rmv.2205.
  • [19] Md Mahadi Hasan;Muhammad Usama Islam;Muhammad Jafar Sadeq;Wai-Keung Fung;Jasim Uddin. Review on the Evaluation and Development of Artificial Intelligence for COVID-19 Containment.. Sensors (Basel, Switzerland)(IF=3.5). 2023. PMID:36617124. DOI: 10.3390/s23010527.
  • [20] Gunjan Arora;Jayadev Joshi;Rahul Shubhra Mandal;Nitisha Shrivastava;Richa Virmani;Tavpritesh Sethi. Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19.. Pathogens (Basel, Switzerland)(IF=3.3). 2021. PMID:34451513. DOI: 10.3390/pathogens10081048.
  • [21] Anshu Ankolekar;Lisanne Eppings;Fabio Bottari;Inês Freitas Pinho;Kit Howard;Rebecca Baker;Yang Nan;Xiaodan Xing;Simon Lf Walsh;Wim Vos;Guang Yang;Philippe Lambin. Using artificial intelligence and predictive modelling to enable learning healthcare systems (LHS) for pandemic preparedness.. Computational and structural biotechnology journal(IF=4.1). 2024. PMID:38831762. DOI: 10.1016/j.csbj.2024.05.014.
  • [22] Nurul Azam Mohd Salim;Yap Bee Wah;Caitlynn Reeves;Madison Smith;Wan Fairos Wan Yaacob;Rose Nani Mudin;Rahmat Dapari;Nik Nur Fatin Fatihah Sapri;Ubydul Haque. Prediction of dengue outbreak in Selangor Malaysia using machine learning techniques.. Scientific reports(IF=3.9). 2021. PMID:33441678. DOI: 10.1038/s41598-020-79193-2.
  • [23] Chien-Hung Lee;Ko Chang;Yao-Mei Chen;Jinn-Tsong Tsai;Yenming J Chen;Wen-Hsien Ho. Epidemic prediction of dengue fever based on vector compartment model and Markov chain Monte Carlo method.. BMC bioinformatics(IF=3.3). 2021. PMID:34749630. DOI: 10.1186/s12859-021-04059-x.
  • [24] Reham Abdallah;Sayed Abdelgaber;Hanan Ali Sayed. Leveraging AHP and transfer learning in machine learning for improved prediction of infectious disease outbreaks.. Scientific reports(IF=3.9). 2024. PMID:39741160. DOI: 10.1038/s41598-024-81367-1.
  • [25] Sarah F McGough;Leonardo Clemente;J Nathan Kutz;Mauricio Santillana. A dynamic, ensemble learning approach to forecast dengue fever epidemic years in Brazil using weather and population susceptibility cycles.. Journal of the Royal Society, Interface(IF=3.5). 2021. PMID:34129785. DOI: 10.1098/rsif.2020.1006.
  • [26] Shovanur Haque;Kerrie Mengersen;Ian Barr;Liping Wang;Weizhong Yang;Sotiris Vardoulakis;Hilary Bambrick;Wenbiao Hu. Towards development of functional climate-driven early warning systems for climate-sensitive infectious diseases: Statistical models and recommendations.. Environmental research(IF=7.7). 2024. PMID:38417659. DOI: 10.1016/j.envres.2024.118568.
  • [27] Benjamin D Trump;Stephanie Galaitsi;Jeff Cegan;Igor Linkov. How Will AI Shape the Future of Pandemic Response? Early Clues From Data Analytics.. Risk analysis : an official publication of the Society for Risk Analysis(IF=3.3). 2025. PMID:40926588. DOI: 10.1111/risa.70103.
  • [28] Lanyi Yu;Xiaomei Zhai. Use of artificial intelligence to address health disparities in low- and middle-income countries: a thematic analysis of ethical issues.. Public health(IF=3.2). 2024. PMID:38964129. DOI: 10.1016/j.puhe.2024.05.029.
  • [29] Muhammad Anshari;Mahani Hamdan;Norainie Ahmad;Emil Ali;Hamizah Haidi. COVID-19, artificial intelligence, ethical challenges and policy implications.. AI & society(IF=4.7). 2023. PMID:35607368. DOI: 10.1007/s00146-022-01471-6.
  • [30] Félix Amiot;Benoit Potier. Artificial Intelligence (AI) and Emergency Medicine: Balancing Opportunities and Challenges.. JMIR medical informatics(IF=3.8). 2025. PMID:40802997. DOI: 10.2196/70903.
  • [31] Luca Miglietta;Timothy M Rawson;Ronald Galiwango;Alex Tasker;Damien K Ming;Darlington Akogo;Cecilia Ferreyra;Eric O Aboagye;N Claire Gordon;Carolina Garcia-Vidal;Jesus Rodriguez-Manzano;Alison H Holmes. Artificial intelligence and infectious disease diagnostics: state of the art and future perspectives.. The Lancet. Infectious diseases(IF=31.0). 2025. PMID:40972627. DOI: 10.1016/S1473-3099(25)00354-8.
  • [32] Dimitra Panteli;Keyrellous Adib;Stefan Buttigieg;Francisco Goiana-da-Silva;Katharina Ladewig;Natasha Azzopardi-Muscat;Josep Figueras;David Novillo-Ortiz;Martin McKee. Artificial intelligence in public health: promises, challenges, and an agenda for policy makers and public health institutions.. The Lancet. Public health(IF=25.2). 2025. PMID:40031938. DOI: 10.1016/S2468-2667(25)00036-2.
  • [33] Paula Del Rey Puech;Rebecca Payne;Jasjot Saund;Martin McKee. Mind the (widening) gap: why public health must engage with AI now.. Public health(IF=3.2). 2025. PMID:41232266. DOI: 10.1016/j.puhe.2025.106047.
  • [34] Jason D Morgenstern;Laura C Rosella;Mark J Daley;Vivek Goel;Holger J Schünemann;Thomas Piggott. "AI's gonna have an impact on everything in society, so it has to have an impact on public health": a fundamental qualitative descriptive study of the implications of artificial intelligence for public health.. BMC public health(IF=3.6). 2021. PMID:33407254. DOI: 10.1186/s12889-020-10030-x.
  • [35] Chunhui Li;Guoguo Ye;Yinghan Jiang;Zhiming Wang;Haiyang Yu;Minghui Yang. Artificial Intelligence in battling infectious diseases: A transformative role.. Journal of medical virology(IF=4.6). 2024. PMID:38179882. DOI: 10.1002/jmv.29355.
  • [36] Ankit Sahoo;Janhvi Singh;Kainat Alam;Nabil K Alruwaili;Alhussain Aodah;Waleed H Almalki;Salem Salman Almujri;Majed Alrobaian;Md Abul Barkat;Tanuja Singh;Jonathan A Lal;Mahfoozur Rahman. Medical Artificial Intelligence: Opportunities and Challenges In Infectious Disease Management.. Current medicinal chemistry(IF=3.5). 2025. PMID:40917030. DOI: 10.2174/0109298673390868250728103906.
  • [37] Enrico Santus;Nicola Marino;Davide Cirillo;Emmanuele Chersoni;Arnau Montagud;Antonella Santuccione Chadha;Alfonso Valencia;Kevin Hughes;Charlotta Lindvall. Artificial Intelligence-Aided Precision Medicine for COVID-19: Strategic Areas of Research and Development.. Journal of medical Internet research(IF=6.0). 2021. PMID:33560998. DOI: 10.2196/22453.
  • [38] Diala Haykal;Mohamad Goldust;Hugues Cartier;Patrick Treacy. AI in humanitarian healthcare: a game changer for crisis response.. Frontiers in artificial intelligence(IF=4.7). 2025. PMID:40673211. DOI: 10.3389/frai.2025.1627773.

MaltSci Intelligent Research Services ​

Search for more papers on MaltSci.com ​

Artificial Intelligence · Epidemic Prediction · Machine Learning · Natural Language Processing · Public Health

© 2025 MaltSci