E-ISSN:2583-2468

Research Article

Deep Learning

Applied Science and Engineering Journal for Advanced Research

2025 Volume 4 Number 6 November
Publisherwww.singhpublication.com

Forecasting Health Vulnerabilities through Machine Learning

Jagtap NP1*
DOI:10.54741/ASEJAR/4.6.2025.179

1* Nalini P Jagtap, Assistant Professor, Department of Computer Engineering, Dr. D. Patil Institute of Engineering, Management and Research, Nashik, Maharashtra, India.

Machine Learning Model to Forecast Patient Disease Vulnerability using Data Cleanroom Methodology enable to join Patient data anonymously coming from Patient diagnosed with different disease. Cross Organization data analytics helped to identify pattern in multiple dieses in Patients to train the model. So model can forecast if Patient has one dieses what are chances of having other dieses in future and take preventive actions Based on this project the aim is to investigate the effectiveness of deep learning techniques in the early identification of disease. Two things must be done to accomplish this goal: first, it must be made clear how important it is to promptly identify disease outbreaks in the current global health setting, and second, deep learning techniques must be subjected to a thorough evaluation of how well they perform in this critical job. These goals are part of the study's overall effort to get a thorough understanding of the range of deep-learning approaches that can assist and improve disease outbreak investigation processes. The cutting-edge technology that has supported early intervention and lessened the effects of disease epidemics in the global community is improved by this research.

Keywords: deep learning, data collection, analysis, machine learning, NLP, CNN, ANN

Corresponding Author How to Cite this Article To Browse
Nalini P Jagtap, Assistant Professor, Department of Computer Engineering, Dr. D. Patil Institute of Engineering, Management and Research, Nashik, Maharashtra, India.
Email: 		Jagtap NP, Forecasting Health Vulnerabilities through Machine Learning. Appl Sci Eng J Adv Res. 2025;4(6):19-27.
Available From
https://asejar.singhpublication.com/index.php/ojs/article/view/179

Manuscript Received Review Round 1 Review Round 2 Review Round 3 Accepted
2025-10-13 2025-10-31 2025-11-20
Conflict of Interest Funding Ethical Approval Plagiarism X-checker Note
None Nil Yes 5.30

© 2025 by Jagtap NP and Published by Singh Publication. This is an Open Access article licensed under a Creative Commons Attribution 4.0 International License https://creativecommons.org/licenses/by/4.0/ unported [CC BY 4.0].

Appl Sci Eng J Adv Res 2025;4(6)19
Download PDFBack To Article1. Introduction2. Literature
Review3. Methodology4. Results5. Conclusion6. Research
Recommendation7. Future WorkReferences
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

1. Introduction

a) Project Specification

The project's goal is to use deep learning methods to create a reliable and effective system for early identification of disease epidemics. Social media feeds, medical records and sensor data are different data types that have been analyzed by using neural networks and ML techniques. It also uses NLP and machine vision to sift through unstructured material for useful information and patterns. The first step of information Gathering and Synchronization of all the collected data Collect information from a variety of sources such as medical files, secondary platforms, and others. The study helps to analyze different disease outbreaks and the effectiveness of a neural network to detect all the outbreaks without any hassle.

b) Aim and Objectives

Aim

The study aims to investigate the deep-learning method for early detection of disease outbreaks.

Objectives

  • To investigate the importance of disease Outbreaks in the present time
  • To analyze the performance of the deep learning approach for early detection of disease outbreaks
  • To understand all the deep learning methods that is useful to facilitate the investigation procedures.

c) Research Question

  • How to investigate the importance of disease Outbreaks in the present time?
  • What is the process for analyzing the performance of the deep learning approach for early detection of disease outbreaks?
  • Why is the deep learning method very useful to facilitate the investigation procedures?

d) Research Rationale What is the Issue?

Their transmission, scarce resources, and the potential for high fatality rates are the public health issues caused bydisease outbreaks. They put a strain on healthcare systems, deplete supplies, and cause societal and economic upheaval.

In order to lessen the damage, they cause, prompt discovery and action are essential.

Why is this Issue?

The rapid spread of disease epidemics is a major concern because of the toll they take on healthcare resources. They also cause a lot of deaths, a lot of money lost, and a lot of trouble in society. The public health and societal effects of these threats have been mitigated through early discovery and prompt action.

What is the Issue Now?

The new forms of different viruses create problems for society and create problematic situations. Vaccine and treatment efficacy have also been affected by all these variations that affected public health policies.

2. Literature Review

a) Research Background

Machine learning algorithms are being explored in different fields to predict the outcome of a result, make a model based on the structure, provide information about the society, and help in building generative applications or providing a classification [1]. Machine learning is used in many methods and people get pretty used to it in general terms of finding the issue and also solving the issue by itself. The issues are mainly used in cars for the detection classification and also used in weather forecasts to predict rainfall, similarly, machine learning is also able to be used for the early detection of disease outbreaks.

b)  Critical Assessment

Diseases are harmful for anybody to get, the reason for creating machine learning in the first place is to check the deadly diseases, from bacteria and viruses. The recent virus global pandemic with the Covid 19 gives various details about the disease and how well the disease can sick a person and gives the remedy to avoid the viral infection [2]. The world is evolving, and the use of machine learning can help people whenever they want to and also perform a checkup from doctors and uses ML to predict the outcome of a virus to check a person and use it very carefully.


Appl Sci Eng J Adv Res 2025;4(6)20
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

asejar_179_01
Figure 1: Deep Learning-Based Early detection framework

c) Linkage to Aim

The deep learning method is a process in which machine learning from the computer uses different types of deep learning like ANN, CNN, and deep learning that can help people. The aim is to create a deep-learning model that has the potential to understand the disease and perform general methods of utilization from the data series and used [3]. This paper aims to use machine learning and perform classification functions for disease detection and functionproperly and help people way ahead of time boost and support them and quarantine diseases.

d) Deep Learning for Rapid Disease Epidemic Detection

Emerging infectious diseases have made rapid detection andresponse more important than ever. The relationship between deep learning and public health helps to improve disease surveillance [4]. This procedure is also able to highlight the promise of deep learning as a strong tool in global health security, from utilizing different data information to predicting the spread of outbreaks.

e) Utilizing DL for Predictive Disease Monitoring

The documentary "Epidemia" highlights the importance of deep learning algorithms in epidemiology. This helps to investigate the ML algorithms that help to detect minor patterns suggestive of oncoming outbreaks by analyzing thecombination of sophisticated neural networks with epidemiological data [5]. Explore the revolutionary potential of deep learning to strengthen public health infrastructure against new threats, from real-time surveillance to predictive analytics. Examine real-world examples, discuss ethical concerns, and look ahead to the future of early outbreak detection in any crucial factors that help the medical sector.

asejar_179_02
Figure 2: Deep Learning-Based Early detection framework

f) Theoretical Framework

The theory states that the people or the government support them and for that, they can provide it later. The issues the people handle make the government be in full-fledged focus on the people and a viral infection can be a problem for the people [6]. Machine learning helps people by providing them with the correct or optimum way to avoid viruses and is also used for virus outbreak prediction. People used to get on and off with the use of a machine. The people do not think about the virus, they have problems with the first world problems.

g) Literature Gap

The literature gap shows the other findings about the issues with pandemic viruses which can kill not millions but billions of people. The world could lose its all ration and production comes to a halt. Either way, the use of vaccines is very much appreciated [7]. Machine learning is the use of predicting diseases in a patient, making vaccines, and maintaining the health of the people who could not work or eat because of the pandemic virus. Like the COVID-19 case, the use of machine learning became late to understand theintensity and the nature of the virus and also start theresearch regarding vaccines.

3. Methodology

a) Research Philosophy

This research is based on the concepts of deep learning through which the whole system can be developed nowadays. The ML-based research applies to all fields including health sectors [8].


Appl Sci Eng J Adv Res 2025;4(6)21
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

These ML techniques aredeeply studied for severaltypes of research related to healthcare development and predictive analysis of healthcare parameters.

asejar_179_03
Figure 3: Positivism Philosophy

This research has followed a positivist philosophy for the continuous analysis of datasets experimentally used in a DL model [9]. The deep learning algorithm is based on features and output layers for a better analysis of output models accordingly. Hence the health project related to DL methodology is reviewed from several research and journal papers.

b) Research Approach

This research is a complete framework for the effective development of disease detection systems [10]. Multiple images of MRI scans are required to be analyzed within a particular timeframe for the effective management of health structure. This is the reason behind the development of software tools and techniques for simultaneous work management in health sectors. New types of research are working on ML and DL technologies to simplify disease detection and analysis work. Thus, a deductive approach isused during the research procedure related to disease identification with DL-based software [11]. The whole procedure is becoming more available to the health system due to its explicit techniques and features with detailed and optimized analysis.

c) Research Design

The design of DL technologies is a big point for the easy detection of major heart and chronic diseases. Several research papers have shown that these technologies help to enhance the accuracy of detection systems 1000 times better than traditional testing methods [12].

asejar_179_04
Figure 4: Descriptive Research Design

Hence the project is analyzed based on research papers and previous research books published. The design methods are evolved from the CNN architecture and Pytorch methodologies. However, the design of the project is descriptive based on research articles [13]. The design architectures are tried to define in a better way for future works with the health management system efficiently.

d) Data Collection Method

This data collection method for deep learning architectures is critically discussed in a better way. Health diseases and their characteristics are the features of this research, obtained from plenty of reference articles. This research methodology is improved with the proper analysis of secondary data because this data is collected from previous years' journal papers. The data is not compared with any other experiments related to healthcare strategy [14]. Hence the research allows thematic analysis with all relevant real- life examples associated with deep learning technologies. Data related to diseases are efficiently analyzed with this method for a better evaluation of data to make it optimized for use.

e) Ethical Considerations

In this study, ethical questions are of the utmost significance. First and foremost, rigorous privacy and permission laws must be followed when using medical data, even when it has been anonymized, to protect patient security and autonomy. In order to preserve confidence and credibility, it is crucial that the research process be transparent and that any possible conflicts with interests are disclosed [15].


Appl Sci Eng J Adv Res 2025;4(6)22
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

In order to eliminate biases and guarantee fair and equal results, the appropriate management of deep learning techniques and the resulting results, particularlywithin the healthcare industry, requires constant examination. Finally, open access and cooperation should be given top priority when disseminating research findings to benefit the larger scientific and health communities while preserving authorship and intellectual property rights.

4. Results

a) Critical Analysis

In Deep Learning for Early Identification of Disease Outbreaks, the study's objective is to investigate the applicability of deep learning techniques for the early identification of disease outbreaks [16]. The study's aims appear promising, but a thorough examination exposes both the research design and approach advantages and possible drawbacks. The investigation's goal takes on a pressing issue in the realm of public health. In the modern day, the significance of disease outbreaks cannot be understated, particularly in the context of international health emergencies such as the COVID-19 pandemic. The second goal, which examine the process of deep learning techniques in the case of early detection. Healthcare is one area where deep learning has been shown to have tremendous potential [17]. The main difficulties with data accessibility, model broadening, and understanding arise in its application to the detection of disease outbreaks. Thus, while evaluating the efficacy of deep learning techniques, the study must take into consideration these possible constraints.

In order to operationalize the study findings, it is essential to complete the third aim, which entails comprehending the deep learning techniques helpful for facilitating investigation procedures [18]. This is important to recognize that deep learning techniques have been demanding resources and need specialized understanding. The project should thus offer information about the viability and scalability of using these techniques in actual disease surveillance systems. Having access to reliable data and an effective assessment methodology has been necessary for the study to be successful in meeting its goals [19]. It is admirable that the study is making the effort it is by looking into deep learning for early illness outbreak identification.

The research's success thinges on its capacity to deal with the difficulties of illness monitoring, data accessibility, effectiveness of the models, and ethical issues [20]. The knowledge about the deep learning approach that helps with the early identification of disease outbreaks needs to be advanced and this also needs a rigorous and critical solution to these issues.

b) Finding and Discussion

Theme 1: The Significance of Disease Outbreaks in the Present Time

Based on the scenario, understanding the relevance of disease outbreaks in the modern world is the study's first major issue. The genesis and spread of infectious illnesses represent a danger to public health and safety in this age of global connectedness and growing urbanization [21]. After examining the significance of disease outbreaks, the research seeks to highlight the seriousness of this problem.

asejar_179_05
Figure 5: Report Disease Outbreaks all over the world

This subject emphasizes the vital need for preventative measures and early detection techniques to lessen the effects of such epidemics [22]. The study lays the foundation for a thorough investigation of deep-learning techniques as a potential remedy by diving into both the ancient and moderncontext of disease outbreaks.

Theme 2: Deep Learning as a Tool for Early Detection

The second subject is the potential of deep learning as a tool for the early identification of disease epidemics [23].


Appl Sci Eng J Adv Res 2025;4(6)23
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

Deep learning has become more popular as a tool for analyzing huge datasets and finding patterns that might point to the beginning of an outbreak as the fields of ML and artificial method of looking at deep learning for infectious disease intelligence have advanced. The goal of the study is to evaluate the deep learning techniques performed in thissituation [24]. Deep learning's technical features are explored in this area, which also emphasizes the use of deep learning in early warning and epidemiological monitoring systems.

Theme 3: Evaluating the Efficacy of Deep Learning Approaches

According to this project concentrating on the examination of deep learning methodologies, theme three digs even further into the core of the subject [25]. This subject evaluates the viability and efficacy of using deep learning techniques for early detection. The research intends to give empirical proof of the validity of these strategies through careful analysis and experimentation. It examines different algorithms, mathematical models, as well as data sources todetermine which deep learning approaches are most helpful in facilitating the inquiry processes [26]. These subjects stress the need for data-driven decisions and the ongoingimportant public health issue. The main goal of this study is to examine the relevancy of disease outbreaks today as well as evaluate how well deep learning approaches haveimprovement of deep learning modelsto improve theireffectiveness in identifying disease outbreaks.

Theme 4: Facilitating Investigation Procedures through Deep Learning

The study's fourth and concluding topic stresses the value of deep learning in streamlining procedures for disease outbreak investigation [27]. Deep learning techniques have speeded up epidemic research, allowing for quicker reaction and prevention measures, in addition to early detection. In order to comprehend, manage, and limit disease epidemics, this subject examines the numerous ways in which deep learning might assist epidemiologists, healthcare providers, and policymakers [28]. It draws attention to the advantages of technology and statistical modelling for enhancing the way people react to new health concerns.

asejar_179_06
Figure 6: Infection disease response using flow chart.

Based on this research, thematically analyzed and four interrelated topics are found [29]. These topics highlight the importance of disease outbreaks in the modern world, the relevance of deep learning for initial detection, the assessment of deep learning methodologies, and the potential for deep learning to speed up investigativeprocesses [30]. These ideas present a thorough picture of the application of modern technology that helps to improve the capacity to track and respond to epidemics of disease, eventually increasing public health preparation and response.

c) Evaluation

The discussion emphasizesthe study's all-encompassing method of looking at deep learning for infectious disease detection [31]. It does agood job of addressing the importance of disease outbreaks, highlights the promise of deep learning, systematically assesses its performance, and stresses its role in expediting investigative methods. Therefore, the study has to incorporate actual case studies or real-world applications to confirm the theoretical findings to improve assessment. It would also increase the study's validity by taking into account the ethical and privacy issues related to the use of data in healthcare, to explain these issues, and suggest precautions [32]. Though the study offers insightful information on real-world applications and ethical issues would be advantageous.

5. Conclusion

The project has identified the requirement to use cutting-edge technology, such asdeep learning to solve this important public health issue.


Appl Sci Eng J Adv Res 2025;4(6)24
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

The main goal of this study is to examine the relevancy of disease outbreaks today as well as evaluate how well deep learning approaches have performed in early detection and attempt to fully comprehend pertinent deep learning techniques. The work has made a significant contribution to the study of epidemiology and disease surveillance by achieving several goals. It not only highlights the importance of quick outbreak detection but also exemplifies how deep learning techniques have useful tools in this effort. This improves the capacity to protect public health and reduce the effects of new health risks, and it has prepared the path for more efficient, data-driven, and proactive disease outbreak control tactics. This research is an important step toward a healthcare system that is more adaptable and responsive to the constantly changing global health concerns.

6. Research Recommendation

Several recommendations are made to enhance disease outbreak surveillance and response. It is essential to fund additional research and development into deep learning methods for illness diagnosis. In order to fully utilize these cutting-edge technologies, collaboration between data scientists, epidemiologists, and public health organizations has been promoted [33]. Apart from that, it is crucial to encourage data integration and exchange among healthcare organizations and institutions. In order to ensure seamless information sharing, standardized data formats and protocols have been created. Early warning systems that incorporate deep learning with current surveillance infrastructure have sent public health authorities timely alerts. Sufficient resource allocation is necessary for the deployment and maintenance of deep learning-based disease surveillance systems, especially in areas prone to outbreaks [34]. The overall goal of these suggestions is to improve disease outbreak identification and response, improving public health readiness around the world.

7. Future Work

The capacity for disease surveillance and response needs to be improved in future work in the field of “Deep Learning for Early Detection of Disease Outbreaks” has offered significant areas. The development of deep learning algorithms to manage various and changing illness patterns is one area for investigation.

These multidimensional data streams have added important information and boosted outbreak forecasting precision. Research efforts have also focused on creating deep learning models that are comprehensible and interpretable [35]. Investigating the possibilities of federated learning enables numerous institutions to jointly train deep learning models without disclosing sensitive information. Efforts in this approach have improved disease surveillance systems’ effectiveness and responsiveness, ultimately boosting public health resilience around the world.

References

1. Ronakkumar Bathani. (2024). Building HIPAA-compliant cross-organizational data analytics: Leveraging snowflake data cleanrooms. International Journal of Intelligent Systems and Applications in Engineering, 12(13s), 760–766.

2. A. Abbas et al. (2023). Drones in plant disease assessment, efficient monitoring, and detection: A way forward to smart agriculture. Agronomy, 13(6), 1524. doi:10.3390/agronomy13061524.

3. A. Wang et al. (2023). A review of social media data utilization for the prediction of disease outbreaks and understanding public perception. Big Data and Cognitive Computing, 7(2), 72. doi:10.3390/bdcc7020072.

4. U. O. Dilber et al. (2023). Computer-aided detection and classification of monkeypox and chickenpox lesion in human subjects using deep learning framework. Diagnostics, 13(2), 292. doi:10.3390/diagnostics13020292.

5. M. D. K., Thomas Leitner, & Ruian Ke. (2022). A deep learning approach to real-time HIV outbreak detection using genetic data. PLoS Computational Biology, 18(10). doi:10.1371/journal.pcbi.1010598.

6. R. K. Dasaradharami, & R. G. Thippa. (2023). Federated learning approach for early detection of chest lesion caused by covid-19 infection using particle swarm optimization. Electronics, 12(3), 710. doi:10.3390/electronics12030710.

7. A. S. Jaradat et al. (2023). Automated monkeypox skin lesion detection using deep learning and transfer learning techniques. International Journal of Environmental Research and Public Health, 20(5), 4422. doi:10.3390/ijerph20054422.


Appl Sci Eng J Adv Res 2025;4(6)25
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

8. B. D. Deebak, & F. Al-Turjman. (2023). EEI-IoT: Edge-enabled intelligent IoT framework for early detection of covid-19 threats. Sensors, 23(6), 2995. doi:10.3390/s23062995.

9. B. Gao et al. (2023). Early detection of dendroctonusvalens infestation at tree level with a hyperspectral UAV image. Remote Sensing, 15(2), 407. doi:10.3390/rs15020407.

10. M. O. Ojo, & A. Zahid. (2023). Improving deep learning classifiers performance via preprocessing and class imbalance approaches in a plant disease detection pipeline. Agronomy, 13(3), 887. doi:10.3390/agronomy13030887.

11. G. Yu et al. (2023). Detection and identification of fish skin health status referring to four common diseases based on improved YOLOv4 model. Fishes, 8(4), 186. doi:10.3390/fishes8040186.

12. J. Cui, & F. Tan. (2023). Rice plaque detection and identification based on an improved convolutional neural network. Agriculture, 13(1), 170. doi:10.3390/agriculture13010170.

13. Y. Ai et al. (2022). Application of machine learning for multi- community COVID-19 outbreak predictions with wastewater surveillance. PLoS One, 17(11). doi:10.1371/journal.pone.0277154.

14. C. G. Simhadri, & K. K. Hari. I. (2023). Automatic recognition of rice leaf diseases using transfer learning. Agronomy, 13(4), 961. doi:10.3390/agronomy13040961.

15. L. Sen et al. (2023). An effective pyramid neural network based on graph-related attentions structure for fine- grained disease and pest identification in intelligent agriculture. Agriculture, 13(3), 567. doi:10.3390/agriculture13030567.

16. S. Al-Shoukry, T. H. Rassem, & N. M. Makbol. (2020). Alzheimer’s diseases detection by using deep learning algorithms: A mini-review. in IEEE Access, 8, pp. 77131-77141. doi:10.1109/ACCESS.2020.2989396.

17. V. Ninkovic, A. Valka, D. Dumic, & D. Vukobratovic. (2021). Deep learning-based packet detection and carrier frequency offset estimation in IEEE 802.11ah. in IEEE Access, 9, pp. 99853-99865. doi:10.1109/ACCESS.2021.3096853.

18. Q. Zhang, V. Piuri, E. A. Clancy, D. Zhou, T. Penzel, & W. W. Hu. (2021). IEEE access special section editorial: advanced information sensing and

learning technologies for data-centric smart health applications. in IEEE Access, 9, 30404-30407. doi:10.1109/ACCESS.2021.3057527.

19. A. Khattak et al. (2021). Automatic detection of citrus fruit and leaves diseases using deep neural network model. in IEEE Access, 9, 112942-112954. doi:10.1109/ACCESS.2021.3096895.

20. P. Jiang, Y. Chen, B. Liu, D. He, & C. Liang. (2019). Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks. in IEEE Access, 7, pp. 59069-59080. doi:10.1109/ACCESS.2019.2914929.

21. P. Ghosh et al. (2021). Efficient prediction of cardiovascular disease using machine learning algorithms with relief and LASSO feature selection techniques. in IEEE Access, 9, pp. 19304-19326. doi:10.1109/ACCESS.2021.3053759.

22. A. Qayyum, J. Qadir, M. Bilal, & A. Al-Fuqaha. (2021). Secure and robust machine learning for healthcare: A survey. in IEEE Reviews in Biomedical Engineering, 14, pp. 156-180. doi:10.1109/RBME.2020.3013489.

23. D. Rufaidah et al. (2023). Harnessing machine learning in early COVID-19 detection and prognosis: A comprehensive systematic review. Cureus, 15(5). doi:10.7759/cureus.38373.

24. G. Yogeswararao et al. (2022). An efficient densely connected convolutional neural network for identification of plant diseases. Multimedia Tools Appl, 81(23), 32791-32816. doi:10.1007/s11042-022-13053-1.

25. L. Quach et al. (2023). Using the term frequency-inverse document frequency for the problem of identifying shrimp diseases with state description text. International Journal of Advanced Computer Science and Applications, 14(5). doi:10.14569/IJACSA.2023.0140577.

26. M. U. Tariq et al. (2023). Harnessing the power of AI: Advanced deep learning models optimization for accurate SARS-CoV-2 forecasting. PLoS One, 18(7). doi:10.1371/journal.pone.0287755.

27. G. Franzo et al. (2023). When everything becomes bigger: big data for big poultry production. Animals, 13(11), 1804. doi:10.3390/ani13111804.


Appl Sci Eng J Adv Res 2025;4(6)26
Jagtap NP. Forecasting Health Vulnerabilities through Machine Learning

28. T. Aziz, C. Charoenlarpnopparut, & S. Mahapakulchai. (2023). Deep learning-based hemorrhage detection for diabetic retinopathy screening. Scientific Reports (Nature Publisher Group), 13(1), 1479. doi:10.1038/s41598-023-28680-3.

29. A. Abugabah, & S. Farah. (2023). Intelligent health care and diseases management system: multi-day-ahead predictions of COVID-19. Mathematics, 11(4), 1051. doi:10.3390/math11041051.

30. A. Hamza et al. (2023). D2BOF-COVIDNet: A framework of deep bayesian optimization and fusion-assisted optimal deep features for covid-19 classification using chest x-ray and mri scans. Diagnostics, 13(1), 101. doi:10.3390/diagnostics13010101.

31. A. Wang et al. (2023). A review of social media data utilization for the prediction of disease outbreaks and understanding public perception. Big Data and Cognitive Computing, 7(2), 72. doi:10.3390/bdcc7020072.

32. A. Abbas et al. (2023). Drones in plant disease assessment, efficient monitoring, and detection: A way forward to smart agriculture. Agronomy, 13(6), 1524. doi:10.3390/agronomy13061524.

33. R. Sangeetha et al. (2023). An improved agro deep learning model for detection of panama wilts disease in banana leaves. Agri Engineering, 5(2), 660. doi:10.3390/agriengineering5020042.

34. U. O. Dilber et al. (2023). Computer-aided detection and classification of monkeypox and chickenpox lesion in human subjects using deep learning framework. Diagnostics, 13(2), 292. doi:10.3390/diagnostics13020292.

35. M. D. K., Thomas Leitner, & Ruian Ke. (2022). A deep learning approach to real-time HIV outbreak detection using genetic data. PLoS Computational Biology, 18(10). doi:10.1371/journal.pcbi.1010598.

Disclaimer / Publisher's Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of Journals and/or the editor(s). Journals and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Appl Sci Eng J Adv Res 2025;4(6)27