Accessible Real-Time Chickenpox Screening for Outbreak Management in Low-Resource Communities

Chickenpox remains a highly contagious disease that is challenging to diagnose swiftly due to the subjectivity of visual assessments and delays in laboratory testing. Exacerbated by declining vaccination rates following the COVID-19 pandemic, the risk of rapid outbreaks in community settings, such as schools and childcare centres, has significantly increased. In low-resource and remote communities where traditional diagnostic expertise is limited, these delays hinder effective disease management. To address this healthcare accessibility gap, this study proposes an affordable, standalone, and real-time chickenpox screening system powered by a Raspberry Pi. The prototype uses deep learning-based image classification to assist with early detection, complemented by a secure, privacy-preserving web interface that enables authorised medical personnel to efficiently monitor cases and validate predictions. To optimize the system for community use, an empirical comparative study between ResNet-50 and MobileNetV2 architectures was conducted using a balanced dataset of 1,000 dermatological images. While MobileNetV2 offered higher sensitivity (recall), the ResNet-50 model demonstrated superior reliability and balanced performance—achieving a validation accuracy of 83.5%, a precision of 87.6%, and an F1-score of 82.5%. Real-time testing confirmed that ResNet-50 minimizes false positives, making it the optimal choice to prevent unnecessary anxiety or intervention during community screening. Ultimately, this work delivers a practical, edge-optimized digital health tool that democratizes disease screening, providing a scalable solution to enhance community health security and mitigate infectious disease outbreaks in underserved regions.

Chickenpox screening, Community health, Healthcare accessibility

1. Y. Srivastav, M. Rawat, A. Prajapati, N. Bano, and M. Kumar, “Review of the symptoms, pathogenesis, and available treatments for the Chickenpox,” International Journal of Pharmacology and Clinical Research, vol. 5, no. 1, pp. 22–29, Jan. 2023, doi: 10.33545/26647613.2023.v5.i1a.21. [Google Scholar] [Crossref]

2. “Varicella Zoster Virus Management in Health Care Settings,” 2019, [Online]. Available: http://www.bccdc.ca/health-. [Google Scholar] [Crossref]

3. S. Thakur, D. Banerjee, D. Upadhyay, and R. S. Rawat, “Understanding Chickenpox Dynamics: CNN and Random Forest in Action,” in 2024 4th International Conference on Computer, Communication, Control & Information Technology (C3IT), IEEE, Sep. 2024, pp. 1–7. doi: 10.1109/C3IT60531.2024.10829453. [Google Scholar] [Crossref]

4. D. Uzun Ozsahin, M. T. Mustapha, B. Uzun, B. Duwa, and I. Ozsahin, “Computer-Aided Detection and Classification of Monkeypox and Chickenpox Lesion in Human Subjects Using Deep Learning Framework,” Diagnostics, vol. 13, no. 2, Jan. 2023, doi: 10.3390/diagnostics13020292. [Google Scholar] [Crossref]

5. Seyyed Kamran Hosseini, Faraidoon Habibi, and Naqibullah Vakil I, “Deep ensemble learning for chickenpox detection from clinical images,” International Journal of Science and Research Archive, vol. 12, no. 1, pp. 344–352, May 2024, doi: 10.30574/ijsra.2024.12.1.0771. [Google Scholar] [Crossref]

6. A. Ghosh, A. Sufian, F. Sultana, A. Chakrabarti, and D. De, “Fundamental concepts of convolutional neural network,” in Intelligent Systems Reference Library, vol. 172, Springer, 2019, pp. 519–567. doi: 10.1007/978-3-030-32644-9_36. [Google Scholar] [Crossref]

7. J. Gu et al., “Recent advances in convolutional neural networks,” Pattern Recognit, vol. 77, pp. 354–377, May 2018, doi: 10.1016/j.patcog.2017.10.013. [Google Scholar] [Crossref]

8. W. Fang, P. E. D. Love, H. Luo, and L. Ding, “Computer vision for behaviour-based safety in construction: A review and future directions,” Jan. 01, 2020, Elsevier Ltd. doi: 10.1016/j.aei.2019.100980. [Google Scholar] [Crossref]

9. D. Palaz, M. Magimai-Doss, and R. Collobert, “End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition,” Speech Commun, vol. 108, pp. 15–32, Apr. 2019, doi: 10.1016/j.specom.2019.01.004. [Google Scholar] [Crossref]

10. H. C. Li, Z. Y. Deng, and H. H. Chiang, “Lightweight and resource-constrained learning network for face recognition with performance optimization,” Sensors (Switzerland), vol. 20, no. 21, pp. 1–20, Nov. 2020, doi: 10.3390/s20216114. [Google Scholar] [Crossref]

11. L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J Big Data, vol. 8, no. 1, Dec. 2021, doi: 10.1186/s40537-021-00444-8. [Google Scholar] [Crossref]

12. F. Lawan Gambo, G. Maksha Wajiga, E. Joshua Garba, and A. Aliyu Abdullahi, “Prediction of Learning Style Using Facial Expressions with Convolutional Neural Network Special Issue on Computing and Communication Technologies Prediction of Learning Style Using Facial Expressions with Convolutional Neural Network,” International Journal of Information Processing and Communication (IJIPC), vol. 9, no. 2, pp. 389–399, 2020, [Online]. Available: https://www.researchgate.net/publication/341764303. [Google Scholar] [Crossref]

13. Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” May 27, 2015, Nature Publishing Group. doi: 10.1038/nature14539. [Google Scholar] [Crossref]

14. J. Bharadiya and J. P. Bharadiya, “Convolutional Neural Networks for Image Classification,” Article in International Journal of Innovative Research in Science Engineering and Technology, vol. 8, no. 5, 2023, doi: 10.5281/zenodo.7952031. [Google Scholar] [Crossref]

15. A. B. Amjoud and M. Amrouch, “Object Detection Using Deep Learning, CNNs and Vision Transformers: A Review,” IEEE Access, vol. 11, pp. 35479–35516, 2023, doi: 10.1109/ACCESS.2023.3266093. [Google Scholar] [Crossref]

16. L. Jiao et al., “A survey of deep learning-based object detection,” IEEE Access, vol. 7, pp. 128837–128868, 2019, doi: 10.1109/ACCESS.2019.2939201. [Google Scholar] [Crossref]

17. S. J. S. Gardezi, A. Elazab, B. Lei, and T. Wang, “Breast cancer detection and diagnosis using mammographic data: Systematic review,” Jul. 01, 2019, JMIR Publications Inc. doi: 10.2196/14464. [Google Scholar] [Crossref]

18. K. Sharma, Kishlay, V. Kumar, and M. Mittal, “MonkeyPox, Measles and ChickenPox Detection through Image-Processing using Residual Neural Network (ResNet),” in 2023 6th International Conference on Information Systems and Computer Networks, ISCON 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ISCON57294.2023.10112085. [Google Scholar] [Crossref]

19. J. Liang, “Image classification based on RESNET,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Oct. 2020. doi: 10.1088/1742-6596/1634/1/012110. [Google Scholar] [Crossref]

20. S. Noor, N. Ismat, and A. Siddiqui, “Deep Learning for Viral Detection: Affordable Camera Technology in Public Health,” 2024. [Online]. Available: https://www.researchgate.net/publication/383864008. [Google Scholar] [Crossref]

21. O. A. Alrusaini, “Deep Learning Models for the Detection of Monkeypox Skin Lesion on Digital Skin Images,” IJACSA) International Journal of Advanced Computer Science and Applications, vol. 14, no. 1, p. 2023, Jan. 2023, doi: http://dx.doi.org/10.14569/IJACSA.2023.0140170. [Google Scholar] [Crossref]

22. C. V. N. Rondón, D. A. C. Carvajal, B. M. Delgado, S. A. C. Casadiego, and D. G. Ibarra, “An Architecture for Microprocessor-Executable Skin Cancer Classification,” in 2023 IEEE 8th International Conference for Convergence in Technology, I2CT 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/I2CT57861.2023.10126432. [Google Scholar] [Crossref]

23. N. Nazmee, M. S. Ali, S. Mahmud, K. Alam, A. Chakrabarty, and M. Fahim-Ul-Islam, “Enhancing Monkeypox Diagnosis: A Machine Learning Approach for Skin Lesion Classification,” in 2023 26th International Conference on Computer and Information Technology, ICCIT 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICCIT60459.2023.10441041. [Google Scholar] [Crossref]

24. S. Mali3 Rd, “Signature Verification using ResNet-50 and Transfer Learning 1 st Deepali Narwade1*, Latika Desai2 nd,” International Journal of Research and Analytical Reviews, p. 26, 2023, [Online]. Available: www.ijrar.org. [Google Scholar] [Crossref]

25. Y. Hu, H. Tang, and G. Pan, “Spiking Deep Residual Networks,” IEEE Trans Neural Netw Learn Syst, vol. 34, no. 8, pp. 5200–5205, Aug. 2023, doi: 10.1109/TNNLS.2021.3119238. [Google Scholar] [Crossref]

• Migrant Health in Morocco: Between Law and Reality
• CaknaMinda: An Educator-Centred Mobile App for Early Screening of Mental Health and Schizophrenia Risks
• Health System and Nursing Strategies for Enhancing Male Participation in Family Planning: Evidence from Tema General Hospital, Ghana.
• From Īśvara-Praṇidhāna to Parā-Bhakti: Convergent Paths of Aṣṭāṅga Yoga and Bhakti Yoga
• Evidence-Based Psycho-Oncological Interventions: A Multimodal Approach to Supportive Care