Computational Modelling and Predictive Analysis of Aquagenic Urticaria for Automated Dermatological Assessment

Abstract

Aquagenic Urticaria (AU) is a rare dermatological condition characterized by the development of itchy, red welts upon contact with water, including sweat and tears. Traditional diagnosis relies heavily on clinical observation and patient-reported symptoms, which can be subjective and time-consuming. This paper proposes a computational approach to model and predict the onset and severity of Aquagenic Urticaria using machine learning and data-driven dermatological analysis. By integrating patient data, environmental factors, and skin response metrics, our framework aims to enable automated and early detection of AU episodes. Experimental simulations demonstrate the potential of predictive models to enhance diagnostic accuracy, reduce misdiagnosis, and provide personalized alerts for affected individuals. The proposed system represents a step toward AI-assisted dermatology, offering a scalable solution for rare skin conditions.

Introduction

Aquagenic Urticaria (AU) is an extremely rare hypersensitivity disorder where contact with water triggers itchy, red welts and wheals. Daily activities like bathing, exercise, or exposure to sweat can provoke symptoms, making diagnosis and management challenging. Traditional diagnostic methods rely on clinical observation, patient history, and water challenge tests, which are often subjective and require specialist oversight.

To address these limitations, the paper proposes a computational, AI-driven framework for automated detection and severity prediction of AU. The system integrates patient-specific data, environmental factors, symptom logs, and skin images, using machine learning (ML) and deep learning (CNNs) to enable predictive analysis and real-time dermatological evaluation. This approach aims to improve diagnostic accuracy, reduce reliance on manual observation, and assist both clinicians and patients in managing AU effectively.

Literature Insights

• AU Diagnosis & Management: Traditional approaches include water provocation tests and histopathological evaluation; research emphasizes clinical complexity and limited epidemiological understanding.

• AI & Machine Learning in Dermatology: ML algorithms (SVM, Random Forest) and deep learning (CNNs) have shown high accuracy in classifying skin diseases, suggesting applicability for rare conditions like AU.

• Predictive & IoT Applications: Supervised models, KNN, regression analytics, and embedded IoT monitoring demonstrate the potential for personalized and real-time health predictions.

• Cross-Domain Techniques: Methods from chronic urticaria, medical image analysis, and physiological monitoring provide a foundation for computational approaches to AU.

Overall, the literature supports the feasibility of using data-driven, AI-enabled systems for rare dermatological conditions.

Proposed Computational Framework

1. Data Collection Module

   • Aggregates patient demographics, medical history, symptom logs, environmental data (humidity, temperature, water exposure), and skin images.

2. Data Preprocessing Module

   • Image Enhancement: Improves skin image clarity.

   • Feature Extraction: Captures lesion shape, color, and temporal changes.

   • Normalization: Ensures consistent scaling across features for ML processing.

3. Predictive Modeling Module

   • Machine Learning: SVM, Random Forest for initial classification.

   • Deep Learning: CNNs analyze skin images to detect subtle erythema and wheals.

   • Temporal Analysis: Uses symptom logs and environmental factors to anticipate flare-ups.

4. Automated Assessment Module

   • AU Detection: Identifies episodes of AU.

   • Severity Prediction: Classifies symptom intensity as low, medium, or high.

   • Alert & Recommendations: Provides real-time guidance for patients or clinicians.

Results

• Dataset: 500 skin images from AU-affected and healthy individuals, combined with symptom logs and environmental data.

• Performance Metrics:

• Observations:

  • High alignment between predicted and actual severity levels.

  • Deep learning accurately detects subtle skin changes.

  • Integration of environmental and patient-specific data enhances predictive reliability.

  • Supports real-time, automated dermatological assessment and aids clinical decision-making.

Conclusion

The proposed computational model for Aquagenic Urticaria demonstrates the effectiveness of integrating image analysis, machine learning, and patient-specific data to enable automated detection and severity prediction of this rare dermatological condition. The results show high accuracy, precision, and recall in AU detection, with severity predictions closely matching clinical assessments, indicating the model’s potential to assist dermatologists in early diagnosis and personalized patient management. By combining environmental factors, symptom logs, and skin images, the framework provides a robust, data-driven approach that reduces reliance on subjective evaluation. For future work, the model can be enhanced by incorporating larger, multi-institutional datasets, real-time monitoring through wearable devices, and advanced deep learning architectures to further improve prediction accuracy, extend coverage to other rare skin conditions, and enable fully AI-assisted dermatological care.

References

[1] C. Rujitharanawong et al., “A Systematic Review of Aquagenic Urticaria–Subgroups and Treatment Options,” J. Allergy Clin. Immunol. Pract., vol. 10, no. 8, pp. 2154–2162, Aug. 2022. doi: 10.1016/j.jaip.2022.04.033. [2] A. Bajoghli et al., “Aquagenic urticaria in an adolescent: differential diagnosis and management,” BMJ Case Rep., vol. 17, no. 8, p. e260091, Aug. 2024. doi: 10.1136/bcr-2024-260091. [3] M. Fukayama et al., “Case of aquagenic urticaria: Case report and the results of histopathological examination,” J. Dermatol., vol. 48, no. 1, pp. 88–91, 2021. doi: 10.1111/1346-8138.15615. [4] K. M. Almustafa, “Predictive modeling and optimization in dermatology: Machine learning for skin disease classification,” Comput. Biol. Med., vol. 189, p. 109946, May 2025. doi: 10.1016/j.compbiomed.2025.109946. [5] J. Sun et al., “Machine Learning Methods in Skin Disease Recognition: A Systematic Review,” Processes, vol. 11, no. 4, p. 1003, Mar. 2023. doi: 10.3390/pr11041003. [6] A. M. Zbrzezny and T. Krzywicki, “Artificial Intelligence in Dermatology: A Review of Methods, Clinical Applications, and Perspectives,” Appl. Sci., vol. 15, no. 14, p. 7856, Jul. 2025. doi: 10.3390/app15147856. [7] Y. S. Pathania, “Artificial Intelligence in Chronic Urticaria: Unsupervised Versus Supervised Machine Learning,” Actas Dermosifiliogr., vol. 114, pp. 659–659, Jul.–Aug. 2023. doi: 10.1016/j.ad.2022.06.030. [8] S. R. Gaddam et al., \"AI-Based System for Early Detection of Skin Cancer Using Image Analysis,\" 2025 IEEE 4th International Conference for Advancement in Technology (ICONAT), Goa, India, 2025, pp. 1-5, doi: 10.1109/ICONAT66879.2025.11362657. [9] P. Akhila, R. Sahith, V. T. Ram Pavan Kumar M, N. K. Bhagavatham, K. Spandana and S. Vikruthi, \"Interpretable Deep Learning Model for Pneumonia Diagnosis from Chest X-Rays,\" 2025 Third International Conference on Emerging Applications of Material Science and Technology (ICEAMST), Bengaluru, India, 2025, pp. 1-6, doi: 10.1109/ICEAMST67459.2025.11335643. [10] S. Vikruthi, T. Reddy Singasani, V. T. Ram Pavan Kumar M, K. Spandana, M. Narasimha Raju and C. Raghavendra, \"An Advanced Learning Based Diabetes Mellitus Prediction Using KNN,\" 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS), Bengaluru, India, 2024, pp. 1542-1548, doi: 10.1109/ICICNIS64247.2024.10823238. [11] M. V. Babu, V. Ramya, and V. S. Murugan, \"Implementation of wearable device for upper limb rehabilitation using embedded IoT,\" Int. J. Electron. Signals Syst. Manag. Sci., vol. 16, no. 1, pp. 90–95, Mar. 2024. [Online]. Available: https://doi.org/10.1504/IJESMS.2024.136972 [12] M. V. . Babu, V. . Ramya, and V. S. . Murugan, “A Proposed High Efficient Current Control Technique for Home Based Upper Limb Rehabilitation and Health Monitoring System during Post Covid-19”, Int J Intell Syst Appl Eng, vol. 12, no. 2s, pp. 600–607, Oct. 2023. [13] Veeresh Babu, M., Ramya, V., & Senthil Murugan, V. (2023). Design and development of embedded/SQL home based upper limb rehabilitation. International Journal of Healthcare Management, 16(4), 513–523. https://doi.org/10.1080/20479700.2022.2124492 [14] P. V. Reddy, D. Ganesh, S. Reddy Gaddam, C. Swarna Lalitha, S. Muqthadar Ali and K. Sakibaev, \"Empirical Assessment of Profit Predicting Deep Learning Methods,\" 2025 5th International Conference on Soft Computing for Security Applications (ICSCSA), Salem, India, 2025, pp. 1674-1679, doi: 10.1109/ICSCSA66339.2025.11171150. [15] Y. K. Gupta, S. Reddy Gaddam, H. Gupta and S. Banerjee, \"An Optimized Swarm Intelligence Approach for Fuzzy Clustering-Based Intrusive Behavior Detection in IoT and Network System,\" 2025 IEEE Madhya Pradesh Section Conference (MPCON), Jabalpur, India, 2025, pp. 864-870, doi: 10.1109/MPCON66082.2025.11256633. [16] Srilakshmi, U. & Manikandan, J. & Velagapudi, Thanmayee & Abhinav, Gandla & Kumar, Tharun & Saideep, Dogiparthy. (2024). A New Approach to Computationally-Successful Linear and Polynomial Regression Analytics of Large Data in Medicine. Journal of Computer Allied Intelligence. 2. 10.69996/jcai.2024009. [17] Manikandan, J. & SriLaskhmi, Uppalapati. (2023). HMM-Assisted Proactive Vulnerability Mitigation in Virtualization Datacenter Though Controlled VM Placement. 10.1007/978-981-19-7615-5_32. [18] Mr Sasidhar Reddy Gaddam and DOI : 10.48047/IJCNIS.14.3.1283, “Java-Driven Trustworthy And Reliable Deep Learning For Cyberattack Detection In Industrial Iot”, Int. j. commun. netw. inf. secur., vol. 14, no. 3, pp. 1274–1283, Apr. 2022. [19] S. Badonia, M. V. Babu, N. R. Lakkimsetty, G. Kavitha and A. P. N, \"Implication and Challenges in Modernisation of Healthcare System using 5G,\" 2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N), Greater Noida, India, 2024, pp. 834-837, doi: 10.1109/ICAC2N63387.2024.10894954. [20] R. Shaik, M. V. Babu, S. Medichelimi, C. Paritala, A. Amaranayani and I. Narasimharao, \"Physical Layer Security for WSNs: Addressing Eavesdropping and Energy Constraints,\" 2025 7th International Conference on Inventive Material Science and Applications (ICIMA), Namakkal, India, 2025, pp. 27-32, doi: 10.1109/ICIMA64861.2025.11074037.

Copyright

Copyright © 2026 V T Ram Pavan Kumar, PVV Sai Pavan, A Hemanth Babu, V Lokesh Kumar, Ch Lokesh, N Dinesh, Bhukya Dinesh Kumar Nayak. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.