Blood Group Prediction Using Fingerprint

This paper has described a complete system for blood group prediction from fingerprint images using deep learning. The system combines fingerprint biometric analysis with a CNN-based classification model - specifically, a transfer learning architecture built on EfficientNetB3 - to predict one of eight ABO/Rh blood group types from a single fingerprint image. A web-based interface makes the system accessible to non-expert users and delivers results in near real-time. Experimental evaluation confirmed that the system achieves satisfactory classification accuracy across all eight blood group classes, with performance validated through accuracy, precision, recall, and F1-score metrics. The results suggest that a genuine, if modest, statistical relationship exists between fingerprint patterns and blood groups that can be leveraged by sufficiently expressive machine learning models. The primary contribution of this work is demonstrating the practical viability of non-invasive blood group screening through fingerprint analysis. While the system is not intended to replace clinical blood typing, it offers a promising complement to conventional methods in scenarios where speed, accessibility, and non-invasiveness are priorities - including emergency triage, forensic profiling, and healthcare delivery in remote or resource-limited settings. Future work will focus on expanding the dataset across broader demographic groups, exploring multi-finger fusion strategies, integrating real-time fingerprint scanner hardware, and investigating explainable AI techniques to visualize which ridge features most influence the model's predictions.

[1]   Al Habsi, T., Al Khabori, H., Al Qasmi, S., Al Habsi, T., Al Mushaiqri, M., Das, S., and Sirasanagandla, S. R., "The association between fingerprint patterns and blood groups in the Omani population," Arab Gulf Journal of Scientific Research, 2023. [2]   Rastogi, A., Bashar, M. A., Sheikh, N. A., and Bashar,M. A., "Relation of Primary Fingerprint Patterns With Gender and Blood Group: A Dermatoglyphic Study From a Tertiary Care Institute in Eastern India," Cureus, vol. 15, no. 5, 2023. doi: https://doi.org/10.7759/cureus.38459. [3]       Swathi, K., Sushmita, K., and Horadi, K. V., "Fingerprint based blood group prediction using deep learning," International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), vol. 3, no. 1, 2024. doi: https://doi.org/10.48175/IJARSCT-15393. [4]   Agastin, S., Charles, Y., Kandeeban, S., and Akila, S., "Blood Group Prediction Using Fingerprint Images with Deep                    Learning,"  March   2026.     doi: https://doi.org/10.22214/ijraset.2026.78231. [5]  Sanyasamma, H. B., Gogineni, M. B., Rani, N., Akhila,P. K., Pinjala, and Kumar, K. P., "Precise monkeypox identification utilizing transfer learning via EfficientNetB3 and tailored Keras callbacks," Asian Food of Biological Sciences, vol. 6, no. 6, pp. 2488–2494, 2024. [6]     Gaouar, S., Hamza-Cherif, S., and Rahmoun, A., "MalariaScope: Leveraging explainable AI for enhanced malaria diagnosis through deep learning-based blood cell classification," Studies in Engineering and Exact Sciences, vol. 5, no. 2, p. e12006, 2024. [7]   Moslemi, C., Sækmose, S. G., Larsen, R., Bay, J. T., Brodersen, T., Didriksen, M., Hjalgrim, H., Banasik, K., and Nielsen, K. R., "Genetic prediction of 33 blood group phenotypes using an existing genotype dataset," Transfusion, vol. 64, no. 2, 2024. [8]   Hafid, A. and Abdullah, S., "Estimating physiological parameters in various age groups: Windkessel 4 element model and PPG waveform analysis approach," in 2023 IEEE 4th International Multidisciplinary Conference on Engineering Technology (IMCET), Beirut, Lebanon, 2023,pp. 194–197. [9]    Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P., "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. [10]    Tan, M. and Le, Q. V., "EfficientNet: Rethinking model scaling for convolutional neural networks," in Proceedings of the 36th International Conference on Machine Learning (ICML), 2019, pp. 6105–6114.