Authors : Fatima Aliyeva; Mustafa Hacıyev; Ayshan Salmanova; Vafa Atayeva

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/ypjmfkdk

Scribd : https://tinyurl.com/t58496tr

DOI : https://doi.org/10.38124/ijisrt/26jul047

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Current blood grouping methods based on agglutination require 25–30 minutes, depend on unstable reagents, and rely on subjective visual interpretation, leading to critical delays in emergency medical settings. This study proposed a novel biotechnological system, designated FFBT (Fast Finger Blood Type), aimed at reducing blood group determination time to less than 5 minutes through the integration of nano-protein catalysts and artificial intelligence (AI)-based image analysis. The conceptual system was designed as a three-stage platform. First, nano-protein catalysts were added to standard anti-A, anti-B, and anti-D reagents to accelerate antigen-antibody reaction kinetics by five to seven times. Second, a nanoscopic imaging system was designed to visualise antigen morphological shapes (circular, triangular, or combined) at the nanometre scale. Third, an AI algorithm employing real-time image processing was designed to automatically classify blood groups (A, B, AB, O) within less than 5 minutes. If implemented as proposed, the FFBT system is expected to achieve a ten-to fifteen-fold reduction in analysis time (from 25–30 min to less than 5 minutes), a 60 percent to 70 percent decrease in sample volume, 98 percent accuracy, and improved stability with reusability of the activating substances. The proposed FFBT system integrates nanotechnology, biochemistry, and artificial intelligence, offering a potential portable, rapid, and accurate solution for emergency medicine, blood banks, and transfusion services.

Keywords : Blood Group Determination; Nanotechnology; Artificial Intelligence; Rapid Diagnostics; FFBT.

References :

1. S. R. Sharma, D. Sharma, V. Panchal, and P. Asati, "Overview of fingerprint-based blood-grouping using various tools and techniques," Medico Leg Update, vol. 25, no. 3, pp. 16-27, 2025. doi:10.37506/65z8av60
2. Y. Xu, R. Wang, D. Ge, X. Huang, Y. Yang, Z. Meng, et al., "Evaluation of a new solid-phase ABO and RhD blood grouping kit," Transfus Med, vol. 36, no. 1, pp. 28-36, 2026. doi:10.1111/tme.70032
3. Y. Li, Y. Zhang, S. Liang, D. Cao, W. Ye, et al., "Paper-based fluorescent assay for blood typing and antibody titer determination using long-term ambient-stored bioengineered RBCs," Nat Commun, vol. 17, no. 1, pp. 1-15, 2026. doi:10.1038/s41467-026-69213-6
4. S. Korchagin, E. Zaychenkova, E. Ershov, P. Pishchev, and Y. Vengerov, "Image-based second opinion for blood typing," Health Inf Sci Syst, vol. 12, no. 1, p. 28, 2024. doi:10.1007/s13755-024-00289-4
5. S. A. Korchagin, E. E. Zaychenkova, D. A. Sharapov, E. I. Ershov, Y. V. Butorin, and Y. Y. Vengerov, "An algorithm of blood typing using serological plate images," Comput Opt, vol. 47, no. 6, pp. 958-967, 2023. doi:10.18287/2412-6179-CO-1339
6. P. Wang, M. He, Y. Ma, Y. Yang, and R. Hu, "An accumulation pretreatment-free POCT biochip for visual and sensitive ABO/Rh blood cell typing," Biosensors, vol. 15, no. 11, p. 731, 2025. doi:10.3390/bios15110731
7. M. F. Mahmood, "Machine learning techniques to classify blood groups and Rh-factors," AIP Conf Proc, vol. 3232, no. 1, p. 040009, 2024. doi:10.1063/5.0236272