A retrospective study on the application of machine learning models for prediction of Feline panleukopenia virus (FPV) infection in cats using hematological and blood biochemistry databases
,
,
and
Article Sidebar
Full Text: 
PDF
Abstract
This study evaluated the applicability of machine learning models for supporting the diagnosis of Feline panleukopenia virus (FPV) infection in cats based on routine haematological and blood biochemical data. A retrospective study was conducted on 60 cats, including 30 healthy cats and 30 FPV-infected cats, collected from veterinary clinics in Ho Chi Minh City. The data were preprocessed, standardized, and analyzed using seven machine learning algorithms, including Logistic Regression, KNN, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, and Naïve Bayes, combined with k-fold cross-validation. The results showed that Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and SVM achieved an accuracy of 92%, with Random Forest demonstrating optimal performance (AUC = 1.00). Feature importance analysis and PCA identified Mon#, WBC, and GLU as the main predictive biomarkers, while also demonstrating a clear separation between healthy and FPV-infected cats, confirming the potential application of machine learning in veterinary clinical practice.
Tóm tắt
Nghiên cứu này được tiến hành nhằm đánh giá khả năng ứng dụng các mô hình học máy trong hỗ trợ chẩn đoán nhiễm Feline panleukopenia virus (FPV) ở mèo dựa trên dữ liệu huyết học và sinh hóa máu thường quy. Nghiên cứu hồi cứu được thực hiện trên 60 cá thể mèo, gồm 30 mèo khỏe mạnh và 30 mèo nhiễm FPV, được thu thập tại các phòng khám thú y ở Thành phố Hồ Chí Minh. Dữ liệu được tiền xử lý, chuẩn hóa và phân tích bằng bảy thuật toán học máy, bao gồm Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine và Naïve Bayes, kết hợp với phương pháp kiểm định chéo k-fold. Kết quả cho thấy Logistic Regression, Decision Tree, Random Forest, Gradient Boosting và SVM đạt độ chính xác 92%, trong đó Random Forest cho hiệu năng tối ưu (AUC = 1.00). Kết quả của phân tích tầm quan trọng của biến và PCA xác định bạch cầu đơn nhân (Mon#), bạch cầu tổng số (WB) và đường huyết (GLU) là các chỉ dấu dự báo chính, đồng thời chứng minh khả năng phân tách rõ ràng giữa mèo khỏe và mèo viêm ruột truyền nhiễm (FPV), khẳng định tiềm năng ứng dụng học máy trong thực hành lâm sàng thú y.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Al Moubayed, N., McGowan, A., Smyth, B., & McChesney, I. (2020). An artificial neural network-based model to predict chronic kidney disease in aged cats. Journal of Veterinary Internal Medicine, 34(5), 1920–1931. https://doi.org/10.1111/jvim.15892
Banzato, T., Bedin, M., Burti, S., Zotti, A., & Bonsembiante, F. (2018). Machine learning classification of feline polycystic kidney disease using ultrasonographic texture analysis. Journal of Veterinary Internal Medicine, 32(6), 2043–2049.
https://doi.org/10.1111/jvim.15323
Basran, P. S., Appleman, E., & Punke, J. (2023). Combining ultrasound radiomics, complete blood count, and serum biochemical biomarkers for diagnosing intestinal disorders in cats using machine learning. Veterinary Radiology & Ultrasound, 64(5), 942-950. https://doi.org/10.1111/vru.13257
Beam, A. L., & Kohane, I. S. (2018). Big data and machine learning in health care. JAMA, 319(13), 1317–1318. https://doi.org/10.1001/jama.2017.18391
Biourge, V., Delmotte, S., Feugier, A., Bradley, R., McAllister, M., & Elliott, J. (2020). An artificial neural network‐based model to predict chronic kidney disease in aged cats. Journal of Veterinary Internal Medicine, 34(5), 1920-1931. https://doi.org/10.1111/jvim.15892
Bradley, R., Tagkopoulos, I., Kim, M., Kokinias, Y., Panagiotakos, T., Kennedy, J., Ling, G. V., & Cowgill, L. D. (2019). Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. Journal of Veterinary Internal Medicine, 33(6), 2644–2656. https://doi.org/10.1111/jvim.15623
Dishow, M. H., Al-Obaidi, Q. T., & Al-Naqshabendy, A. A. (2024). Feline panleukopenia virus in Duhok, Iraq: Clinical, hematological and serum biochemistry changes in clinically and subclinically infected cats. Basrah Journal of Veterinary Research, 23(1), 75–89. https://doi.org/10.23975/bjvr.2024.146878.1059
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G. S., Thrun, S., & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29.
https://doi.org/10.1038/s41591-018-0316-z
Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media.
Greene, C. E. (2022). Infectious diseases of the dog and cat (5th ed.). Elsevier.
Gülersoy, E., Erol, B. B., Ok, M., & Sevinç, M. (2023). Diagnostic performances of clinical and hematological parameters in cats naturally infected with feline panleukopenia virus. Journal of the Hellenic Veterinary Medical Society, 74(3), 4315-4326. https://doi.org/10.12681/jhvms.30721
Han, J., Pei, J., & Tong, H. (2022). Data mining: concepts and techniques. Morgan Kaufmann.
Hussein, A., & Awad, A. (2024). The coding complete genomic sequence of a feline panleukopenia virus detected from a domestic cat (Felis catus) in Chattogram, Bangladesh. Microbiology Resource Announcements, 13(8), e00209-24.
https://doi.org/10.1128/mra.00209-24
Irgashev, A., & Musayev, A. (2023). Changes in hematological and biochemical parameters in feline panleukopenia. Exploratory Animal and Medical Research, 13(2), 276-280. https://doi.org/10.52635/eamr/13.2.276-280
Kaya, A., Aydin, F., Altug, N., Kaya, I. C., Onur, A., Ural, K., Timurkan, M. O., Keles, I., & Cakiroglu, D. (2023). Molecular investigation of Feline Panleukopenia in an endangered leopard cat (Prionailurus bengalensis) rescued from central Turkey. Comparative Immunology, Microbiology and Infectious Diseases, 95, 101960. https://doi.org/10.1016/j.cimid.2023.101960
Pandey, S. (2022). Feline panleukopenia infections: treatment and control in Nepal. European Journal of Veterinary Medicine, 2(1), 10-14. https://doi.org/10.24018/ejvetmed.2022.2.1.19
Pegoraro, F. B., da Silva, M. M., de Souza, R. P., & Fernandes, C. G. (2025). Application of principal component analysis as a prediction model for feline sporotrichosis. Veterinary Sciences, 12(1), 32. https://doi.org/10.3390/vetsci12010032
Soni, P. K., & Ganguly, S. (2022). Feline panleukopenia: A re-emergent viral disease of cats. Veterinary World, 15(3), 547–554. https://doi.org/10.14202/vetworld.2022.547-554
Truyen, U., & Lörcher, S. (2020). Feline panleukopenia virus DNA shedding following modified live virus vaccination in persistently infected cats with feline chronic kidney disease. Viruses, 12(3), 320. https://doi.org/10.3390/v12030320
Truyen, U., Addie, D., Belák, S., Boucraut-Baralon, C., Egberink, H., Frymus, T., ... & Horzinek, M. C. (2009). Feline panleukopenia. ABCD guidelines on prevention and management. Journal of Feline Medicine & Surgery, 11(7), 538-546. https://doi.org/10.1016/j.jfms.2009.05.002
Vanden Broecke, L., Syme, H. M., Elliott, J., Elliott, D. A., & Geddes, R. F. (2025). Early detection of feline chronic kidney disease via 3-hydroxykynurenine and machine learning. Scientific Reports, 15(1), 90019. https://doi.org/10.1038/s41598-025-90019-x