Assessing the feasibility of applying machine learning to diagnosing non-effusive feline infectious peritonitis.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
30 Jan 2024
30 Jan 2024
Historique:
received:
28
08
2023
accepted:
20
01
2024
medline:
31
1
2024
pubmed:
31
1
2024
entrez:
30
1
2024
Statut:
epublish
Résumé
Feline infectious peritonitis (FIP) is a severe feline coronavirus-associated syndrome in cats, which is invariably fatal without anti-viral treatment. In the majority of non-effusive FIP cases encountered in practice, confirmatory diagnostic testing is not undertaken and reliance is given to the interpretation of valuable, but essentially non-specific, clinical signs and laboratory markers. We hypothesised that it may be feasible to develop a machine learning (ML) approach which may be applied to the analysis of clinical data to aid in the diagnosis of disease. A dataset encompassing 1939 suspected FIP cases was scored for clinical suspicion of FIP on the basis of history, signalment, clinical signs and laboratory results, using published guidelines, comprising 683 FIP (35.2%), and 1256 non-FIP (64.8%) cases. This dataset was used to train, validate and evaluate two diagnostic machine learning ensemble models. These models, which analysed signalment and laboratory data alone, allowed the accurate discrimination of FIP and non-FIP cases in line with expert opinion. To evaluate whether these models may have value as a diagnostic tool, they were applied to a collection of 80 cases for which the FIP status had been confirmed (FIP: n = 58 (72.5%), non-FIP: n = 22 (27.5%)). Both ensemble models detected FIP with an accuracy of 97.5%, an area under the curve (AUC) of 0.969, sensitivity of 95.45% and specificity of 98.28%. This work demonstrates that, in principle, ML can be usefully applied to the diagnosis of non-effusive FIP. Further work is required before ML may be deployed in the laboratory as a diagnostic tool, such as training models on datasets of confirmed cases and accounting for inter-laboratory variation. Nevertheless, these results illustrate the potential benefit of applying ML to standardising and accelerating the interpretation of clinical pathology data, thereby improving the diagnostic utility of existing laboratory tests.
Identifiants
pubmed: 38291072
doi: 10.1038/s41598-024-52577-4
pii: 10.1038/s41598-024-52577-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2517Informations de copyright
© 2024. The Author(s).
Références
Pedersen, N. C. An update on feline infectious peritonitis: Diagnostics and therapeutics. Vet. J. 201, 133–141. https://doi.org/10.1016/j.tvjl.2014.04.016 (2014).
doi: 10.1016/j.tvjl.2014.04.016
pubmed: 24857253
pmcid: 7110619
Weiss, R. C. & Scott, F. W. Pathogenesis of feline infetious peritonitis: Pathologic changes and immunofluorescence. Am. J. Vet. Res. 42, 2036–2048 (1981).
pubmed: 6280518
Cave, T. A., Golder, M. C., Simpson, J. & Addie, D. D. Risk factors for feline coronavirus seropositivity in cats relinquished to a UK rescue charity. J. Feline Med. Surg. 6, 53–58. https://doi.org/10.1016/j.jfms.2004.01.003 (2004).
doi: 10.1016/j.jfms.2004.01.003
pubmed: 15123148
pmcid: 7129206
Felten, S. et al. Correlation of feline coronavirus shedding in feces with coronavirus antibody titer. Pathogens https://doi.org/10.3390/pathogens9080598 (2020).
doi: 10.3390/pathogens9080598
pubmed: 32707796
pmcid: 7459802
Taylor. S., T. S., Gunn-Moore. D., Barker. E, and Sorrell. S. An update on treatment of feline infectious peritonitis in the UK. https://www.vettimes.co.uk/article/an-update-on-treatment-of-feline-infectious-peritonitis-in-the-uk (2022).
Taylor, S., Barker, E. Feline infectious peritonitis: Hope on the horizon for cats. https://www.vettimes.co.uk/article/feline-infectious-peritonitis-hope-on-the-horizon-for-cats (2021).
Herrewegh, A. A. et al. Detection of feline coronavirus RNA in feces, tissues, and body fluids of naturally infected cats by reverse transcriptase PCR. J. Clin. Microbiol. 33, 684–689 (1995).
doi: 10.1128/jcm.33.3.684-689.1995
pubmed: 7751377
pmcid: 228014
Tasker, S. Diagnosis of feline infectious peritonitis: Update on evidence supporting available tests. J. Feline Med. Surg. 20, 228–243. https://doi.org/10.1177/1098612X18758592 (2018).
doi: 10.1177/1098612X18758592
pubmed: 29478397
Tsai, H. Y., Chueh, L. L., Lin, C. N. & Su, B. L. Clinicopathological findings and disease staging of feline infectious peritonitis: 51 cases from 2003 to 2009 in Taiwan. J. Feline Med. Surg. 13, 74–80. https://doi.org/10.1016/j.jfms.2010.09.014 (2011).
doi: 10.1016/j.jfms.2010.09.014
pubmed: 21216644
pmcid: 7129202
Wang, Y. T., Su, B. L., Hsieh, L. E. & Chueh, L. L. An outbreak of feline infectious peritonitis in a Taiwanese shelter: Epidemiologic and molecular evidence for horizontal transmission of a novel type II feline coronavirus. Vet. Res. 44, 57. https://doi.org/10.1186/1297-9716-44-57 (2013).
doi: 10.1186/1297-9716-44-57
pubmed: 23865689
pmcid: 3720556
Kipar, A. & Meli, M. L. Feline infectious peritonitis: Still an enigma?. Vet. Pathol. 51, 505–526. https://doi.org/10.1177/0300985814522077 (2014).
doi: 10.1177/0300985814522077
pubmed: 24569616
Hartmann, K. Feline infectious peritonitis. Vet. Clin. N. Am. Small Anim. Pract. 35, 39–79. https://doi.org/10.1016/j.cvsm.2004.10.011 (2005).
doi: 10.1016/j.cvsm.2004.10.011
Giordano, A., Paltrinieri, S., Bertazzolo, W., Milesi, E. & Parodi, M. Sensitivity of Tru-cut and fine needle aspiration biopsies of liver and kidney for diagnosis of feline infectious peritonitis. Vet. Clin. Pathol. 34, 368–374. https://doi.org/10.1111/j.1939-165X.2005.tb00063.x (2005).
doi: 10.1111/j.1939-165X.2005.tb00063.x
pubmed: 16270262
pmcid: 7482175
Dunbar, D. et al. Diagnosis of non-effusive feline infectious peritonitis by reverse transcriptase quantitative PCR from mesenteric lymph node fine-needle aspirates. J. Feline Med. Surg. 21, 910–921. https://doi.org/10.1177/1098612X18809165 (2019).
doi: 10.1177/1098612X18809165
pubmed: 30407137
Tasker, S. et al. Feline infectious peritonitis: European advisory board on cat diseases guidelines. Viruses https://doi.org/10.3390/v15091847 (2023).
doi: 10.3390/v15091847
pubmed: 37896864
pmcid: 10459272
de Dombal, F. T., Leaper, D. J., Staniland, J. R., McCann, A. P. & Horrocks, J. C. Computer-aided diagnosis of acute abdominal pain. Br. Med. J. 2, 9–13. https://doi.org/10.1136/bmj.2.5804.9 (1972).
doi: 10.1136/bmj.2.5804.9
pubmed: 4552594
pmcid: 1789017
Adams, I. D. et al. Computer aided diagnosis of acute abdominal pain: a multicentre study. Br. Med. J. (Clin. Res. Ed.) 293, 800–804. https://doi.org/10.1136/bmj.293.6550.800 (1986).
doi: 10.1136/bmj.293.6550.800
pubmed: 3094664
Cooper, G. F. et al. An evaluation of machine-learning methods for predicting pneumonia mortality. Artif. Intell. Med. 9, 107–138. https://doi.org/10.1016/S0933-3657(96)00367-3 (1997).
doi: 10.1016/S0933-3657(96)00367-3
pubmed: 9040894
Woolery, L. K. & Grzymala-Busse, J. Machine learning for an expert system to predict preterm birth risk. J. Am. Med. Inform. Assoc. 1, 439–446. https://doi.org/10.1136/jamia.1994.95153433 (1994).
doi: 10.1136/jamia.1994.95153433
pubmed: 7850569
pmcid: 116227
Wu, J. et al. Rapid and accurate identification of COVID-19 infection through machine learning based on clinical available blood test results. medRxiv 5, 536 (2020).
Yan, L. et al. Prediction of criticality in patients with severe Covid-19 infection using three clinical features: A machine learning-based prognostic model with clinical data in Wuhan. MedRxiv https://doi.org/10.1101/2020.02.27.20028027 (2020).
doi: 10.1101/2020.02.27.20028027
pubmed: 33173928
pmcid: 7654924
Trambaiolli, L. R. et al. Improving Alzheimer’s disease diagnosis with machine learning techniques. Clin. EEG Neurosci. 42, 160–165. https://doi.org/10.1177/155005941104200304 (2011).
doi: 10.1177/155005941104200304
pubmed: 21870467
Hathaway, Q. A. et al. Machine-learning to stratify diabetic patients using novel cardiac biomarkers and integrative genomics. Cardiovasc. Diabetol. 18, 78. https://doi.org/10.1186/s12933-019-0879-0 (2019).
doi: 10.1186/s12933-019-0879-0
pubmed: 31185988
pmcid: 6560734
Hornbrook, M. C. et al. Early colorectal cancer detected by machine learning model using gender, age, and complete blood count data. Dig. Dis. Sci. 62, 2719–2727 (2017).
doi: 10.1007/s10620-017-4722-8
pubmed: 28836087
Tseng, Y.-J. et al. Predicting breast cancer metastasis by using serum biomarkers and clinicopathological data with machine learning technologies. Int. J. Med. Inform. 128, 79–86. https://doi.org/10.1016/j.ijmedinf.2019.05.003 (2019).
doi: 10.1016/j.ijmedinf.2019.05.003
pubmed: 31103449
Wang, H.-Y. et al. Increase Trichomonas vaginalis detection based on urine routine analysis through a machine learning approach. Sci. Rep. 9, 11074. https://doi.org/10.1038/s41598-019-47361-8 (2019).
doi: 10.1038/s41598-019-47361-8
pubmed: 31423009
pmcid: 6698480
Tanner, L. et al. Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. PLoS Negl. Trop. Dis. 2, e196. https://doi.org/10.1371/journal.pntd.0000196 (2008).
doi: 10.1371/journal.pntd.0000196
pubmed: 18335069
pmcid: 2263124
Tahghighi, P., Appleby, R. B., Norena, N., Ukwatta, E. & Komeili, A. Machine learning can appropriately classify the collimation of ventrodorsal and dorsoventral thoracic radiographic images of dogs and cats. Am. J. Vet. Res. https://doi.org/10.2460/ajvr.23.03.0062 (2023).
doi: 10.2460/ajvr.23.03.0062
pubmed: 37253451
Dumortier, L., Guépin, F., Delignette-Muller, M.-L., Boulocher, C. & Grenier, T. Deep learning in veterinary medicine, an approach based on CNN to detect pulmonary abnormalities from lateral thoracic radiographs in cats. Sci. Rep. https://doi.org/10.1038/s41598-022-14993-2 (2022).
doi: 10.1038/s41598-022-14993-2
pubmed: 35794167
pmcid: 9258008
Bradley, R. et al. Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. J. Vet. Intern. Med. 33, 2644–2656. https://doi.org/10.1111/jvim.15623 (2019).
doi: 10.1111/jvim.15623
pubmed: 31557361
pmcid: 6872623
Reagan, K. L. et al. Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs. J. Vet. Diagn. Investig. 34, 612–621 (2022).
doi: 10.1177/10406387221096781
Machado, G., Mendoza, M. R. & Corbellini, L. G. What variables are important in predicting bovine viral diarrhea virus? A random forest approach. Vet. Res. 46, 85. https://doi.org/10.1186/s13567-015-0219-7 (2015).
doi: 10.1186/s13567-015-0219-7
pubmed: 26208851
pmcid: 4513962
Pfannschmidt, K., Hüllermeier, E., Held, S. & Neiger, R. Information Processing and Management of Uncertainty in Knowledge-Based Systems 450–461 (Springer International Publishing, 2016).
doi: 10.1007/978-3-319-40596-4_38
R: A language and environment for statistical computing (R Foundation for Statistical Computing, 2019).
caret: Classification and Regression Training (2020).
McNemar, Q. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12, 153–157. https://doi.org/10.1007/BF02295996 (1947).
doi: 10.1007/BF02295996
pubmed: 20254758
Fagerland, M. W., Lydersen, S. & Laake, P. The McNemar test for binary matched-pairs data: Mid-p and asymptotic are better than exact conditional. BMC Med. Res. Methodol. 13, 1–8 (2013).
doi: 10.1186/1471-2288-13-91
Robin, X. et al. pROC: An open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform. 12, 77. https://doi.org/10.1186/1471-2105-12-77 (2011).
doi: 10.1186/1471-2105-12-77