FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Equine veterinary journal2025; doi: 10.1111/evj.14517

Integration of machine learning and viscoelastic testing to improve survival prediction in horses experiencing acute abdominal pain at a veterinary teaching hospital.

Abstract: Viscoelastic coagulation testing (VCT) identifies subclinical disruption of coagulation homeostasis and may improve prognostication, particularly for patients with severe systemic inflammation or shock. Machine learning (ML) algorithms may capture complex relationships between clinical variables better than linear regression (GLM). Objective: To evaluate the utility of ML models incorporating VCT and clinical data to predict survival outcomes in horses with acute abdominal pain. Methods: Retrospective observational cohort study. Methods: VCT (VCM Vet™) was performed on 57 horses with acute abdominal pain at admission, with clinical data collected retrospectively. Coagulopathy was defined as ≥2 abnormal VCT parameters. GLM and random forest (RF) classification models were developed to predict short-term survival. A training cohort of 40 horses was used for model development, and model performance was determined using the remaining 17 horses. RF models were implemented in a web-based application to demonstrate clinical application. Results: There were 31 survivors and 26 non-survivors. The majority of cases were colitis (47.7%), with smaller proportions of impactions, strangulating obstructions and other causes of colic. Coagulopathy diagnosis alone performed poorly for survival prediction (sensitivity 81% [95% CI 64-94], specificity 31% [95% CI 15-50], AUC = 0.515). Final GLM included SIRS score (OR 0.37 [95% CI 0.071-1.68]; p = 0.2), L-lactate (OR 0.51 [0.25-0.82]; p = 0.02), clot time (CT; OR 1.0 [0.99-1.0], p = 0.39), and clot amplitude at 10 min (A10; OR 0.89 [0.74-1.02], p = 0.2). Final RF model included heart rate, PCV, L-lactate, white blood cell count, neutrophil count, clot amplitude at 20 min (A20) and CT. RF models improved sensitivity (RFfull 91% [95% CI 60-100]; RFreduced 83% [95% CI 42-99]) and specificity (both 83% [95% CI 42-99]) compared to GLM (sensitivity 65% [95% CI 47-79], specificity 42% [95% CI 26-61]). Conclusions: Small number of horses, convenience sampling. Model validation with an independent population is needed to support clinical applicability. Conclusions: L-lactate remains a key predictor of survival in horses with colic. The integration of VCT with clinical data in machine learning models may enhance prognostication.
© 2025 The Author(s). Equine Veterinary Journal published by John Wiley & Sons Ltd on behalf of EVJ Ltd.
Get Full Text
Publication Date: 2025-04-24 PubMed ID: 40275538PubMed Central: PMC12323807DOI: 10.1111/evj.14517Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

This research investigates how the combination of machine learning models and viscoelastic coagulation testing can improve survival predictions in horses suffering from acute abdominal pain.

Research Objective

  • The purpose of this research was to determine the usefulness of machine learning models that incorporate viscoelastic coagulation testing and clinical data to predict the survival outcomes in horses with acute abdominal pain.

Methodology

  • The study used a retrospective observational cohort study methodology.
  • Viscoelastic coagulation testing was performed on 57 horses with acute abdominal pain upon admission, and clinical data was collected retrospectively.
  • A diagnosis of coagulopathy was defined when two or more abnormal VCT parameters were present.
  • The researchers developed two types of models: Generalised Linear Models (GLM) and random forest (RF) classification models to predict the horses’ short-term survival.
  • They used a training cohort of 40 horses for model development, and validated the performance of these models with the remaining 17 horses.
  • The RF models were deployed on a web-based application to showcase how they could be used clinically.

Results

  • Out of the 57 horses, 31 survived and 26 did not. The most common case among the horses was colitis (47.7%), with fewer instances of impactions, strangulating obstructions, and other causes of colic.
  • Using coagulopathy diagnosis alone was not efficient for survival prediction (sensitivity 81%, specificity 31%, AUC=0.515).
  • In the final GLM model, Systemic Inflammatory Response Syndrome (SIRS) score, L-lactate, clot time (CT), and clot amplitude at 10 min (A10) were the variables used.
  • The final RF model incorporated parameters such as heart rate, Pack Cell Volume (PCV), L-lactate, white blood cell count, neutrophil count, clot amplitude at 20 min (A20), and CT.
  • The RF models displayed better sensitivity (83-91%) and specificity (both 83%) compared to the GLM model (sensitivity 65% and specificity 42%).

Limitations

  • The main limitation of the study was a small sample size and the use of convenience sampling.
  • Model validation using an independent population is required to further support the use of this model in a clinical setting.

Conclusions

  • The level of L-lactate remains a crucial predictor of survival in horses suffering from colic.
  • The integration of Viscoelastic Coagulation Testing data with clinical data in machine learning models potentially enhances the quality of prognostication.

Cite This Article

APA
Macleod BM, Wilkins PA, McCoy AM, Bishop RC. (2025). Integration of machine learning and viscoelastic testing to improve survival prediction in horses experiencing acute abdominal pain at a veterinary teaching hospital. Equine Vet J. https://doi.org/10.1111/evj.14517

Publication

Equine veterinary journal
ISSN: 2042-3306
NlmUniqueID: 0173320
Country: United States
Language: English

Researcher Affiliations

Macleod, Brandi M
  • Department of Veterinary Clinical Medicine, University of Illinois, Urbana, Illinois, USA.
Wilkins, Pamela A
  • Department of Veterinary Clinical Medicine, University of Illinois, Urbana, Illinois, USA.
McCoy, Annette M
  • Department of Veterinary Clinical Medicine, University of Illinois, Urbana, Illinois, USA.
Bishop, Rebecca C
  • Department of Veterinary Clinical Medicine, University of Illinois, Urbana, Illinois, USA.

Grant Funding

  • T35 OD011145 / NIH HHS
  • Entegrion, Inc.
  • Boehringer Ingelheim

Conflict of Interest Statement

CONFLICT OF INTEREST STATEMENT. The authors declare no conflicts of interest.

References

This article includes 46 references
  1. Bishop RC, Gutierrez-Nibeyro SD, Stewart MC, McCoy AM. Performance of predictive models of survival in horses undergoing emergency exploratory laparotomy for colic. Vet Surg 2022;51:891–902.
    doi: 10.1111/vsu.13839pmc: PMC9545965pubmed: 35674231google scholar: lookup
  2. Epstein KL, Brainard BM, Gomez-Ibanez SE, Lopes MA, Barton MH, Moore JN. Thrombelastography in horses with acute gastrointestinal disease. J Vet Intern Med 2011;25:307–14.
    doi: 10.1111/j.1939-1676.2010.0673.xpubmed: 21314719google scholar: lookup
  3. Roy MF, Kwong GPS, Lambert J, Massie S, Lockhart S. Prognostic value and development of a scoring system in horses with systemic inflammatory response syndrome. J Vet Intern Med 2017;31:582–92.
    doi: 10.1111/jvim.14670pmc: PMC5354005pubmed: 28207163google scholar: lookup
  4. Furr MO, Lessard P, White NA 2nd. Development of a colic severity score for predicting the outcome of equine colic. Vet Surg 1995;24:97–101.
    doi: 10.1111/j.1532-950x.1995.tb01302.xpubmed: 7778263google scholar: lookup
  5. Grulke S, Olle E, Detilleux J, Gangl M, Caudron I, Serteyn D. Determination of a gravity and shock score for prognosis in equine surgical colic. J Vet Med A Physiol Pathol Clin Med 2001;48:465–73.
    doi: 10.1046/j.1439-0442.2001.00374.xpubmed: 11710672google scholar: lookup
  6. French NP, Smith J, Edwards GB, Proudman CJ. Equine surgical colic: risk factors for postoperative complications. Equine Vet J 2002;34:444–9.
    doi: 10.2746/042516402776117791pubmed: 12358045google scholar: lookup
  7. Mendez-Angulo JL, Mudge MC, Vilar-Saavedra P, Stingle N, Couto CG. Thromboelastography in healthy horses and horses with inflammatory gastrointestinal disorders and suspected coagulopathies. J Vet Emerg Crit Care (San Antonio) 2010;20:488–93.
    doi: 10.1111/j.1476-4431.2010.00576.xpubmed: 20955299google scholar: lookup
  8. Dallap BL, Dolente B, Boston R. Coagulation profiles in 27 horses with large colon volvulus. J Vet Emerg Crit Care 2003;13:215–25.
    doi: 10.1111/j.1534-6935.2003.00102.xgoogle scholar: lookup
  9. Dolente BA, Wilkins PA, Boston RC. Clinicopathologic evidence of disseminated intravascular coagulation in horses with acute colitis. J Am Vet Med Assoc 2002;220:1034–8.
    doi: 10.2460/javma.2002.220.1034pubmed: 12420783google scholar: lookup
  10. Dunkel B, Chan DL, Boston R, Monreal L. Association between hypercoagulability and decreased survival in horses with ischemic or inflammatory gastrointestinal disease. J Vet Intern Med 2010;24:1467–74.
    doi: 10.1111/j.1939-1676.2010.0620.xpubmed: 21054544google scholar: lookup
  11. Monreal L, Cesarini C. Coagulopathies in horses with colic. Vet Clin North Am Equine Pract 2009;25:247–58.
    doi: 10.1016/j.cveq.2009.04.001pubmed: 19580937google scholar: lookup
  12. Johnstone IB, Crane S. Haemostatic abnormalities in horses with colic—their prognostic value. Equine Vet J 1986;18:271–4.
    doi: 10.1111/j.2042-3306.1986.tb03624.xpubmed: 3758003google scholar: lookup
  13. Bishop RC, Kemper AM, Burges JW, Jandrey KE, Wilkins PA. Preliminary evaluation of reference intervals for a point-of-care viscoelastic coagulation monitor (VCM Vet) in healthy adult horses. J Vet Emerg Crit Care 2023;33:540–8.
    doi: 10.1111/vec.13317pubmed: 37561043google scholar: lookup
  14. Epstein KL, Brainard BM, Giguere S, Vrono Z, Moore JN. Serial viscoelastic and traditional coagulation testing in horses with gastrointestinal disease. J Vet Emerg Crit Care 2013;23:504–16.
    doi: 10.1111/vec.12095pubmed: 24028350google scholar: lookup
  15. An Q, Rahman S, Zhou J, Kang JJ. A comprehensive review on machine learning in healthcare industry: classification, restrictions, opportunities and challenges. Sensors 2023;23(9):4178.
    doi: 10.3390/s23094178pmc: PMC10180678pubmed: 37177382google scholar: lookup
  16. Bradley R, Tagkopoulos I, Kim M, Kokkinos Y, Panagiotakos T, Kennedy J. Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. J Vet Intern Med 2019;33:2644–56.
    doi: 10.1111/jvim.15623pmc: PMC6872623pubmed: 31557361google scholar: lookup
  17. Szlosek D, Coyne M, Riggott J, Knight K, McCrann DJ, Kincaid D. Development and validation of a machine learning model for clinical wellness visit classification in cats and dogs. Front Vet Sci 2024;11:1348162.
    doi: 10.3389/fvets.2024.1348162pmc: PMC11392780pubmed: 39280839google scholar: lookup
  18. Akinsulie OC, Idris I, Aliyu VA, Shahzad S, Banwo OG, Ogunleye SC. The potential application of artificial intelligence in veterinary clinical practice and biomedical research. Front Vet Sci 2024;11: 1347550.
    doi: 10.3389/fvets.2024.1347550pmc: PMC10864457pubmed: 38356661google scholar: lookup
  19. Ferrini S, Rollo C, Bellino C, Borriello G, Cagnotti G, Corona C. A novel machine learning-based web application for field identification of infectious and inflammatory disorders of the central nervous system in cattle. J Vet Intern Med 2023;37:766–73.
    doi: 10.1111/jvim.16664pmc: PMC10061175pubmed: 36896810google scholar: lookup
  20. Kaveh N, Ebrahimi A, Asadi E. Comparative analysis of random forest, exploratory regression, and structural equation modeling for screening key environmental variables in evaluating rangeland above-ground biomass. Eco Inform 2023;77:102251.
    doi: 10.1016/j.ecoinf.2023.102251google scholar: lookup
  21. RStudio Team. RStudio: integrated development for R. Boston, MA: RStudio, PBC; 2020.
  22. Wickham H, François R, Henry L, Müller K. dplyr: a grammar of data manipulation. R package version 1.0.2 2020.
  23. Wickham H. ggplot2: elegant graphics for data analysis. New York: Springer-Verlag; 2016.
  24. Robinson D. broom: an R package for converting statistical analysis objects into tidy data frames. R package version 0.7.3 2020.
  25. Harrell FE. Missing data. Regression modeling strategies New York, NY: Springer International Publishing; 2015. p. 45–61.
  26. Stoica P, Selen Y. Model-order selection. IEEE Signal Process Mag 2004;21:36–47.
    doi: 10.1109/msp.2004.1311138google scholar: lookup
  27. Liaw A, Wiener M. Classification and regression by randomForest. Forest 2001;2/3:1–22.
  28. Kursa MB, Rudnicki WR. Feature selection with the Boruta package. J Stat Softw 2010;36(11):1–13.
    doi: 10.18637/jss.v036.i11google scholar: lookup
  29. Breiman L. Random forests. Mach Learn 2001;45:5–32.
    doi: 10.1023/a:1010933404324google scholar: lookup
  30. Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez J-C. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 2011;12(77):77.
    doi: 10.1186/1471-2105-12-77pmc: PMC3068975pubmed: 21414208google scholar: lookup
  31. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988;44(3):837–45.
    doi: 10.2307/2531595pubmed: 3203132google scholar: lookup
  32. Sun X, Xu W. Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Signal Process Lett 2014;21:1389–93.
    doi: 10.1109/LSP.2014.2337313google scholar: lookup
  33. Kuhn M. caret: classification and regression training. R package version 6.0–90 2021.
  34. Chang W, Cheng J, Allaire J, Sievert C, Schloerke B, Xie Y. shiny: web application framework for R. R package version 1.9.1.9000 2024.
  35. Gygi JP, Kleinstein SH, Guan L. Predictive overfitting in immunological applications: pitfalls and solutions. Hum Vaccin Immunother 2023;19:2251830.
    doi: 10.1080/21645515.2023.2251830pmc: PMC10498807pubmed: 37697867google scholar: lookup
  36. Peng Y, Nagata MH. An empirical overview of nonlinearity and overfitting in machine learning using COVID-19 data. Chaos Soliton Fract 2020;139:110055.
    doi: 10.1016/j.chaos.2020.110055pmc: PMC7324351pubmed: 32834608google scholar: lookup
  37. Mitchell MW. Bias of the random forest out-of-bag (OOB) error for certain input parameters. Open J Stat 2011;1:205–11.
    doi: 10.4236/ojs.2011.13024google scholar: lookup
  38. Han S, Williamson BD, Fong Y. Improving random forest predictions in small datasets from two-phase sampling designs. BMC Med Inform Decis Mak 2021;21(1):322.
    doi: 10.1186/s12911-021-01688-3pmc: PMC8607560pubmed: 34809631google scholar: lookup
  39. Thoefner MB, Ersboll AK, Hesselholt M. Prognostic indicators in a Danish hospital-based population of colic horses. Equine Vet J 2000;32(S32):11–8.
    doi: 10.1111/j.2042-3306.2000.tb05328.xpubmed: 11202376google scholar: lookup
  40. Farrell A, Kersh K, Liepman R, Dembek KA. Development of a colic scoring system to predict outcome in horses. Front Vet Sci 2021;8:697589.
    doi: 10.3389/fvets.2021.697589pmc: PMC8531487pubmed: 34692803google scholar: lookup
  41. Reeves MJ, Curtis CR, Salman MD, Hilbert BJ. Prognosis in equine colic patients using multivariable analysis. Can J Vet Res 1989;53:87–94.
    pmc: PMC1255520pubmed: 2914230
  42. Blikslager AT, Roberts MC. Accuracy of clinicians in predicting site and type of lesion as well as outcome in horses with colic. J Am Vet Med Assoc 1995;207:1444–7.
    doi: 10.2460/javma.1995.207.11.1444pubmed: 7493873google scholar: lookup
  43. Freden GO, Provost PJ, Rand WM. Reliability of using results of abdominal fluid analysis to determine treatment and predict lesion type and outcome for horses with colic: 218 cases (1991–1994). J Am Vet Med Assoc 1998;213:1012–5.
    doi: 10.2460/javma.1998.213.07.1012pubmed: 9777000google scholar: lookup
  44. Vitale V, Viu J, Armengou L, Ríos J, Jose-Cunilleras E. Prognostic value of measuring heart rate variability at the time of hospital admission in horses with colic. Am J Vet Res 2020;81:147–52.
    doi: 10.2460/ajvr.81.2.147pubmed: 31985289google scholar: lookup
  45. Cihan P. Horse surgery and survival prediction with artificial intelligence models: performance comparison of original, imputed, balanced, and feature-selected datasets. Kafkas Univ Vet Fak Derg 2024;30:233–41.
  46. Fraiwan MA, Abutarbush SM. Using artificial intelligence to predict survivability likelihood and need for surgery in horses presented with acute abdomen (colic). J Equine Vet Sci 2020;90:102973.
    doi: 10.1016/j.jevs.2020.102973pubmed: 32534764google scholar: lookup

Citations

This article has been cited 1 times.
  1. Nocera I, Cingottini D, Di Franco C, Sala G, Bindi F, Spadari A, Rinnovati R, Vitale V, Jose-Cunilleras E, Sgorbini M. In-Depth Analysis of the Prognostic Factors Associated with Short-Term Outcome in Equine Colic Patients: Multicentric Retrospective Study. Animals (Basel) 2026 Feb 5;16(3).
    doi: 10.3390/ani16030496pubmed: 41681477google scholar: lookup
Subscribe to our newsletter
Join 99,850 horse owners like you who receive our email updates on horse health and nutrition.