Machine-learning algorithm as a prognostic tool in non-obstructive acute-on-chronic kidney disease in the cat

Renard, Jade; Faucher, Mathieu R; Combes, Anaïs; Concordet, Didier; Reynolds, Brice S

doi:10.1177/1098612x211001273

Cited by 6 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Medications administered and urine culture results also were recorded. Duration of hospitalization, bpH as well as SCr, potassium, and bicarbonate concentrations (24 hours after hospitalization, 48 hours after hospitalization, and at the time of discharge) were noted 25 . Development of oligo‐anuria and fluid overload during hospitalization were recorded if present.…”

Section: Methodsmentioning

confidence: 99%

“…Duration of hospitalization, bpH as well as SCr, potassium, and bicarbonate concentrations (24 hours after hospitalization, 48 hours after hospitalization, and at the time of discharge) were noted. 25 Development of oligo‐anuria and fluid overload during hospitalization were recorded if present. Follow‐up time points were divided into 3 periods (short‐term: 0‐1 week, mid‐term: 1 week‐3 months, and long‐term subdivided as 3‐6 months, 6‐12 months, and >12 months).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Benign ureteral obstruction in cats: Outcome with medical management

Mérindol

Vachon

Juette

et al. 2023

Veterinary Internal Medicne

View full text Add to dashboard Cite

Background Limited information is available regarding the outcome of medical management (MM) of benign ureteral obstruction in cats (BUO). Hypothesis Describe clinical characteristics and outcome of MM of BUO. Animals Seventy‐two client‐owned cats with 103 obstructed kidneys. Methods Medical records of cats diagnosed with BUO between 2010 and 2021 that received >72 hours of MM were retrospectively reviewed. Clinical data, treatment, and outcome were reviewed. Outcome was classified as success, partial success, or failure based on ultrasound findings. Factors associated with outcome were assessed. Results Seventy‐two cats with 103 obstructed kidneys were enrolled. The causes of obstruction were uroliths in 73% (75/103), strictures in 13.5% (14/103), and pyonephrosis in 13.5% (14/103) of affected kidneys. Median serum creatinine concentration at presentation was 4.01 mg/dL (range, 1.30‐21.3 mg/dL). Outcome after MM was considered a success in 30% (31/103), partial success in 13% (13/103), and failure in 57% (59/103) of kidneys. Success was reported in 23% (17/75) of kidneys with uroliths, 50% (7/14) with pyonephrosis, and 50% (7/14) with strictures. Median time to a successful outcome was 16 days (range, 3‐115 days). Distal and smaller uroliths (median length, 1.85 mm) were significantly associated with success (P = .05 and P = .01, respectively). Median survival times were 1188 days (range, 60‐1700 days), 518 days (range, 7‐1812 days), and 234 days (range, 4‐3494 days) for success, partial success, and failure, respectively. Conclusions and Clinical Importance We found a higher success rate for MM of BUO than previously reported. Smaller distal uroliths (<1‐2 mm) were more likely to pass.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Benign ureteral obstruction in cats: Outcome with medical management

Mérindol

Vachon

Juette

et al. 2023

Veterinary Internal Medicne

View full text Add to dashboard Cite

show abstract

“…Especially, there were emerging studies applying machine learning to animal health. Renard et al developed an algorithm to predict the short-term and medium-term survival rates of cats with acute and chronic kidney diseases [ 19 ]. Banzato et al used a convolutional neural network (CNN) to identify common radiological findings from chest X-rays in cats [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

A non-invasive method to determine core temperature for cats and dogs using surface temperatures based on machine learning

Zhao,

Li,

Zhuang

et al. 2024

BMC Vet Res

View full text Add to dashboard Cite

Background Rectal temperature (RT) is an important index of core temperature, which has guiding significance for the diagnosis and treatment of pet diseases. Objectives Development and evaluation of an alternative method based on machine learning to determine the core temperatures of cats and dogs using surface temperatures. Animals 200 cats and 200 dogs treated between March 2022 and May 2022. Methods A group of cats and dogs were included in this study. The core temperatures and surface body temperatures were measured. Multiple machine learning methods were trained using a cross-validation approach and evaluated in one retrospective testing set and one prospective testing set. Results The machine learning models could achieve promising performance in predicting the core temperatures of cats and dogs using surface temperatures. The root mean square errors (RMSE) were 0.25 and 0.15 for cats and dogs in the retrospective testing set, and 0.15 and 0.14 in the prospective testing set. Conclusion The machine learning model could accurately predict core temperatures for companion animals of cats and dogs using easily obtained body surface temperatures.

show abstract

“…Researchers have attempted to address various aspects of companion animal medicine using ML and AI, from the evaluation of the criteria in structured histology reports [17] to the differentiation between inflammatory bowel disease and alimentary lymphoma in cats [18] to the early prediction of canine cancer through blood serum analysis [19] and the short-and medium-term survival of acute-on-chronic kidney disease in cats using DT models [20]. In their work using ML to predict leptospirosis, Reagan et al [21] cautioned that models should have some form of post-implementation evaluation for each new population that the model is applied to.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests

Imada,

Arango-Sabogal,

Bauman

et al. 2024

Animals

View full text Add to dashboard Cite

Machine learning algorithms have been applied to various animal husbandry and veterinary-related problems; however, its use in Johne’s disease diagnosis and control is still in its infancy. The following proof-of-concept study explores the application of tree-based (decision trees and random forest) algorithms to analyze repeat milk testing data from 1197 Canadian dairy cows and the algorithms’ ability to predict future Johne’s test results. The random forest models using milk component testing results alongside past Johne’s results demonstrated a good predictive performance for a future Johne’s ELISA result with a dichotomous outcome (positive vs. negative). The final random forest model yielded a kappa of 0.626, a roc AUC of 0.915, a sensitivity of 72%, and a specificity of 98%. The positive predictive and negative predictive values were 0.81 and 0.97, respectively. The decision tree models provided an interpretable alternative to the random forest algorithms with a slight decrease in model sensitivity. The results of this research suggest a promising avenue for future targeted Johne’s testing schemes. Further research is needed to validate these techniques in real-world settings and explore their incorporation in prevention and control programs.

show abstract

Machine-learning algorithm as a prognostic tool in non-obstructive acute-on-chronic kidney disease in the cat

Cited by 6 publications

References 19 publications

Benign ureteral obstruction in cats: Outcome with medical management

Benign ureteral obstruction in cats: Outcome with medical management

A non-invasive method to determine core temperature for cats and dogs using surface temperatures based on machine learning

Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests

Contact Info

Product

Resources

About