← Articles

Low et al: Machine‐learning prediction of postoperative complications after high tibial osteotomy for canine cranial cruciate ligament disease
Veterinary Surgery 7, 2025

🔍 Key Findings

  • Postoperative complications occurred in 20% of stifles, including 7.5% minor, 10.3% surgical, and 3.4% medical complications.
  • The PROSPECT machine-learning model achieved high predictive accuracy: 92.3% for surgical complications, 91.9% for minor, and 94.3% for medical.
  • Top predictive features included surgical technique, implant type, patient age, and surgeon identity.
  • Surgeon-specific variables influenced predictions, indicating operator experience and technique matter.
  • Engineered interaction features (e.g., breed × implant) were more predictive than raw clinical data alone.
  • Rottweiler, intact male status, and higher bodyweight were associated with increased complication risk; Labradors had decreased risk.
  • Model calibration was strong, especially for high and low probability predictions; midrange predictions were less reliable.
  • The model supports individualized, probabilistic risk assessment, which could inform client counseling and tailored postoperative care.

PROSPECT = Predicting Risk Of Surgical compli­cations aftEr CCWO and TPLO

Simini Surgery Review Podcast

How critical is this paper for crushing the Boards?

🚨 Must-know. I’d bet on seeing this.

📚 Useful background, not must-know.

💤 Skip it. Doubt it’ll ever show up.

Thanks for the feedback!
‍We'll keep fine-tuning the articles vault.
Oops — didn’t go through.
‍Mind trying that again?
← Articles

Low et al: Machine‐learning prediction of postoperative complications after high tibial osteotomy for canine cranial cruciate ligament disease
Veterinary Surgery 7, 2025

🔍 Key Findings

  • Postoperative complications occurred in 20% of stifles, including 7.5% minor, 10.3% surgical, and 3.4% medical complications.
  • The PROSPECT machine-learning model achieved high predictive accuracy: 92.3% for surgical complications, 91.9% for minor, and 94.3% for medical.
  • Top predictive features included surgical technique, implant type, patient age, and surgeon identity.
  • Surgeon-specific variables influenced predictions, indicating operator experience and technique matter.
  • Engineered interaction features (e.g., breed × implant) were more predictive than raw clinical data alone.
  • Rottweiler, intact male status, and higher bodyweight were associated with increased complication risk; Labradors had decreased risk.
  • Model calibration was strong, especially for high and low probability predictions; midrange predictions were less reliable.
  • The model supports individualized, probabilistic risk assessment, which could inform client counseling and tailored postoperative care.

PROSPECT = Predicting Risk Of Surgical compli­cations aftEr CCWO and TPLO

Simini Surgery Review Podcast

Join Now to Access Key Summaries to more Veterinary Surgery Articles!
Log InSign Up

Multiple Choice Questions on this study

In Low 2025 et al., on machine-learning prediction, what was the approximate overall postoperative complication rate following high tibial osteotomy in dogs?

A. 10%
B. 20%
C. 30%
D. 35%
E. 5%

Answer: 20%

Explanation: Approximately 20% of stifles developed complications postoperatively, per the study findings.
In Low 2025 et al., on machine-learning prediction, which factor was shown to have a significant impact on the model’s predictions and may represent a modifiable risk?

A. Sex of the dog
B. Surgeon identity
C. Meniscal release
D. Bilateral disease
E. Presence of osteoarthritis

Answer: Surgeon identity

Explanation: The study emphasized that surgeon-related variables heavily influenced complication prediction.
In Low 2025 et al., on machine-learning prediction, which type of model was used to develop the PROSPECT algorithm?

A. Logistic regression
B. Decision tree
C. Support vector machine
D. eXtreme Gradient Boosting (XGBoost)
E. Random forest

Answer: eXtreme Gradient Boosting (XGBoost)

Explanation: The authors used XGBoost, a powerful machine-learning model for structured data.
In Low 2025 et al., on machine-learning prediction, what was the performance accuracy of the PROSPECT model in predicting *surgical* complications?

A. 79.5%
B. 84.2%
C. 89.9%
D. 92.3%
E. 96.1%

Answer: 92.3%

Explanation: The model achieved 92.3% accuracy for predicting surgical complications.
In Low 2025 et al., on machine-learning prediction, which of the following breeds was associated with a significantly *reduced* risk of postoperative complications?

A. German Shepherd
B. Doberman Pinscher
C. Rottweiler
D. Labrador Retriever
E. English Springer Spaniel

Answer: Labrador Retriever

Explanation: Labradors had a significantly lower risk of complications compared to other breeds.

Elevate Your Infection Control Protocol

Implement Simini Protect Lavage for superior, clinically-proven post-operative skin antisepsis and reduced infection risk.

Start Your Free Trial TodayStart Your Free Trial

Review More Key Summaries from this Veterinary Surgery Journal Issue

Dobberstein

 et al: 

Primary repair of nonsteroidal anti‐inflammatory drug‐associated full thickness gastrointestinal ulcers in 11 dogs

Galliano

 et al: 

Subcutaneous vascular access port implantation in the axillary or femoral/external iliac vein at the time of full limb amputation in dogs

Evers

 et al: 

Accuracy of needle arthroscopy for the diagnosis of medial meniscal tears in dogs with cranial cruciate ligament rupture

de Moya

 et al: 

Closed reduction and fluoroscopic-guided percutaneous pinning of femoral capital physeal or neck fractures: Thirteen fractures in 11 dogs

Marshall

 et al: 

Delayed union, non-union and mal-union in 442 dogs