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

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

Know What Matters in the Literature - and Why

We distill peer-reviewed surgical studies into clinically relevant summaries and
exam-style questions, so you can make informed decisions with confidence.

Get Instant Access to Surgical Summaries

Free Access. No Spam. Just Smarter Surgical Learning

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.

Access the full library of surgical summaries and exam-style questions.

Get Instant Access