Orthopaedic Research Society Annual Meeting
Orthopaedic Research Society Annual Meeting
Source:

Yeo I, et al. Paper 32. Presented at: Orthopaedic Research Society Annual Meeting; Feb. 12-16, 2021 (virtual meeting).

Disclosures: Yeo reports no relevant financial disclosures.
February 22, 2021
1 min read
Save

Patient, procedure factors may predict surgical site infection risk after TJA

Source:

Yeo I, et al. Paper 32. Presented at: Orthopaedic Research Society Annual Meeting; Feb. 12-16, 2021 (virtual meeting).

Disclosures: Yeo reports no relevant financial disclosures.
You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Use of an artificial neural network model identified Charlson comorbidity index and smoking status as the strongest predictors of surgical site infection after total joint arthroplasty, according to results.

Ingwon Yeo, MD, a research fellow in the bioengineering lab in the department of orthopedics at Massachusetts General Hospital, and colleagues randomly partitioned data of 11,882 patients who underwent primary total hip and knee arthroplasty into training (n=9,506) and testing (n=2,376) datasets for an artificial neural network model. Variables used to predict surgical site infection included patient and procedure factors, such as BMI, American Society of Anesthesiologists score, smoking status, anesthesia, duration of tourniquet in cases of knee surgery and tranexamic acid usage and dose, according to Yeo.

“Then, [we applied] principal component analysis and logistic regression to reduce the large dimensionality to the seven most statistically influential parameters,” Yeo said in his presentation at the Orthopaedic Research Society Annual Meeting. “To avoid the problem of overfitting associated with artificial neural network, fivefold validation was employed in this study. The area under the curve [AUC] and receiver operating characteristic analysis was used as the accuracy metric predicting surgical site infection in primary total joint arthroplasty.”

Ingwon Yeo
Ingwon Yeo

Yeo noted an overall incidence of surgical site infection after primary TJA of 2.7%.

“This artificial neural network model had an AUC of 0.78,” Yeo said. “The threshold probability was 0.66, which had a sensitivity of 0.76 and specificity of 0.7.”

The artificial neural network identified age, gender, Charlson comorbidity index, smoking, alcohol use, diabetes and insurance type as the most influential predictors of surgical site infection, according to Yeo.

“Among these variables, Charlson comorbidity index and smoking were the strongest predictors for surgical site infection,” Yeo said.