A Scoring System That Predicts Difficult Lipoma Resection: Logistic Regression and Tenfold Cross-Validation Analysis

Most lipomas are readily dissected and removed. However, some cases can pose surgical difficulties. This retrospective study sought to identify clinical and radiological risk factors that predict difficult lipoma resection and can be used in a clinically useful scoring system that predicts difficulty preoperatively.

The study cohort consisted of all consecutive patients who underwent resection of pathology-confirmed lipoma during 2016-2018 at a tertiary care referral center in Tokyo, Japan. Surgical difficulty was defined as difficulty separating some/all of the tumor from the surrounding tissue by hand and inability to extract the tumor in one piece. Descriptive, univariate, and multivariate logistic regression analyses were conducted to identify predictive factors. The predictive accuracy of the scoring system that included these factors was assessed by tenfold cross-validation analysis. Receiver-operating curve (ROC) analysis was conducted to identify the optimal cutoff score for predicting surgical difficulty.

Of the 86 cases, 36% involved surgical difficulty. Multivariate analysis showed that subfascial intramuscular location (odds ratio 42.7, 95% confidence interval 3.0-608.0), broad touching of underlying structures (46.5, 3.7-586.0), in-flowing blood vessels (9.3, 1.1-78.5), and unclear boundaries (109.0, 1.1-1110.0) significantly predicted surgical difficulty. These factors were used to construct a 0-4 point scoring system (with one point per variable). On cross-validation, the accuracy of the scoring system was 82.4% (Cohen's kappa of 0.57). ROC analysis showed that scores ≥ 2 predicted surgical difficulty with sensitivity and specificity of 55% and 98%, respectively.

Our scoring system accurately predicted lipoma resection difficulty and may help operators prepare, thereby facilitating surgery.