A nomogram for evaluation and analysis of difficulty in retroperitoneal laparoscopic adrenalectomy: A single-center study with prospective validation using LASSO-logistic regression

Abstract

BackgroundWhile it is known that inaccurate evaluation for retroperitoneal laparoscopic adrenalectomy (RPLA) can affect the surgical results of patients, no stable and effective prediction model for the procedure exists. In this study, we aimed to develop a computed tomography (CT) -based radiological-clinical prediction model for evaluating the surgical difficulty of RPLA.MethodData from 398 patients with adrenal tumors treated by RPLA in a single center from August 2014 to December 2020 were retrospectively analyzed and divided into sets. The influencing factors were selected by least absolute shrinkage and selection operator regression model (LASSO). Additionally, the nomogram was constructed. A receiver operating characteristic curve was used to analyze the prediction efficiency of the nomogram. The C-index and bootstrap self-sampling methods were used to verify the discrimination and consistency of the nomogram.ResultThe following 11 independent influencing factors were selected by LASSO: body mass index, diabetes mellitus, scoliosis, hyperlipidemia, history of operation, tumor diameter, distance from adrenal tumor to upper pole of kidney, retro renal fat area, hyperaldosteronism, pheochromocytoma and paraganglioma, and myelolipoma. The area under the curve (AUC) of the training set was 0.787, and 0.844 in the internal validation set. Decision curve analyses indicated the model to be useful. An additional 117 patients were recruited for prospective validation, and AUC was 0.848.ConclusionThis study developed a radiological-clinical prediction model proposed for predicting the difficulty of RPLA procedures. This model was suitable, accessible, and helpful for individualized surgical preparation and reduced operational risk. Thus, this model could contribute to more patients’ benefit in circumventing surgical difficulties because of accurate predictive abilities.

Development and validation of machine-learning models for the difficulty of retroperitoneal laparoscopic adrenalectomy based on radiomics

“…Through the comprehensive comparison of different models, it was found that the RF model exhibits the best prediction performance, thus making it our recommended model. Furthermore, in comparison to clinical models in previous study ( 16 ), our RF model exhibited superiority as evidenced by 2000 Bootstrap tests (D = 7.155, P < 0.001). The discrimination power of models can be effectively compared using two measures: the Net Classification Index (NRI) and the Integrated Discrimination Improvement (IDI).…”

“…The final retained variables included “Shape Features” like “Maximum3DDiameter”. Moreover, many studies have generally confirmed that the maximum diameter of the tumor is an essential factor affecting the difficulty of removing AT ( 9 , 10 , 16 – 20 ). In addition, “First Order Features”, which are linearly correlated with the CT value of the tumor, such as “90Percentile” were also included.…”

“…Malignant and benign AT have different degrees of enhancement during arterial enhancement, which increases the risk of bleeding during surgery ( 18 , 24 , 25 ). It may also be because lipid-rich AT has lower CT values and requires more attention during surgery to prevent breaking the capsule, which prolongs the operation time ( 9 , 16 , 20 ). “DifferenceEntropy” in “GLCM Features” measures the randomness or complexity of differences between pixel intensity values.…”

“…BMI is used to assess the degree of obesity and also affects it. However, it mainly reflects the overall body fat composition, while the distribution of visceral fat, especially perirenal fat, may differ ( 9 , 16 ). Therefore, there is still controversy over BMI prediction of surgical difficulty.…”

“…Referring to previous studies ( 9 , 10 , 16 – 20 ) and combining practical experience, we defined cases with serious surgical difficulty if any of the following conditions were met: 1) operation time ≥ P 75 (150 min), 2) intraoperative injury to organs or vessels requiring blood transfusion, 3) conversion from minimally invasive to open surgery, 4) postoperative complications of Clavien-Dindo classification ( 21 ) greater than or equal to grade 3, 5) Postoperative hospital stay ≥ P 95 (15 days).…”