Department of Surgery, Medical Research Institute, Alexandria University, 165 Horreya Avenue, Hadara, 21561, Alexandria, Egypt.
Madina Women's Hospital, Alexandria, Egypt.
Obes Surg. 2024 Sep;34(9):3445-3458. doi: 10.1007/s11695-024-07433-9. Epub 2024 Aug 8.
The utility of preoperative abdominal ultrasonography (US) in evaluating patients with obesity before metabolic bariatric surgery (MBS) remains ambiguously defined.
Retrospective analysis whereby patients were classified into four groups based on ultrasound results. Group 1 had normal findings. Group 2 had non-significant findings that did not affect the planned procedure. Group 3 required additional or follow-up surgeries without changing the surgical plan. Group 4, impacting the procedure, needed further investigations and was subdivided into 4A, delaying surgery for more assessments, and 4B, altering or canceling the procedure due to critical findings. Machine learning techniques were utilized to identify variables.
Four thousand four hundred eighteen patients' records were analyzed. Group 1 was 45.7%. Group 2, 35.7%; Group 3, 17.0%; Group 4, 1.5%, Group 4A, 0.8%; and Group 4B, 0.7%, where surgeries were either canceled (0.3%) or postponed (0.4%). The hyperparameter tuning process identified a Decision Tree classifier with a maximum tree depth of 7 as the most effective model. The model demonstrated high effectiveness in identifying patients who would benefit from preoperative ultrasound before MBS, with training and testing accuracies of 0.983 and 0.985. It also showed high precision (0.954), recall (0.962), F1 score (0.958), and an AUC of 0.976.
Our study found that preoperative ultrasound demonstrated clinical utility for a subset of patients undergoing metabolic bariatric surgery. Specifically, 15.9% of the cohort benefited from the identification of chronic calculous cholecystitis, leading to concomitant cholecystectomy. Additionally, surgery was postponed in 1.4% of the cases due to other findings. While these findings indicate a potential benefit in certain cases, further research, including a cost-benefit analysis, is necessary to fully evaluate routine preoperative ultrasound's overall utility and economic impact in this patient population.
术前腹部超声(US)在评估肥胖患者代谢减重手术(MBS)前的作用仍不明确。
回顾性分析,根据超声结果将患者分为四组。第 1 组为正常表现。第 2 组为无明显异常,不影响手术计划。第 3 组需要进一步手术或随访,不改变手术计划。第 4 组影响手术,需要进一步检查,又分为 4A 组(因需进一步评估而延迟手术)和 4B 组(因关键发现而改变或取消手术)。利用机器学习技术识别变量。
分析了 4418 例患者的记录。第 1 组占 45.7%,第 2 组占 35.7%,第 3 组占 17.0%,第 4 组占 1.5%,第 4A 组占 0.8%,第 4B 组占 0.7%,其中手术被取消(0.3%)或推迟(0.4%)。超参数调整过程确定了一个最大树深度为 7 的决策树分类器作为最有效的模型。该模型在识别接受 MBS 术前超声检查的患者方面表现出很高的有效性,训练和测试准确率分别为 0.983 和 0.985。它还表现出较高的精度(0.954)、召回率(0.962)、F1 分数(0.958)和 AUC(0.976)。
本研究发现,术前超声对代谢减重手术患者的一部分有临床作用。具体来说,15.9%的患者受益于慢性胆石性胆囊炎的发现,导致同期胆囊切除术。此外,由于其他发现,1.4%的病例手术被推迟。虽然这些发现表明在某些情况下可能有一定的益处,但需要进一步的研究,包括成本效益分析,以充分评估在这一患者群体中常规术前超声的整体效用和经济影响。