(1) Background: The difficulty of pelvic operation is greatly affected by anatomical constraints. Defining this difficulty and assessing it based on conventional methods has some limitations. Artificial intelligence (AI) has enabled rapid advances in surgery, but its role in assessing the difficulty of laparoscopic rectal surgery is unclear. This study aimed to establish a difficulty grading system to assess the difficulty of laparoscopic rectal surgery, as well as utilize this system to evaluate the reliability of pelvis-induced difficulties described by MRI-based AI. (2) Methods: Patients who underwent laparoscopic rectal surgery from March 2019 to October 2022 were included, and were divided into a non-difficult group and difficult group. This study was divided into two stages. In the first stage, a difficulty grading system was developed and proposed to assess the surgical difficulty caused by the pelvis. In the second stage, AI was used to build a model, and the ability of the model to stratify the difficulty of surgery was evaluated at this stage, based on the results of the first stage; (3) Results: Among the 108 enrolled patients, 53 patients (49.1%) were in the difficult group. Compared to the non-difficult group, there were longer operation times, more blood loss, higher rates of anastomotic leaks, and poorer specimen quality in the difficult group. In the second stage, after training and testing, the average accuracy of the four-fold cross validation models on the test set was 0.830, and the accuracy of the merged AI model was 0.800, the precision was 0.786, the specificity was 0.750, the recall was 0.846, the F1-score was 0.815, the area under the receiver operating curve was 0.78 and the average precision was 0.69; (4) Conclusions: This study successfully proposed a feasible grading system for surgery difficulty and developed a predictive model with reasonable accuracy using AI, which can assist surgeons in determining surgical difficulty and in choosing the optimal surgical approach for rectal cancer patients with a structurally difficult pelvis.

BACKGROUND: There is concern regarding the possibility of postoperative complications for laparoscopic right colectomy. OBJECTIVE: To evaluate the risk factors for postoperative complications for patients undergoing laparoscopic right colectomy. DESIGN: This was an observational study. SETTINGS: This was a post hoc analysis of a prospective, multicenter, randomized controlled trial (RELARC trial, NCT02619942). PATIENTS: Patients included in the modified intention-to-treat analysis in the RELARC trial were all enrolled in this study. MAIN OUTCOME MEASURES: Risk factors for postoperative complications were identified using univariate and multivariable logistic regression analysis. RESULTS: Of 995 patients, 206 (20.7%) had postoperative complications. Comorbidity (p = 0.02; OR: 1.544; 95% CI, 1.077–2.212) and operative time >180 minutes (p = 0.03; OR: 1.453; 95% CI, 1.032–2.044) were independent risk factors for postoperative complications, whereas female sex (p = 0.04; OR: 0.704; 95% CI, 0.506–0.980) and extracorporeal anastomosis (p < 0.001; OR: 0.251; 95% CI, 0.166–0.378) were protective factors. Eighty patients (8.0%) had overall surgical site infection, 53 (5.3%) had incisional surgical site infection, and 33 (3.3%) had organ/space surgical site infection. Side-to-side anastomosis was a risk factor for overall surgical site infection (p < 0.001; OR: 1.912; 95% CI, 1.118–3.268) and organ/space surgical site infection (p = 0.005; OR: 3.579; 95% CI, 1.455–8.805). The extracorporeal anastomosis was associated with a reduced risk of overall surgical site infection (p < 0.001; OR: 0.239; 95% CI, 0.138–0.413), organ/space surgical site infection (p = 0.002; OR: 0.296; 95% CI, 0.136–0.646), and incisional surgical site infection (p < 0.001; OR: 0.179; 95% CI, 0.099–0.322). Diabetes (p = 0.039; OR: 2.090; 95% CI, 1.039–4.205) and conversion to open surgery (p = 0.013; OR: 5.403; 95% CI, 1.437–20.319) were risk factors for incisional surgical site infection. LIMITATIONS: Due to the retrospective nature, the key limitation is the lack of prospective documentation and standardization regarding the perioperative management of these patients, such as preoperative optimization, bowel preparation regimens, and antibiotic regimens, which may be confounder factors of complications. All surgeries were performed by experienced surgeons, and the patients enrolled were relatively young, generally healthy, and without obesity. It is unclear whether the results will be generalizable to obese and other populations worldwide. CONCLUSIONS: Male sex, comorbidity, prolonged operative time, and intracorporeal anastomosis were independent risk factors for postoperative complications of laparoscopic right colectomy. Side-to-side anastomosis was associated with an increased risk of organ/space surgical site infection. Extracorporeal anastomosis could reduce the incidence of overall surgical site infection. Diabetes and conversion to open surgery were associated with an increased risk of incisional surgical site infection. See Video Abstract. ClinicalTrials.gov identifier: NCT02619942 FACTORES DE RIESGO DE COMPLICACIONES POSOPERATORIAS EN COLECTOMÍA DERECHA LAPAROSCÓPICA: UN ANÁLISIS POST HOC DEL ENSAYO RELARC: ANTECEDENTES: Existe preocupación con respecto a la posibilidad de complicaciones postoperatorias en colectomía derecha laparoscópica. OBJETIVO: Evaluar los factores de riesgo de complicaciones postoperatorias en pacientes sometidos a colectomía derecha laparoscópica. DISEÑO: Este fue un estudio observacional. ENTORNO CLINICO: Este fue un análisis post hoc de un ensayo controlado aleatorio, multicéntrico y prospectivo: ensayo RELARC (NCT02619942). PACIENTES: Todos los pacientes incluidos en el análisis de intención de tratar modificado en el ensayo RELARC fueron inscritos en este estudio. PRINCIPALES MEDIDAS DE RESULTADO: Los factores de riesgo de complicaciones posoperatorias se identificaron mediante análisis de regresión logística univariante y multivariable. RESULTADOS: De 995 pacientes, 206 (20,7%) tuvieron complicaciones postoperatorias. La comorbilidad (p = 0,02, OR: 1,544, IC 95%: 1,077–2,212) y el tiempo operatorio >180 min (p = 0,03, OR: 1,453, IC 95%: 1,032–2,044) fueron factores de riesgo independientes de complicaciones postoperatorias. Mientras que el sexo femenino (p = 0,04, OR: 0,704, IC 95%: 0,506–0,980) y la anastomosis extracorpórea (p < 0,001, OR: 0,251, IC 95%: 0,166–0,378) fueron factores protectores. 80 (8,0%) tenían infección general del sitio quirúrgico (ISQ), 53 (5,3%) tenían ISQ incisional y 33 (3,3%) tenían ISQ de órgano/espacio. Anastomosis latero-lateral fue un factor de riesgo para la ISQ general (p < 0,001, OR: 1,912, IC 95%: 1,118–3,268) y ISQ órgano/espacio (p = 0,005, OR: 3,579, IC 95%: 1,455–8.805). La anastomosis extracorpórea se asoció con un riesgo reducido de ISQ general (p < 0,001, OR: 0,239, IC 95%: 0,138–0,413), ISQ órgano/espacio (p = 0,002, OR: 0,296, IC 95%: 0,136–0,646), e ISQ incisional (p < 0,001, OR: 0,179, IC 95%: 0,099–0,322). Diabetes (p = 0,039, OR: 2,090, IC 95%: 1,039–4,205) y la conversión a cirugía abierta (p = 0,013, OR: 5,403, IC 95%: 1,437–20,319) fueron factores de riesgo para ISQ incisional. LIMITACIONES: Debido a la naturaleza retrospectiva, la limitación clave es la falta de documentación prospectiva y estandarización sobre el manejo perioperatorio de estos pacientes, como la optimización preoperatoria, los regímenes de preparación intestinal y los regímenes de antibióticos, que pueden ser factores de confusión de las complicaciones. Todas las cirugías fueron realizadas por cirujanos experimentados y los pacientes inscritos eran relativamente jóvenes, generalmente sanos y no obesos. No está claro si los resultados serán generalizables a las poblaciones obesas y de otro tipo en todo el mundo. CONCLUSIONES: Sexo masculino, comorbilidad, el tiempo operatorio prolongado y anastomosis intracorpórea fueron factores de riesgo independientes de complicaciones postoperatorias de la colectomía derecha laparoscópica. Anastomosis latero-lateral se asoció con un mayor riesgo de SSI de órgano/espacio. La anastomosis extracorpórea podría reducir la incidencia de ISQ general. La diabetes y la conversión a cirugía abierta se asociaron con un mayor riesgo de ISQ incisional. (Traducción— Dr. Francisco M. Abarca-Rendon)

PURPOSE: Internal iliac and obturator lymph nodes are common sites of metastasis in rectal cancer. This study developed a machine learning (ML) model using clinical data to predict lymph node metastasis and applied the Shapley Additive explanations (SHAP) method for interpretation. MATERIALS AND METHODS: Retrospectively, data from patients with rectal cancer at four Chinese centers—who underwent total mesorectal excision and lateral pelvic lymph node dissection without neoadjuvant therapy—were collected. Two centers provided training/test sets (3:1 ratio) and two centers supplied external validation. Lymph node enlargement was determined by imaging and confirmed by pathology. Five ML models were evaluated by AUC, accuracy, and F1 score. Key features included demographics, tumor stage, tumor-to-anal verge distance, imaging measurements, tumor histological differentiation, preoperative carcinoembryonic antigen, and carbohydrate antigen 19-9. SHAP was used to assess feature importance. RESULTS: Of the 411 cases (174 positives) in the training/test sets and 109 cases (43 positives) in external validation, the random forest (RF) model ranked second in terms of AUC and accuracy in the training set (0.999, 0.995), whereas it achieved the highest AUC and accuracy (0.877 and 0.788) in the test set. In the external validation, the RF model outperformed all other ML models (AUC of 0.899, accuracy of 0.827). Overall, the RF model demonstrates the superior overall performance. According to the SHAP analysis, the most important predictors of internal iliac and obturator lymph node metastasis were, in descending order, the short-axis diameter of enlarged lymph nodes, regional lymph node metastasis, and tumor-to-anal verge distance. At the individual patient level, SHAP force plots provided explanations of the RF model predictions for internal iliac and obturator lymph node metastasis. CONCLUSION: An interpretable ML model was developed that accurately predicts internal iliac and obturator lymph node metastasis using clinical data. SHAP analysis enhances understanding of feature contributions, supporting personalized treatment planning.