[Complicated gastric cancer and modern treatment approaches]. / Oslozhnennye formy raka zheludka ­ sovremennye podkhody k lecheniyu.

Among all patients with gastric cancer, 40% admit to the hospitals due to cancer-related complications. The most common complications of gastric cancer are bleeding (22-80%), malignant gastric outlet obstruction (26-60%), and perforation (less than 5%). The main treatment methods for gastric cancer complicated by bleeding are various forms of endoscopic hemostasis, transarterial embolization and external beam radiotherapy. Surgical treatment is possible in case of ineffective management. However, surgical algorithm is not standardized. Malignant gastric outlet stenosis requires decompression: endoscopic stenting, palliative gastroenterostomy. Surgical treatment is also possible (gastrectomy, proximal or distal resection of the stomach). The main problem for patients with complicated gastric cancer is the lack of standardized algorithms and abundance of potential surgical techniques. The aim of our review is to systematize available data on the treatment of complicated gastric cancer and to standardize existing methods.

Propensity score-matched retrospective cohort study of endoscopic ultrasound-guided gastroenterostomy and enteral stenting for malignant gastric outlet.

BACKGROUND: Symptomatic malignant gastric outlet obstruction (GOO) significantly reduce patients' quality of life. Endoscopic treatment involves enteral stenting or endoscopic ultrasonography to perform gastroenterostomy (EUS-GE). Aim was to compare enteral stenting with EUS-GE for endoscopic treatment of malignant GOO. METHODS: We retrospectively compared enteral stenting with EUS-GE for the treatment of malignant GOO. Patients treated at our institution were identified and a propensity score matching analysis was performed. Treatment failure was the primary outcome, while the secondary endpoints were time until treatment failure, technical and clinical success rates, and adverse event rates. RESULTS: Eighty-eight patients were included in the final analysis. Of whom, 44 were included in each of the two treatment groups. Treatment failure occurred significantly more frequently in the enteral stenting group (13/44) compared with the EUS-GE group (4/44; hazard ratio: 4,9; 95% CI 1.6-15.1). A Kaplan-Meier analysis revealed a median time until treatment failure of 22.0 weeks (95% CI 4.6-39.4) in the enteral stenting group compared with 76.0 weeks (95% CI 55.9-96.1) in the EUS-GE group (P = .002). No difference in technical success and clinical success was detected. Technical success was achieved in 43/44 patients (97.7%) in the enteral stenting group compared with 41/44 patients (93.2%) in the EUS-GE group, while clinical success was achieved in 32/44 (72.7%) and 35/44 (79.5%) patients, respectively. Nine adverse events were observed (9/44, 10.2%). There were no differences in 30-day adverse event rate and 30-day mortality rate. CONCLUSION: EUS-GE was superior to enteral stenting in the treatment of malignant GOO in terms of treatment failure and time until treatment failure in a propensity score-matched cohort.

Comparative efficacy of uncut Roux-en-Y and Billroth II anastomosis in gastrointestinal reconstruction following laparoscopic radical gastrectomy for distal gastric cancer.

This study retrospectively analyzed the clinical efficacy of Uncut Roux-en-Y and Billroth II anastomoses in gastrointestinal reconstruction following laparoscopic D2 radical gastrectomy for distal gastric cancer. The primary objective was to compare the postoperative outcomes, including quality of life and complication rates, between the 2 surgical techniques. One hundred patients diagnosed with distal gastric cancer were enrolled between June 2020 and May 2023. Patients underwent laparoscopic D2 gastrectomy and were categorized into either the Uncut Roux-en-Y or Billroth II anastomosis groups based on the technique used for gastrointestinal reconstruction. The inclusion and exclusion criteria were strictly followed. Surgical parameters, quality of life assessed using the Visick grading index, and postoperative complications were also evaluated. Statistical analyses were performed using SPSS version 27.0. The groups were comparable in terms of demographic and baseline clinical parameters. The Uncut Roux-en-Y group had a significantly longer duration of surgery (P < .001). However, there were no statistically significant differences in other surgical parameters. According to the Visick grading index, patients in the Uncut Roux-en-Y group reported a significantly better quality of life than those in the Billroth II group (P < .05). Additionally, Uncut Roux-en-Y was associated with a significantly lower incidence of dumping syndrome and bile reflux (P < .05). Although Uncut Roux-en-Y anastomosis requires longer surgical time, it offers significant advantages in terms of postoperative quality of life and reduced rates of dumping syndrome and bile reflux. Our findings suggest that Uncut Roux-en-Y may be a superior option for gastrointestinal reconstruction after laparoscopic D2 gastrectomy for distal gastric cancer.

Revealing Insights: A Comprehensive Overview of Gastric Outlet Obstruction Management, with Special Emphasis on EUS-Guided Gastroenterostomy.

Gastric outlet obstruction (GOO) poses a common and challenging clinical scenario, characterized by mechanical blockage in the pylorus, distal stomach, or duodenum, resulting in symptoms such as nausea, vomiting, abdominal pain, and early satiety. Its diverse etiology encompasses both benign and malignant disorders. The spectrum of current treatment modalities extends from conservative approaches to more invasive interventions, incorporating procedures like surgical gastroenterostomy (SGE), self-expandable metallic stents (SEMSs) placement, and the advanced technique of endoscopic ultrasound-guided gastroenterostomy (EUS-GE). While surgery is favored for longer life expectancy, stents are preferred in malignant gastric outlet stenosis. The novel EUS-GE technique, employing a lumen-apposing self-expandable metal stent (LAMS), combines the immediate efficacy of stents with the enduring benefits of gastroenterostomy. Despite its promising outcomes, EUS-GE is a technically demanding procedure requiring specialized expertise and facilities.

Quality of Life Following the Surgical Management of Gastric Cancer Using Patient-Reported Outcomes: A Systematic Review.

Introduction: Surgical management of gastric adenocarcinoma can have a drastic impact on a patient's quality of life (QoL). There is high variability among surgeons' preferences for the type of resection and reconstructive method. Peri-operative and cancer-specific outcomes remain equivalent between the different approaches. Therefore, postoperative quality of life can be viewed as a deciding factor for the surgical approach. The goal of this study was to interrogate patient QoL using patient-reported outcomes (PROs) following gastrectomy for gastric cancer. Methods: This systematic review was registered at Prospero and followed PRISMA guidelines. Medline, Embase, and Scopus were used to perform a literature search on 18 January 2020. A set of selection criteria and the data extraction sheet were predefined. Covidence (Melbourne, Australia) software was used; two reviewers (P.C.V. and E.J.) independently reviewed the articles, and a third resolved conflicts (A.B.F.). Results: The search yielded 1446 studies; 308 articles underwent full-text review. Ultimately, 28 studies were included for qualitative analysis, including 4630 patients. Significant heterogeneity existed between the studies. Geography was predominately East Asian (22/28 articles). While all aspects of quality of life were found to be affected by a gastrectomy, most functional or symptom-specific measures reached baseline by 6-12 months. The most significant ongoing symptoms were reflux, diarrhoea, and nausea/vomiting. Discussion: Generally, patients who undergo a gastrectomy return to baseline QoL by one year, regardless of the type of surgery or reconstruction. A subtotal distal gastrectomy is preferred when proper oncologic margins can be obtained. Additionally, no one form of reconstruction following gastrectomy is statistically preferred over another. However, for subtotal distal gastrectomy, there was a trend toward Roux-en-Y reconstruction as superior to abating reflux.

Uncut Roux-en-Y reconstruction after distal gastrectomy for gastric cancer.

BACKGROUND: Choosing an optimal reconstruction method is pivotal for patients with gastric cancer undergoing distal gastrectomy. The uncut Roux-en-Y reconstruction, a variant of the conventional Roux-en-Y approach (or variant of the Billroth II reconstruction), employs uncut devices to occlude the afferent loop of the jejunum. This modification is designed to mitigate postgastrectomy syndrome and enhance long-term functional outcomes. However, the comparative benefits and potential harms of this approach compared to other reconstruction techniques remain a topic of debate. OBJECTIVES: To assess the benefits and harms of uncut Roux-en-Y reconstruction after distal gastrectomy in patients with gastric cancer. SEARCH METHODS: We searched CENTRAL, PubMed, Embase, WanFang Data, China National Knowledge Infrastructure, and clinical trial registries for published and unpublished trials up to November 2023. We also manually reviewed references from relevant systematic reviews identified by our search. We did not impose any language restrictions. SELECTION CRITERIA: We included randomised controlled trials (RCTs) and quasi-RCTs comparing uncut Roux-en-Y reconstruction versus other reconstructions after distal gastrectomy for gastric cancer. The comparison groups encompassed other reconstructions such as Billroth I, Billroth II (with or without Braun anastomosis), and Roux-en-Y reconstruction. DATA COLLECTION AND ANALYSIS: We used standard Cochrane methodological procedures. The critical outcomes included health-related quality of life at least six months after surgery, major postoperative complications within 30 days after surgery according to the Clavien-Dindo Classification (grades III to V), anastomotic leakage within 30 days, changes in body weight (kg) at least six months after surgery, and incidence of bile reflux, remnant gastritis, and oesophagitis at least six months after surgery. We used the GRADE approach to evaluate the certainty of the evidence. MAIN RESULTS: We identified eight trials, including 1167 participants, which contributed data to our meta-analyses. These trials were exclusively conducted in East Asian countries, predominantly in China. The studies varied in the types of uncut devices used, ranging from 2- to 6-row linear staplers to suture lines. The follow-up periods for long-term outcomes spanned from 3 months to 42 months, with most studies focusing on a 6- to 12-month range. We rated the certainty of evidence from low to very low. Uncut Roux-en-Y reconstruction versus Billroth II reconstruction In the realm of surgical complications, very low-certainty evidence suggests that uncut Roux-en-Y reconstruction compared with Billroth II reconstruction may make little to no difference to major postoperative complications (risk ratio (RR) 0.98, 95% confidence interval (CI) 0.24 to 4.05; I² = 0%; risk difference (RD) 0.00, 95% CI -0.04 to 0.04; I² = 0%; 2 studies, 282 participants; very low-certainty evidence) and incidence of anastomotic leakage (RR 0.64, 95% CI 0.29 to 1.44; I² not applicable; RD -0.00, 95% CI -0.03 to 0.02; I² = 32%; 3 studies, 615 participants; very low-certainty evidence). We are very uncertain about these results. Focusing on long-term outcomes, low- to very low-certainty evidence suggests that uncut Roux-en-Y reconstruction compared with Billroth II reconstruction may make little to no difference to changes in body weight (mean difference (MD) 0.04 kg, 95% CI -0.84 to 0.92 kg; I² = 0%; 2 studies, 233 participants; low-certainty evidence), may reduce the incidence of bile reflux into the remnant stomach (RR 0.67, 95% CI 0.55 to 0.83; RD -0.29, 95% CI -0.43 to -0.16; number needed to treat for an additional beneficial outcome (NNTB) 4, 95% CI 3 to 7; 1 study, 141 participants; low-certainty evidence), and may have little or no effect on the incidence of remnant gastritis (RR 0.27, 95% CI 0.01 to 5.06; I2 = 78%; RD -0.15, 95% CI -0.23 to -0.07; I2 = 0%; NNTB 7, 95% CI 5 to 15; 2 studies, 265 participants; very low-certainty evidence). No studies reported on quality of life or the incidence of oesophagitis. Uncut Roux-en-Y reconstruction versus Roux-en-Y reconstruction In the realm of surgical complications, very low-certainty evidence suggests that uncut Roux-en-Y reconstruction compared with Roux-en-Y reconstruction may make little to no difference to major postoperative complications (RR 4.74, 95% CI 0.23 to 97.08; I² not applicable; RD 0.01, 95% CI -0.02 to 0.04; I² = 0%; 2 studies, 256 participants; very low-certainty evidence) and incidence of anastomotic leakage (RR 0.34, 95% CI 0.05 to 2.08; I² = 0%; RD -0.02, 95% CI -0.06 to 0.02; I² = 0%; 2 studies, 213 participants; very low-certainty evidence). We are very uncertain about these results. Focusing on long-term outcomes, very low-certainty evidence suggests that uncut Roux-en-Y reconstruction compared with Roux-en-Y reconstruction may increase the incidence of bile reflux into the remnant stomach (RR 10.74, 95% CI 3.52 to 32.76; RD 0.57, 95% CI 0.43 to 0.71; NNT for an additional harmful outcome (NNTH) 2, 95% CI 2 to 3; 1 study, 108 participants; very low-certainty evidence) and may make little to no difference to the incidence of remnant gastritis (RR 1.18, 95% CI 0.69 to 2.01; I² = 60%; RD 0.03, 95% CI -0.03 to 0.08; I² = 0%; 3 studies, 361 participants; very low-certainty evidence) and incidence of oesophagitis (RR 0.82, 95% CI 0.53 to 1.26; I² = 0%; RD -0.02, 95% CI -0.07 to 0.03; I² = 0%; 3 studies, 361 participants; very low-certainty evidence). We are very uncertain about these results. Data were insufficient to assess the impact on quality of life and changes in body weight. AUTHORS' CONCLUSIONS: Given the predominance of low- to very low-certainty evidence, this Cochrane review faces challenges in providing definitive clinical guidance. We found the majority of critical outcomes may be comparable between the uncut Roux-en-Y reconstruction and other methods, but we are very uncertain about most of these results. Nevertheless, it indicates that uncut Roux-en-Y reconstruction may reduce the incidence of bile reflux compared to Billroth-II reconstruction, albeit with low certainty. In contrast, compared to Roux-en-Y reconstruction, uncut Roux-en-Y may increase bile reflux incidence, based on very low-certainty evidence. To strengthen the evidence base, further rigorous and long-term trials are needed. Additionally, these studies should explore variations in surgical procedures, particularly regarding uncut devices and methods to prevent recanalisation. Future research may potentially alter the conclusions of this review.

Optimal reconstruction methods after distal gastrectomy for gastric cancer: a protocol for a systematic review and network meta-analysis update.

BACKGROUND: Distal gastrectomy (DG) is a commonly used surgical procedure for gastric cancer (GC), with three reconstruction methods available: Billroth I, Billroth II, and Roux-en-Y. In 2018, our team published a systematic review to provide guidance for clinical practice on the optimal reconstruction method after DG for GC. However, since then, new evidence from several randomized controlled trials (RCTs) has emerged, prompting us to conduct an updated systematic review and network meta-analysis to provide the latest comparative estimates of the efficacy and safety of the three reconstruction methods after DG for GC. METHOD: This systematic review and network meta-analysis update followed the PRISMA-P guidelines and will include a search of PubMed, Embase, and the Cochrane Library for RCTs comparing the outcomes of Billroth I, Billroth II, or Roux-en-Y reconstruction after DG for patients with GC. Two independent reviewers will screen the titles and abstracts based on predefined eligibility criteria, and two reviewers will assess the full texts of relevant studies. The Bayesian network meta-analysis will evaluate various outcomes, including quality of life after surgery, anastomotic leakage within 30 days after surgery, operation time, intraoperative blood loss, major postoperative complications within 30 days after surgery, incidence and severity of bile reflux, and loss of body weight from baseline. ETHICS AND DISSEMINATION: The review does not require ethical approval. The findings of the review will be disseminated through publication in an academic journal, presentations at conferences, and various media outlets. INPLASY REGISTRATION NUMBER: INPLASY2021100060.

Risk factors for abdominal surgical infectious complications after distal gastrectomy for gastric cancer: A post-hoc analysis of a randomized controlled trial (JCOG0912).

BACKGROUND: Abdominal surgical infectious complications (ASIC) after gastrectomy for gastric cancer impair patients' survival and quality of life. JCOG0912 was conducted to compare laparoscopy-assisted distal gastrectomy with open distal gastrectomy for clinical stage IA or IB gastric cancer. The present study aimed to identify risk factors for ASIC using prospectively collected data. METHODS: We performed a post-hoc analysis of the risk factors for ASIC using the dataset from JCOG0912. All complications were evaluated according to the Clavien-Dindo classification (CD). ASIC was defined as CD grade I or higher anastomotic leakage, pancreatic fistula, abdominal abscess, and wound infection. Analyses were performed using the logistic regression model for univariable and multivariable analyses. RESULTS: A total of 910 patients were included (median age, 63 years; male sex, 61 %). Among them, ASIC occurred in 5.8 % of patients. In the univariable analysis, male sex (odds ratio [OR] 2.855, P = 0.003), diabetes (OR 2.565, P = 0.029), and Roux-en-Y (R-Y) reconstruction (vs. Billroth Ⅰ, OR 2.707, P = 0.002) were significant risk factors for ASIC. In the multivariable analysis, male sex (OR 2.364, P = 0.028) and R-Y reconstruction (vs. Billroth Ⅰ, OR 2.310, P = 0.015) were independent risk factors for ASIC. CONCLUSIONS: Male sex and R-Y reconstruction were risk factors for ASIC after distal gastrectomy. Therefore, when performing surgery on male patients or when R-Y reconstruction is selected after gastrectomy for gastric cancer, surgeons should pay special attention to prevent ASIC.

Intragastric free cancer cells may be attached to automatic staplers during anastomosis in patients with gastric cancer.

BACKGROUND: Automatic staplers are often used to reconstruct the digestive tract during surgeries for gastric cancer. Intragastric free cancer cells adhering to automatic staplers may come in contact with the laparoscopic port area and progress to port site recurrence. This study aimed to investigate the presence/absence of cancer cells adhering to automatic staplers during gastric cancer surgery using cytological examinations. We further determined the positive predictive clinicopathological factors and clinical implications of free cancer cells attached to automatic staplers. METHODS: This study included 101 patients who underwent distal gastrectomy for gastric cancer. Automatic staplers used for anastomosis in gastric cancer surgeries were shaken in 150 ml of saline solution to collect the attached cells. Papanicolaou stains were performed. We tested the correlation between cancer-cell positivity and clinicopathological factors to identify risk factors arising from the presence of attached cancer cells to the staplers. RESULTS: Based on the cytology, cancer cells were detected in 7 of 101 (6.9%) stapler washing fluid samples. Univariate analysis revealed that circular staplers, type 1 tumors, and positive lymph nodes were significantly associated with higher detection of free cancer cells adhering to staplers. No significant differences in other factors were detected. Of the seven cases with positive cytology, one developed anastomotic recurrence. CONCLUSIONS: Exfoliated cancer cells adhered to the automatic staplers used for anastomoses in 6.9% of the staplers used for distal gastrectomies in patients with gastric cancer. Staplers used for gastric cancer surgeries should be handled carefully.

Book-Binding Technique in Totally Laparoscopic Distal Gastrectomy with Billroth I Reconstruction: Clinical Results and Outcomes in 188 Patients with Gastric Cancer.

BACKGROUND: Laparoscopic gastrectomy is widely used as a curative treatment for gastric cancer. Although delta-shaped anastomosis is commonly used for Billroth I anastomosis after totally laparoscopic distal gastrectomy (TLDG), it has some drawbacks. The book-binding technique (BBT) was developed as an alternative, and this study aimed to examine its short-term results in 188 consecutive cases. STUDY DESIGN: This retrospective study included patients who underwent BBT reconstruction after TLDG for gastric malignancy between 2011 and 2020. BBT is a technique for intracorporeal gastroduodenostomy, which is a triangular anastomosis with a linear stapler that does not require additional dissection or rotation of the duodenum. The short-term outcomes of BBT reconstruction and postoperative endoscopic findings were analyzed. RESULTS: This study evaluated 188 patients who underwent TLDG and BBT reconstruction. Anastomotic stenosis and leakage occurred in 1.1% and 0.5% of the patients, respectively. The median time to the first diet was 3.1 days, and the median postoperative hospital stay was 11.9 days. BBT anastomoses were performed by 19 surgeons and took an average of 32.8 minutes to complete, with completion times decreasing as the surgical team became more proficient. On endoscopy performed 1 year postoperatively, 5.2% had reflux esophagitis (grade A or higher), 67.8% had gastritis (grade 1 or higher), 37.4% had residual food (grade 1 or higher), and 37.4% had bile reflux (grade 1). CONCLUSIONS: BBT is a safe and feasible method for intracorporeal gastroduodenostomy in TLDG for patients with gastric malignancy and demonstrates good surgical outcomes.

Endoscopic ultrasonography-guided gastroenterostomy versus uncovered duodenal metal stenting for unresectable malignant gastric outlet obstruction (DRA-GOO): a multicentre randomised controlled trial.

BACKGROUND: Endoscopic ultrasonography-guided gastroenterostomy (EUS-GE) is a novel endoscopic method to palliate malignant gastric outlet obstruction. We aimed to assess whether the use of EUS-GE with a double balloon occluder for malignant gastric outlet obstruction could reduce the need for reintervention within 6 months compared with conventional duodenal stenting. METHODS: The was an international, multicentre, randomised, controlled trial conducted at seven sites in Hong Kong, Belgium, Brazil, India, Italy, and Spain. Consecutive patients (aged ≥18 years) with malignant gastric outlet obstruction due to unresectable primary gastroduodenal or pancreatobiliary malignancies, a gastric outlet obstruction score (GOOS) of 0 (indicating an inability in intake food or liquids orally), and an Eastern Cooperative Oncology Group performance status score of 3 or lower were included and randomly allocated (1:1) to receive either EUS-GE or duodenal stenting. The primary outcome was the 6-month reintervention rate, defined as the percentage of patients requiring additional endoscopic intervention due to stent dysfunction (ie, restenosis of the stent due to tumour ingrowth, tumour overgrowth, or food residue; stent migration; or stent fracture) within 6 months, analysed in the intention-to-treat population. Prespecified secondary outcomes were technical success (successful placement of a stent), clinical success (1-point improvement in gastric outlet obstruction score [GOOS] within 3 days), adverse events within 30 days, death within 30 days, duration of stent patency, GOOS at 1 month, and quality-of-life scores. This study is registered with ClinicalTrials.gov (NCT03823690) and is completed. FINDINGS: Between Dec 1, 2020, and Feb 28, 2022, 185 patients were screened and 97 (46 men and 51 women) were recruited and randomly allocated (48 to the EUS-GE group and 49 to the duodenal stent group). Mean age was 69·5 years (SD 12·6) in the EUS-GE group and 64·8 years (13·0) in the duodenal stent group. All randomly allocated patients completed follow-up and were analysed. Reintervention within 6 months was required in two (4%) patients in the EUS-GE group and 14 (29%) in the duodenal stent group [p=0·0020; risk ratio 0·15 [95% CI 0·04-0·61]). Stent patency was longer in the EUS-GE group (median not reached in either group; HR 0·13 [95% CI 0·08-0·22], log-rank p<0·0001). 1-month GOOS was significantly better in the EUS-GE group (mean 2·41 [SD 0·7]) than the duodenal stent group (1·91 [0·9], p=0·012). There were no statistically significant differences between the EUS-GE and duodenal stent groups in death within 30 days (ten [21%] vs six [12%] patients, respectively, p=0·286), technical success, clinical success, or quality-of-life scores at 1 month. Adverse events occurred 11 (23%) patients in the EUS-GE group and 12 (24%) in the duodenal stent group within 30 days (p=1·00); three cases of pneumonia (two in the EUS-GE group and one in the duodenal stent group) were considered to be procedure related. INTERPRETATION: In patients with malignant gastric outlet obstruction, EUS-GE can reduce the frequency of reintervention, improve stent patency, and result in better patient-reported eating habits compared with duodenal stenting, and the procedure should be used preferentially over duodenal stenting when expertise and required devices are available. FUNDING: Research Grants Council (Hong Kong Special Administrative Region, China) and Sociedad Española de Endoscopia Digestiva.

Automatic surgical phase recognition-based skill assessment in laparoscopic distal gastrectomy using multicenter videos.

BACKGROUND: Gastric surgery involves numerous surgical phases; however, its steps can be clearly defined. Deep learning-based surgical phase recognition can promote stylization of gastric surgery with applications in automatic surgical skill assessment. This study aimed to develop a deep learning-based surgical phase-recognition model using multicenter videos of laparoscopic distal gastrectomy, and examine the feasibility of automatic surgical skill assessment using the developed model. METHODS: Surgical videos from 20 hospitals were used. Laparoscopic distal gastrectomy was defined and annotated into nine phases and a deep learning-based image classification model was developed for phase recognition. We examined whether the developed model's output, including the number of frames in each phase and the adequacy of the surgical field development during the phase of supra-pancreatic lymphadenectomy, correlated with the manually assigned skill assessment score. RESULTS: The overall accuracy of phase recognition was 88.8%. Regarding surgical skill assessment based on the number of frames during the phases of lymphadenectomy of the left greater curvature and reconstruction, the number of frames in the high-score group were significantly less than those in the low-score group (829 vs. 1,152, P < 0.01; 1,208 vs. 1,586, P = 0.01, respectively). The output score of the adequacy of the surgical field development, which is the developed model's output, was significantly higher in the high-score group than that in the low-score group (0.975 vs. 0.970, P = 0.04). CONCLUSION: The developed model had high accuracy in phase-recognition tasks and has the potential for application in automatic surgical skill assessment systems.