Prediction of pouchitis after ileal pouch-anal anastomosis in patients with ulcerative colitis using artificial intelligence and deep learning.

BACKGROUND: Pouchitis is one of the major postoperative complications of ulcerative colitis (UC), and it is still difficult to predict the development of pouchitis after ileal pouch-anal anastomosis (IPAA) in UC patients. In this study, we examined whether a deep learning (DL) model could predict the development of pouchitis. METHODS: UC patients who underwent two-stage restorative proctocolectomy with IPAA at Keio University Hospital were included in this retrospective analysis. The modified pouchitis disease activity index (mPDAI) was evaluated by the clinical and endoscopic findings. Pouchitis was defined as an mPDAI ≥ 5.860; endoscopic pouch images before ileostomy closure were collected. A convolutional neural network was used as the DL model, and the prediction rates of pouchitis after ileostomy closure were evaluated by fivefold cross-validation. RESULTS: A total of 43 patients were included (24 males and 19 females, mean age 39.2 ± 13.2 years). Pouchitis occurred in 14 (33%) patients after ileostomy closure. In less than half of the patients, mPDAI scores matched before and after ileostomy closure. Most of patients whose mPDAI scores did not match before and after ileostomy closure had worse mPDAI scores after than before. The prediction rate of pouchitis calculated by the area under the curve using the DL model was 84%. Conversely, the prediction rate of pouchitis using mPDAI before ileostomy closure was 62%. CONCLUSION: The prediction rate of pouchitis using the DL model was more than 20% higher than that using mPDAI, suggesting the utility of the DL model as a prediction model for the development of pouchitis. It could also be used to determine early interventions for pouchitis.

Safety and feasibility of laparoscopic surgery for elderly rectal cancer patients in Japan: a nationwide study.

BACKGROUND: This study aimed to analyse the perioperative results from a national dataset of rectal cancer resections in elderly patients. METHODS: The clinical records of patients undergoing rectal cancer surgery between 2012 and 2014 were retrieved from the Japanese National Clinical Database and analysed retrospectively. Patients were categorized according to age and those 80 years or older were defined as elderly. Subgroups were also defined according to the surgical approach (laparoscopy versus open surgery). The short-term outcomes, including mortality, anastomotic leak, surgical site infections and medical complications were compared between subgroups. RESULTS: Of 56 175 patients undergoing rectal cancer surgery, some 6717 patients were elderly and laparoscopy was performed in 46.8 per cent of the sample. When comparing laparoscopy and open surgery in elderly patients, the operative mortality rate (1.5 versus 2.8 per cent; P < 0.001), the incidence of anastomotic leakage (5.2 versus 6.5 per cent; P = 0.026), surgical site infections (6.0 versus 8.0 per cent; P = 0.001), pneumonia (1.4 versus 2.5 per cent; P = 0.001), renal failure (0.7 versus 1.3 per cent; P = 0.016) and cardiac events (0.3 versus 0.8 per cent; P = 0.008) were lower for laparoscopy than for open surgery. The overall complication rate in elderly patients (19.5 per cent) was comparable to that in the younger group (P = 0.07). However, incidence of systemic complications was significantly higher in elderly than in younger patients (all P < 0.001). CONCLUSION: Laparoscopy was safe and feasible in elderly patients compared with open surgery. However, the rates of systemic complications were significantly higher than in younger patients.

Meta-analysis of the risk of small bowel obstruction following open or laparoscopic colorectal surgery.

BACKGROUND: One of the potential advantages of laparoscopic compared with open colorectal surgery is a reduction in postoperative bowel obstruction events. Early reports support this proposal, but accumulated evidence is lacking. METHODS: A systematic review and meta-analysis was performed of randomized clinical trials and observational studies by searching the PubMed and Cochrane Library databases from 1990 to August 2015. The primary outcomes were early and late postoperative bowel obstruction following laparoscopic and open colorectal surgery. Both ileus and bowel obstruction were defined as a postoperative bowel obstruction. Subgroup and sensitivity analyses were performed, and a random-effects model was used to account for the heterogeneity among the studies. RESULTS: Twenty-four randomized clinical trials and 88 observational studies were included in the meta-analysis; 106 studies reported early outcome and 12 late outcome. Collectively, these studies reported on the outcomes of 148 392 patients, of whom 58 133 had laparoscopic surgery and 90 259 open surgery. Compared with open surgery, laparoscopic surgery was associated with reduced rates of early (odds ratio 0·62, 95 per cent c.i. 0·54 to 0·72; P < 0·001) and late (odds ratio 0·61, 0·41 to 0·92; P = 0·019) postoperative bowel obstruction. Weighted mean values for early postoperative bowel obstruction were 8 (95 per cent c.i. 6 to 10) and 5 (3 to 7) per cent for open and laparoscopic surgery respectively, and for late bowel obstruction were 4 (2 to 6) and 3 (1 to 5) per cent respectively. CONCLUSION: The reduction in postoperative bowel obstruction demonstrates an advantage of laparoscopic surgery in patients with colorectal disease.