Use of artificial intelligence for the prediction of lymph node metastases in early-stage colorectal cancer: systematic review.

BACKGROUND: Risk evaluation of lymph node metastasis for early-stage (T1 and T2) colorectal cancers is critical for determining therapeutic strategies. Traditional methods of lymph node metastasis prediction have limited accuracy. This systematic review aimed to review the potential of artificial intelligence in predicting lymph node metastasis in early-stage colorectal cancers. METHODS: A comprehensive search was performed of papers that evaluated the potential of artificial intelligence in predicting lymph node metastasis in early-stage colorectal cancers. Studies were appraised using the Joanna Briggs Institute tools. The primary outcome was summarizing artificial intelligence models and their accuracy. Secondary outcomes included influential variables and strategies to address challenges. RESULTS: Of 3190 screened manuscripts, 11 were included, involving 8648 patients from 1996 to 2023. Due to diverse artificial intelligence models and varied metrics, no data synthesis was performed. Models included random forest algorithms, support vector machine, deep learning, artificial neural network, convolutional neural network and least absolute shrinkage and selection operator regression. Artificial intelligence models' area under the curve values ranged from 0.74 to 0.9993 (slide level) and 0.9476 to 0.9956 (single-node level), outperforming traditional clinical guidelines. CONCLUSION: Artificial intelligence models show promise in predicting lymph node metastasis in early-stage colorectal cancers, potentially refining clinical decisions and improving outcomes. PROSPERO REGISTRATION NUMBER: CRD42023409094.

Textbook outcomes for liver resection: can a medium sized centre have acceptable outcomes?

BACKGROUND: Textbook outcome (TO) is an objective, composite measure of clinical outcomes in surgery. TO in liver surgery has been used in previous international studies to define and compare performance across centres. This study aimed to review TO rates following liver resection at a single institution. The secondary aim was to use a CuSum analysis to evaluate monitoring of performance quality over time for colorectal cancer liver metastases (CRCLM). METHODS: All patients undergoing liver resection for benign and malignant causes from Christchurch Hospital hepatobiliary unit between 2005 and 2022 were included. Textbook outcomes measures were the absence of; intraoperative incidents, Clavien-Dindo >3 complication, 90 day re-admission, 90 day mortality, R1 resection, and post-operative bile leak/liver failure. Sequential CuSum analysis was performed to review achievement of TO in liver resections for colorectal cancer liver metastases (CRCLM). RESULTS: Four hundred and seventy-eight patients were included in this study, 54 had resection for benign pathology, 290 for CRCLM and 134 for other malignancies. TO was achieved in 74% of cases overall, with rates for benign, CRCLM and other malignancy being 82%, 73% and 74% respectively (P = 0.405). CuSum analysis documented a deterioration in performance after patient 60, with return to baseline by end of study period. CONCLUSIONS: TO for liver resection in a medium sized centre in New Zealand are comparable to published rates. It is possible to use process control techniques like CuSum with the binary result of TO to monitor performance, providing opportunity for continuous improvement in surgical units.

Quality of life in early-onset colorectal cancer patients: systematic review.

BACKGROUND: There is an increasing incidence of early-onset colorectal cancer; however, the psychosocial impacts of this disease on younger adults have been seldom explored. METHODS: A systematic review was conducted according to the PRISMA guidelines. The Cochrane Central Register of Controlled Trials, MEDLINE, Embase, CINAHL, PubMed, and Scopus were searched, and papers were included if published in English within the last 10 years and if they reported results separately by age (including early-onset colorectal cancer, defined as colorectal cancer diagnosed before the age of 50 years). Critical appraisal of all studies was done using the Joanna Briggs Institute tools. The primary outcome of interest was the global quality of life in patients with early-onset colorectal cancer. Secondary outcomes included the effect on sexual function, body image, finances, career, emotional distress, and social and family functioning. RESULTS: The search yielded 168 manuscripts and 15 papers were included in the review after screening. All studies were observational, and included a total of 18 146 patients, of which 5015 were patients with early-onset colorectal cancer. The studies included scored highly using Joanna Briggs Institute critical appraisal tools, indicating good quality and a low risk of bias, but data synthesis was not performed due to the wide range of scoring systems that were used across the studies. Six papers reported significant negative impacts on quality of life in patients with early-onset colorectal cancer. Three of the four studies that compared the quality of life in patients with early-onset colorectal cancer with older patients found that the younger group had worse mean quality-of-life scores (P ≤ 0.05). Secondary outcomes measured in five studies in relation to sexual dysfunction, body image, financial and career impacts, and social and family impacts and in eight studies in relation to emotional distress were found to be more severely impacted in those with early-onset colorectal cancer compared with those with late-onset colorectal cancer. CONCLUSION: Whilst data are limited, the impact of colorectal cancer is different in patients with early-onset colorectal cancer compared with older patients in relation to several aspects of the quality of life. This is particularly prominent in areas of global quality of life, sexual functioning, family concerns, and financial impacts.