Development of artificial blood loss and duration of excision score to evaluate surgical difficulty of total laparoscopic anterior resection in rectal cancer

Spurred by advances in processing power, memory, storage, and an unprecedented wealth of data, computers are being asked to tackle increasingly complex learning tasks, often with astonishing success. Computers have now mastered a popular variant of poker, learned the laws of physics from experimental data, and become experts in video games - tasks that would have been deemed impossible not too long ago. In parallel, the number of companies centered on applying complex data analysis to varying industries has exploded, and it is thus unsurprising that some analytic companies are turning attention to problems in health care. The purpose of this review is to explore what problems in medicine might benefit from such learning approaches and use examples from the literature to introduce basic concepts in machine learning. It is important to note that seemingly large enough medical data sets and adequate learning algorithms have been available for many decades, and yet, although there are thousands of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Thus, part of my effort will be to identify what obstacles there may be to changing the practice of medicine through statistical learning approaches, and discuss how these might be overcome.

The STROCSS guideline was developed in 2017 to improve the reporting quality of observational studies in surgery. Building on its impact and usefulness, we sought to update the guidelines two years after its publication.

Laparoscopic surgery as an alternative to open surgery in patients with rectal cancer has not yet been shown to be oncologically safe. The aim in the COlorectal cancer Laparoscopic or Open Resection (COLOR II) trial was to compare laparoscopic and open surgery in patients with rectal cancer. A non-inferiority phase 3 trial was undertaken at 30 centres and hospitals in eight countries. Patients (aged ≥18 years) with rectal cancer within 15 cm from the anal verge without evidence of distant metastases were randomly assigned to either laparoscopic or open surgery in a 2:1 ratio, stratified by centre, location of tumour, and preoperative radiotherapy. The study was not masked. Secondary (short-term) outcomes-including operative findings, complications, mortality, and results at pathological examination-are reported here. Analysis was by modified intention to treat, excluding those patients with post-randomisation exclusion criteria and for whom data were not available. This study is registered with ClinicalTrials.gov, number NCT00297791. The study was undertaken between Jan 20, 2004, and May 4, 2010. 1103 patients were randomly assigned to the laparoscopic (n=739) and open surgery groups (n=364), and 1044 were eligible for analyses (699 and 345, respectively). Patients in the laparoscopic surgery group lost less blood than did those in the open surgery group (median 200 mL [IQR 100-400] vs 400 mL [200-700], p<0·0001); however, laparoscopic procedures took longer (240 min [184-300] vs 188 min [150-240]; p<0·0001). In the laparoscopic surgery group, bowel function returned sooner (2·0 days [1·0-3·0] vs 3·0 days [2·0-4·0]; p<0·0001) and hospital stay was shorter (8·0 days [6·0-13·0] vs 9·0 days [7·0-14·0]; p=0·036). Macroscopically, completeness of the resection was not different between groups (589 [88%] of 666 vs 303 [92%] of 331; p=0·250). Positive circumferential resection margin (<2 mm) was noted in 56 (10%) of 588 patients in the laparoscopic surgery group and 30 (10%) of 300 in the open surgery group (p=0·850). Median tumour distance to distal resection margin did not differ significantly between the groups (3·0 cm [IQR 2·0-4·8] vs 3·0 cm [1·8-5·0], respectively; p=0·676). In the laparoscopic and open surgery groups, morbidity (278 [40%] of 697 vs 128 [37%] of 345, respectively; p=0·424) and mortality (eight [1%] of 699 vs six [2%] of 345, respectively; p=0·409) within 28 days after surgery were similar. In selected patients with rectal cancer treated by skilled surgeons, laparoscopic surgery resulted in similar safety, resection margins, and completeness of resection to that of open surgery, and recovery was improved after laparoscopic surgery. Results for the primary endpoint-locoregional recurrence-are expected by the end of 2013. Ethicon Endo-Surgery Europe, Swedish Cancer Foundation, West Gothia Region, Sahlgrenska University Hospital. Copyright © 2013 Elsevier Ltd. All rights reserved.