Lara Rimmer1, Callum Howard2, Leonardo Picca2, Mohamad Bashir3. 1. Vascular Surgery Department, Royal Blackburn Teaching Hospital, Haslingden Road, Blackburn, BB23HH, UK. lararimmer@gmail.com. 2. Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, UK. 3. Vascular Surgery Department, Royal Blackburn Teaching Hospital, Haslingden Road, Blackburn, BB23HH, UK.
Abstract
BACKGROUND: Artificial intelligence (AI) is a field involving computational simulation of human intelligence processes; these applications of deep learning could have implications in the specialty of emergency surgery (ES). ES is a rapidly advancing area, and this review will outline the most recent advances. METHODS: A literature search encompassing the uses of AI in surgery was conducted across large databases (Pubmed, OVID, SCOPUS). Two doctors (LR, CH) both collated relevant papers and appraised them. Papers included were published within the last 5 years, and a "snowball effect" used to collate further relevant literature. RESULTS: AI has been shown to provide value in predicting surgical outcomes and giving personalised patient risks based on inputted data. Further to this, image recognition technology within AI has showed success in fracture identification and breast cancer diagnosis. Regarding theatre presence, supervised robots have carried out suturing and anastomosis of bowel in controlled environments to a high standard. CONCLUSION: AI has potential for integration across surgical services, from diagnosis to treatment, and aiding the surgeon in key decision-making for risks per patient. Fully automated surgery may be the future, but at present, AI needs human supervision.
BACKGROUND: Artificial intelligence (AI) is a field involving computational simulation of human intelligence processes; these applications of deep learning could have implications in the specialty of emergency surgery (ES). ES is a rapidly advancing area, and this review will outline the most recent advances. METHODS: A literature search encompassing the uses of AI in surgery was conducted across large databases (Pubmed, OVID, SCOPUS). Two doctors (LR, CH) both collated relevant papers and appraised them. Papers included were published within the last 5 years, and a "snowball effect" used to collate further relevant literature. RESULTS: AI has been shown to provide value in predicting surgical outcomes and giving personalised patient risks based on inputted data. Further to this, image recognition technology within AI has showed success in fracture identification and breast cancer diagnosis. Regarding theatre presence, supervised robots have carried out suturing and anastomosis of bowel in controlled environments to a high standard. CONCLUSION: AI has potential for integration across surgical services, from diagnosis to treatment, and aiding the surgeon in key decision-making for risks per patient. Fully automated surgery may be the future, but at present, AI needs human supervision.
Entities:
Keywords:
Artificial intelligence (AI); Big data; Emergency surgery (ES); Machine learning
Authors: Karl Y Bilimoria; Yaoming Liu; Jennifer L Paruch; Lynn Zhou; Thomas E Kmiecik; Clifford Y Ko; Mark E Cohen Journal: J Am Coll Surg Date: 2013-09-18 Impact factor: 6.113
Authors: Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun Journal: Nature Date: 2017-01-25 Impact factor: 49.962
Authors: Jakub Olczak; Niklas Fahlberg; Atsuto Maki; Ali Sharif Razavian; Anthony Jilert; André Stark; Olof Sköldenberg; Max Gordon Journal: Acta Orthop Date: 2017-07-06 Impact factor: 3.717