Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia.

OBJECTIVES: There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. METHODS: An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). RESULTS: In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. CONCLUSIONS: The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.

Does the Internet promote the unregulated use of fecal microbiota transplantation: a potential public health issue?

INTRODUCTION: The Internet has become an increasingly popular resource for medical information. Fecal microbiota transplantation (FMT) has changed the treatment of Clostridium difficile with cure rates of 81% following one infusion of FMT, further studies have since validated these findings. The Medicines and Health care Products Regulatory Agency has classified FMT as a medicine and hence should be only utilized in strict clinical settings. METHODS: We searched Facebook, Twitter, Google, and YouTube using the words "Faecal Microbiota Transplantation" and "FMT". We utilized the first 50 hits on each site. We analyzed the percentage of articles that fell outside regulated medical practice. We searched how many clinics in the UK advertised practice that falls outside suggested guidelines. RESULTS: Google, YouTube, and Facebook had a variety of information regarding FMT available. Nine out of 50 (18%) of the top 50 google searches can be considered articles that fall outside regulated practice. YouTube highlighted four videos describing how to self-administer FMT, one of these was for ulcerative colitis. Fourteen percent of the top 50 YouTube videos fall outside regulated practice and 8% of the top 50 Facebook searches fall outside regulated clinical practice. There were two clinics in the UK advertising FMT for uses that fall outside regulated practice. CONCLUSION: Clinicians and patients need to be aware of the resources available through social media and the Internet. It should be appreciated that some websites fall outside regulated clinical practice. Private clinics offering FMT need to ensure that they are offering FMT within a regulated framework.

Tumor-associated macrophages promote Ezrin phosphorylation-mediated epithelial-mesenchymal transition in lung adenocarcinoma through FUT4/LeY up-regulation.

Tumor-associated macrophages (TAMs) are key components of tumor microenvironment (TME) during tumorigenesis and progression. However, the role of TAMs in lung adenocarcinoma is still unclear. In this study, we aimed to clarify the mechanism underlying the crosstalk between TAMs and epithelial-mesenchymal transition (EMT) of lung adenocarcinoma. Fucosyltransferase IV (FUT4) and its synthetic cancer sugar antigen Lewis Y (LeY) was aberrantly elevated in various solid tumors, it plays critical role in the invasion and metastasis. Here, we found that in lung adenocarcinoma samples, the density of TAMs correlates with E-cadherin level and LeY level. In vitro assays, M2 macrophages promoted FUT4/LeY expression through the transforming growth factor-ß1(TGF-ß1)/Smad2/3 signaling pathway. FUT4/LeY was indispensable in M2 macrophages-mediated cytoskeletal remodeling and EMT. Furthermore, fucosylation of Ezrin mediated by FUT4/LeY can promote the phosphorylation of Ezrin, which was the critical mechanism of M2 macrophages-induced EMT. In vivo assays confirmed that M2 macrophages promoted EMT through the up-regulation of LeY and phosphorylated Ezrin. Together, our results revealed that TAMs promote Ezrin phosphorylation-mediated EMT in lung adenocarcinoma through FUT4/LeY- mediated fucosylation. Targeting this newly identified signaling may offer new possibilities for immunotherapy in lung adenocarcinoma.