Detecting Task Difficulty of Learners in Colonoscopy: Evidence from Eye-Tracking.

Eye-tracking can help decode the intricate control mechanism in human performance. In healthcare, physicians-in-training require extensive practice to improve their healthcare skills. When a trainee encounters any difficulty in the practice, they will need feedback from experts to improve their performance. Personal feedback is time-consuming and subjected to bias. In this study, we tracked the eye movements of trainees during their colonoscopic performance in simulation. We examined changes in eye movement behavior during the moments of navigation loss (MNL), a signature sign for task difficulty during colonoscopy, and tested whether deep learning algorithms can detect the MNL by feeding data from eye-tracking. Human eye gaze and pupil characteristics were learned and verified by the deep convolutional generative adversarial networks (DCGANs); the generated data were fed to the Long Short-Term Memory (LSTM) networks with three different data feeding strategies to classify MNLs from the entire colonoscopic procedure. Outputs from deep learning were compared to the expert's judgment on the MNLs based on colonoscopic videos. The best classification outcome was achieved when we fed human eye data with 1000 synthesized eye data, where accuracy (91.80%), sensitivity (90.91%), and specificity (94.12%) were optimized. This study built an important foundation for our work of developing an education system for training healthcare skills using simulation.

Exendin-4 enhances the sensitivity of prostate cancer to enzalutamide by targeting Akt activation.

BACKGROUND: Glucagon-like peptide 1 (GLP-1) and its analogs are first-line choices for the treatment of type 2 diabetes mellitus. Recent studies have shown that they exhibit antitumor properties in some tumors. We previously found that a GLP-1 analog, exendin-4 (Ex-4), inhibited the growth of prostate cancer cells through suppressing the PI3K/Akt/mTOR pathway, which is activated in response to enzalutamide treatment and reported to be closely related to resistance to enzalutamide. So we speculated that exendin-4 may enhance the sensitivity of prostate cancer to enzalutamide through inhibiting Akt activation. METHODS: LNCap and CWR22RV1 cell lines, as well as mice bearing xenografts formed from the two cells, were used. RESULTS: Exendin-4 in combination with enzalutamide dramatically suppressed tumor growth of prostate cancer cells compared to enzalutamide alone; exendin-4 is capable of antagonizing enzalutamide-induced invasion and migration of both prostate cancer cells (P < .05). Furthermore, the combination treatment significantly reduced Akt and mTOR levels that were triggered by enzalutamide administration, caused a further decrease in nuclear AR localization compared with the enzalutamide as a monotherapy (P < .5), though exendin-4 treatment alone showed no effect on nuclear AR. CONCLUSION: Our study demonstrated that exendin-4 alleviated resistance to enzalutamide, and suggested that exendin-4 combined with enzalutamide may be a more efficacious treatment for patients with advanced prostate cancer.

Exendin-4 does not modify growth or apoptosis of human colon cancer cells.

AIM: Glucagon-like peptide-1 (GLP-1) receptor agonists are a kind of very popular antidiabetes drugs. They promote cell proliferation and survival through activation of signaling pathways in human islet cells involving phosphate idylinositol 3 kinase (PI3K) and extracellular regulated kinases 1 and 2 (ERK1/2), which are frequently activated in human colon cancer cells. Then, it is possible that taking GLP-1 receptor (GLP-1R) agonists persistently would induce proliferation of ß cells as well as colon cancer cells. So, clarifying the effects and mechanisms of GLP-1R agonists on colon cancer cells has important clinical implications. MATERIALS AND METHODS: We investigated GLP-1R expression in human colon cancer tissue samples with immunohistochemisty analysis and explored the effects of exendin-4, a GLP-1 receptor agonist, on colon cancer cells in vitro and in vivo. RESULTS: The results showed lack of GLP-1R expression in both human colon cancer tissues and colon cancer cell lines. Exendin-4 did not enhance the proliferation and migration of colon cancer cell lines in vitro, and nor did it inhibit apoptosis induced by cytotoxic agents such as 5-fluorouracil (5-FU) or irinotecan. In addition, exendin-4 did not promote the propagation of colon cancer cells in vivo. CONCLUSION: Our study suggests that GLP-1R agonists do not modify the growth or survival of human colon cancer cells and may be safe for diabetic patients with colon cancer.