A novel artificial intelligence-assisted "vascular healing" diagnosis for prediction of future clinical relapse in patients with ulcerative colitis: a prospective cohort study (with video).

BACKGROUND AND AIMS: Image-enhanced endoscopy has attracted attention as a method for detecting inflammation and predicting outcomes in patients with ulcerative colitis (UC); however, the procedure requires specialist endoscopists. Artificial intelligence (AI)-assisted image-enhanced endoscopy may help nonexperts provide objective accurate predictions with the use of optical imaging. We aimed to develop a novel AI-based system using 8853 images from 167 patients with UC to diagnose "vascular-healing" and establish the role of AI-based vascular-healing for predicting the outcomes of patients with UC. METHODS: This open-label prospective cohort study analyzed data for 104 patients with UC in clinical remission. Endoscopists performed colonoscopy using the AI system, which identified the target mucosa as AI-based vascular-active or vascular-healing. Mayo endoscopic subscore (MES), AI outputs, and histologic assessment were recorded for 6 colorectal segments from each patient. Patients were followed up for 12 months. Clinical relapse was defined as a partial Mayo score >2 RESULTS: The clinical relapse rate was significantly higher in the AI-based vascular-active group (23.9% [16/67]) compared with the AI-based vascular-healing group (3.0% [1/33)]; P = .01). In a subanalysis predicting clinical relapse in patients with MES ≤1, the area under the receiver operating characteristic curve for the combination of complete endoscopic remission and vascular healing (0.70) was increased compared with that for complete endoscopic remission alone (0.65). CONCLUSIONS: AI-based vascular-healing diagnosis system may potentially be used to provide more confidence to physicians to accurately identify patients in remission of UC who would likely relapse rather than remain stable.

Development of short hairpin RNA expression vectors targeting the internal ribosomal entry site of the classical swine fever virus genomic RNA.

BACKGROUND: Classical swine fever (CSF) is a fatal contagious disease affecting pigs caused by classical swine fever virus (CSFV). The disease can be transmitted by pigs and wild boars, and it is difficult to prevent and control. To obtain necessary information to establish the CSFV resistant animals in a future study, we designed lentiviral vector-delivered short hairpin RNAs (shRNAs) targeting the conserved domain III of the internal ribosomal entry site (IRES) of the CSFV genomic RNA. RESULTS: First, we confirmed the effects of siRNAs on CSFV-IRES activity. We observed significant inhibition of CSFV-IRES activity by si42 (domain IIIa), si107 (domain IIIc), and si198 (domain IIIf) in SK-L cells and si56 (domain IIIb), si142 (domain IIId1) and si198 in HEK293 cells without affecting the amount of luciferase RNA. Next, we constructed lentiviral vectors expressing shRNA based on siRNA sequences. Treatment with shRNA-expressing lentivirus was examined at 7 and 14 days post infection in SK-L cells and HEK293 cells, and CSFV-IRES was significantly suppressed at 14 days (sh42) post infection in HEK293 cells without significant cytotoxicity. Next, we examined the silencing effect of siRNA on CSFV replicon RNA and observed a significant effect by si198 after 2 days of treatment and by shRNA-expressing lentivirus (sh56, sh142, and sh198) infection after 14 days of treatment. Treatment of sh198-expressing lentivirus significantly suppressed CSFV infection at 3 days after infection. CONCLUSION: The IRES targeting sh198 expressing lentivirus vector can be a candidate tool for CSFV infection control.

Accuracy in Polyp Size Measurement Among Surgeons, Gastroenterologists, Trainees, and Experts: A Prospective Video-Based Study.

INTRODUCTION: Polyp size determination plays an important role in endoscopic decision making and follow-up determination. However, there is a lack of knowledge of endoscopist accuracy for polyp sizing and efficacy of available tools for size measurement. Our aim was to compare the accuracy of visual assessment, snare, forceps, and virtual scale endoscope (VSE) in estimating polyp size among a diverse group of endoscopists. METHODS: We conducted a prospective video-based study. One hundred twenty polyps measured and recorded along with all available measurement tools were randomized to visual assessment, snare, forceps, or VSE group. Eleven endoscopists conducted video-based measurement using the randomized measurement tool. Primary outcome was relative accuracy in polyp size measurement compared with caliper measurement immediately postresection. RESULTS: One thousand three hundred twenty measurements were performed. VSE had statistically significantly higher relative accuracy when compared to forceps (79.3 vs 71.3%; P < 0.0001). Forceps had statistically significantly higher relative accuracy when compared to visual assessment (71.3 vs 63.6%; P = 0.0036). There was no statistically significant difference when comparing visual assessment and snare-based measurements (63.6 vs 62.8%; P = 0.797). Overall, 21.5% of polyps >5 mm were misclassified as ≤5 mm and 17.3% of polyps ≥10 mm were misclassified as <10 mm. VSE had the lowest percentage of polyps >5 mm misclassified as ≤5 mm (2.6%), polyps ≤5 mm misclassified as >5 mm (5.1%), and polyps <10 mm misclassified as ≥10 mm (1.7%). DISCUSSION: Visual size estimation of polyps is inaccurate independently of training level, sex, and specialty. Size measurement accuracy can be improved using forceps and yields the highest relative accuracy when an adaptive scale technology is used.

Characterization of host factors associated with the internal ribosomal entry sites of foot-and-mouth disease and classical swine fever viruses.

Foot-and-mouth disease virus (FMDV) and classical swine fever virus (CSFV) possess positive-sense single-stranded RNA genomes and an internal ribosomal entry site (IRES) element within their 5'-untranslated regions. To investigate the common host factors associated with these IRESs, we established cell lines expressing a bicistronic luciferase reporter plasmid containing an FMDV-IRES or CSFV-IRES element between the Renilla and firefly luciferase genes. First, we treated FMDV-IRES cells with the French maritime pine extract, Pycnogenol (PYC), and examined its suppressive effect on FMDV-IRES activity, as PYC has been reported to have antiviral properties. Next, we performed microarray analysis to identify the host factors that modified their expression upon treatment with PYC, and confirmed their function using specific siRNAs. We found that polycystic kidney disease 1-like 3 (PKD1L3) and ubiquitin-specific peptidase 31 (USP31) were associated with FMDV-IRES activity. Moreover, silencing of these factors significantly suppressed CSFV-IRES activity. Thus, PKD1L3 and USP31 are host factors associated with the functions of FMDV- and CSFV-IRES elements.