Possible contribution of artificial neural networks and linear discriminant analysis in recognition of patients with suspected atrophic body gastritis

AIM: To investigate whether ANNs and LDA could recognize patients with ABG in a database, containing only clinical and biochemical variables, of a pool of patients with and without ABG, by selecting the most predictive variables and by reducing input data to the minimum.METHODS: Data was collected from 350 consecutive outpatients (263 with ABG, 87 with non-atrophic gastritis and/or celiac disease [controls]). Structured questionnaires with 22 items (anagraphic, anamnestic, clinical, and biochemical data) were filled out for each patient. All patients underwent gastroscopy with biopsies. ANNs and LDA were applied to recognize patients with ABG.Experiment 1: random selection on 37 variables, experiment 2: optimization process on 30 variables, experiment 3:input data reduction on 8 variables, experiment 4: use of only clinical input data on 5 variables, and experiment 5:use of only serological variables.RESULTS: In experiment 1, overall accuracies of ANNs and LDA were 96.6% and 94.6%, respectively, for predicting patients with ABG. In experiment 2, ANNs and LDA reached an overall accuracy of 98.8% and 96.8%,respectively. In experiment 3, overall accuracy of ANNs was 98.4%. In experiment 4, overall accuracies of ANNs and LDA were, respectively, 91.3% and 88.6%. In experiment 5, overall accuracies of ANNs and LDA were,respectively, 97.7% and 94.5%.CONCLUSION: This preliminary study suggests that advanced statistical methods, not only ANNs, but also LDA,may contribute to better address bioptic sampling during gastroscopy in a subset of patients in whom ABG may be suspected on the basis of aspecific gastrointestinal symptoms or non-digestive disorders.

Is proliferative colonic disease presentation changing?

AIM:To compare the site,age and gender of cases of colorectal cancer(CRC) and polyps in a single referral center in Rome,Italy,during two periods.METHODS:CRC data were collected from surgery/pathology registers,and polyp data from colonoscopy reports.Patients who met the criteria for familial adenomatous polyposis,hereditary non-polyposis colorectal cancer syndrome or inflammatory bowel disease were excluded from the study.Overlap of patients between the two groups(cancers and polyps) was carefully avoided.Theχ 2 statistical test and a regression analysis were performed.RESULTS:Data from a total of 768 patients(352 and 416 patients,respectively,in periods A and B) who underwent surgery for cancer were collected.During the same time periods,a total of 1693 polyps were analyzed from 978 patients with complete colonoscopies(428 polyps from 273 patients during period A and 1265 polyps from 705 patients during period B).A proximal shift in cancer occurred during the latter years for both sexes,but particularly in males.Proximal cancer increased > 3-fold in period B compared to period A in males [odds ratio(OR) 3.31,95%CI:2.00-5.47;P < 0.0001).A similar proximal shift was observed for polyps,particularly in males(OR 1.87,95%CI:1.23-2.87;P < 0.0038),but also in females(OR 1.62,95%CI:0.96-2.73;P < 0.07).CONCLUSION:The prevalence of proximal proliferative colonic lesions seems to have increased over the last decade,particularly in males.

A case of oesophageal ulcer developed after taking homeopathic pill in a young woman

食道的溃疡主要由于胃食道的倒流疾病(GERD ) 发生。然而，导致药片的食道的溃疡是一个相当普通的事件。损害主要由于药片或它它的化学作文的陷阱。这份病案报告描述食道的粘膜溃疡在没有食道的混乱的以前的历史并且收到了同种疗法的药的一个健康 35 年的老妇人发生了。现在的盒子表明药片陷阱能甚至在健康年轻个人的食道发生，那食道的粘膜溃疡能被通常任何潜在地粘膜的好攻击的效果认为缺乏的物质触发。

Is colonoscopy sufficient for colorectal cancer surveillance in all HNPCC patients?

有有在 hMSH2 的一个变化的结肠癌衬里的世袭 non-polyposis 的 34 岁的男性被报导。尽管有常规 colonoscopic 后续，他得了包含额外的钠区域的盲肠的癌症。由于亚 occlusive 症状，病人被提交推进结肠镜检查，然而没有瘤形成的清楚的证据。计算断层摄影术 CT 扫描此后执行了的多平面的重建揭示了的薄片透壁集中在在盲肠的阀门附近局部性的尺寸的 2.5 厘米。讨论在右边的结肠癌的很高的风险在病人的后续象对进一步的调查的需要一样在 colonoscopic 考试的可靠性上被做，例如世袭 non-polyposis 结肠癌影响的男 hMSH2 搬运人。