Non-invasive prediction of non-alcoholic steatohepatitis in Japanese patients with morbid obesity by artificial intelligence using rule extraction technology

AIM To construct a non-invasive prediction algorithm for predicting non-alcoholic steatohepatitis(NASH), we investigated Japanese morbidly obese patients using artificial intelligence with rule extraction technology.METHODS Consecutive patients who required bariatric surgery underwent a liver biopsy during the operation. Standard clinical, anthropometric, biochemical measurements were used as parameters to predict NASH and were analyzed using rule extraction technology. One hundred and two patients, including 79 NASH and 23 non-NASH patients were analyzed in order to create the predictionmodel, another cohort with 77 patients including 65 NASH and 12 non-NASH patients were analyzed to validate the algorithm.RESULTS Alanine aminotransferase, C-reactive protein, homeostasis model assessment insulin resistance, albumin were extracted as predictors of NASH using a recursive-rule extraction algorithm. When we adopted the extracted rules for the validation cohort using a highly accurate rule extraction algorithm, the predictive accuracy was 79.2%. The positive predictive value, negative predictive value,sensitivity and specificity were 88.9%, 35.7%, 86.2% and 41.7%, respectively.CONCLUSION We successfully generated a useful model for predicting NASH in Japanese morbidly obese patients based on their biochemical profile using a rule extraction algorithm.

New categorization of human vascular endothelial cells by pro-vs anti-proliferative phenotypes

AIM: To integrally understand the effects of human vascular endothelial cells(VECs) on the proliferation of vascular smooth muscle cells(VSMCs).METHODS: Various kinds of human VECs of different origins were co-cultured with human aortic smooth muscle cells, a representative of human VSMCs. To exclude the irrelevant effects due to growth competition between VECs and VSMCs, the proliferation of VECs had previously been arrested via a low-dose gamma rayirradiation. To discriminately analyze the proliferation of VSMCs from that of VECs, the former cells were labeled with red fluorescent dye while the latter cells were labeled with green fluorescent dye before performing coculture experiments. After 4 d, total cells were harvested and subjected to flow cytometric analyses. Decrements in red fluorescence intensities due to proliferationmediated dilutions were measured and mathematically processed using a specific software to quantitatively evaluate the proliferation of VSMCs. The findings obtained from the flow cytometry-based analyses were further validated by microscopic observations. RESULTS: Commercially available primary cultured human VECs exclusively promoted VSMC proliferation regardless of their tissue origins and we termed these pro-proliferative VECs as "typeⅠ". By contrast, VECs freshly generated from human bone marrow-derived endothelial progenitors cells or human pluripotent stem cells including embryonic stem cells and induced pluripotent stem cells suppressed VSMC proliferation and we termed these anti-proliferative VECs as "typeⅡ". Repetitive subcultures as well as oxidative stress induced "type Ⅱ VECs to typeⅠ" conversion along with an induction of Regulator of G-protein signaling 5(RGS5)Compatibly, anti-oxidant treatments suppressed both the subculture-dependent "typeⅡ to typeⅠ" conversion and an induction of RGS5 gene. Immunostaining studies of clinical specimens indicated that RGS5 protein expressions in endothelial layers were low in norma arteries but they were up-regulated in pathologica arteries including hypertension, atherosclerosis and autoimmune vasculitis in a dose-dependent manner Overexpression and knockdown of RGS5 caused that"typeⅡ to typeⅠ" and "typeⅠ to type Ⅱ" phenotype conversions of VECs, respectively. CONCLUSION: Human VECs are categorized into two types: pro-proliferative RGS5^(high) VECs(typeⅠ) and antiproliferative RGS5 ^(low) VECs(typeⅡ).