Search

The reported prevalence of non-alcoholic fatty liver disease in studies of lean individuals ranges from 7.6% to 19.3%. The aim of the study was to develop machine-learning models for the prediction of fatty liver disease in lean individuals. The present retrospective study included 12,191 lean subjects with a body mass index < 23 kg/m2 who had undergone a health checkup from January 2009 to January 2019. Participants were divided into a training (70%, 8533 subjects) and a testing group (30%, 3568 subjects). A total of 27 clinical features were analyzed, except for medical history and history of alcohol or tobacco consumption. Among the 12,191 lean individuals included in the present study, 741 (6.1%) had fatty liver. The machine learning model comprising a two-class neural network using 10 features had the highest area under the receiver operating characteristic curve (AUROC) value (0.885) among all other algorithms. When applied to the testing group, we found the two-class neural network exhibited a slightly higher AUROC value for predicting fatty liver (0.868, 0.841–0.894) compared to the fatty liver index (FLI; 0.852, 0.824–0.81). In conclusion, the two-class neural network had greater predictive value for fatty liver than the FLI in lean individuals.

Among various eye diseases, glaucoma is one of the leading causes of blindness. Glaucoma is also one of the most common eye diseases in Taiwan. Glaucoma screenings can use optical coherence tomography (OCT) to locate areas in which the retinal nerve fiber layer is thinning. However, because OCT equipment is costly, only large hospitals with well-equipped facilities will have OCT, and regular eye clinics cannot afford such expensive equipment. This has caused many glaucoma patients to worsen because they cannot get an early diagnosis in regular eye clinics in time. This paper proposes a method of using a generative adversarial network (GAN) to generate corresponding OCT images from fundus images to assist family doctors in judging whether further examination is needed based on the generated OCT images to achieve early detection and treatment of glaucoma. In addition, in order to improve the classification accuracy of the system deployed in different hospitals or clinics, this paper also proposes to use the incremental training method to fine-tune the model. The model can be quickly applied by adding a small number of images from a specific clinic or hospital. Experimental results show that the cosine similarity between the generated OCT image and the real OCT image is 97.8%. Combined with the proposed transfer learning method, the classification accuracy of the classification model reaches 83.17%. As well as the use of the incremental method, the accuracy of identifying glaucoma is approximately 78.94%, which is 8.77% higher than the 70.17% accuracy of the initial model. Experimental results show the effectiveness and feasibility of our proposed method.

Carbonic anhydrase VIII (CAVIII) is a member of the CA family, while CA8 is the oncogene. Here we observed increased expression of CAVIII with high expression in colorectal cancer tissues. CAVIII is also expressed in more aggressive types of human colorectal cancer cells. Upregulated CAVIII expression in SW480 cell lines increased vascular endothelial growth factor (VEGF) and reduced miRNA16-5p. Conversely, knockdown of the CAVIII results in VEGF decline by up-regulated miRNA16-5p. Moreover, the collection of different grades of CAVIII expression CRC cells supernatant co-culture with endothelial progenitor cells (EPCs) promotes the ability of tube formation in soft agar and migration in the Transwell experiment, indicating that CAVIII might facilitate cancer-cell-released VEGF via the inhibition of miRNA16-5p signaling. Furthermore, in the xenograft tumor angiogenesis model, knockdown of CAVIII significantly reduced tumor growth and tumor-associated angiogenesis. Taken together, our results prove that the CAVIII/miR-16-5p signaling pathway might function as a metastasis suppressor in CRC. Targeting CAVIII/miR-16-5p may provide a strategy for blocking its metastasis.

To clarify the predictive factors of significant platelet count improvement in thrombocytopenic chronic hepatitis C (CHC) patients. CHC patients with baseline platelet counts of 3/μL receiving direct-acting antiviral (DAA) therapy with at least 12-weeks post-treatment follow-up (PTW12) were enrolled. Significant platelet count improvement was defined as a ≥10% increase in platelet counts at PTW12 from baseline. Platelet count evolution at treatment week 4, end-of-treatment, PTW12, and PTW48 was evaluated. This study included 4922 patients. Sustained virologic response after 12 weeks post-treatment was achieved in 98.7% of patients. Platelet counts from baseline, treatment week 4, and end-of-treatment to PTW12 were 108.8 ± 30.2, 121.9 ± 41.1, 123.1 ± 43.0, and 121.1 ± 40.8 × 103/μL, respectively. Overall, 2230 patients (45.3%) showed significant platelet count improvement. Multivariable analysis revealed that age (odds ratio (OR) = 0.99, 95% confidence interval (CI): 0.99–1.00, p = 0.01), diabetes mellitus (DM) (OR = 1.20, 95% CI: 1.06–1.38, p = 0.007), cirrhosis (OR = 0.66, 95% CI: 0.58–0.75, p < 0.0001), baseline platelet counts (OR = 0.99, 95% CI: 0.98–0.99, p < 0.0001), and baseline total bilirubin level (OR = 0.80, 95% CI: 0.71–0.91, p = 0.0003) were independent predictive factors of significant platelet count improvement. Subgroup analyses showed that patients with significant platelet count improvement and sustained virologic responses, regardless of advanced fibrosis, had a significant increase in platelet counts from baseline to treatment week 4, end-of-treatment, PTW12, and PTW48. Young age, presence of DM, absence of cirrhosis, reduced baseline platelet counts, and reduced baseline total bilirubin levels were associated with significant platelet count improvement after DAA therapy in thrombocytopenic CHC patients.