Machine learning-based comparison of factors influencing estimated glomerular filtration rate in Chinese women with or without non-alcoholic fatty liver.

BACKGROUND: The prevalence of non-alcoholic fatty liver (NAFLD) has increased recently. Subjects with NAFLD are known to have higher chance for renal function impairment. Many past studies used traditional multiple linear regression (MLR) to identify risk factors for decreased estimated glomerular filtration rate (eGFR). However, medical research is increasingly relying on emerging machine learning (Mach-L) methods. The present study enrolled healthy women to identify factors affecting eGFR in subjects with and without NAFLD (NAFLD+, NAFLD-) and to rank their importance. AIM: To uses three different Mach-L methods to identify key impact factors for eGFR in healthy women with and without NAFLD. METHODS: A total of 65535 healthy female study participants were enrolled from the Taiwan MJ cohort, accounting for 32 independent variables including demographic, biochemistry and lifestyle parameters (independent variables), while eGFR was used as the dependent variable. Aside from MLR, three Mach-L methods were applied, including stochastic gradient boosting, eXtreme gradient boosting and elastic net. Errors of estimation were used to define method accuracy, where smaller degree of error indicated better model performance. RESULTS: Income, albumin, eGFR, High density lipoprotein-Cholesterol, phosphorus, forced expiratory volume in one second (FEV1), and sleep time were all lower in the NAFLD+ group, while other factors were all significantly higher except for smoking area. Mach-L had lower estimation errors, thus outperforming MLR. In Model 1, age, uric acid (UA), FEV1, plasma calcium level (Ca), plasma albumin level (Alb) and T-bilirubin were the most important factors in the NAFLD+ group, as opposed to age, UA, FEV1, Alb, lactic dehydrogenase (LDH) and Ca for the NAFLD- group. Given the importance percentage was much higher than the 2nd important factor, we built Model 2 by removing age. CONCLUSION: The eGFR were lower in the NAFLD+ group compared to the NAFLD- group, with age being was the most important impact factor in both groups of healthy Chinese women, followed by LDH, UA, FEV1 and Alb. However, for the NAFLD- group, TSH and SBP were the 5th and 6th most important factors, as opposed to Ca and BF in the NAFLD+ group.

Application of multiple deep learning models for automatic burn wound assessment.

PURPOSE: Accurate assessment of the percentage of total body surface area (%TBSA) burned is crucial in managing burn injuries. It is difficult to estimate the size of an irregular shape by inspection. Many articles reported the discrepancy of estimating %TBSA burned by different doctors. We set up a system with multiple deep learning (DL) models for %TBSA estimation, as well as the segmentation of possibly poor-perfused deep burn regions from the entire wound. METHODS: We proposed boundary-based labeling for datasets of total burn wound and palm, whereas region-based labeling for the dataset of deep burn wound. Several powerful DL models (U-Net, PSPNet, DeeplabV3+, Mask R-CNN) with encoders ResNet101 had been trained and tested from the above datasets. With the subject distances, the %TBSA burned could be calculated by the segmentation of total burn wound area with respect to the palm size. The percentage of deep burn area could be obtained from the segmentation of deep burn area from the entire wound. RESULTS: A total of 4991 images of early burn wounds and 1050 images of palms were boundary-based labeled. 1565 out of 4994 images with deep burn were preprocessed with superpixel segmentation into small regions before labeling. DeeplabV3+ had slightly better performance in three tasks with precision: 0.90767, recall: 0.90065 for total burn wound segmentation; precision: 0.98987, recall: 0.99036 for palm segmentation; and precision: 0.90152, recall: 0.90219 for deep burn segmentation. CONCLUSION: Combining the segmentation results and clinical data, %TBSA burned, the volume of fluid for resuscitation, and the percentage of deep burn area can be automatically diagnosed by DL models with a pixel-to-pixel method. Artificial intelligence provides consistent, accurate and rapid assessments of burn wounds.

IL-10 polymorphisms are associated with coronary artery lesions in acute stage of Kawasaki disease.

BACKGROUND: The literature regarding interleukin (IL)-10 polymorphisms and coronary artery lesions (CALs) in Kawasaki disease (KD) is limited. We investigated whether 3 IL-10 genetic polymorphisms (-1082 A/G, -819 T/C, and -592 A/C) are associated with development of CALs in KD. METHODS AND RESULTS: The genotyping of IL-10 polymorphisms was conducted for 279 KD children (172 without and 107 with CALs in acute stage). Thirty-three patients had CALs in chronic stage and 74 only with transient CALs. The homozygous variant genotype CC of IL-10-819 and IL-10-592 was associated with 80% (P=0.006) and 79% (P=0.008) reduction in risk of CALs in acute stage, respectively. The C allele of IL-10-819 and IL-10-592 was associated with 34% (P=0.034) and 33% (P=0.044) reduction in risk of CALs in acute stage, respectively. Compared with ATA haplotype (adjusted odds ratio (AOR) 0.63, P=0.029) or non-ACC haplotype (AOR 0.64, P=0.033), ACC haplotype was associated with a significantly reduced risk for CALs in acute stage, but not for CALs in chronic stage. Compared with non-ATA haplotype (AOR 1.53, P=0.034), ATA haplotype was associated with a significantly increased risk of CALs, except for CALs in the chronic stage. CONCLUSIONS: The effects of IL-10 gene polymorphism on CALs in acute KD are important. The persistence of CALs in chronic stage depends much more on other factors such as the times of intravenous immunoglobulin treatment.

IL-1B polymorphism in association with initial intravenous immunoglobulin treatment failure in Taiwanese children with Kawasaki disease.

BACKGROUND: Approximately 8-38% of children with Kawasaki disease (KD) will have persistent or recrudescent fever after initial intravenous immunoglobulin (IVIG) treatment and are at increased risk for development of coronary artery abnormalities. Using genetic markers may be helpful to identify the high-risk group of IVIG-resistant patients for aggressive treatment. The aim of this study was to evaluate the associations between 4 potential polymorphisms in the interleukin (IL)-1 family of genes and initial IVIG treatment failure in KD children. METHODS AND RESULTS: A total of 156 KD children (136 with and 20 without a response to IVIG treatment) who were treated with high-dose IVIG (2 g/kg) within 10 days of fever onset were recruited. Polymerase chain reaction and Taqman assays were used for genotyping. A significant increase in IVIG resistance risk was observed for IL-1B -511 TT and IL-1B -31 CC genotypes (adjusted odds ratio (AOR) 5.27, 95% confidence interval (CI) 1.69-16.38, P=0.004; AOR 3.95, 95%CI 1.26-12.41, P=0.019, separately). The diplotype TC/TC (at IL-1B -511 and -31) also showed a significantly increased risk of IVIG resistance (AOR 4.32, 95%CI 1.36-13.71, P=0.013). CONCLUSIONS: The IL-1B -511 TT and IL-1B -31 CC genotypes or the TC/TC diplotype may be associated with initial IVIG treatment failure in Taiwanese children with KD.

Appearance of intratypic recombination of enterovirus 71 in Taiwan from 2002 to 2005.

Genetic recombination is a well-known phenomenon for enteroviruses. In this study, we determined the phylogenetic relationships of five distinct regions of the EV71 genome for 73 EV71 isolates from 1986 and from 1998 to 2005 in Taiwan. Phylogenetic analyses showed that the 5'-UTR, VP4-VP2, VP1, and 3D regions of EV71 isolated in 2004 and 2005 were grouped into genotype C. However, the 2B region of these isolates differed in that it grouped with genotype B, indicating recombination within EV71 had occurred. This intratypic recombination was first seen in 2002 and became predominant in 2004 and 2005. The simplot and bootscan analyses identified two recombination points located at the 3'-termini of the 2A and 3C regions. This intratypic recombination was identified among naturally circulating EV71 isolates in Taiwan, therefore, it suggests that nonstructural genes may recombine to produce new EV71 variants.