Autoimmune Disease Classification by Inverse Association with SNP Alleles

With multiple genome-wide association studies (GWAS) performed across autoimmune diseases, there is a great opportunity to study the homogeneity of genetic architectures across autoimmune disease. Previous approaches have been limited in the scope of their analysis and have failed to properly incorporate the direction of allele-specific disease associations for SNPs. In this work, we refine the notion of a genetic variation profile for a given disease to capture strength of association with multiple SNPs in an allele-specific fashion. We apply this method to compare genetic variation profiles of six autoimmune diseases: multiple sclerosis (MS), ankylosing spondylitis (AS), autoimmune thyroid disease (ATD), rheumatoid arthritis (RA), Crohn''s disease (CD), and type 1 diabetes (T1D), as well as five non-autoimmune diseases. We quantify pair-wise relationships between these diseases and find two broad clusters of autoimmune disease where SNPs that make an individual susceptible to one class of autoimmune disease also protect from diseases in the other autoimmune class. We find that RA and AS form one such class, and MS and ATD another. We identify specific SNPs and genes with opposite risk profiles for these two classes. We furthermore explore individual SNPs that play an important role in defining similarities and differences between disease pairs. We present a novel, systematic, cross-platform approach to identify allele-specific relationships between disease pairs based on genetic variation as well as the individual SNPs which drive the relationships. While recognizing similarities between diseases might lead to identifying novel treatment options, detecting differences between diseases previously thought to be similar may point to key novel disease-specific genes and pathways.     

Predicting Disease Risk Using Bootstrap Ranking and Classification Algorithms

Genome-wide association studies (GWAS) are widely used to search for genetic loci that underlie human disease. Another goal is to predict disease risk for different individuals given their genetic sequence. Such predictions could either be used as a “black box” in order to promote changes in life-style and screening for early diagnosis, or as a model that can be studied to better understand the mechanism of the disease. Current methods for risk prediction typically rank single nucleotide polymorphisms (SNPs) by the p-value of their association with the disease, and use the top-associated SNPs as input to a classification algorithm. However, the predictive power of such methods is relatively poor. To improve the predictive power, we devised BootRank, which uses bootstrapping in order to obtain a robust prioritization of SNPs for use in predictive models. We show that BootRank improves the ability to predict disease risk of unseen individuals in the Wellcome Trust Case Control Consortium (WTCCC) data and results in a more robust set of SNPs and a larger number of enriched pathways being associated with the different diseases. Finally, we show that combining BootRank with seven different classification algorithms improves performance compared to previous studies that used the WTCCC data. Notably, diseases for which BootRank results in the largest improvements were recently shown to have more heritability than previously thought, likely due to contributions from variants with low minimum allele frequency (MAF), suggesting that BootRank can be beneficial in cases where SNPs affecting the disease are poorly tagged or have low MAF. Overall, our results show that improving disease risk prediction from genotypic information may be a tangible goal, with potential implications for personalized disease screening and treatment.     

Classification of Disease in General Practice: A Comparative Study

A comparison is made between the International Classification of Diseases (Eighth Revision) and the classification of the British College of General Practitioners (1963 Revision), with particular reference to their application to the diagnostic data from a family practice in Canada over a period of one year. The International Classification proves superior but would require modification to be ideal for use in recording morbidity from general practice. A plan for such a modification is outlined.     

Deep Transfer Learning Based Classification Model for COVID-19 Disease

The COVID-19 infection is increasing at a rapid rate, with the availability of limited number of testing kits. Therefore, the development of COVID-19 testing kits is still an open area of research. Recently, many studies have shown that chest Computed Tomography (CT) images can be used for COVID-19 testing, as chest CT images show a bilateral change in COVID-19 infected patients. However, the classification of COVID-19 patients from chest CT images is not an easy task as predicting the bilateral change is defined as an ill-posed problem. Therefore, in this paper, a deep transfer learning technique is used to classify COVID-19 infected patients. Additionally, a top-2 smooth loss function with cost-sensitive attributes is also utilized to handle noisy and imbalanced COVID-19 dataset kind of problems. Experimental results reveal that the proposed deep transfer learning-based COVID-19 classification model provides efficient results as compared to the other supervised learning models.     

Automatic Classification of Early Parkinson's Disease with Multi-Modal MR Imaging

Background

In recent years, neuroimaging has been increasingly used as an objective method for the diagnosis of Parkinson''s disease (PD). Most previous studies were based on invasive imaging modalities or on a single modality which was not an ideal diagnostic tool. In this study, we developed a non-invasive technology intended for use in the diagnosis of early PD by integrating the advantages of various modals.

Materials and Methods

Nineteen early PD patients and twenty-seven normal volunteers participated in this study. For each subject, we collected resting-state functional magnetic resonance imaging (rsfMRI) and structural images. For the rsfMRI images, we extracted the characteristics at three different levels: ALFF (amplitude of low-frequency fluctuations), ReHo (regional homogeneity) and RFCS (regional functional connectivity strength). For the structural images, we extracted the volume characteristics from the gray matter (GM), the white matter (WM) and the cerebrospinal fluid (CSF). A two-sample t-test was used for the feature selection, and then the remaining features were fused for classification. Finally a classifier for early PD patients and normal control subjects was identified from support vector machine training. The performance of the classifier was evaluated using the leave-one-out cross-validation method.

Results

Using the proposed methods to classify the data set, good results (accuracy  = 86.96%, sensitivity  = 78.95%, specificity  = 92.59%) were obtained.

Conclusions

This method demonstrates a promising diagnosis performance by the integration of information from a variety of imaging modalities, and it shows potential for improving the clinical diagnosis and treatment of PD.     

柳树黄化病植原体的分子分类

[目的]柳树黄化病是一种重要的植原体病害,本研究旨在明确柳树黄化病植原体(Willow Yellow phytoplasma,WY)的分类地位,为进一步开展致病性和防治研究奠定基础.[方法]采用植原体特异引物通过PCR方法从患病植株DNA中扩增植原体16S rDNA基因和核糖体蛋白基因(ribosomal proteins gene,rp),对所得的序列进行分析,构建同源进化树,并用限制性片段长度多态性(RFTJP)对巢式PCR产物进行分析.[结果]首次从柳树黄化病植原体中分离出了16S rDNA基因和rp基因,大小分别为1246 bp和1212 bp.通过对植原体16S rDNA和rp基因的核苷酸同源性比较和RFLP分析,发现该分离物与16S rI组的核苷酸同源性均在99%以上,与16S rI-C亚组中的小麦蓝矮病植原体同源性高达99.8%(16Sr DNA)和99.6%(rp),且RFLP分析与16SrI-C亚组的植原体有相同的酶切条带.[结论]柳树黄化植原体应划分于16SrI-C亚组.     

Social Determinants and the Classification of Disease: Descriptive Epidemiology of Selected Socially Mediated Disease Constellations

Background

Most major diseases have important social determinants. In this context, classification of disease based on etiologic or anatomic criteria may be neither mutually exclusive nor optimal.

Methods and Findings

Units of analysis comprised large metropolitan central and fringe metropolitan counties with reliable mortality rates – (n = 416). Participants included infants and adults ages 25 to 64 years with selected causes of death (1999 to 2006). Exposures included that residential segregation and race-specific social deprivation variables. Main outcome measures were obtained via principal components analyses with an orthogonal rotation to identify a common factor. To discern whether the common factor was socially mediated, negative binomial multiple regression models were developed for which the dependent variable was the common factor. Results showed that infant deaths, mortality from assault, and malignant neoplasm of the trachea, bronchus and lung formed a common factor for race-gender groups (black/white and men/women). Regression analyses showed statistically significant, positive associations between low socio-economic status for all race-gender groups and this common factor.

Conclusions

Between 1999 and 2006, deaths classified as “assault” and “lung cancer”, as well as “infant mortality” formed a socially mediated factor detectable in population but not individual data. Despite limitations related to death certificate data, the results contribute important information to the formulation of several hypotheses: (a) disease classifications based on anatomic or etiologic criteria fail to account for social determinants; (b) social forces produce demographically and possibly geographically distinct population-based disease constellations; and (c) the individual components of population-based disease constellations (e.g., lung cancer) are phenotypically comparable from one population to another but genotypically different, in part, because of socially mediated epigenetic variations. Additional research may produce new taxonomies that unify social determinants with anatomic and/or etiologic determinants. This may lead to improved medical management of individuals and populations.     

Systematic Classification of Disease Severity for Evaluation of Expanded Carrier Screening Panels

Professional guidelines dictate that disease severity is a key criterion for carrier screening. Expanded carrier screening, which tests for hundreds to thousands of mutations simultaneously, requires an objective, systematic means of describing a given disease''s severity to build screening panels. We hypothesized that diseases with characteristics deemed to be of highest impact would likewise be rated as most severe, and diseases with characteristics of lower impact would be rated as less severe. We describe a pilot test of this hypothesis in which we surveyed 192 health care professionals to determine the impact of specific disease phenotypic characteristics on perceived severity, and asked the same group to rate the severity of selected inherited diseases. The results support the hypothesis: we identified four “Tiers” of disease characteristics (1–4). Based on these responses, we developed an algorithm that, based on the combination of characteristics normally seen in an affected individual, classifies the disease as Profound, Severe, Moderate, or Mild. This algorithm allows simple classification of disease severity that is replicable and not labor intensive.     

SlimPLS: A Method for Feature Selection in Gene Expression-Based Disease Classification

A major challenge in biomedical studies in recent years has been the classification of gene expression profiles into categories, such as cases and controls. This is done by first training a classifier by using a labeled training set containing labeled samples from the two populations, and then using that classifier to predict the labels of new samples. Such predictions have recently been shown to improve the diagnosis and treatment selection practices for several diseases. This procedure is complicated, however, by the high dimensionality if the data. While microarrays can measure the levels of thousands of genes per sample, case-control microarray studies usually involve no more than several dozen samples. Standard classifiers do not work well in these situations where the number of features (gene expression levels measured in these microarrays) far exceeds the number of samples. Selecting only the features that are most relevant for discriminating between the two categories can help construct better classifiers, in terms of both accuracy and efficiency. In this work we developed a novel method for multivariate feature selection based on the Partial Least Squares algorithm. We compared the method''s variants with common feature selection techniques across a large number of real case-control datasets, using several classifiers. We demonstrate the advantages of the method and the preferable combinations of classifier and feature selection technique.     

慢性阻塞性肺疾病患者血清CRP与BODE指数分级的研究

目的:分析COPD患者血清CRP在BODE指数不同级别之间的变化,探讨血清CRP在稳定期COPD患者中的临床价值。方法:2008年12月至2009年12月收集稳定期COPD患者40例,测定肺功能、六分钟步行距离(6MWD),评估呼吸困难程度,计算体质指数(BMI),按BODE指数评分标准进行评分并分级;同时收集10例健康志愿者,为血清学指标提供基线水平,用免疫散射比浊法检测COPD患者和健康志愿者血清CRP。分析COPD患者血清CRP在BODE指数不同级别中的变化,血清CRP经对数转换后应用SPSS16.0统计软件进行统计学分析。结果:按BODE指数分级的各级稳定期COPD患者及健康志愿者之间血清CRP水平存在差异(F=13.051,p=0.000),健康志愿者与BODE指数1级的COPD患者之间血清CRP差异无统计学意义(p=0.42),与BODE指数2级、3级、4级的COPD患者差异有统计学意义(p分别为0.05、0.000、0.000);BODE指数1级的COPD患者与2级、3级、4级的COPD患者之间血清CRP差异均有统计学意义(p分别为0.032、0.000、0.000);BODE指数2级的COPD...     

Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems

Background

Machine learning neuroimaging researchers have often relied on regularization techniques when classifying MRI images. Although these were originally introduced to deal with “ill-posed” problems it is rare to find studies that evaluate the ill-posedness of MRI image classification problems. In addition, to avoid the effects of the “curse of dimensionality” very often dimension reduction is applied to the data.

Methodology

Baseline structural MRI data from cognitively normal and Alzheimer''s disease (AD) patients from the AD Neuroimaging Initiative database were used in this study. We evaluated here the ill-posedness of this classification problem across different dimensions and sample sizes and its relationship to the performance of regularized logistic regression (RLR), linear support vector machine (SVM) and linear regression classifier (LRC). In addition, these methods were compared with their principal components space counterparts.

Principal Findings

In voxel space the prediction performance of all methods increased as sample sizes increased. They were not only relatively robust to the increase of dimension, but they often showed improvements in accuracy. We linked this behavior to improvements in conditioning of the linear kernels matrices. In general the RLR and SVM performed similarly. Surprisingly, the LRC was often very competitive when the linear kernel matrices were best conditioned. Finally, when comparing these methods in voxel and principal component spaces, we did not find large differences in prediction performance.

Conclusions and Significance

We analyzed the problem of classifying AD MRI images from the perspective of linear ill-posed problems. We demonstrate empirically the impact of the linear kernel matrix conditioning on different classifiers'' performance. This dependence is characterized across sample sizes and dimensions. In this context we also show that increased dimensionality does not necessarily degrade performance of machine learning methods. In general, this depends on the nature of the problem and the type of machine learning method.     

Classification of Rhinoentomophthoromycosis into Atypical,Early, Intermediate,and Late Disease: A Proposal

Background

Rhinoentomophthoromycosis, or rhino-facial conidiobolomycosis, is a rare, grossly disfiguring disease due to an infection with entomophthoralean fungi. We report a case of rhinoentomophthoromycosis from Gabon and suggest a staging system, which provides information on the prognosis and duration of antifungal therapy.

Methods

We present a case of rhinoentomophthoromycosis including the histopathology, mycology, and course of disease. For the suggested staging system, all cases on confirmed rhinoentomophthoromycosis published in the literature without language restriction were eligible. Exclusion criteria were missing data on (i) duration of disease before correct diagnosis, (ii) outcome, and (iii) confirmation of entomophthoralean fungus infection by histopathology and/or mycology. We classified cases into atypical (orbital cellulitis, severe pain, fever, dissemination), early, intermediate, and late disease based on the duration of symptoms before diagnosis. The outcome was evaluated for each stage of disease.

Findings

The literature search of the Medpilot database was conducted on January 13, 2014, (updated on January 18, 2015). The search yielded 8,333 results including 198 cases from 117 papers; of these, 145 met our inclusion criteria and were included in the final analysis. Median duration of treatment was 4, 3, 4, and 5 months in atypical, early, intermediate, and late disease, respectively. Cure rates were clearly associated with stage of disease and were 57%, 100%, 82%, and 43% in atypical, early, intermediate, and late disease, respectively.

Conclusion

We suggest a clinical staging system that underlines the benefit of early case detection and may guide the duration of antifungal treatment. The scientific value of this classification is its capacity to structure and harmonize the clinical and research approach towards rhinoentomophthoromycosis.     

我国ICD-10疾病分类编码质量的系统评价

目的 基于文献,系统评价我国出院疾病诊断分类的编码质量。方法 计算机检索SINOMED(CBMdisc)、中国知网（CNKI）、维普数据库（VIP）、万方数据库,并辅以文献追溯的方法,收集2000-2014年间在国内公开发表的所有住院病历出院疾病编码错误率的文章。按纳入和排除标准筛选文献并评价其质量,采用描述性分析方法对编码质量进行定性系统评价。结果 纳入30篇文献中,19篇报道了总体编码错误率,研究对象为全部或大部分疾病10篇,仅针对特定种类或某专科疾病的文献9篇,编码错误率中位数分别是12.99%和20.41%,两者间差异无统计学意义,P＝0.121。编码错误率与时间无关但与研究样本量存在负相关关系,r_s＝-0.702,P＝0.001。16篇报道主要诊断编码错误率的文献中,8篇报道了主要诊断总错误率,11篇文献报道了主要诊断选择的错误率,错误率中位数分别为24.77%和5.17%。结论 我国编码质量水平总体上与现有标准仍存较大差距,政策制定者、医院管理者及病案编码人员应采取更有效措施来缩小差距,提高编码质量。

     

肝病分类诊断与诊疗路径系统的构建及应用价值分析

肝病分类诊断系统是根据肝脏疾病的病因学、临床症候学、检验学、影像学、病理学和解剖学等特性,通过对肝脏疾病的分类、起病状态、病原学检测、肝功能情况、营养状态、感染情况、肝纤维化及肝硬化程度、肝脏并发症情况、多脏器功能情况、肝癌发生及进展情况和伴随疾病等不同层次、全方位的评价,准确反映肝脏疾病状态及各器官功能情况。肝病分类诊断系统中的每一诊断均对应一个以国内外最新诊疗标准、指南、共识等为依据,以循证医学为基础的诊断、治疗、康复及随访方案,最终根据不同诊断,组合生成全面的个体化综合治疗路径,使诊断、治疗、检查、随访以及生活指导更加标准、科学、规范。     

Functional Characterisation of Alpha-Galactosidase A Mutations as a Basis for a New Classification System in Fabry Disease

Fabry disease (FD) is an X-linked hereditary defect of glycosphingolipid storage caused by mutations in the gene encoding the lysosomal hydrolase α-galactosidase A (GLA, α-gal A). To date, over 400 mutations causing amino acid substitutions have been described. Most of these mutations are related to the classical Fabry phenotype. Generally in lysosomal storage disorders a reliable genotype/phenotype correlation is difficult to achieve, especially in FD with its X-linked mode of inheritance. In order to predict the metabolic consequence of a given mutation, we combined in vitro enzyme activity with in vivo biomarker data. Furthermore, we used the pharmacological chaperone (PC) 1-deoxygalactonojirimycin (DGJ) as a tool to analyse the influence of individual mutations on subcellular organelle-trafficking and stability. We analysed a significant number of mutations and correlated the obtained properties to the clinical manifestation related to the mutation in order to improve our knowledge of the identity of functional relevant amino acids. Additionally, we illustrate the consequences of different mutations on plasma lyso-globotriaosylsphingosine (lyso-Gb3) accumulation in the patients'' plasma, a biomarker proven to reflect the impaired substrate clearance caused by specific mutations. The established system enables us to provide information for the clinical relevance of PC therapy for a given mutant. Finally, in order to generate reliable predictions of mutant GLA defects we compared the different data sets to reveal the most coherent system to reflect the clinical situation.