Thorsten Dickhaus

Introduction to machine learning for brain imaging

Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.

Prevalence of Polyneuropathy in Pre-Diabetes and Diabetes Is Associated With Abdominal Obesity and Macroangiopathy : The MONICA/KORA Augsburg Surveys S2 and S3

OBJECTIVE—It is controversial whether there is a glycemic threshold above which polyneuropathy develops and which are the most important factors associated with polyneuropathy in the general population. The aim of this study was to determine the prevalence and risk factors of polyneuropathy in subjects with diabetes, impaired fasting glucose (IFG), impaired glucose tolerance (IGT), or normal glucose tolerance (NGT). RESEARCH DESIGN AND METHODS—Subjects with diabetes (n = 195) and control subjects matched for age and sex (n = 198) from the population-based MONICA (Monitoring Trends and Determinants on Cardiovascular Diseases)/KORA (Cooperative Research in the Region of Augsburg) Augsburg Surveys 1989/1990 (S2) and 1994/1995 (S3) aged 25–74 years were contacted again and assessed in 1997/1998 by the Michigan Neuropathy Screening Instrument using a score cut point >2. An oral glucose tolerance test was performed in the control subjects. RESULTS—Among the control subjects, 46 (23.2%) had IGT, 71 (35.9%) had IFG, and 81 had NGT. The prevalence of polyneuropathy was 28.0% in the diabetic subjects, 13.0% in those with IGT, 11.3% in those with IFG, and 7.4% in those with NGT (P ≤ 0.05 for diabetes vs. NGT, IFG, and IGT). In the entire population studied (n = 393), age, waist circumference, and diabetes were independent factors significantly associated with polyneuropathy, whereas in the diabetic group polyneuropathy was associated with age, waist circumference, and peripheral arterial disease (PAD) (all P < 0.05). CONCLUSIONS—The prevalence of polyneuropathy is slightly increased in individuals with IGT and IFG compared with those with NGT. The association with waist circumference and PAD suggests that the latter and abdominal obesity may constitute important targets for strategies to prevent diabetic polyneuropathy.

Neuropathic pain in diabetes, prediabetes and normal glucose tolerance: the MONICA/KORA Augsburg Surveys S2 and S3.

OBJECTIVE The prevalence of neuropathic pain in prediabetes and the associated risk factors in the general population are not known. The aim of this study was to determine the prevalence and risk factors of neuropathic pain in subjects with diabetes, impaired fasting glucose (IFG), impaired glucose tolerance (IGT), or normal glucose tolerance (NGT). DESIGN Survey of neuropathic painful polyneuropathy assessed by the Michigan Neuropathy Screening Instrument using its pain-relevant questions and an examination score cutpoint >2 in a diabetic and control population. An oral glucose tolerance test was performed in the control subjects. SETTING Population of the city of Augsburg and two surrounding counties. PATIENTS Subjects with diabetes (N = 195) and controls matched for age and sex (N = 198) from the population-based MONItoring trends and determinants in CArdiovascular/Cooperative Research in the Region of Augsburg (MONICA/KORA) Augsburg Surveys S2 and S3 aged 25-74 years. RESULTS Among the controls, 46 (23.2%) had IGT (either isolated or combined with IFG), 71 (35.9%) had isolated IFG, and 81 had NGT. The prevalence (95% confidence interval) of neuropathic pain was 13.3 (8.9-18.9)% in the diabetic subjects, 8.7 (2.4-20.0)% in those with IGT, 4.2 (0.9-11.9)% in those with IFG, and 1.2 (0.03-6.7)% in those with NGT (overall P = 0.003). In the entire population (N = 393), age, weight, peripheral arterial disease (PAD), and diabetes were risk factors significantly associated with neuropathic pain, while in the diabetic group, these factors were age, weight, and PAD (all P < 0.05). CONCLUSIONS The prevalence of neuropathic pain is two- to threefold increased in subjects with IGT and diabetes compared with those with isolated IFG. Apart from diabetes, the predominant risk factors are age, obesity, and PAD.

Epigenetic quantification of tumor-infiltrating T-lymphocytes

The immune system plays a pivotal role in tumor establishment. However, the role of T-lymphocytes within the tumor microenvironment as major cellular component of the adaptive effector immune response and their counterpart, regulatory T-cells (Treg), responsible for suppressive immune modulation, is not completely understood. This is partly due to the lack of reliable technical solutions for specific cell quantification in solid tissues. Previous reports indicated that epigenetic marks of immune cells, such as the Treg specifically demethylated region (TSDR) within the FOXP3 gene, may be exploited as robust analytical tool for Treg-quantification. Here, we expand the concept of epigenetic immunophenotyping to overall T-lymphocytes (oTL). This tool allows cell quantification with at least equivalent precision to FACS and is adoptable for analysis of blood and solid tissues. Based on this method, we analyse the frequency of Treg, oTL and their ratio in independent cohorts of healthy and tumorous ovarian, colorectal and bronchial tissues with 616 partly donor-matched samples. We find a shift of the median ratio of Treg-to-oTL from 3-8% in healthy tissue to 18-25% in all tumor entities. Epigenetically determined oTL frequencies correlate with the outcome of colorectal and ovarian cancers. Together, our data show that the composition of immune cells in tumor microenvironments can be quantitatively assessed by epigenetic measurements. This composition is disturbed in solid tumors, indicating a fundamental mechanism of tumor immune evasion. Epigenetic quantification of T-lymphocytes serves as independent clinical parameter for outcome prognosis.

Large-scale EEG/MEG source localization with spatial flexibility.

We propose a novel approach to solving the electro-/magnetoencephalographic (EEG/MEG) inverse problem which is based upon a decomposition of the current density into a small number of spatial basis fields. It is designed to recover multiple sources of possibly different extent and depth, while being invariant with respect to phase angles and rotations of the coordinate system. We demonstrate the methods ability to reconstruct simulated sources of random shape and show that the accuracy of the recovered sources can be increased, when interrelated field patterns are co-localized. Technically, this leads to large-scale mathematical problems, which are solved using recent advances in convex optimization. We apply our method for localizing brain areas involved in different types of motor imagery using real data from Brain-Computer Interface (BCI) sessions. Our approach based on single-trial localization of complex Fourier coefficients yields class-specific focal sources in the sensorimotor cortices.

On Optimal Channel Configurations for SMR-based Brain–Computer Interfaces

One crucial question in the design of electroencephalogram (EEG)-based brain–computer interface (BCI) experiments is the selection of EEG channels. While a setup with few channels is more convenient and requires less preparation time, a dense placement of electrodes provides more detailed information and henceforth could lead to a better classification performance. Here, we investigate this question for a specific setting: a BCI that uses the popular CSP algorithm in order to classify voluntary modulations of sensorimotor rhythms (SMR). In a first approach 13 different fixed channel configurations are compared to the full one consisting of 119 channels. The configuration with 48 channels results to be the best one, while configurations with less channels, from 32 to 8, performed not significantly worse than the best configuration in cases where only few training trials are available. In a second approach an optimal channel configuration is obtained by an iterative procedure in the spirit of stepwise variable selection with nonparametric multiple comparisons. As a surprising result, in the second approach a setting with 22 channels centered over the motor areas was selected. Thanks to the acquisition of a large data set recorded from 80 novice participants using 119 EEG channels, the results of this study can be expected to have a high degree of generalizability.

Prevalence and risk factors of neuropathic pain in survivors of myocardial infarction with pre-diabetes and diabetes. The KORA Myocardial Infarction Registry

The lowest glycemic threshold for and the risk factors associated with neuropathic pain have not been established. The aim of this study was to determine the prevalence and risk factors of neuropathic pain in survivors of myocardial infarction with diabetes, impaired glucose tolerance (IGT), impaired fasting glucose (IFG), normal glucose tolerance (NGT). Subjects aged 25–74 years with diabetes (n=214) and controls matched for age and sex (n=212) from the population‐based KORA (Cooperative Health Research in the Region of Augsburg) Myocardial Infarction Registry were assessed for neuropathic pain by the Michigan Neuropathy Screening Instrument using its pain‐relevant questions and an examination score cutpoint >2. An oral glucose tolerance test was performed in the controls. Among the controls, 61 (28.8%) had IGT (either isolated or combined with IFG), 70 (33.0%) had isolated IFG, and 81 had NGT. The prevalence of neuropathic pain was 21.0% in the diabetic subjects, 14.8% in those with IGT, 5.7% in those with IFG, and 3.7% in those with NGT (overall p<0.001). In the entire population studied (n=426), age, waist circumference, peripheral arterial disease (PAD), and diabetes were independent factors significantly associated with neuropathic pain, while in the diabetic group it was waist circumference, physical activity, and PAD (all p<0.05). In conclusion, the prevalence of neuropathic pain is relatively high among survivors of myocardial infarction with diabetes and IGT compared to those with isolated IFG and NGT. Associated cardiovascular risk factors including abdominal obesity and low physical activity may constitute targets to prevent neuropathic pain in this population.

Predicting BCI performance to study BCI illiteracy

a Berlin Institute of Technology, Machine Learning Laboratory, Berlin, Germany b Fraunhofer FIRST IDA, Berlin, Germany c Dept. of Neurology, Campus Benjamin Franklin, Charite University Medicine Berlin, Germany d Institute of Medical Psychology and Behavioral Neurobiology, Universitat Tubingen, Germany e Department of Biological Psychology, Clinical Psychology and Psychotherapy, University of Wurzburg, Germany

Simultaneous Statistical Inference in Dynamic Factor Models

Based on the theory of multiple statistical hypothesis testing, we elaborate simultaneous statistical inference methods in dynamic factor models. In particular, we employ structural properties of multivariate chi-squared distributions in order to construct critical regions for vectors of likelihood ratio statistics in such models. In this, we make use of the asymptotic distribution of the vector of test statistics for large sample sizes, assuming that the model is identified and model restrictions are testable. Examples of important multiple test problems in dynamic factor models demonstrate the relevance of the proposed methods for practical applications.

Simultaneous Statistical Inference

We introduce the problem of simultaneous statistical inference, with particular emphasis on testing multiple hypotheses. After a historic overview, general notation for the whole work is set up and different sources of multiplicity are distinguished. We define a variety of classical and modern type I and type II error rates in multiple hypotheses testing, analyze some relationships between them, and consider different ways to cope with structured systems of hypotheses. Relationships between multiple testing and other simultaneous statistical inference problems, in particular the construction of confidence regions for multi-dimensional parameters, as well as selection, ranking and partitioning problems, are elucidated. Finally, a general outline of the remainder of the work is given. Simultaneous statistical inference is concerned with the problem of making several decisions simultaneously based on one and the same dataset. In this work, simultaneous statistical decision problems will mainly be formalized by multiple hypotheses andmultiple tests. Not all simultaneous statistical decision problems are given in this formulation in the first place, but they can often be re-formulated in terms of multiple test problems. General relationships between multiple testing and other kinds of simultaneous statistical decision problems will briefly be discussed in Sect. 1.3. Moreover, we will refer to specific connections at respective occasions. For instance, we will elucidate connections between multiple testing and binary classification in Chap.6 and discuss multiple testing methods in the context of model selection in Chap.7. The origins of multiple hypotheses testing can at least be traced back to Bonferroni (1935, 1936). The “Bonferroni correction”(cf. Example 3.1) is a generic method for evaluating several statistical tests simultaneously and ensuring that the probability for at least one type I error is bounded by a pre-defined significance level α. The latter criterion is nowadays referred to as (strong) control of the familywise error rate (FWER) at level α and will be defined formally in Definition 1.2 below. In well-defined model classes, the Bonferroni method can be improved. In the 1950s, especially analysis of variance (ANOVA) models have been studied with respect to multiple comparisons of group-specific means. For instance, Tukey (1953) T. Dickhaus, Simultaneous Statistical Inference, 1 DOI: 10.1007/978-3-642-45182-9_1,