RESUMEN
Depression (DEP) and dementia of the Alzheimer's type (DAT) represent the most common neuropsychiatric disorders in elderly patients. Accurate differential diagnosis is indispensable to ensure appropriate treatment. However, DEP can yet mimic cognitive symptoms of DAT and patients with DAT often also present with depressive symptoms, impeding correct diagnosis. Machine learning (ML) approaches could eventually improve this discrimination using neuropsychological test data, but evidence is still missing. We therefore employed Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) and conventional Logistic Regression (LR) to retrospectively predict the diagnoses of 189 elderly patients (68 DEP and 121 DAT) based on either the well-established Consortium to Establish a Registry for Alzheimer's Disease neuropsychological assessment battery (CERAD-NAB) or a flexible battery approach (FLEXBAT). The best performing combination consisted of FLEXBAT and NB, correctly classifying 87.0% of patients as either DAT or DEP. However, all accuracies were similar across algorithms and test batteries (83.0% - 87.0%). Accordingly, our study is the first to show that common ML algorithms with their default parameters can accurately differentiate between patients clinically diagnosed with DAT or DEP using neuropsychological test data, but do not necessarily outperform conventional LR.
RESUMEN
Infections have numerous effects on the brain. However, possible roles of the brain in protecting against infection, and the developmental origin and role of brain signaling in immune response, are largely unknown. We exploited a unique Xenopus embryonic model to reveal control of innate immune response to pathogenic E. coli by the developing brain. Using survival assays, morphological analysis of innate immune cells and apoptosis, and RNA-seq, we analyzed combinations of infection, brain removal, and tail-regenerative response. Without a brain, survival of embryos injected with bacteria decreased significantly. The protective effect of the developing brain was mediated by decrease of the infection-induced damage and of apoptosis, and increase of macrophage migration, as well as suppression of the transcriptional consequences of the infection, all of which decrease susceptibility to pathogen. Functional and pharmacological assays implicated dopamine signaling in the bacteria-brain-immune crosstalk. Our data establish a model that reveals the very early brain to be a central player in innate immunity, identify the developmental origins of brain-immune interactions, and suggest several targets for immune therapies.
RESUMEN
OBJECTIVE: Psycholinguistic evidence suggests that certain word characteristics might influence recall rates in word-list learning tests. These effects were investigated in the German California Verbal Learning Test (CVLT-G) in a clinical setting. METHOD: Subjects were memory clinic patients without cognitive diagnosis (N = 45) and with dementia of the Alzheimer type (DAT) (N = 48) matched for age, sex, depressive symptoms, and education. The CVLT-G's words were analyzed with regard to length, frequency, and neighborhood size and dichotomized into low and high value groups. For each linguistic variable, a 2 (diagnosis: control vs. DAT) × 3 (time: Trial 1 vs. Trial 5 vs. Long Delay Free Recall) × 2 (linguistic: low vs. high) repeated measures analysis of variance (RM-ANOVA) was conducted. RESULTS: RM-ANOVAs revealed a main effect for frequency, F(1,91) = 21.03, p < 0.001, and interactions between time and frequency, F(1.97,179.09) = 5.18, p = 0.007, and diagnosis and neighborhood, F(1.77,161.23) = 13.60, p < 0.001. High-frequency words were better recalled at Trial 5 (Cohen's d = 0.37) and long delayed free recall (d = 0.16) and learning from Trials 1 to 5 was better for high-frequency words (d = 0.39). Controls recalled large neighborhood words better whereas the opposite was true for persons with DAT (d = 0.76). CONCLUSION: Frequency and neighborhood size seem to influence learning and retention in the CVLT-G with neighborhood size producing opposed effects for persons with and without DAT. These results are in line with international experimental studies and likely not specific to the German language. Potential diagnostic implications and possibilities for test construction and interpretation are discussed.
