Refine
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
Institute
- Medizin (4)
Importance: The entry of artificial intelligence into medicine is pending. Several methods have been used for the predictions of structured neuroimaging data, yet nobody compared them in this context.
Objective: Multi-class prediction is key for building computational aid systems for differential diagnosis. We compared support vector machine, random forest, gradient boosting, and deep feed-forward neural networks for the classification of different neurodegenerative syndromes based on structural magnetic resonance imaging.
Design, setting, and participants: Atlas-based volumetry was performed on multi-centric T1-weighted MRI data from 940 subjects, i.e., 124 healthy controls and 816 patients with ten different neurodegenerative diseases, leading to a multi-diagnostic multi-class classification task with eleven different classes.
Interventions: N.A.
Main outcomes and measures: Cohen’s kappa, accuracy, and F1-score to assess model performance.
Results: Overall, the neural network produced both the best performance measures and the most robust results. The smaller classes however were better classified by either the ensemble learning methods or the support vector machine, while performance measures for small classes were comparatively low, as expected. Diseases with regionally specific and pronounced atrophy patterns were generally better classified than diseases with widespread and rather weak atrophy.
Conclusions and relevance: Our study furthermore underlines the necessity of larger data sets but also calls for a careful consideration of different machine learning methods that can handle the type of data and the classification task best.
Background: The newly introduced German pediatric screening examination at the end of the third year of life (U7a) incorporates visual function testing in particular; there is no ophthalmic screening during childhood in Germany. The purpose of this study is to investigate the relationship between participation in U7a and visual function at the preschool health examination (PHE) in the sixth year of life. Methods: This study evaluated PHE data from school enrollment years 2009/2010 to 2014/2015 of Rhineland-Palatinate, Germany. Visual acuity (VA) at PHE was assessed with Rodenstock visual acuity test device (tumbling E) wearing glasses if present. The relationship between participation in U7a and VA <0.7 at PHE was calculated for reduced monocular and binocular VA using multiple logistic regression adjusted for potential confounders. Results: Data from 189,704 children (91,041 girls) in 35 out of 36 districts were included. The first children to participate in U7a were enrolled in 2011/2012 school year. In total, 90,339 children (47.6%) had U7a before PHE, while 99,365 (52.4%) had not. VA <0.7 in at least one eye was measured at PHE in 8429 (4.4%) children, and in both eyes in 4345 (2.3%) children. Participation in U7a was not associated with VA <0.7 at PHE (odds ratio 0.99; 95% confidence interval: 0.94–1.04). Conclusions: The proportion of children with VA <0.7 at PHE was high. No beneficial effect of newly introduced German U7a pediatric screening examination was found for reduced VA at PHE.
Memory Concerns, Memory Performance and Risk of Dementia in Patients with Mild Cognitive Impairment
(2014)
Background: Concerns about worsening memory (“memory concerns”; MC) and impairment in memory performance are both predictors of Alzheimer's dementia (AD). The relationship of both in dementia prediction at the pre-dementia disease stage, however, is not well explored. Refined understanding of the contribution of both MC and memory performance in dementia prediction is crucial for defining at-risk populations. We examined the risk of incident AD by MC and memory performance in patients with mild cognitive impairment (MCI).
Methods: We analyzed data of 417 MCI patients from a longitudinal multicenter observational study. Patients were classified based on presence (n = 305) vs. absence (n = 112) of MC. Risk of incident AD was estimated with Cox Proportional-Hazards regression models.
Results: Risk of incident AD was increased by MC (HR = 2.55, 95%CI: 1.33–4.89), lower memory performance (HR = 0.63, 95%CI: 0.56–0.71) and ApoE4-genotype (HR = 1.89, 95%CI: 1.18–3.02). An interaction effect between MC and memory performance was observed. The predictive power of MC was greatest for patients with very mild memory impairment and decreased with increasing memory impairment.
Conclusions: Our data suggest that the power of MC as a predictor of future dementia at the MCI stage varies with the patients' level of cognitive impairment. While MC are predictive at early stage MCI, their predictive value at more advanced stages of MCI is reduced. This suggests that loss of insight related to AD may occur at the late stage of MCI.
Background: Austria has recently been embroiled in the complex debate on the legalization of measures to end life prematurely. Empirical data on end-of-life decisions made by Austrian physicians barely exists. This study is the first in Austria aimed at finding out how physicians generally approach and make end-of-life therapy decisions.
Methods: The European end-of-life decisions (EURELD) questionnaire, translated and adapted by Schildmann et al., was used to conduct this cross-sectional postal survey. Questions on palliative care training, legal issues, and use of and satisfaction with palliative care were added. All Austrian specialists in hematology and oncology, a representative sample of doctors specialized in internal medicine, and a sample of general practitioners, were invited to participate in this anonymous postal survey.
Results: Five hundred forty-eight questionnaires (response rate: 10.4%) were evaluated. 88.3% of participants had treated a patient who had died in the previous 12 months. 23% of respondents had an additional qualification in palliative medicine. The cause of death in 53.1% of patients was cancer, and 44.8% died at home. In 86.3% of cases, pain relief and / or symptom relief had been intensified. Further treatment had been withheld by 60.0%, and an existing treatment discontinued by 49.1% of respondents. In 5 cases, the respondents had prescribed, provided or administered a drug which had resulted in death. 51.3% of physicians said they would never carry out physician-assisted suicide (PAS), while 30.3% could imagine doing so under certain conditions. 38.5% of respondents supported the current prohibition of PAS, 23.9% opposed it, and 33.2% were undecided. 52.4% of physicians felt the legal situation with respect to measures to end life prematurely was ambiguous. An additional qualification in palliative medicine had no influence on measures taken, or attitudes towards PAS.
Conclusions: The majority of doctors perform symptom control in terminally ill patients. PAS is frequently requested but rarely carried out. Attending physicians felt the legal situation was ambiguous. Physicians should therefore receive training in current legislation relating to end-of-life choices and medical decisions. The data collected in this survey will help political decision-makers provide the necessary legal framework for end-of-life medical care.