Search

Using results from genome-wide association studies for understanding complex traits is a current challenge. Here we review how genotype data can be used with different machine learning (ML) methods to predict phenotype occurrence and severity from genotype data. We discuss common feature encoding schemes and how studies handle the often small number of samples compared to the huge number of variants. We compare which ML methods are being applied, including recent results using deep neural networks. Further, we review the application of methods for feature explanation and interpretation., (© 2021 Walter de Gruyter GmbH, Berlin/Boston.)

Along with digitization, automatic data-driven decision support systems become increasingly popular. Mortality prediction is a vital part of that decision process. With more data available, sophisticated machine learning models like (Artificial) Neural Networks (NNs) can be applied and promise favorable performance. We evaluate the reproducibility of a published mortality prediction approach using NNs along with the possibility to generalize it to a bigger and more generic dataset. We describe an extensive preprocessing pipeline, as well as the evaluation of different sampling techniques and NN architectures. Through training on a loss function that optimizes both, precision and recall, in combination with a good set of hyperparameters and a set of new features, we use a NN to predict in-hospital mortality with accuracy, sensitivity, and area under the receiver operating characteristic score of greater than 0.8., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Critical care can benefit from analyzing data by machine learning approaches for supporting clinical routine and guiding clinical decision-making. Developing data-driven approaches for an early detection of systemic inflammatory response syndrome (SIRS) in patients of pediatric intensive care and exploring the possibility of an approach using training data sets labeled automatically beforehand by knowledge-based approaches rather than clinical experts. Using naïve Bayes classifier and an artificial neuronal network (ANN), trained with real data labeled by (1) domain experts ad (2) a knowledge-based decision support system (CDSS). Accuracies were evaluated by the data set labeled by domain experts using a 10-fold cross validation. The ANN approach trained with data labeled by domain experts yielded a specificity of 0.9139 and sensitivity of 0.8979, whereas the approach trained with a data set labeled by a knowledge-based CDSS achieves a specificity of 0.9220 and a sensitivity of 0.8887. ANN yielded promising results for data-driven detection of pediatric SIRS with real data. Our comparison shows the feasibility of using training data labeled automatically by knowledge-based approaches rather than manually allocated by experts. [ABSTRACT FROM AUTHOR]

Neural networks are one option to implement decision support systems for health care applications. In this paper, we identify optimal settings of neural networks for medical diagnoses: The study involves the application of supervised machine learning using an artificial neural network to distinguish between gout and leukaemia patients. With the objective to improve the base accuracy (calculated from the initial set‐up of the neural network model), several enhancements are analysed, such as the use of hyperbolic tangent activation function instead of the sigmoid function, the use of two hidden layers instead of one, and transforming the measurements with linear regression to obtain a smoothened data set. Another setting we study is the impact on the accuracy when using a data set of reduced size but with higher data quality. We also discuss the tradeoff between accuracy and runtime efficiency. [ABSTRACT FROM AUTHOR]