A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

Abstract

The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the "small n large p" problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients' omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers.

From genetics to systems biology of stress-related mental disorders

“…Therefore these models do not lend themselves to easy interpretation, a common requirement in the biological sciences. However, even with this potential drawback, they have shown promise in analyzing genomic datasets ( Arloth et al, 2020 ; Chen et al, 2019 ; Min et al, 2017 ; Tranchevent et al, 2019 ). Deep learning has enabled efficient multimodal neuroimaging fusion, capitalizing on the strength of each modality ( Maglanoc et al, 2020 ; Plis et al, 2014 ; Sui et al, 2012 ; Zhang et al, 2020 ).…”

HINT: Hierarchical interaction network for clinical-trial-outcome predictions

“…d Logistic regression (LR): LR was used 10,25 for trial outcome predictions. d Random Forest (RF): Similar to LR, RF was used 10,25 15 It uses the same feature as HINT. The feature vectors are fed into a threelayer feedforward neural network, where the hidden dimensions are 500 and 100, and the rectified linear unit (ReLU) function is used as an activation function in the hidden layer to provide nonlinearity.…”

“…Due to the limited data and task scope, existing methods often simplify their predictions by limited input features and rely on classical classification methods (e.g., random forest) that are not explicitly designed for modeling the interaction of different trial components. 8,9,12,13,15 This simplified assumption impedes the prediction performance of the existing works.…”

Prediction of the Development of Periodontal Disease

“…The review [11] provides data on the eff ective use of artifi cial neural networks in the organization of medical services. It is used to predict the development of tuberculosis and neuroblastoma [12,13]. In addition, the use of artifi cial neural networks to predict outbreaks of COVID-19 is described [14].…”