Improving the accuracy of diagnostics tasks is essential in various medical fields. When there are small data for training, there are high risks of overfitting or underfitting the machine learning model. This makes it impossible to apply it in practice. To solve such a problem, we can use various data augmentation methods. This paper focuses on neural network methods of data augmentation. The authors have investigated a variational autoencoder and approach based on GAN to generate artificial numerical data and then use it by machine-learning-based classifiers. The authors examined the proposed method for diagnosing diabetes mellitus development task. Experiments confirmed that autoencoders generated a dataset similar to an initial one, with a similarity score being 0.93. The authors established a significant accuracy improvement of Random Forest, AdaBoost, and Logistic regression classifiers based on processing an extended dataset. The application of the new dataset obtained using GAN does not ensure satisfactory accuracy. Such an issue may be due to a lack of samples for the training of this neural networks class. Further research is likely to be carried out into ensembles based on a single machine learning method, which will process decorrelated samples acquired by methods investigated in this paper.
The development of modern medicine has been marked by digitizing a wide variety of information and
the automation of many processes [
However, the scarce data may impede the implementation of machine learning. Alternatively, abnormal data may lead to increased accuracy, which is a critical point in this area.
One possible solution to this problem lies in adopting data augmentation methods. This approach can allow synthesizing of enough data to train the selected artificial intelligence tool.
Nowadays, there are quite a few simple methods for manipulating an available sample of data to
increase its size. The data are enlarged both by rows and by columns [
Many neural network methods have been developed to increase a dataset today. A wide variety of
artificial neural network topologies are employed here. The augmentation is performed using a variety
of information - from time series to images. Generative adversarial network [
This section includes a description of two neural-network-based approaches for numerical data augmentation used in this paper. The main objective is to improve the classification accuracy in Clinical Medicine based on expanded datasets.
The first approach selected is a new method for generating an artificial dataset based on a Generative
adversarial network (GAN) [
A peculiarity of this method is that the authors use a special normalization method and a set of stateof-the-art model learning methods, and a post-annotated network. In other respects, the method works like a conventional GAN.
Another interesting method is data augmentation based on a variational autoencoder [
While designing methods based on variational autoencoder, one should define the number of neurons in the first and the second latent layers and set the number of latent factors. It will contain all applicable information and serve as a decoder to recover all initial inputs. After all the necessary settings have been made, the learning procedure can be performed.
If the hidden dependencies between variables are linear, the variational autoencoder works as a PCA
method [
The synthesis of the new data is as follows. Beforehand we know the variance and the mean of our latent variables, which are determined by the autoencoder. The next step is the use of a normal distribution with the variance and the mean for each of the latent variables. It is needed for the selection of the value for all latent variables. It is these that serve as starting points from which all attributes of the initial data set can be reproduced.
In case the latent dependencies between variables are linear, the variational autoencoder works like
the PCA method [
Diagnostics tasks are widespread in the medical industry. The majority of them are reduced to a
classification task, and we can apply machine learning techniques. For example, in [
Simulation of the classifiers investigated based on extended datasets using neural network methods. Experimental studies were carried out by dividing the dataset randomly into two parts at a ratio of 80% to 20%. Cross-validation was then applied (5 times). In this way, the reliability of the results was ensured.
The paper presents two neural network approaches for the artificial expansion of short datasets. Let us consider the outcomes and evaluations of the synthesized data for each of them.
Autoencoder-based modeling was carried out in order to synthesize a new dataset whose size would
match the size of the original dataset. A comparison between the synthesized dataset with the original
one based on several indicators from [
In addition, Figure 2 presents a comparison of the feature distributions for the initial and synthesized datasets.
It should be noted that the autoencoder generated the same number of instances of each class as the number of instances in the initial dataset.
The application results of different classifiers on the extended dataset are summarised in Table 1.
Figure 2: Distribution per features for initial and synthetic datasets
Total accuracy (autoencoders) 0,8 0,78 0,76 0,74 0,72 0,7
0 75 150 225 300 500 768 AdaBoost 0,7631 0,7652 0,7746 0,7745 0,7904 0,8203 0,8301 Logistic Regression 0,7696 0,7794 0,7844 0,7836 0,796 0,8029 0,8295 Random Forest 0,7656 0,7628 0,7637 0,7775 0,797 0,8116 0,8249
SVC 0,7591 0,7664 0,7593 0,7563 0,7782 0,7856 0,7985
As can be seen from Figure 3 the increase in the number of additionally added, artificially generated vectors to the initial data set led to an increase in the accuracy of all classifiers. The highest accuracy was obtained by added to the initial set the same dimension of the artificial sample (768 additional vectors).
The authors adopted the method from [
Figure 4 shows a comparison of the feature distributions for the initial and synthesized datasets.
It is worth remarking that the GAN-based method attempted to balance the dataset. It generated significantly more instances of the smaller class compared to the initial dataset.
The application results of different classifiers on the extended dataset are summarised in Table 2.
Figure 4: Distribution per features for initial and synthetic datasets
Total accuracy (GAN) 0,78 0,76 0,74 0,72 0,7 0,68 0,66 0,64
0 75 150 225 300 500 768 AdaBoost 0,7631 0,7509 0,7364 0,7543 0,7876 0,7905 0,8015 Logistic Regression 0,7696 0,7604 0,7462 0,7321 0,7148 0,7272 0,7352 Random Forest 0,7656 0,7426 0,732 0,7452 0,7456 0,7516 0,7946
SVC 0,7591 0,7509 0,7255 0,7261 0,7064 0,7027 0,7326
As can be seen from Figure 5 the increase in the number of additionally added, artificially generated vectors to the initial data set did not always lead to an increase in the accuracy of the classifiers. Only extension of the initial set by more than 60% of new, artificially synthesized data vectors helped to reduce the errors of classifiers. The highest accuracy, as in the previous case, was obtained by added to the initial dataset the same dimension of the artificial sample (768 additional vectors). 3.2.
This section compares both the new datasets generated by both methods under investigation and the classification results based on their application.
In this paper, a comparison of the results obtained by every method investigated was performed on the
basis of some indicators from [
As shown in Table 1, the data augmentation method based on the autoencoder provides significantly higher results in comparison with the dataset obtained by GAN. This can significantly affect the performance of classifiers with these data.
However, such dataset decorrelation enables the construction of ensemble models based on a single classifier to process different datasets. This approach can significantly improve the accuracy of classification methods in medicine.
The performance of both neural network approaches was compared by determining the accuracy of a few known classifiers: Random forest classifier; AdaBoost classifier; Logistic regression classifier; SVM classifier. They were employed for classification based on the initial and new datasets. It should be noted that the dimensionality of the new datasets was doubled, thus the synthesized data were added to the original one. The outcomes that are based on Total accuracy, Precision, and Recall are shown in Fig. 6. Since the problem is not balanced, F-measure was not taken into account.
GAN Autoencoder Initial dataset SVM classifier
Logit classifier
AdaBoost classifier Random forest classifier
GAN SVM classifier
Logit classifier
AdaBoost classifier Random forest classifier
GAN SVM classifier
Logit classifier
AdaBoost classifier Random forest classifier 0,65 0 0
0,75 Total accuracy 0,8
0,85
0,7 0,2 a) b) 0,4
Recall Precision 0,6 0,8
Initial dataset 0,2 0,4 0,6 0,8
1
From the graphs in Fig. 6, it follows that the highest accuracy based on all performance indicators is achieved by using a synthesized dataset with an autoencoder. The application of GAN for data augmentation shows a much lower performance of the known classifiers compared to processing an initial dataset (based on the total accuracy). However, AdaBoost and Random Forest algorithms provide more accurate results in this case. This can be explained by the insufficient amount of training data for effective GAN performance, which affected the one of SVM and Logistic Regression classifiers.
This paper deals with the numerical data augmentation task in Clinical Medicine. The authors have experimentally evaluated the performance of modern neural network methods to solve the problem: autoencoders and a GAN. Such an approach helps to reduce risks of overfitting or underfitting when using machine learning models in case of small data processing.
The modeling of the performance of these methods has been carried out using the dataset for solving a classification task. In this case, we tried to predict the possibility of diabetes development. The dataset is not balanced. Experiments have shown that autoencoders generate the most similar data according to the Similiarity score. In addition, the accuracy of classifiers based on these data is significantly higher. Compared with the initial dataset, we have improved the target resolution accuracy by about 10%.
Given the different results of the similarity evaluation of the synthesized datasets concerning the initial one and the different accuracy of the classifiers based on such data, the ensemble learning approach can be used in further research to improve the accuracy of various diagnostics tasks. In particular, the approach of constructing a stacking ensemble of homotypic classifiers that will process different systematically studied datasets seems promising. This very approach can provide a significant increase in the accuracy of classifiers when solving applied tasks of diagnostics in various fields [1015] when processing average datasets.
The National Research Foundation of Ukraine funds this study from the state budget of Ukraine within the project “Decision support system for modeling the spread of viral infections” (№ 2020.01 / 0025).