Development of a neural network for diagnosing the risk of depression according to the experimental data of the stop signal paradigm

These days, the ability to predict the result of the development of the system is the guarantee of the successful functioning of the system. Improving the quality and volume of information, complicating its presentation, the need to detect hidden connections makes it ineffective, and most often impossible, to use classical statistical forecasting methods. Among the various forecasting methods, methods based on the use of artificial neural networks occupy a special place. The main objective of our work is to create a neural network that predicts the risk of depression in a person using data obtained using a motor control performance testing system. The stop-signal paradigm (SSP) is an experimental technique to assess a person’s ability to activate deliberate movements or inhibit movements that have become inadequate to external conditions. In modern medicine, the SSP is most commonly used to diagnose movement disorders such as Parkinson’s disease or the effects of stroke. We hypothesized that SSP could serve as a basis for detecting the risk of affective diseases, including depression. The neural network we are developing is supposed to combine such behavioral indicators as: the amount of missed responses, amount of correct responses, average time, the amount of correct inhibition of movements after stopsignal onset. Such a combination of indicators will provide increased accuracy in predicting the presence of depression in a person. The artificial neural network implemented in the work allows diagnosing the risk of depression on the basis of the data obtained in the stop-signal task. An architecture was developed and a system was implemented for testing motor control indicators in humans, then it was tested in real experiments. A comparison of neural network technologies and methods of mathematical statistics was carried out. A neural network was implemented to diagnose the risk of depression using stop-signal paradigm data. The efficiency of the neural network (in terms of accuracy) was demonstrated on data with an expert assessment for the presence of depression and data from the motor control testing system.

1. About Keras [Electronic resource]. URL: https://keras.io/about/.

2. Dense layer [Electronic resource]. URL: https://keras.io/api/layers/core_layers/dense/.

3. Haykin S. Neural Networks. A Comprehensive Foundation. Moscow: Williams Publ., 2006. (in Russian)

4. Ivanov R., Kazantsev F., Zavarzin E., Klimenko A., Milakhina N., Matushkin Yu., Savostyanov A., Lashin S. ICBrainDB: An integrated database for finding associations between genetic factors and EEG markers of depressive disorders. J. Pers. Med. 2022;12(1):53. DOI 10.3390/jpm12010053.

5. Layer activation functions [Electronic resource]. URL: https://keras.io/api/layers/activations/.

6. Matplotlib documentation – Matplotlib 3.5.1 documentation [Electronic resource]. URL: https://matplotlib.org/stable/index.html.

7. Mean Squared Error (MSE) [Electronic resource]. URL: https://www.probabilitycourse.com/chapter9/9_1_5_mean_squared_error_MSE. php.

8. Model training APIs [Electronic resource]. URL: https://keras.io/api/models/model_training_apis/.

9. Models API [Electronic resource]. URL: https://keras.io/api/models/.

10. Normalization of input vectors (Normalization) – Loginom Wiki [Electronic resource]. URL: https://wiki.loginom.ru/articles/normalization.html.

11. Pandas documentation – pandas 1.4.2 documentation [Electronic resource]. URL: https://pandas.pydata.org/pandas-docs/stable/.

12. ReLu Function in Python – JournalDev [Electronic resource]. URL: https://www.journaldev.com/45330/relu-function-in-python.

13. SGD [Electronic resource]. URL: https://keras.io/api/optimizers/sgd/.

14. Vinogradova E.Yu. Principles of choosing the optimal topology of neural network to support managerial decision making. Uprav lenets = The Manager. 2012;7-8:74-78. (in Russian)