Prediction of Depression Index Based on LSTM and CNN

Yi Li; Zida Cai; Jingyi Wang

doi:10.62051/7xyy5c33

Authors

Yi Li
Zida Cai
Jingyi Wang

DOI:

https://doi.org/10.62051/7xyy5c33

Keywords:

LSTM; CNN; Prediction of depression index.

Abstract

In recent years, with the increase of social pressure and the acceleration of life pace, the incidence of depression has shown a rising trend, which makes the prevention, intervention and treatment of depression research is particularly important. At the same time, depression index is an important index used to measure and evaluate the degree of individual depression. In this paper, the MADRS scores corresponding to Montgomery Depression Scale were studied as depression index. In this paper, a depression index prediction model based on long short-term memory neural network (LSTM) and convolutional neural network (CNN) was established by collecting the data of several depressed patients in a hospital. The results show that the model has good predictive ability and stability, which can make a real-time judgment of depression in clinic and improve the efficiency of medical department.

Downloads

Download data is not yet available.

References

[1] Wang Y, Li Z. Depression Detection with Dynamic and Static Visual Features [J]. Journal of circuits, systems and computers, 2023 (18): 32.

[2] Knapskog A B, Barca M L, Engedal K. A comparison of the validity of the Cornell Scale and the MADRS in detecting depression among memory clinic patients [J]. Dement Geriatr Cogn Disord, 2011, 32 (4): 287-294.

[3] Sandheep P, Vineeth S, Poulose M, et al. Performance analysis of deep learning CNN in classification of depression EEG signals [C] // TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON). IEEE, 2019.

[4] Bashiri F, Mokhtarpour A. Depression classification and recognition by graph-based features of EEG signals [J]. International journal of medical engineering and informatics, 2022 (3): 14.

[5] Li Y, Fang Y, Ren X, et al. EEG-based depression recognition using feature selection method with fuzzy label [J]. Journal of King Saud University - Computer and Information Sciences, 2024, 36 (3).

[6] Zhang Y, Fu Z. The study of EEG Recognition of Depression on Bi-LSTM based on ERP P300 [J]. E3S Web of Conferences, 2020, 185 (18): 02007.

[7] Hu X, Shu J, Jin Z. Depression tendency detection model for Weibo users based on Bi-LSTM [J]. IEEE, 2021.

[8] Muzammel M, Salam H, Hoffmann Y, et al. AudVowelConsNet: A Phoneme-Level Based Deep CNN Architecture for Clinical Depression Diagnosis [J]. 2020.

[9] Thekkekara J P, Yongchareon S, Liesaputra V. An attention-based CNN-BiLSTM model for depression detection on social media text [J]. Expert Systems with Applications, 2024, 249.

[10] Lin L, Chen X, Shen Y, et al. Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model [J]. Applied Sciences, 2020, 10 (23): 8701.