Abstract
As it is not possible to identify mental risk elements through basic physical examinations and even individuals suspected of having serious depression do not take mental examinations as much as physical examinations, it is necessary to specifically predict and analyze mental diseases through basic physical examinations alone. Therefore, in this study, a model capable of predicting severe depression through physical elements and individual environmental factors is created, and its accuracy, sensitivity, and specificity are analyzed. In particular, neural networks are utilized for the prediction of severe depression. The artificial neural network (ANN) model is used and the results are compared. The comparison of the results the ANN model using various optimization methods revealed that the severe depression prediction accuracy of the ANN model is 83.16%. In addition, the prediction accuracy of the machine learning algorithm for severe depression prediction is presented in detail by comparing the area under curve (AUC) results of the two models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lee, S.H., Park, M., Yoon, D.H., Lee, Y., Kim, S.S.: Gender difference in associations between serum cholesterol levels and depression symptoms in healthy general population. Korean J. Psychosom. Med. 25(1), 27–32 (2017)
Sahebzamani, F.M., DAoust, R.F., Friedrich, D., Aiyer, A.N., Reis, S.E., Kip, K.E.: Relationship among low cholesterol levels, depressive symptoms, aggression, hostility, and cynicism. J. Clin. Lipidol. 7, 208–216 (2013)
Schatz, I.J., Masaki, K., Yano, K., Chen, R., Rodriguez, B.L., Curb, J.D.: Cholesterol and all-cause mortality in elderly people from the Honolulu Heart Program: a cohort study. Lancet 358, 351–355 (2001)
Lee, H.S.: Depression and related risk factors in the elderly with a focused on health habits, mental health, chronic diseases, and nutrient intake status. J. Korean Diet Assoc. 24(2), 169–180 (2018)
Kronke, K., Spitzer, R.L., Williams, J.B.: The PHQ-9: validity of a brief depression severity measure. J. Gen. Intern. Med. 16(9), 606–613 (2001)
Park, S.J., Choi, H.R., Choi, J.H., Kim, K., Hong, J.P.: Reliability and validity of the Korean version of the patient health questionnaire-9 (PHQ-9). Anxiety Mood 6(2), 119–124 (2010)
Kingma, D., Ba, J.: ADAM: a method for stochastic optimization. In: International Conference on Learning Representations. San Diego, CA, USA (2015)
Sovierzoski, M.A., Argoud, F.I., Azevedo, F.M.: Evaluation of ANN classifiers during supervised training with ROC analysis and cross validation. In: International Conference on BioMedical Engineering and Informatics, pp. 274–278 (2008)
Acknowledgements
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2017R1C1B5017556).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Park, H. (2020). Classifying Serious Depression Based on Blood Test: A Machine Learning Approach. In: Barolli, L., Xhafa, F., Hussain, O. (eds) Innovative Mobile and Internet Services in Ubiquitous Computing . IMIS 2019. Advances in Intelligent Systems and Computing, vol 994. Springer, Cham. https://doi.org/10.1007/978-3-030-22263-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-22263-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22262-8
Online ISBN: 978-3-030-22263-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)