Neural network approaches to grade adult depression

Subhagata Chattopadhyay, Preetisha Kaur, Fethi Rabhi, U. Rajendra Acharya

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g.; 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches - 'supervised', i.e.; classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e.; 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.

Original languageEnglish
Pages (from-to)2803-2815
Number of pages13
JournalJournal of Medical Systems
Volume36
Issue number5
DOIs
Publication statusPublished - 01-10-2012
Externally publishedYes

Fingerprint

Fuzzy inference
Backpropagation
Depression
Neural networks
Supervised learning
Self organizing maps
Learning
Cluster Analysis
Classifiers
Unsupervised learning
Hybrid systems
MATLAB
Decision Making
Screening
Decision making
Quality of Life
Psychology
Incidence

All Science Journal Classification (ASJC) codes

  • Medicine (miscellaneous)
  • Information Systems
  • Health Informatics
  • Health Information Management

Cite this

Chattopadhyay, S., Kaur, P., Rabhi, F., & Acharya, U. R. (2012). Neural network approaches to grade adult depression. Journal of Medical Systems, 36(5), 2803-2815. https://doi.org/10.1007/s10916-011-9759-1
Chattopadhyay, Subhagata ; Kaur, Preetisha ; Rabhi, Fethi ; Acharya, U. Rajendra. / Neural network approaches to grade adult depression. In: Journal of Medical Systems. 2012 ; Vol. 36, No. 5. pp. 2803-2815.
@article{d363a02c01454855ab57c8add881df7c,
title = "Neural network approaches to grade adult depression",
abstract = "Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g.; 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches - 'supervised', i.e.; classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e.; 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.",
author = "Subhagata Chattopadhyay and Preetisha Kaur and Fethi Rabhi and Acharya, {U. Rajendra}",
year = "2012",
month = "10",
day = "1",
doi = "10.1007/s10916-011-9759-1",
language = "English",
volume = "36",
pages = "2803--2815",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "5",

}

Chattopadhyay, S, Kaur, P, Rabhi, F & Acharya, UR 2012, 'Neural network approaches to grade adult depression', Journal of Medical Systems, vol. 36, no. 5, pp. 2803-2815. https://doi.org/10.1007/s10916-011-9759-1

Neural network approaches to grade adult depression. / Chattopadhyay, Subhagata; Kaur, Preetisha; Rabhi, Fethi; Acharya, U. Rajendra.

In: Journal of Medical Systems, Vol. 36, No. 5, 01.10.2012, p. 2803-2815.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network approaches to grade adult depression

AU - Chattopadhyay, Subhagata

AU - Kaur, Preetisha

AU - Rabhi, Fethi

AU - Acharya, U. Rajendra

PY - 2012/10/1

Y1 - 2012/10/1

N2 - Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g.; 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches - 'supervised', i.e.; classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e.; 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.

AB - Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g.; 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches - 'supervised', i.e.; classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e.; 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.

UR - http://www.scopus.com/inward/record.url?scp=84867309019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867309019&partnerID=8YFLogxK

U2 - 10.1007/s10916-011-9759-1

DO - 10.1007/s10916-011-9759-1

M3 - Article

C2 - 21833604

AN - SCOPUS:84867309019

VL - 36

SP - 2803

EP - 2815

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 5

ER -