Journal of Clinical and Diagnostic Research, ISSN - 0973 - 709X

Users Online : 8017

Original article / research
Year : 2017 | Month : May | Volume : 11 | Issue : 5 | Page : VC01 - VC04

Artificial Neural Network (ANN) Model to Predict Depression among Geriatric Population at a Slum in Kolkata, India

Arkaprabha Sau, Ishita Bhakta

1. Junior Resident, Department of Community Medicine, R.G. Kar Medical College and Hospital, Kolkata, West Bengal, India. 2. PhD Research Fellow, Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal, India.

Correspondence Address :
Dr. Arkaprabha Sau,
Professor Colony, Kanakpur, Panskura R.S., Purba Medinipur-721152, West Bengal, India.


Introduction: Depression is one of the most important causes of mortality and morbidity among the geriatric population. Although, the aging brain is more vulnerable to depression, it cannot be considered as physiological and an inevitable part of ageing. Various sociodemographic and morbidity factors are responsible for the depression among them. Using Artificial Neural Network (ANN) model depression can be predicted from various sociodemographic variables and co morbid conditions even at community level by the grass root level health care workers.

Aim: To predict depression among geriatric population from sociodemographic and morbidity attributes using ANN.

Materials and Methods: An observational descriptive study with cross-sectional design was carried out at a slum under the service area of Bagbazar Urban Health and Training Centre (UHTC) in Kolkata. Among 126 elderlies under Bagbazar UHTC, 105 were interviewed using predesigned and pretested schedule. Depression status was assessed using 30 item Geriatric Depression Scale. WEKA 3.8.0 was used to develop the ANN model and test its performance.

Results: Prevalence of depression among the study population was 45.7%. Various sociodemographic variables like age, gender, literacy, living spouse, working status, personal income, family type, substance abuse and co morbid conditions like visual problem, mobility problem, hearing problem and sleeping problem were taken into consideration to develop the model. Prediction accuracy of this ANN model was 97.2%.

Conclusion: Depression among geriatric population can be predicted accurately using ANN model from sociodemographic and morbidity attributes.


Cross-sectional design, Geriatric depression scale, Machine learning

How to cite this article :

Arkaprabha Sau, Ishita Bhakta. ARTIFICIAL NEURAL NETWORK (ANN) MODEL TO PREDICT DEPRESSION AMONG GERIATRIC POPULATION AT A SLUM IN KOLKATA, INDIA. Journal of Clinical and Diagnostic Research [serial online] 2017 May [cited: 2017 Jun 28 ]; 11:VC01-VC04. Available from

DOI and Others

DOI: 10.7860/JCDR/2017/23656.9762

Date of Submission: Aug 20, 2016
Date of Peer Review: Nov 28, 2016
Date of Acceptance: Dec 28, 2016
Date of Publishing: May 01, 2017


JCDR is now Monthly and more widely Indexed .
  • PubMed Central® (PMC)New
  • Academic Search Complete Database
  • Chemical Abstracts Service
  • Directory of Open Access Journals (DOAJ)
  • EBSCOhostNew
  • Embase & EMbiology
  • Google Scholar
  • HINARI Access to Research in Health Programme
  • Indian Science Abstracts (ISA)
  • Journal seek Database
  • Open J-Gate
  • Popline (reproductive health literature)