Stacked Bi-directional LSTM Layer Based Model for Prediction of Possible Heart Disease during Lockdown Period of COVID-19

Bidirectional LSTM


  • Samir Kumar Bandyopadhyay
  • Shawni Dutta Professor, Department of Computer Science and Engineering, University of Calcutta, Kolkata, India.


Mental Anxiety, Cardiac Troubles, Stacked Bi-LSTM, RNN, Deep Learning


Cardiovascular Disease (CVD) affects the walls of the arteries that
supply the myocardium. CVD is not a single disease. It is a cluster of
diseases and injuries that affect the cardiovascular system i.e. the heart
and blood vessels. Heart failure is concern in patients with COVID-19.
Alternately mental anxiety during lockdown period of COVID-19 may
increase CVD. For assisting health care system, an automated tool is
proposed in this paper that uses Reccurrent Neural Network (RNN).
A stacked bi-directional LSTM layer based model is proposed in this
paper that considers interfering factors from past health records while
detecting patients with cardiac problems. Experimental results have
indicated promising accuracy of 93.22% in predicting patients with
cardiac troubles.


Rajkumar RP. COVID-19 and mental health: A review

of the existing literature. Asian J Psychiatr 2020; 52: 102066.

De Hert M, Detraux J, Vancampfort D. The intriguing

relationship between coronary heart disease and

mental disorders. 2018; 31-40.

Shen SHI, Dinggang Wu Gurrong. Deep Learning in

Medical Image Analysis. Annu Rev Biomed Eng 2017;

: 221-248. DOI: 10.1146/annurev-bioeng-071516.

Kirmani M. Cardiovascular Disease Prediction using

Data Mining Techniques. Orient J Comput Sci Technol

; 10(2): 520-528. DOI:10.13005/ojcst/10.02.38.

Sai PP, Reddy C. International Journal of Computer

Science and Mobile Computing Heart Disease Prediction

Using Ann Algorithm In Data Mining. Int J Comput Sci

Mob Comput 2017; 6(4): 168-172.

Bahrami B, Hosseini Shirvani M. Prediction and

Diagnosis of Heart Disease by Data Mining Techniques.

J Multidiscip Eng Sci Technol 2015; 2(2): 3159-1340.

Mohan S, Thirumalai C, Srivastava G. Effective heart

disease prediction using hybrid machine learning

techniques. IEEE Access 2019; 7: 81542-81554. DOI:


Chauhan A, Jain A, Sharma P, Deep V. Heart Disease

Prediction using Evolutionary Rule Learning. Int Conf

Computational Intell Commun Technol CICT 2018; 1-4.

DOI: 10.1109/CIACT.2018.8480271.

Gonsalves AH, Thabtah F, Mohammad RMA,

Singh G. Prediction of coronary heart disease

using machine learning: An experimental analysis.

ACM Int Conf Proceeding Ser 2019; 51-56. DOI:


Nwankpa C, Ijomah W, Gachagan A, Marshall S.

Activation Functions: Comparison of trends in Practice

and Research for Deep Learning. 2018; 1-20.

Lipton ZC, Berkowitz J, Elkan C. A Critical Review of

Recurrent Neural Networks for Sequence Learning.

; 1-38.

Soutner D, Müller L. Application of LSTM neural

networks in language modelling. Lect Notes Comput

Sci 2013; 8082: 105-112. DOI: 10.1007/978-3-642-


You Y, Hseu J, Ying C, Demmel J, Keutzer K, CJ Hsieh.

Large-batch training for LSTM and beyond. Int Conf

High Perform Comput Networking, Storage Anal SC

; 1-15. DOI:10.1145/3295500.3356137.

Janocha K, Czarnecki WM. On loss functions for deep

neural networks in classification. Schedae Informaticae

; 25: 49-59. DOI: 10.4467/20838476SI.16.004.6185.

Hossin M, Sulaiman MN. A Review on Evaluation

Metrics for Data Classification Evaluations. Int J Data

Min Knowl Manag Process 2015; 5(2): 1-11. DOI:


Vieira SM, Kaymak U, Sousa JMC. Cohen’s kappa

coefficient as a performance measure for feature

selection. IEEE World Congr Comput Intell WCCI 2010;

DOI: 10.1109/FUZZY.2010.5584447.

Blake C, Keogh E, Merz CJ. UCI repository of machine

learning databases” [

MLRepository.html], Department of Information and

Computer Science, University of California, Irvine,

CA, 1998.