A hybrid model for heart disease prediction using recurrent neural network and long short term memory

ORIGINAL RESEARCH
A hybrid model for heart disease prediction using recurrent
neural network and long short term memory
Girish S. Bhavekar1 • Agam Das Goswami1
Received: 28 October 2021 / Accepted: 2 February 2022 / Published online: 21 February 2022
The Author(s), under exclusive licence to Bharati Vidyapeeth’s Institute of Computer Applications and Management 2022
Abstract Cardiac and cardiovascular diseases are among
the most prevalent and dangerous ailments that influence
human health. The detection of cardiac disease in its early
stages by the use of early-stage symptoms is a major
problem in today’s environment. As a result, there is a
demand for a technology that can identify cardiac disease
in a non-invasive manner while also being less expensive.
In this research we have developed a hybrid deep learning
methodology for the categorization of cardiac disease.
Classifying synthetic data using RNN and LSTM hybrid
approaches has been done using different cross-validations.
The system’s performance also be evaluated using a variety
of machine learning methods and soft computing approa-
ches. During the classification process, RNN employs three
separate activation functions. To balance the data, certain
pre-processing methods were used to sort and classify the
data. The extraction of features has been done using rela-
tional, bigram, and density-based approaches. We
employed a variety of machine learning and deep learning
methods to assess system performance throughout the trial.
The accuracy of each algorithm’s categorization is shown
in the results section. As a result, we can say that deep
hybrid learning is more accurate than either classic deep
learning or machine learning techniques used alone.
Keywords Heart disease prediction RNN LSTM
Vascular age of heart Risk calculation Machine
learning Internet of Things
1 Introduction
Our hearts pump oxygen-rich blood throughout our bodies
via a network of arteries and veins, making them the most
important organs in our bodies. Our hearts can be affected
by a variety of conditions like heart disease [1]. Heart ill-
ness is considered a dangerous condition since we fre-
quently hear that the majority of people die as a result of
heart disease and other types of heart-related ailments
[2, 3]. Most medical researchers have noted that, on many
occasions, the majority of heart patients do not survive
their heart attacks and die as a result of them [4]. The rising
incidence of cardiovascular disorders, which are associated
with a high death rate, is posing a substantial concern and
placing a significant strain on healthcare systems across the
world. Although males are more likely than females to
suffer from cardiovascular disorders, particularly in middle
or old age, youngsters can also suffer from comparable
health problems [5–7]. Heart illnesses are classified into
several categories, including coronary artery disease, con-
genital heart disease, arrhythmia, and others. Heart disease
manifests itself in a variety of ways, with symptoms such
as chest discomfort, dizziness, and excessive perspiration
being among them. The most common causes of heart
disease are smoking, high blood pressure, diabetes, obesity,
and other factors [8]. Recent advancements in the field of
health decision-making have resulted in the development
of machine learning systems for health-related applications
[9]. They are intended to increase the accuracy of cardiac
diagnosis choices through the use of computer-aided design
technologies. Furthermore, these instruments place their
faith in optimization [10], clustering, and ML computation
models [11] [9, 12]. Because of the development of
machine learning and artificial intelligence, researchers
may now construct the best prediction model possible
Agam Das Goswami
agam.goswami@vitap.ac.in
1
School of Electronics Engineering, VIT-AP University,
Academic Block 2, Vijayawada, Andhra Pradesh 522237,
India
123
Int. j. inf. tecnol. (June 2022) 14(4):1781–1789
https://doi.org/10.1007/s41870-022-00896-y

based on the huge amount of data that is already accessible.
Recent research that has focused on heart-related concerns
in both adults and children has stressed the need to lower
the mortality rate associated with cardiac and cardiovas-
cular diseases (CVDs) [7]. When machine learning algo-
rithms are trained on appropriate datasets, they perform at
their peak [13, 14]. There are a lot of ways to prepare data
for algorithms that use consistency to make predictions.
Data mining, relief selection, or the LASSO method can be
used to make sure that the data is ready to make a more
accurate prediction. Once the right features have been
chosen, classifiers and hybrid models can be used to predict
how likely it is that a disease will happen. Researchers
have used different methods to make classifiers and hybrid
models [15, 16]. Heart disease can be unpredictable be-
cause there aren’t enough medical datasets, a lot of dif-
ferent types of ML algorithms to choose from, and not
enough detailed analysis [7, 17]. Classification software
relies heavily on the process of feature selection. Because
characteristics taken from the object are the primary source
of categorization. Classification results can be improved by
utilizing the finest characteristics [18]. It is critical to
choose the relevant characteristics that may be employed as
risk factors in forecasting models. To construct successful
prediction models, it is important to pick the optimal
combination of features and machine learning algorithms.
Risk factors that fit the three criteria of high prevalence,
considerable influence on heart disease independently, and
controllability or treatability should be assessed for their
impact in order to lower the risks [7, 18]. It is critical to
choose the relevant characteristics that may be employed as
risk factors in forecasting models. To construct successful
prediction models, it is important to pick the optimal
combination of features and machine learning algorithms.
Risk factors that fit the three criteria of high prevalence,
considerable influence on heart disease independently, and
controllability or treatability should be assessed for their
impact in order to lower the risks [18].
The following are the most significant contributions
made by this paper:
• This paper discusses the application of RNN-LSTM in
the implementation of collaborative classification
approaches for detection and classification.
• In order to carry out this research, a fictional Cleveland
heart disease dataset.
Furthermore, the following sections of this document are
examined, as Sect. 2 offers a motivation with literature
study of several currently available approaches. The
methods of research methodology and dataset selection
investigation are described in Sect. 3, and the algorithm
result and discussion specification for the suggested
implementation is shown in Sect. 4. The concluding
Sect. 5 provides the results of the suggested approach as
well as a comparison with other state-of-the-art procedures.
Section 6 examines the work completed to date as well as
its future potential, followed by a conclusion.
2 Motivation
Here, the need for a new algorithm to predict heart disease
and the pros and cons of existing research are looked at as
well. The challenges and the literature review are thought
to be below (Table 1).
In order to classify, several researchers use different
artificial intelligence techniques such as machine learning
[26–31] and deep learning [32–34] algorithms. In this
approach for heart disease prediction, machine learning
was employed 60% of the time, whereas deep learning
techniques were used 30% of the time. Many machine
learning approaches, including Naive Bayes [35, 36],
Decision Tree, KNN [37, 38], Support Vector Machine
[39, 40], Random Forest [41], Logistic Regression, Opti-
mization technique [42] and others are used to categories
the cancer dataset. Deep learning approaches based on the
ANN have been used by many researchers. The RNN and
CNN deep learning algorithms were used. In the classifi-
cation of ECG images and other visual data, convolutional
neural networks (CNNs) [41–43] are often used. A recur-
rent neural network (RNN), multi-layered feed-forward
neural network (MLFFNN) [44] is a kind of artificial
neural network [43, 45] that improves on prior networks
with fixed-size input and output vectors.
3 Research methodology and dataset selection
The proposed system has divided into two different phases,
training and testing. In this research, an effective disease
prediction using deep learning techniques is proposed. To
achieve decent classification accuracy, the dataset plays an
important role in the entire execution process. The data
from the first synthesis was gathered (UCI Machine
Learning Repository Heart Disease Data Set). The dataset
was obtained from the University of California, Irvine
Machine Learning Repository. It is made up of 14 columns,
one of which is shown below with a brief description of
each (Table 2).
The above Fig. 1 describes a training and testing phases
of synthetic Cleveland data classification. The training
module generates Background Knowledge (BK) for all
classes, and predict the class label for new input record
during module testing. The system also calculates vascular
age of Heart (VaH) using below formula,
1782 Int. j. inf. tecnol. (June 2022) 14(4):1781–1789
123

b
p ¼ 1 S0 t
ð Þexpð
Pp
i¼1
:bivi
Pn
i¼1
:bivi
ð1Þ
where S0 t
ð Þ is the baseline survival at follow up time t
(where t = 10 years), bi is the estimated regression coef-
ficient, vi denoted the log transformed measured value of
the ith risk factor, vi is the corresponding mean and p
indicates the number of risk factors.
3.1 Experimental setup
We used a Windows 10 computer with 8 GB of RAM and
the Python programming language to conduct our experi-
ment. The datasets listed below are used in the
implementation.
3.2 Algorithm
In proposed system we made hybrid deep learning classi-
fication algorithm collaboration with RNN and LSTM. The
below we demonstrate each phase of system execution with
our hybrid algorithm (Tables 3, 4).
3.3 Performance metrics
The performance metrics explored to determine the effi-
cacy of the proposed Classification for Heart Disease using
hybrid model are enlisted below:
Precision: also known as positive predictively, is the
number of relevant positive forecasted samples.
Table 1 Literature review analysis
Sr.
no.
Author Technique Advantages Disadvantages/future work
1 Rani et al. [1] Hybrid decision support
system
A hybrid decision support system can be
used in remote places when modern
medical facilities are unavailable
Only if a person has heart disease may it be
diagnosed. This technique does not allow
for the assessment of the degree of cardiac
disease
2 Ali et al. [19] Predicting heart disease
risk using supervised
learning and discrete
weights
Minimal false alarms, minimal process
overhead, and maximum label
prediction accuracy are all achieved
with this system
The dimensionality of different training
corpus formats must be dealt with by
employing ensemble classification
procedures in the most efficient manner
3 Swarnalatha [9] Cluster-based DT
learning (CDTL)
Attains high prediction accuracy The ideal decision tree’s structure can be
drastically altered by even the smallest
change in the input
4 Saranya and
Pravin [20]
A technique based on
global sensitivity
analysis
When picking attributes for classification,
global sensitivity analysis is more
important than individual feature
selection approaches
Requires high computation time for attribute
selection
5 Ghosh et al. [7] Machine learning
algorithms using relief
and LASSO feature
selection techniques
Results in a far better level of accuracy
than comparable tasks
The level of missing data influences the
performance
6 Prakash et al.
[21]
Genetic algorithm (GA)
with (RBF) radial basis
function (GA-RBF)
It also reduced the number of
characteristics, which improved
accuracy while also saving patients time
and money
The complex training process due to large
volume of data
7 Ali et al. [22] Ensemble deep learning
and feature fusion
To enhance heart disease prediction, low-
dimensional and specialised weighted
information must be extracted
Data mining is required to improve the
dataset for heart disease diagnostics
8 Yazdani et al.
[23]
Strength scores with
significant predictors
Achieved highest confidence score Accordingly, the machine learning
approaches utilised in this research are
confined to the most commonly used in
heart disease prediction research
9 Thanga Selvi
and
Muthulakshmi
[24]
Optimal ANN An appropriate method for analysing
large amounts of data in order to
develop a heart disease prediction
model
The high computation time is the main
drawback of this system
10 Pandian [25] Fuzzy rules are used in
the Intelligent Big Data
Analytics Model
(IBDAM)
This method has resulted in more accurate
illness prediction
The inaccurate data lead to lower accuracy
Int. j. inf. tecnol. (June 2022) 14(4):1781–1789 1783
123

Precision P
ð Þ ¼
TP
TP þ FP
: ð7Þ
Sensitivity: or recall, is another term for this. How many
positive samples are correctly expected to be positive?
Recall R
ð Þ ¼
TP
TP þ FN
: ð8Þ
Accuracy: can be defined as it is ration of correct clas-
sification to the number of total classification.
Accuracy A
ð Þ ¼
TP þ TN
TP þ TN þ FP þ FN
: ð9Þ
F-Measure: is the harmonic mean of precision and
recall, so it is called the F-Measure.
F-Measure F
ð Þ ¼ 2
Precision Recall
Precision þ Recall
: ð10Þ
4 Results and discussions
A thorough experimental study was conducted on the
systems that were deployed on the widow’s platform,
which was running Python 3.7 and the RESNET100 deep
Table 2 Dataset information
Attributes Description Type
Age Patient’s age expressed as a number of years Numeric value
Sex 1 = male, 0 = female Nominal value
Cp Chest aches and pains Numeric value
Trestbps Resting Bp (mmHg) Numeric value
Chol Cholesterol in the blood (milligrams per deciliter) Numeric value
Fbs 120 mg/dl fasting False: 1 Equals 1 Nominal value
Restecg Resting ecg result Numeric value
Thalach Max. heart rate Numeric value
Exang EIA (Exercise induced angina) (1 = yes, 0 = no) Nominal value
Oldpeak Exercise-induced ST depression vs rest Numeric value
Slope The slope of the peak of the ST line Numeric value
Ca Major vessels coloured by fluoroscopy (0–3) Numeric value
Thal 1 = Nominal, 2 = fixed defect, 3 = reversible defect Numeric value
Target 1 or 0 Nominal value
Monitor log
dataset
Pre-process Normalized
Feature
Extraction
Feature Selection
Predicted Result
Analysis
Train DB
Test Classifier
Train Classifier
Fig. 1 Proposed system
architecture
123

learning framework, and a thorough experimental study
was conducted.
4.1 Experiment using RNN-LSTM (sigmoid)
Our goal in this experiment was to demonstrate the clas-
sification accuracy of RNN (Sigmoid) using the Cleveland
heart disease dataset. The results of similar trials utilizing
different cross validation methods are presented in Table 5.
This analysis found that 15-fold cross validation has the
highest average classification accuracy (95.0%) of the
methods tested.
In this case, fivefold cross validation with RNN and
sigmoid function achieves 93.6% accuracy (Fig. 2). Fig-
ure 3 depicts cross validation of tenfold data, whereas
Fig. 4 depicts the same. During module testing, the accu-
racy of both functions is almost the same.
4.2 Experiment using recurrent neural network
(TanH)
The classification accuracy of RNNs using the Cleveland
dataset is shown in Fig. 3, and the results of analogous
experiments using the cross validation approach are shown
in Table 6. According to our findings, 15-fold cross vali-
dation achieves the highest average classification accuracy
of 93.55% and 94.90% for RNNs using Tan-h respectively.
The variables and functions that were utilized in the sug-
gested detection algorithm are listed below.
Table 3 Execution of training
Table 4 Execution of testing
Table 5 Classification accuracy RNN-LSTM
RNN (sigmoid) Fold 5 (%) Fold 10 (%) Fold 15 (%)
Accuracy 93.60 94.80 95.10
Precision 92.20 93.00 94.10
Recall 92.00 93.25 94.35
F1 score 92.60 93.80 94.90
123

Xt: Input vector given to algorithm
Ht: hidden vector given to algorithm
Yt: output vector given to algorithm:
4.3 Experiment using recurrent neural network
(ReLU)
With the use of the Cleveland dataset, we investigate the
classification accuracy of ReLU in this experiment. Similar
studies have been performed on other cross-validations
(Fold5, Fold10, and Fold15), and the results are provided in
Table 7 for comparison. Taking into consideration the
findings of this study, we can conclude that tenfold cross
validation yields the highest classification accuracy for
93.60%
92.20%
92.00%
92.60%
94.80%
93.00%
93.25%
93.80%
95.10%
94.10%
94.35%
94.90%
A C C U R A C Y P R E C I SI ON R E C A L L F 1 S C O R E
CLA SSI F ICATI ON A CCU R A CY R N N -
LSTM
Fold 5 Fold 10 Fold 15
Fig. 2 System validation with
various cross validation using
RNN-LSTM (sigmoid)
92.40%
91.50%
91.80%
92.10%
93.55%
92.60%
93.10%
93.05%
94.90%
93.90%
94.20%
94.70%
A C C U R A CY P R E C I SI ON R E C A L L F 1 S C O R E
CLASSI FICATI ON ACCURACY RNN-
LSTM( TANH)
Fig. 3 System validation with
various cross validation using
RNN-LSTM (Tanh)
94.2
94.3
94.15
93.2
95.3
95.7
95.8
95.6
97.1
95.3
97.4
97.5
ACCURACY PRECISION RECALL F1 SCORE
ACCURACY
Fig. 4 System validation with various cross validation using RNN-
LSTM (ReLU)
Table 6 Classification accuracy RNN-LSTM
RNN (Tanh) Fold 5 (%) Fold 10 (%) Fold 15 (%)
Accuracy 92.40 93.55 94.90
Precision 91.50 92.60 93.90
Recall 91.80 93.10 94.20
F1 score 92.10 93.05 94.70
Table 7 Classification accuracy RNN-LSTM (ReLU)
RNN (ReLU) Fold 5 (%) Fold 10 (%) Fold 15 (%)
Accuracy 94.19 95.29 97.09
Precision 94.31 95.71 95.29
Recall 94.14 95.82 97.39
F1 score 93.19 95.60 97.49
123

RNN, with a classification accuracy of 95.30% and 97.10%
for tenfold cross validation, respectively for RNN.
The Table 7 carried out 5-, 10- and 15-fold cross vali-
dation training of RNN (Tan h activation function).
Using a machine learning technique, the suggested deep
learning classification algorithm is depicted in the pre-
ceding Fig. 4. This graphic illustrates the difference
between the results obtained with and without cross-vali-
dation. The identification of sickness has been accom-
plished by the use of a minimum of three concealed layers.
Following the results of this experiment, we conclude that
RNN with sigmoid gives superior detection accuracy than
the other two activation functions used in this study as well
as the random forest machine learning method.
Table 8 ML classifiers on
Cleveland heart disease dataset
ML classifiers Accuracy (%) Precision (%) Recall (%) F-Measure (%)
SVM (linear) 85.71 84.09 86.04 85.05
Naı̈ve Bayes 78.02 76.74 76.74 76.74
Decision tree 79.12 77.27 79.06 78.16
Random forest 81.31 82.5 76.74 79.51
Logistic regression 82.41 80.0 83.72 81.81
K nearest neighbor 80.21 83.33 80.0 81.63
XG boost 82.41 81.39 81.39 81.39
72.00%
74.00%
76.00%
78.00%
80.00%
82.00%
84.00%
86.00%
88.00%
Accuracy Precision Recall F- Measure
ML Classifiers on Cleveland heart disease dataset
SVM ( Linear) Naïve Bayes Decision Tree
Random Forest Logistic Regression K Nearest Neighbor
XG Boost
Fig. 5 ML Classifiers on
0.00%
50.00%
100.00%
150.00%
Accuracy Precision Recall F- Measure
DL Classifiers on Cleveland heart disease dataset
Mul-layer perceptron
Deep Neural Net work (20 0 epochs)
Rec urrent Neural Network
Long Sort Term Memory Network
Hybrid Deep learning Model (RNN+LSTM)
Fig. 6 DL Classifiers on
Table 9 DL classifiers on Cleveland heart disease dataset
DL classifiers Accuracy (%) Precision (%) Recall (%) F-Measure (%)
Multi-layer perceptron 72.52 70.45 72.09 71.26
Deep neural network (200 epochs) 80.21 83.33 80.0 81.63
Recurrent neural network 88.52 88.51 91.17 89.85
Long sort term memory network 86.88 88.23 88.23 88.23
Hybrid deep learning model (RNN ? LSTM) 95.10 94.28 97.05 95.65
123

4.4 Comparative analysis of system
Another study is looking into the possibilities of illness
diagnosis using supervised machine learning classification.
The suggested system makes four comparisons between
our study and the findings of other systems, all of which are
based on comparable and/or many datasets, as defined by
our findings (Table 8; Figs. 5, 6).
The Cleveland heart disease dataset has not yet been
subjected to the use of RNN, LSTM, or RNN ? LSTM
hybrid models. This study’s accuracy is 95.10%, which is
higher than the accuracy of previous ML and DL models.
Table 9, Fig. 7 depicts the deep learning classification
accuracy of a proposed model utilising several current
machine learning methods as measured by deep learning.
In terms of accuracy, the suggested hybrid models out-
perform the Support Vector Machine, the Decision Tree,
and the KNN algorithms in terms of accuracy. A training
set and a test set are used to organize or classify data in the
most recent expected sample, which is the most recent
expected sample. The input function modules and their
associated class labels are the building blocks of the
training package. After learning from these two learning
sets, an arrangement (classification) model is constructed,
which organizes the input courses into labels that match
them. Afterwards, the model is tested against a test set that
is constructed from the class labels of orthonormal course
labels.
5 Conclusion
To analyses the proposed system, we used a variety of
machine learning methods, including a hybrid deep learn-
ing algorithm that we developed. In addition, the cooper-
ation of deep learning algorithms and the performance of
digital algorithms are calculated in the results sec-
tion. When the RNN is used to run the system, it causes
memory difficulties in the feedback layers to arise. By
using LSTM, we can successfully overcome the memory
issue and handle vast amounts of data in a timely manner.
The hybrid deep learning algorithms achieve an average
classification accuracy of around 95.10% on a variety of
cross-validation tests. Selection of activation function,
epoch size, and choice of the kind of features are all
variables that may be changed. The system’s future
development will involve the analysis of real-time IoT data
in order to perform experiments, which will be part of the
system’s future growth.
Declarations
Conflict of interest It has been declared by the authors that they have
no conflict of interest.
References
1. Rani P, Kumar R, Sid NMO, Anurag A (2021) A decision support
system for heart disease prediction based upon machine learning.
J Reliab Intell Environ 7(3):263–275. https://doi.org/10.1007/
s40860-021-00133-6
2. Assari R, Azimi P, Reza Taghva M (2017) Heart disease diag-
nosis using data mining techniques. Int J Econ Manag Sci
06(03):750–753. https://doi.org/10.4172/2162-6359.1000415
3. Krishnaiah V, Srinivas M, Narsimha G, Chandra NS (2014)
Diagnosis of heart disease patients using fuzzy classification
technique. IEEE Int Conf Comput Commun Technol. https://doi.
org/10.1109/ICCCT2.2014.7066746
4. Mamatha Alex P, Shaji SP (2019) Prediction and diagnosis of
heart disease patients using data mining technique. In: Proceed-
ings of the 2019 IEEE international conference on communica-
tion and signal processing. ICCSP 2019, pp 848–852. https://doi.
org/10.1109/ICCSP.2019.8697977
5. Jousilahti P, Vartiainen E, Tuomilehto J, Puska P (1999) Sex,
age, cardiovascular risk factors, and coronary heart disease.
Circulation 99(9):1165–1172. https://doi.org/10.1161/01.cir.99.9.
1165
6. Subhadra K, Vikas B (2019) Neural network based intelligent
system for predicting heart disease. Int J Innov Technol Explor
Eng 8(5):484–487. [Online]. https://www.researchgate.net/pub
lication/332035370_Neural_network_based_intelligent_system_
for_predicting_heart_disease
7. Ghosh P et al (2021) Efficient prediction of cardiovascular dis-
ease using machine learning algorithms with relief and LASSO
feature selection techniques. IEEE Access 9:19304–19326.
https://doi.org/10.1109/ACCESS.2021.3053759
8. Razmjooy N, Rashid Sheykhahmad F, Ghadimi N (2018) A
hybrid neural network—world cup optimization algorithm for
melanoma detection. Open Med 13(1):9–16. https://doi.org/10.
1515/med-2018-0002
9. Swarnalatha GMP (2021) Optimal feature selection through a
cluster—based DT learning (CDTL) in heart disease prediction.
Evol Intell 14(2):583–593. https://doi.org/10.1007/s12065-019-
00336-0
10. Moallem P, Razmjooy N, Ashourian M (2013) Computer vision-
based potato defect detection using neural networks and support
vector machine. Int J Robot Autom 28(2):137–145. https://doi.
org/10.2316/Journal.206.2013.2.206-3746
11. Mousavi BS (2011) Digital image segmentation using rule-base
classifier. Am J Sci Res 35(35):17–23. [Online]. https://www.
academia.edu/38367918/Digital_Image_Segmentation_Using_
Rule_Base_Classifier
12. Amin MS, Chiam YK, Varathan KD (2019) Identification of
significant features and data mining techniques in predicting heart
disease. Telemat Inform 36:82–93. https://doi.org/10.1016/j.tele.
2018.11.007
13. Kondababu A, Siddhartha V, Kumar BHKB, Penumutchi B
(2021) Materials today: proceedings a comparative study on
machine learning based heart disease prediction. Mater Today
Proc. https://doi.org/10.1016/j.matpr.2021.01.475
14. Singh D, Samagh JS (2020) A comprehensive review of heart
disease prediction using machine learning. J Crit Rev
7(12):281–285. https://doi.org/10.31838/jcr.07.12.54
15. Tama BA, Im S, Lee S (2020) Improving an intelligent detection
system for coronary heart disease using a two-tier classifier
ensemble. Biomed Res Int. https://doi.org/10.1155/2020/9816142
123

16. Youssef MM, Mousa SA, Baloola MO, Fouda BM (2020) The
impact of mobile augmented reality design implementation on
user engagement. CCIS. Springer book series, vol 1244
17. Kausar N, Palaniappan S, Samir BB, Abdullah A, Dey N (2016)
Systematic analysis of applied data mining based optimization
algorithms in clinical attribute extraction and classification for
diagnosis of cardiac patients. Intell Syst Ref Libr 96:217–231.
https://doi.org/10.1007/978-3-319-21212-8_9
18. Saranya G, Pravin A (2021) Hybrid global sensitivity analysis
based optimal attribute selection using classification techniques
by machine learning algorithm. Wirel Pers Commun. https://doi.
org/10.1007/s11277-021-08796-3
19. Ali F et al (2021) Feature optimization by discrete weights for
heart disease prediction using supervised learning. Soft Comput
25(3):1821–1831. https://doi.org/10.1007/s00500-020-05253-4
20. Saranya G, Pravin A (2021) Learning algorithm. Wirel Pers
Commun. https://doi.org/10.1007/s11277-021-08796-3
21. Prakash B, Debnath D, Midhun B (2021) A hybrid machine
learning approach to identify coronary diseases using feature
selection mechanism on heart disease dataset. Distrib Parallel
Databases. https://doi.org/10.1007/s10619-021-07329-y
22. Ali F et al (2020) A smart healthcare monitoring system for heart
disease prediction based on ensemble deep learning and feature
fusion. Inf Fusion 63:208–222. https://doi.org/10.1016/j.inffus.
2020.06.008
23. Yazdani A, Varathan KD, Chiam YK, Malik AW, Azman W,
Ahmad W (2021) A novel approach for heart disease prediction
using strength scores with significant predictors. BMC Med
Inform Decis Mak. https://doi.org/10.1186/s12911-021-01527-5
24. Thanga Selvi R, Muthulakshmi I (2021) An optimal artificial
neural network based big data application for heart disease
diagnosis and classification model. J Ambient Intell Humaniz
Comput 12(6):6129–6139. https://doi.org/10.1007/s12652-020-
02181-x
25. Pandian MSA (2021) Intelligent big data analytics model for
efficient cardiac disease prediction with IoT devices in WSN
using fuzzy rules. Wirel Pers Commun. https://doi.org/10.1007/
s11277-021-08788-3
26. Muthulakshmi RTSI (2021) An optimal artificial neural network
based big data application for heart disease diagnosis and clas-
sification model. J Ambient Intell Humaniz Comput
12(6):6129–6139. https://doi.org/10.1007/s12652-020-02181-x
27. Safa M, Pandian A (2021) Intelligent big data analytics model for
efficient cardiac disease prediction with IoT devices in WSN
using fuzzy rules. Wirel Pers Commun. https://doi.org/10.1007/
s11277-021-08788-3
28. Shidnal S, Latte MV, Kapoor A (2021) Crop yield prediction:
two-tiered machine learning model approach. Int J Inf Technol
13(5):1983–1991. https://doi.org/10.1007/s41870-019-00375-x
29. Niranjan D, Kavya M, Neethi KT, Prarthan KM, Manjuprasad B
(2021) Machine learning based analysis of pulse rate using
Panchamahabhutas and Ayurveda. Int J Inf Technol
30. Nayakwadi N, Fatima R (2021) Automatic handover execution
technique using machine learning algorithm for heterogeneous
wireless networks. Int J Inf Technol 13(4):1431–1439. https://doi.
org/10.1007/s41870-021-00627-9
31. Mangrulkar A, Rane SB, Sunnapwar V (2021) Automated skull
damage detection from assembled skull model using computer
vision and machine learning. Int J Inf Technol 13(5):1785–1790.
https://doi.org/10.1007/s41870-021-00752-5
32. Mahajan J, Banal K, Mahajan S (2021) Estimation of crop pro-
duction using machine learning techniques: a case study of JK.
Int J Inf Technol 13(4):1441–1448. https://doi.org/10.1007/
s41870-021-00653-7
33. Bojamma AM, Shastry C (2021) A study on the machine learning
techniques for automated plant species identification: current
trends and challenges. Int J Inf Technol 13(3):989–995. https://
doi.org/10.1007/s41870-019-00379-7
34. Divate MS (2021) Sentiment analysis of Marathi news using
LSTM. Int J Inf Technol 13(5):2069–2074. https://doi.org/10.
1007/s41870-021-00702-1
35. Pattekari A, Parveen SA (2012) Prediction system for heart dis-
ease using Naı̈ve Bayes. Int J Adv Comput Math Sci
3(3):290–294
36. Dulhare UN (2018) Prediction system for heart disease using
Naive Bayes and particle swarm optimization. Biomed Res
29(12):2646–2649. https://doi.org/10.4066/biomedicalresearch.
29-18-620
37. Kulkarni TR, Dushyanth ND (2021) Performance evaluation of
deep learning models in detection of different types of arrhythmia
using photo plethysmography signals. Int J Inf Technol
38. Pandey NN, Muppalaneni NB (2021) A novel algorithmic
approach of open eye analysis for drowsiness detection. Int J Inf
Technol 13(6):2199–2208. https://doi.org/10.1007/s41870-021-
00811-x
39. Patil AR, Subbaraman S (2021) Performance analysis of static
hand gesture recognition approaches using artificial neural net-
work, support vector machine and two stream based transfer
learning approach. Int J Inf Technol. https://doi.org/10.1007/
s41870-021-00831-7
40. Chandra MA, Bedi SS (2021) Survey on SVM and their appli-
cation in image classification. Int J Inf Technol 13(5):1867–1877.
https://doi.org/10.1007/s41870-017-0080-1
41. Sharma LD, Sunkaria RK (2019) Detection and delineation of the
enigmatic U-wave in an electrocardiogram. Int J Inf Technol
13(6):2525–2532. https://doi.org/10.1007/s41870-019-00287-w
42. Usha Kirana SP, D’Mello DA (2021) Energy-efficient enhanced
Particle Swarm Optimization for virtual machine consolidation in
cloud environment. Int J Inf Technol 13(6):2153–2161. https://
doi.org/10.1007/s41870-021-00745-4
43. Mane DT, Tapdiya R, Shinde SV (2021) Handwritten Marathi
numeral recognition using stacked ensemble neural network. Int J
Inf Technol 13(5):1993–1999. https://doi.org/10.1007/s41870-
021-00723-w
44. Kumar R, Srivastava S, Dass A, Srivastava S (2019) A novel
approach to predict stock market price using radial basis function
network. Int J Inf Technol 13(6):2277–2285. https://doi.org/10.
1007/s41870-019-00382-y
45. Sharma LD, Chhabra H, Chauhan U, Saraswat RK, Sunkaria RK
(2021) Mental arithmetic task load recognition using EEG signal
and Bayesian optimized K-nearest neighbor. Int J Inf Technol
123

A hybrid model for heart disease prediction using recurrent neural network and long short term memory

More Related Content

Similar to A hybrid model for heart disease prediction using recurrent neural network and long short term memory (20)

More from BASMAJUMAASALEHALMOH (10)

Recently uploaded (20)

A hybrid model for heart disease prediction using recurrent neural network and long short term memory