References

Mana Saleh Al Reshan, Samina Amin, Muhammad Ali Zeb, Adel Sulaiman, Hani
Alshahrani, Asadullah Shaikh, “A Robust Heart Disease Prediction System Using Hybrid
Deep Neural Networks”, IEEE Access, Vol. 11, pp. 121574 – 121591, 2023.

Despite being the leading cause of global mortality, predicting heart disease remains a
crucial but challenging task. Early detection and accurate prediction are vital for timely
interventions and better patient outcomes. This paper proposes a novel Hybrid Deep
Neural Network (HDNN) system to enhance heart disease prediction accuracy. Combining
three deep learning models - Artificial Neural Networks, Convolutional Neural Networks,
and Long Short-Term Memory - the HDNN extracts and learns complex patterns from
diverse data, achieving a promising accuracy of 98.86%. This outperforms existing
methods, suggesting its potential for integration into healthcare systems, ultimately
contributing to improved medical diagnosis and patient care.

Abdulwahab Ali Almazroi, Eman A. Aldhahri, Saba Bashir, And Sufyan Ashfaq, “A
Clinical Decision Support System For Heart Disease Prediction Using Deep Learning”,
IEEE Access, vol. 11, pp. 61646 - 61659, 2023.

Despite being the leading cause of death globally, early detection of heart disease remains
elusive. While vast medical data exists, untapped hidden patterns hold the key to better
diagnosis. This research leverages machine learning, specifically deep learning, to unlock
these patterns and build an accurate heart disease prediction model. Using a Kera’s-based
deep learning model with varying configurations of dense neural networks, the study
tested performance across multiple datasets. The proposed model outperformed both
individual models and ensemble approaches, achieving higher accuracy, sensitivity, and
specificity. This signifies the potential of deep learning in revolutionizing heart disease
diagnosis and paving the way for earlier intervention and improved outcomes.

Norma Latif Fitriyani, Muhammad Syafrudin, Ganjar Alfian (Member, Ieee), And Jongtae
Rhee, “An Effective Heart Disease Prediction Model for a Clinical Decision Support
System”, IEEE Access, Vol. 8, pp. 133034 - 133050, 2020.
Heart disease, a global killer, can be tackled by catching it early. To aid doctors, this study
presents a powerful heart disease prediction model for a clinical decision support system.
It uses sophisticated techniques to clean and balance data, then predicts with high accuracy
(up to 98.4%). This outperforms other models and even past research. Additionally, a
prototype system was built to help doctors diagnose heart disease based on patients' data,
enabling earlier treatment, and potentially saving lives.

Ghulab Nabi Ahmad, Hira Fatima, Shafiullah, Abdelaziz Salah Saidi, And Imdadullah,
“Efficient Medical Diagnosis of Human Heart Diseases Using Machine Learning”, IEEE
Access, Vol. 10, pp. 80151 - 80173, 2022.

Predicting heart disease, a major medical challenge, often requires extensive effort from
doctors. This paper utilizes machine learning algorithms like XGBoost to predict cardiac
disease with high accuracy (up to 100%!), outperforming previous studies. Our analysis
across multiple datasets highlights XGBoost's effectiveness, making it a valuable tool for
real-world healthcare problems.

Supriya V. Mahadevkar, Bharti Khemani, Shruti Patil, Ketan Kotecha, Deepali R. Vora,
Ajith Abraham, “A Review On Machine Learning Styles In Computer Vision Techniques
And Future Directions”, IEEE Access, Vol. 10, pp. 107293 - 107329, 2022.

The field of computer vision has seen a rise in the use of machine learning in recent years.
This is due to the increasing availability of data and the ability of machine learning
algorithms to learn from this data. There are three main types of machine learning:
supervised, unsupervised, and reinforcement learning. Supervised learning is when an
algorithm is trained on a set of labelled data. Unsupervised learning is when an algorithm
is trained on a set of unlabelled data. Reinforcement learning is when an algorithm is
trained through trial and error.

Chunyan Guo, Jiabing Zhang, Yang Liu, Yaying Xie, Zhiqiang Han, And Jiansheyu,
“Recursion Enhanced Random Forest With An Improved Linear Model For Heart Disease
Detection On The Internet Of Medical Things Platform”, IEEE Access, Vol. 8, pp. 59247 -
59256, 2020.

Heart disease, a leading cause of death, poses a major challenge for doctors. Machine
learning offers hope. This paper proposes RFRF-ILM, a new model, to identify key
features that predict heart disease. By analysing various combinations of features and
classification methods, RFRF-ILM achieves high accuracy (96.6%), stability (96.8%), and
F-measure (96.7%). Our study pinpoints age, high blood pressure, and diabetes as
important risk factors. Early detection and preventive measures against these factors can
help combat this deadly disease.

Qi An, Saifur Rahman, Jingwen Zhou and James Jin Kang, “A Comprehensive Review on
Machine Learning in Healthcare Industry”, PMCID: PMC10180678, DOI:
10.3390/s23094178, 2023.

Machine learning is transforming healthcare, empowering medical professionals with

advanced diagnostic and treatment tools. While researchers leverage medical data for
disease detection and pattern analysis, studies on enhancing data accuracy and efficiency
using machine learning remain scarce. We bridge this gap by exploring the effectiveness of
machine learning algorithms in optimizing heart rate data transmission metrics (accuracy
and efficiency). We delve into both supervised and unsupervised algorithms, assessing
their suitability for various data sizes and showcasing their application in time series tasks
based on past values. This exploration paves the way for utilizing machine learning to
optimize healthcare data and revolutionize patient care.

Mohd Javaid, Abid Haleem, Ravi Pratap Singh, Rajiv Suman, Shanay Rab,
“Significance of machine learning in healthcare”, Vol. 3, pp. 58-73, 2022.

Healthcare systems overburdened by physician shortages see a beacon of hope in AI.

Analysing vast healthcare data, AI helps optimize clinical trials, identify early outbreak
risks, and streamline hospital operations. From suggesting personalized treatments to
freeing up precious time for patient care, AI-powered tools promise a revolution. This
technology will empower both physicians and hospitals, enabling more informed
decisions, personalized care, and a future of improved healthcare outcomes at lower costs.
Gaurav Parashar, Alka Chaudhary, Ajay Rana, “Systematic Mapping Study of AI/Machine
Learning in Healthcare and Future Directions”, PMCID: PMC8444522, DOI:
10.1007/s42979-021-00848-6, 2021.

This study maps research on machine learning in healthcare. We reviewed top journals,
articles, and papers using keywords like "machine learning in healthcare," finding 1400
hits on Google Scholar. Analysing these by research objective, methodology, problem
type, and disease studied, we identified five categories: interpretable machine learning,
medical image evaluation, electronic health record processing, security/privacy
frameworks, and transfer learning. Notably, cancer was the most studied disease, epilepsy
the least, and medical image evaluation the leading focus area. A promising trend was the
rise of interpretable machine learning/explainable AI. This work aims to guide future
researchers in navigating this dynamic field and exploring its promising avenues.

K. Shailaja, B. Seetharamulu, M. A. Jabbar, “Machine Learning in Healthcare: A Review”,

IEEE, Second International Conference on Electronics, Communication and Aerospace
Technology (ICECA), Coimbatore, 2018.

Machine Learning is modern and highly sophisticated technological applications became a

huge trend in the industry. Machine Learning is Omni present and is widely used in
various applications. It is playing a vital role in many fields like finance, medical science
and in security. Machine learning is used to discover patterns from medical data sources
and provide excellent capabilities to predict diseases. In this paper, we review various
machine learning algorithms used for developing efficient decision support for healthcare
applications. This paper helps in reducing the research gap for building efficient decision
support system for medical applications.

Rohan Bhardwaj, Ankita R. Nambiar, Debojyoti Dutta, “A Study of Machine Learning in

Healthcare”, IEEE, 41st Annual Computer Software and Applications Conference
(COMPSAC), Turin, Italy, 2017.

The recent surge in machine learning has ignited a revolution across industries and
research. Healthcare stands to benefit immensely from this transformative technology.
This paper delves into the untapped potential of machine learning applications in
healthcare, showcasing how industry pioneers are leveraging its power to revolutionize
diagnostics, personalize treatment, and optimize research for a healthier future.

Munira Ferdous, Jui Debnath and Narayan Ranjan Chakraborty, “Machine Learning
Algorithms in Healthcare: A Literature Survey”, IEEE, 11th International Conference on
Computing, Communication and Networking Technologies (ICCCNT), Kharagpur, 2020.

Machine learning shines in predicting diseases but choosing the right algorithm can be a
daunting task. Researchers often struggle to find accurate and comprehensive information
scattered across various studies. To bridge this gap, we analysed numerous papers,
creating a data table of machine learning algorithm accuracy for different diseases. This
one-stop resource empowers researchers and practitioners to easily identify the best
algorithms for their specific needs, ultimately maximizing the contribution of machine
learning in healthcare.

Sneha Grampurohit, Chetan Sagarnal, “Disease Prediction using Machine Learning

Algorithms”, IEEE, 10th International Conference on Emerging Trends in Engineering and
Technology - Signal and Information Processing (ICETET-SIP-22), Nagpur, 2020.

The explosion of data mining in healthcare has spawned innovative uses of machine
learning for extracting hidden insights within medical databases. This research explores
machine learning's potential in disease prediction, aiming to assist physicians through
early diagnosis. Using a patient sample, three algorithms - Decision Tree, Random Forest,
and Naive Bayes - were trained on disease data to predict disease onset with high
accuracy. This comparative study paves the way for implementing these algorithms in
real-world healthcare settings, potentially revolutionizing patient care and community
services.

Chaimaa Boukhatem, Heba Yahia Youssef, Ali Bou Nassif, “Heart Disease Prediction
Using Machine Learning”, IEEE, 1st International Conference on Innovations in
Information and Communication Technology (ICIICT), Chennai, 2022.

The term cardiovascular disease encompasses critical conditions affecting the heart,
posing life-threatening risks. In response to this, researchers are actively engaged in
developing intelligent systems that can accurately diagnose such diseases using electronic
health data, employing machine learning algorithms. This study introduces various
machine learning approaches to predict heart diseases by utilizing data related to key
health factors from patients. The research showcases four classification methods:
Multilayer Perceptron (MLP), Support Vector Machine (SVM), Random Forest (RF), and
Naïve Bayes (NB) for constructing predictive models. Preceding model development, data
underwent pre-processing and feature selection. The models were assessed based on
accuracy, precision, recall, and F1-score, with the SVM model demonstrating the highest
performance at 91.67% accuracy.

Taher M. Gazal, Amer Ibrahim, Ali sheraz Akram, Zahid Hussain, Sundus Munir, “Heart
Disease Prediction Using Machine Learning”, IEEE, International Conference on Business
Analytics for Technology and Security (ICBATS), Dubai, 2023.

The escalating incidence of heart disease necessitates proactive measures in predicting and
preventing potential harm to individuals. Accurate diagnosis of heart disease is a intricate
task that demands meticulous attention. This research paper primarily concentrates on
identifying patients at a higher risk of developing heart diseases based on various medical
features, such as chest pain. We propose a heart disease prediction system that utilizes
previous medical data to determine whether a patient is susceptible. Machine learning
algorithms, specifically Support Vector Machine and K-Nearest Neighbour, are employed
for prediction and classification. The models yielded satisfactory results, demonstrating
their capability to effectively predict heart disease. Notably, the accuracy achieved with K-
Nearest Neighbour and Support Vector Machine surpassed that of algorithms used in prior
research, such as Naive Bayes, showcasing their potential for enhanced predictive
accuracy.

Susmita Ray, “A Quick Review of Machine Learning Algorithms”, IEEE, International

Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon),
Faridabad, 2019.

Machine learning, a prominent domain within Artificial Intelligence, has emerged as a

pivotal element in digitalization solutions, garnering significant attention in the digital
landscape. This paper undertakes a concise review of several widely employed machine
learning algorithms, recognized for their popularity. The author aims to illuminate the
strengths and weaknesses of these algorithms, specifically considering their practical
applications. This scrutiny seeks to facilitate informed decision-making when choosing a
suitable learning algorithm tailored to meet the specific requirements of an application

Vijeta Sharma, Shrinkala Yadav, Manjari Gupta, “Heart Disease Prediction using Machine
Learning Techniques”, IEEE, 2nd International Conference on Advances in Computing,
Communication Control and Networking (ICACCCN), Greater Noida, 2021.

In accordance with a recent World Health Organization (WHO) study, there has been a
surge in heart-related diseases, resulting in 17.9 million annual fatalities. The increasing
population further complicates early-stage diagnosis and treatment initiation. Leveraging
recent technological advancements, Machine Learning (ML) techniques have significantly
contributed to the healthcare sector through various research endeavours. This paper aims
to construct an ML model for predicting heart disease based on relevant parameters.
Utilizing a benchmark dataset from UCI on heart disease prediction, comprising 14
distinct parameters, we employed machine learning algorithms, including Random Forest,
Support Vector Machine (SVM), Naive Bayes, and Decision Tree, for model development.
Our research also delves into identifying correlations among different attributes in the
dataset using standard ML methods and leveraging these insights for efficient heart disease
prediction. Results indicate that, compared to other ML techniques, Random Forest
exhibits superior accuracy in a shorter timeframe for prediction. This model can serve as a
valuable decision support system for medical practitioners in their clinics.

K. Dhananjay Rao, M. Satya Dev Kumar, D. Akshitha, K. Nagamaleswara Rao, “Machine

Learning Based Cardiovascular Disease Prediction”, IEEE, International Conference on
Computer, Power and Communications (ICCPC), Chennai, 2023.

Detecting a heart attack in its early stages poses significant challenges, despite the
availability of various heart attack detection devices. Machine learning, however, offers a
heightened level of accuracy in this domain. When applied in the healthcare sector,
machine learning has the potential to enhance precision and enable early disease diagnosis.
This research focuses on computing the likelihood of heart disease occurrences by
analysing medical parameters within datasets. Utilizing machine learning algorithms in
Python, historical patient records are processed to forecast future occurrences, contributing
to early intervention and potentially saving lives. The primary goal is to predict heart
disease by examining patient datasets and user data, providing insights into the likelihood
of heart disease. Machine learning emerges as a critical factor in prediction, and robust
algorithms, such as Logistic Regression and Artificial Neural Networks, are employed in
constructing an accurate heart disease prediction system. The proposed techniques are
further validated for accuracy in predicting cardiovascular diseases, emphasizing their
potential impact in advancing early diagnosis and intervention.

Krishna Battula, Raghupatruni Durgadinesh, Killi Suryapratap, Gedela Vinaykumar, “Use

of Machine Learning Techniques in the Prediction of Heart Disease”, IEEE, International
Conference on Electrical, Computer, Communications and Mechatronics Engineering
(ICECCME), Mauritius, 2021.

Machine learning, often perceived as a facet of computer science, transcends disciplinary

boundaries and finds applications in diverse fields. Its utility spans signal processing,
image and speech recognition, electronic design automation, and autonomous vehicles,
among others. This paper aims to identify the most accurate method for predicting heart
disease, recognizing the potential for early detection to mitigate risks and initiate timely
treatment. Leveraging machine learning techniques allows for efficient handling of vast
medical datasets and expedites the diagnostic process. Python was selected for
implementation due to its simplicity, widespread use, and availability of machine learning
libraries. The project employed various methods such as Logistic Regression, k Nearest
Neighbours (KNN), Decision Trees, and Random Forest on a training dataset to predict
heart disease, subsequently evaluating accuracy on a testing dataset. Among these, the
Random Forest algorithm demonstrated superior performance, achieving an accuracy of
88.16%, highlighting its effectiveness in fitting the data compared to the other three
algorithms.
Montu Saw, Tarun Saxena, Sanjana Kaithwas, Rahu Yadav, Nidhi Lal, “Estimation of
Prediction for Getting Heart Disease Using Logistic Regression Model of Machine
Learning”, IEEE, International Conference on Computer Communication and Informatics
(ICCCI), Coimbatore, 2020.

In the contemporary era, the escalating number of deaths attributed to heart disease poses a
significant concern, with approximately one person succumbing to it every minute. The
rapid expansion of Information Technology has led to the daily generation and storage of
substantial amounts of data. To transform this data into meaningful insights, various
algorithms are employed for data analysis. Healthcare professionals specializing in cardiac
disease face limitations in accurately predicting the probability of such conditions. This
paper seeks to enhance the accuracy of heart disease prediction by employing the Logistic
Regression model of machine learning. The focus is on utilizing a healthcare dataset to
classify patients based on their likelihood of having heart diseases, leveraging the
information available in their records.

Mohammad Ahzar, Dr. L, Mary Gladence, “Machine Learning Approach for Predicting
Disease in Heart Using Logistic Regression”, IEEE, 5th International Conference on
Contemporary Computing and Informatics (IC3I), Uttar Pradesh, 2023.

The human heart holds a pivotal role in the functioning of the human body. Precision and
accuracy in diagnosing and predicting heart diseases are crucial, given the potential
consequences of even small errors leading to fatigue and, in extreme cases, individual
mortality. The prevalence of heart-related deaths is significant, with daily counts
witnessing an exponential increase. Addressing this challenge requires leveraging the
knowledge gained from the field of Machine Learning (ML), which serves as an excellent
guide for predicting a wide array of events derived from natural occurrences. This article
employs the UCI repository dataset for instructional purposes and experimentation, aiming
to evaluate the machine learning accuracy of a cardiac disease prediction algorithm. The
algorithms under scrutiny include k-nearest neighbours, decision trees, linear regression,
and support vector devices (SVM). The implementation is facilitated through Anaconda
(Jupiter) Notebook, an excellent tool for Python programming. With its diverse libraries
and header files, Anaconda enhances the accuracy and uniqueness of data, contributing to
the effectiveness of the cardiac disease prediction algorithm.