Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis DOI Creative Commons
Ferdi Özbilgin, Çetin Kurnaz, Ertan Aydın

et al.

Diagnostics, Journal Year: 2023, Volume and Issue: 13(6), P. 1081 - 1081

Published: March 13, 2023

Coronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to heart muscles. It is most common type of disease has highest mortality rate. Early diagnosis CAD can prevent from progressing make treatment easier. Optimal treatment, in addition early detection CAD, improve prognosis for these patients. This study proposes a new method non-invasive using iris images. In this study, iridology, analyzing diagnose health conditions, was combined with image processing techniques detect total 198 volunteers, 94 104 without. The transformed into rectangular format integral differential operator rubber sheet methods, region cropped according map. Features were extracted wavelet transform, first-order statistical analysis, Gray-Level Co-Occurrence Matrix (GLCM), Gray Level Run Length (GLRLM). model’s performance evaluated based on accuracy, sensitivity, specificity, precision, score, mean, Area Under Curve (AUC) metrics. proposed model 93% accuracy rate predicting Support Vector Machine (SVM) classifier. With method, artery be preliminarily diagnosed by analysis without needing electrocardiography, echocardiography, effort tests. Additionally, easily used support telediagnosis applications integrated telemedicine systems.

Language: Английский

Machine Learning-Based Automated Diagnostic Systems Developed for Heart Failure Prediction Using Different Types of Data Modalities: A Systematic Review and Future Directions DOI Creative Commons
Ashir Javeed, Shafqat Ullah Khan,

Liaqat Ali

et al.

Computational and Mathematical Methods in Medicine, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 30

Published: Feb. 3, 2022

One of the leading causes deaths around globe is heart disease. Heart an organ that responsible for supply blood to each part body. Coronary artery disease (CAD) and chronic failure (CHF) often lead attack. Traditional medical procedures (angiography) diagnosis have higher cost as well serious health concerns. Therefore, researchers developed various automated diagnostic systems based on machine learning (ML) data mining techniques. ML-based provide affordable, efficient, reliable solutions detection. Various ML, methods, modalities been utilized in past. Many previous review papers presented systematic reviews one type modality. This study, therefore, targets prediction different types modalities, i.e., clinical feature-based modality, images, ECG. Moreover, this paper critically evaluates methods presents limitations these methods. Finally, article provides some future research directions domain detection multiple modalities.

Language: Английский

Citations

64
MBGAN: An improved generative adversarial network with multi-head self-attention and bidirectional RNN for time series imputation DOI
Qingjian Ni,

Xuehan Cao

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 115, P. 105232 - 105232

Published: Aug. 1, 2022

Language: Английский

Citations

42
Classification of Parkinson’s disease and its stages using machine learning DOI Creative Commons
John Michael Templeton, Christian Poellabauer, Sandra Schneider

et al.

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Aug. 18, 2022

As digital health technology becomes more pervasive, machine learning (ML) provides a robust way to analyze and interpret the myriad of collected features. The purpose this preliminary work was use ML classification assess benefits relevance neurocognitive features both tablet-based assessments self-reported metrics, as they relate Parkinson's Disease (PD) its stages [Hoehn Yahr (H&Y) Stages 1-5]. Further, aims compare perceived versus sensor-based abilities. In study, 75 participants ([Formula: see text] PD; [Formula: control) completed 14 functional tests (e.g., motor, memory, speech, executive, multifunction), movement Berg Balance Scale), standardized questionnaires PDQ-39). Decision tree allowed for discrimination PD from healthy controls with an accuracy text], early advanced text]; compared current gold standard tools [e.g., accuracy) accuracy)]. Significant were also identified using decision classification. Device magnitude acceleration significant in 12 text]), regardless test type. For between diagnosed control populations, 17 motor device acceleration), 9 number correct/incorrect interactions), 8 timing time interactions) significant. (H&Y 1 2) 3, 4, 5) PD, 7 accuracy, Finally, depicts that functionality individuals differed functionalities. early-stage shown be lower than scores notable deficits memory executive function. However, had elevated perceptions (1.57x) behavioral functions populations. Machine systems allows comprehensive understanding neurodegenerative diseases their may depict new influence ways should configured.

Language: Английский

Citations

42
Enhancing Digital Health Services with Big Data Analytics DOI Creative Commons
Nisrine Berros, Fatna Elmendili,

Youness Filaly

et al.

Big Data and Cognitive Computing, Journal Year: 2023, Volume and Issue: 7(2), P. 64 - 64

Published: March 30, 2023

Medicine is constantly generating new imaging data, including data from basic research, clinical and epidemiology, health administration insurance organizations, public services, non-conventional sources such as social media, Internet applications, etc. Healthcare professionals have gained the integration of big in many ways, tools for decision support, improved research methodologies, treatment efficacy, personalized care. Finally, there are significant advantages saving resources reallocating them to increase productivity rationalization. In this paper, we will explore how can be applied field digital health. We explain features its particularities, available use it. addition, a particular focus placed on latest work that addresses analysis domain, well technical organizational challenges been discussed. propose general strategy medical organizations looking adopt or leverage analytics. Through study, healthcare institutions considering analytics technology, those already using it, gain thorough comprehensive understanding potential use, effective targeting, expected impact.

Language: Английский

Citations

34
Exploring the dominant features and data-driven detection of polycystic ovary syndrome through modified stacking ensemble machine learning technique DOI Creative Commons
Sayma Alam Suha, Muhammad Nazrul Islam

Heliyon, Journal Year: 2023, Volume and Issue: 9(3), P. e14518 - e14518

Published: March 1, 2023

Polycystic ovary syndrome (PCOS) is the most frequent endocrinological anomaly in reproductive women that causes persistent hormonal secretion disruption, leading to formation of numerous cysts within ovaries and serious health complications. But real-world clinical detection technique for PCOS very critical since accuracy interpretations being substantially dependent on physician's expertise. Thus, an artificially intelligent prediction model might be a feasible additional error prone time-consuming diagnostic technique. In this study, modified ensemble machine learning (ML) classification approach proposed utilizing state-of-the-art stacking identification with patients' symptom data; employing five traditional ML models as base learners then one bagging or boosting meta-learner stacked model. Furthermore, three distinct types feature selection strategies are applied pick different sets features varied numbers combinations attributes. To evaluate explore dominant necessary predicting PCOS, variety other ten classifiers trained, tested assessed sets. As outcomes, significantly enhances comparison existing based techniques case all varieties However, among various investigated categorize non-PCOS patients, 'Gradient Boosting' classifier meta learner outperforms others 95.7% while top 25 selected using Principal Component Analysis (PCA)

Language: Английский

Citations

33
A survey on deep learning models for detection of COVID-19 DOI Open Access
Javad Mozaffari, Abdollah Amirkhani, Shahriar B. Shokouhi

et al.

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 35(23), P. 16945 - 16973

Published: May 27, 2023

Language: Английский

Citations

25
Chest X-ray Images for Lung Disease Detection Using Deep Learning Techniques: A Comprehensive Survey DOI
Mohammed A. A. Al‐qaness,

Jie Zhu,

Dalal AL-Alimi

et al.

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: 31(6), P. 3267 - 3301

Published: Feb. 19, 2024

Language: Английский

Citations

12
Advances of AI in image-based computer-aided diagnosis: A review DOI Creative Commons
Mst. Nilufa Yeasmin, Md Al Amin,

Tasmim Jamal Joti

et al.

Array, Journal Year: 2024, Volume and Issue: 23, P. 100357 - 100357

Published: July 6, 2024

Over the past two decades, computer-aided detection and diagnosis have emerged as a field of research. The primary goal is to enhance diagnostic treatment procedures for radiologists clinicians in medical image analysis. With help big data advanced artificial intelligence (AI) technologies, such machine learning deep algorithms, healthcare system can be made more convenient, active, efficient, personalized. this literature survey was present thorough overview most important developments related (CAD) systems imaging. This considerable importance researchers professionals both computer sciences. Several reviews on specific facets CAD imaging been published. Nevertheless, main emphasis study cover complete range capabilities review article introduces background concepts used typical by outlining comparing several methods frequently employed recent studies. also presents comprehensive well-structured medicine, drawing meticulous selection relevant publications. Moreover, it describes process handling images state-of-the-art AI-based technologies imaging, along with future directions CAD. indicates that algorithms are effective method diagnose detect diseases.

Language: Английский

Citations

12
A novel methodology using RNN + LSTM + ML for predicting student’s academic performance DOI
Ashima Kukkar, Rajni Mohana, Aman Sharma

et al.

Education and Information Technologies, Journal Year: 2024, Volume and Issue: 29(11), P. 14365 - 14401

Published: Jan. 6, 2024

Language: Английский

Citations

11
A reliable predict-then-optimize approach for minimizing aircraft fuel consumption DOI
Ziming Wang, Dabin Xue, Lingxiao Wu

et al.

Transportation Research Part D Transport and Environment, Journal Year: 2025, Volume and Issue: 142, P. 104693 - 104693

Published: March 17, 2025

Language: Английский

Citations

1