Unsupervised machine learning to investigate trajectory patterns of COVID-19 symptoms and physical activity measured via the MyHeart Counts App and smart devices DOI Creative Commons
Varsha Gupta, Sokratis Kariotis, Mohammed Rajab

et al.

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: Dec. 22, 2023

Abstract Previous studies have associated COVID-19 symptoms severity with levels of physical activity. We therefore investigated longitudinal trajectories in a cohort healthcare workers (HCWs) non-hospitalised and their real-world 121 HCWs history infection who had monitored through at least two research clinic visits, via smartphone were examined. compatible provided an Apple Watch Series 4 asked to install the MyHeart Counts Study App collect symptom data multiple activity parameters. Unsupervised classification analysis identified trajectory patterns long short duration. The prevalence for persistence any was 36% fatigue loss smell being most prevalent individual (24.8% 21.5%, respectively). 8 features obtained groups high low Of these parameters only ‘distance moved walking or running’ trajectories. report long-term HCWs, method identify trends, investigate association. These highlight importance tracking from onset recovery even individuals. increasing ease collecting non-invasively wearable devices provides opportunity association other cardio-respiratory diseases.

Language: Английский

Heart Disease Prediction Using Machine Learning DOI

Chaimaa Boukhatem,

Heba Youssef, Ali Bou Nassif

et al.

2022 Advances in Science and Engineering Technology International Conferences (ASET), Journal Year: 2022, Volume and Issue: unknown, P. 1 - 6

Published: Feb. 21, 2022

Cardiovascular disease refers to any critical condition that impacts the heart. Because heart diseases can be life-threatening, researchers are focusing on designing smart systems accurately diagnose them based electronic health data, with aid of machine learning algorithms. This work presents several approaches for predicting diseases, using data major factors from patients. The paper demonstrated four classification methods: Multilayer Perceptron (MLP), Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes (NB), build prediction models. Data preprocessing feature selection steps were done before building models evaluated accuracy, precision, recall, F1-score. SVM model performed best 91.67% accuracy.

Language: Английский

Citations

83
Machine Learning and AI Technologies for Smart Wearables DOI Open Access

Kah Phooi Seng,

Li-Minn Ang, Eno Peter

et al.

Electronics, Journal Year: 2023, Volume and Issue: 12(7), P. 1509 - 1509

Published: March 23, 2023

The recent progress in computational, communications, and artificial intelligence (AI) technologies, the widespread availability of smartphones together with growing trends multimedia data edge computation devices have led to new models paradigms for wearable devices. This paper presents a comprehensive survey classification smart wearables research prototypes using machine learning AI technologies. aims these from various technological perspectives which emerged, including: (1) empowered by AI; (2) collection architectures information processing wearables; (3) applications wearables. review covers wide range enabling technologies prototypes. main findings are that there significant technical challenges networking communication aspects such as issues routing overheads, computational complexity storage, algorithmic application-dependent training inference. concludes some future directions market potential research.

Language: Английский

Citations

43
Designing interpretable ML system to enhance trust in healthcare: A systematic review to proposed responsible clinician-AI-collaboration framework DOI
Elham Nasarian, Roohallah Alizadehsani, U. Rajendra Acharya

et al.

Information Fusion, Journal Year: 2024, Volume and Issue: 108, P. 102412 - 102412

Published: April 6, 2024

Language: Английский

Citations

31
Future of Artificial Intelligence (AI) - Machine Learning (ML) Trends in Pathology and Medicine DOI Creative Commons
Matthew G. Hanna,

Liron Pantanowitz,

Rajesh Dash

et al.

Modern Pathology, Journal Year: 2025, Volume and Issue: 38(4), P. 100705 - 100705

Published: Jan. 5, 2025

Artificial intelligence (AI) and machine learning (ML) are transforming the field of medicine. Health care organizations now starting to establish management strategies for integrating such platforms (AI-ML toolsets) that leverage computational power advanced algorithms analyze data provide better insights ultimately translate enhanced clinical decision-making improved patient outcomes. Emerging AI-ML trends in pathology medicine reshaping by offering innovative solutions enhance diagnostic accuracy, operational workflows, decision support, These tools also increasingly valuable research which they contribute automated image analysis, biomarker discovery, drug development, trials, productive analytics. Other related include adoption ML operations managing models settings, application multimodal multiagent AI utilize diverse sources, expedited translational research, virtualized education training simulation. As final chapter our educational series, this review article delves into current adoption, future directions, transformative potential medicine, discussing their applications, benefits, challenges, perspectives.

Language: Английский

Citations

8
Reshaping the healthcare world by AI-integrated wearable sensors following COVID-19 DOI
Bangul Khan,

Rana Talha Khalid,

Khair Ul Wara

et al.

Chemical Engineering Journal, Journal Year: 2025, Volume and Issue: 505, P. 159478 - 159478

Published: Jan. 11, 2025

Language: Английский

Citations

2
Current methods in explainable artificial intelligence and future prospects for integrative physiology DOI Creative Commons
Bettina Finzel

Pflügers Archiv - European Journal of Physiology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 25, 2025

Abstract Explainable artificial intelligence (XAI) is gaining importance in physiological research, where now used as an analytical and predictive tool for many medical research questions. The primary goal of XAI to make AI models understandable human decision-makers. This can be achieved particular through providing inherently interpretable methods or by making opaque their outputs transparent using post hoc explanations. review introduces core topics provides a selective overview current physiology. It further illustrates solved discusses open challenges existing practical examples from the field. article gives outlook on two possible future prospects: (1) provide trustworthy integrative (2) integrating expertise about explanation into method development useful beneficial human-AI partnerships.

Language: Английский

Citations

2
Arabic fake news detection based on deep contextualized embedding models DOI Open Access
Ali Bou Nassif, Ashraf Elnagar,

Omar Elgendy

et al.

Neural Computing and Applications, Journal Year: 2022, Volume and Issue: 34(18), P. 16019 - 16032

Published: May 3, 2022

Language: Английский

Citations

55
Explainable AI in Diagnosing and Anticipating Leukemia Using Transfer Learning Method DOI Creative Commons
Wahidul Hasan Abir, Md. Fahim Uddin, Faria Rahman Khanam

et al.

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 14

Published: April 27, 2022

This research paper focuses on Acute Lymphoblastic Leukemia (ALL), a form of blood cancer prevalent in children and teenagers, characterized by the rapid proliferation immature white cells (WBCs). These atypical can overwhelm healthy cells, leading to severe health consequences. Early accurate detection ALL is vital for effective treatment improving survival rates. Traditional diagnostic methods are time-consuming, costly, prone errors. The proposes an automated approach using computer-aided (CAD) models, leveraging deep learning techniques enhance accuracy efficiency leukemia diagnosis. study utilizes various transfer models like ResNet101V2, VGG19, InceptionV3, InceptionResNetV2 classifying ALL. methodology includes Local Interpretable Model-Agnostic Explanations (LIME) ensuring validity reliability AI system's predictions. critical overcoming "black box" nature AI, where decisions made often opaque unaccountable. highlights that proposed method InceptionV3 model achieved impressive 98.38% accuracy, outperforming other tested models. results, verified LIME algorithm, showcase potential this accurately identifying ALL, providing valuable tool medical practitioners. underscores impact explainable artificial intelligence (XAI) diagnostics, paving way more transparent trustworthy applications healthcare.

Language: Английский

Citations

47
Mobile Apps for COVID-19 Detection and Diagnosis for Future Pandemic Control: Multidimensional Systematic Review DOI Creative Commons
Mehdi Gheisari, Mustafa Ghaderzadeh, Huxiong Li

et al.

JMIR mhealth and uhealth, Journal Year: 2023, Volume and Issue: 12, P. e44406 - e44406

Published: Aug. 18, 2023

In the modern world, mobile apps are essential for human advancement, and pandemic control is no exception. The use of technology detection diagnosis COVID-19 has been subject numerous investigations, although thorough analysis prevention conducted using apps, creating a gap.

Language: Английский

Citations

25
COVID-19 Detection Systems Using Deep-Learning Algorithms Based on Speech and Image Data DOI Creative Commons
Ali Bou Nassif, Ismail Shahin,

Mohamed Bader

et al.

Mathematics, Journal Year: 2022, Volume and Issue: 10(4), P. 564 - 564

Published: Feb. 11, 2022

The global epidemic caused by COVID-19 has had a severe impact on the health of human beings. virus wreaked havoc throughout world since its declaration as worldwide pandemic and affected an expanding number nations in numerous countries around world. Recently, substantial amount work been done doctors, scientists, many others working frontlines to battle effects spreading virus. integration artificial intelligence, specifically deep- machine-learning applications, sector contributed substantially fight against providing modern innovative approach for detecting, diagnosing, treating, preventing In this proposed work, we focus mainly role speech signal and/or image processing detecting presence COVID-19. Three types experiments have conducted, utilizing speech-based, image-based, image-based models. Long short-term memory (LSTM) utilized classification patient’s cough, voice, breathing, obtaining accuracy that exceeds 98%. Moreover, CNN models VGG16, VGG19, Densnet201, ResNet50, Inceptionv3, InceptionResNetV2, Xception benchmarked chest X-ray images. VGG16 model outperforms all other models, achieving 85.25% without fine-tuning 89.64% after performing techniques. Furthermore, speech–image-based evaluated using same seven attaining 82.22% InceptionResNetV2 model. Accordingly, it is inessential combined be employed diagnosis purposes speech-based each shown higher terms than

Language: Английский

Citations

37