A Novel Classification of Machine Learning Applications in Healthcare

Thamara, Abeer; Elsersy, Mohamed; Sherif, Ahmed; Hassan, Heba A.; Abdel-Salam, Omar E.; Almotairi, Khaled H.

doi:10.1109/menacomm50742.2021.9678232

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years classification models have been used in various clinical applications, for example, in medical diagnosis, disease classification, prediction of clinical outcomes, and treatment responses [ 5 , 6 , 7 , 8 ]. There are several ML classification algorithms, three of the most widely used in healthcare applications are Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN) [ 9 , 10 , 11 ]. However, in most classification problems in real-life applications, the sample sizes between the different classes are unbalanced [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Classification Models of Action Research Arm Test Activities in Post-Stroke Patients Based on Human Hand Motion

Padilla-Magaña

Pitarch

2022

Sensors

View full text Add to dashboard Cite

The Action Research Arm Test (ARAT) presents a ceiling effect that prevents the detection of improvements produced with rehabilitation treatments in stroke patients with mild finger joint impairments. The aim of this study was to develop classification models to predict whether activities with similar ARAT scores were performed by a healthy subject or by a subject post-stroke using the extension and flexion angles of 11 finger joints as features. For this purpose, we used three algorithms: Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN). The dataset presented class imbalance, and the classification models presented a low recall, especially in the stroke class. Therefore, we implemented class balance using Borderline-SMOTE. After data balancing the classification models showed significantly higher accuracy, recall, f1-score, and AUC. However, after data balancing, the SVM classifier showed a higher performance with a precision of 98%, a recall of 97.5%, and an AUC of 0.996. The results showed that classification models based on human hand motion features in combination with the oversampling algorithm Borderline-SMOTE achieve higher performance. Furthermore, our study suggests that there are differences in ARAT activities performed between healthy and post-stroke individuals that are not detected by the ARAT scoring process.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification Models of Action Research Arm Test Activities in Post-Stroke Patients Based on Human Hand Motion

Padilla-Magaña

Pitarch

2022

Sensors

View full text Add to dashboard Cite

show abstract

Classification Models in Post-stroke Patients Based in Human Hand Motion

Pitarch

Padilla-Magaña

Omar

et al. 2023

Advances in Digital Human Modeling

View full text Add to dashboard Cite

Application of internet of things in healthcare domain

Almotairi

2022

J. Umm Al-Qura Univ. Eng.Archit.

View full text Add to dashboard Cite

Internet of things (IoT) enables machine-to-machine, human-to-human and machine-to-human interaction. Recent advancement in IoT systems has positively impacted the daily activities of humans, from accessing information to the delivery of service in real-time. This has improved healthcare management and services, especially in medical hospitals, for effective and timely access to diagnostic information and treatment of patients. Several existing research mainly focused on the design of IoT architecture, its challenges, and benefits to human society with minor or without considering applying IoT in the healthcare domain. To bridge this gap, this study investigates the implications of IoT integration in the healthcare management domain. It presents a detailed discussion on IoT utilization to improve the functionalities of hospital management system. It also discusses some potential emerging innovations that aids the development and application of IoT in hospital management systems. Investigations show that healthcare personnel can administer treatments to patients anytime–anywhere. Patients, especially the elderly are administered treatment, as well as monitoring their wellbeing while at home with the support of wearable sensor devices. Also, some of the challenges that impedes the integration of IoT application into healthcare domain includes generation of irrelevant huge amount of data, issues of security and privacy of patient information and high cost of IoT adoption. Furthermore, the future research trends in adoption of IoT to improve healthcare domain includes stroke and epileptic seizure predictions and prosthetic sensors which is used to retrieve relevant data or information to aid the treatment of a patient in real-time.

show abstract

A Novel Classification of Machine Learning Applications in Healthcare

Cited by 4 publications

References 27 publications

Classification Models of Action Research Arm Test Activities in Post-Stroke Patients Based on Human Hand Motion

Classification Models of Action Research Arm Test Activities in Post-Stroke Patients Based on Human Hand Motion

Classification Models in Post-stroke Patients Based in Human Hand Motion

Application of internet of things in healthcare domain

Contact Info

Product

Resources

About