Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.45937
A. Samala, Soha Rawas
This study investigates the potential of Chat Generative Pre-Trained Transformer (ChatGPT) as a virtual healthcare assistant to enhance the quality of patient care. Inadequate patient care within healthcare systems is a key issue that has resulted in lower satisfaction and medical errors. Virtual healthcare assistants, exemplified by ChatGPT, have emerged as a promising solution to mitigate these challenges. A comprehensive literature review compares the benefits and drawbacks of using virtual healthcare assistants with those of human healthcare providers to assess their effectiveness in enhancing patient care. The article discusses the ChatGPT development process, including the data sources used, training and validation, and the integration of this technology into healthcare systems. The results of testing ChatGPT in patient care, including patient feedback, are provided. The study interprets these findings and indicates that ChatGPT can significantly enhance patient care. The implications of implementing virtual healthcare assistants in the healthcare sector are also explored, along with potential future research areas for enhancing ChatGPT. This study provides important new insights into how virtual healthcare assistants might enhance patient care and offers recommendations for healthcare organizations and legislators on leveraging ChatGPT. It shows that the astonishing development in patient care, known as ChatGPT, has the potential to revolutionize the healthcare industry.
{"title":"Generative AI as Virtual Healthcare Assistant for Enhancing Patient Care Quality","authors":"A. Samala, Soha Rawas","doi":"10.3991/ijoe.v20i05.45937","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.45937","url":null,"abstract":"This study investigates the potential of Chat Generative Pre-Trained Transformer (ChatGPT) as a virtual healthcare assistant to enhance the quality of patient care. Inadequate patient care within healthcare systems is a key issue that has resulted in lower satisfaction and medical errors. Virtual healthcare assistants, exemplified by ChatGPT, have emerged as a promising solution to mitigate these challenges. A comprehensive literature review compares the benefits and drawbacks of using virtual healthcare assistants with those of human healthcare providers to assess their effectiveness in enhancing patient care. The article discusses the ChatGPT development process, including the data sources used, training and validation, and the integration of this technology into healthcare systems. The results of testing ChatGPT in patient care, including patient feedback, are provided. The study interprets these findings and indicates that ChatGPT can significantly enhance patient care. The implications of implementing virtual healthcare assistants in the healthcare sector are also explored, along with potential future research areas for enhancing ChatGPT. This study provides important new insights into how virtual healthcare assistants might enhance patient care and offers recommendations for healthcare organizations and legislators on leveraging ChatGPT. It shows that the astonishing development in patient care, known as ChatGPT, has the potential to revolutionize the healthcare industry.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"3 2‐3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140239117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.46773
Ricardo Yauri, Gerson Mallqui
This paper describes the use of Internet of Things (IoT) technologies, digital twins (DT), and augmented reality (AR) to raise awareness and disseminate the use of digital services within the INICTEL-UNI institutional project financed by the Inter-American Development Bank to strengthen technological services and satisfy the technological needs of companies, promoting digital transformation in Peru. Within various fields, such as technical education, construction, and manufacturing, challenges are faced related to the adoption of advanced technologies and the need to improve efficiency. The main objective of this paper is to implement an IoT control and visualization system with DT and AR in a digital transformation space. A system is shown to create a technological demonstrator environment that visualizes and monitors sensor data on physical IoT devices in real time, allowing users to interact and operate them through an ESP32 module with data transmission with the MQTT protocol and an AR application developed in Unity and Vuforia. The study results successfully demonstrated the efficiency of real-time communication between the IoT device and the AR application, as well as the efficient ability to perform tasks, validated by users with no prior experience.
本文介绍了物联网（IoT）技术、数字双胞胎（DT）和增强现实（AR）在 INICTEL-UNI 机构项目中的应用，该项目由美洲开发银行资助，旨在加强技术服务，满足企业的技术需求，促进秘鲁的数字化转型。在技术教育、建筑和制造业等各个领域，都面临着采用先进技术和提高效率的挑战。本文的主要目的是在数字化转型空间内，利用 DT 和 AR 实现物联网控制和可视化系统。该系统创建了一个技术演示环境，可实时可视化和监控物理物联网设备上的传感器数据，允许用户通过使用 MQTT 协议传输数据的 ESP32 模块以及使用 Unity 和 Vuforia 开发的 AR 应用程序进行交互和操作。研究结果成功证明了物联网设备与 AR 应用程序之间的实时通信效率，以及执行任务的高效能力，并得到了无经验用户的验证。
{"title":"IoT Control and Visualization System with Digital Twins and Augmented Reality in a Digital Transformation Space","authors":"Ricardo Yauri, Gerson Mallqui","doi":"10.3991/ijoe.v20i04.46773","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.46773","url":null,"abstract":"This paper describes the use of Internet of Things (IoT) technologies, digital twins (DT), and augmented reality (AR) to raise awareness and disseminate the use of digital services within the INICTEL-UNI institutional project financed by the Inter-American Development Bank to strengthen technological services and satisfy the technological needs of companies, promoting digital transformation in Peru. Within various fields, such as technical education, construction, and manufacturing, challenges are faced related to the adoption of advanced technologies and the need to improve efficiency. The main objective of this paper is to implement an IoT control and visualization system with DT and AR in a digital transformation space. A system is shown to create a technological demonstrator environment that visualizes and monitors sensor data on physical IoT devices in real time, allowing users to interact and operate them through an ESP32 module with data transmission with the MQTT protocol and an AR application developed in Unity and Vuforia. The study results successfully demonstrated the efficiency of real-time communication between the IoT device and the AR application, as well as the efficient ability to perform tasks, validated by users with no prior experience.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"32 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140265776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.43623
Chaimae Zaoui, F. Benabbou, Abdelaziz Ettaoufik, K. Sabiri
E-health systems rely on information and communication technology to support and improve various aspects of health services, delivery, and management. The success of artificial intelligence techniques has led to the emergence of a variety of systems designed to address a wide range of healthcare issues. In particular, gathering data on patient activity and behavior has enabled the development of reliable predictive systems for detecting chronic diseases and forecasting their progression. Human activity detection is a vast and emerging field, and various datasets have been collected for training different machine learning and deep learning (DL) models. The University of Milano Bicocca smartphone-based human activity recognition (UniMiB-SHAR) dataset is widely used for analyzing and recognizing human actions, including walking, running, and other daily activities. However, the autoencoder (AE) technique trained on this dataset yields poor performance. This paper aims to enhance the performance of AEs on the challenging UniMiB-SHAR dataset by introducing a convolutional AE model and employing novel preprocessing techniques, including normalization, magnitude, principal component analysis (PCA), and balancing methods such as SMOTEEN and ADASYNE. The experimental results demonstrate that the proposed AE model achieved successful performance, surpassing the state-of-the-art methods, with accuracies of 96.56% for activities of daily living (ADL), 98.86% for Fall, and 88.47% for the full dataset.
{"title":"Human Activity Recognition Using Convolutional Autoencoder and Advanced Preprocessing","authors":"Chaimae Zaoui, F. Benabbou, Abdelaziz Ettaoufik, K. Sabiri","doi":"10.3991/ijoe.v20i04.43623","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.43623","url":null,"abstract":"E-health systems rely on information and communication technology to support and improve various aspects of health services, delivery, and management. The success of artificial intelligence techniques has led to the emergence of a variety of systems designed to address a wide range of healthcare issues. In particular, gathering data on patient activity and behavior has enabled the development of reliable predictive systems for detecting chronic diseases and forecasting their progression. Human activity detection is a vast and emerging field, and various datasets have been collected for training different machine learning and deep learning (DL) models. The University of Milano Bicocca smartphone-based human activity recognition (UniMiB-SHAR) dataset is widely used for analyzing and recognizing human actions, including walking, running, and other daily activities. However, the autoencoder (AE) technique trained on this dataset yields poor performance. This paper aims to enhance the performance of AEs on the challenging UniMiB-SHAR dataset by introducing a convolutional AE model and employing novel preprocessing techniques, including normalization, magnitude, principal component analysis (PCA), and balancing methods such as SMOTEEN and ADASYNE. The experimental results demonstrate that the proposed AE model achieved successful performance, surpassing the state-of-the-art methods, with accuracies of 96.56% for activities of daily living (ADL), 98.86% for Fall, and 88.47% for the full dataset.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"96 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140079765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.46387
Zakaryae Khomsi, Mohamed El Fezazi, L. Bellarbi
The characterization of tumors is crucial for guiding appropriate treatment strategies and enhancing patient survival rates. Surface thermography shows promise in the non-invasive detection of thermal patterns associated with the existence of breast tumors. Nevertheless, the precise prediction of both tumor size and location using temperature characteristics presents a critical challenge. This is due to the limited availability of thermal images labeled with the corresponding tumor size and location. This work proposes a deep learning approach based on convolutional neural networks (CNN) in combination with thermographic images for estimating breast tumor size and location. Successive COMSOL-based simulations are conducted, including a 3D breast model with various tumor scenarios. Thus, different noise levels were included in the development of the thermographic image dataset. Every image was accordingly labeled with the corresponding tumor location and size to train the CNN model. Mean absolute error (MAE) and the coefficient of determination (R²) were considered as evaluation metrics. The results show that the proposed CNN model achieved a reasonable prediction performance with MAE–R² values of 0.872–98.6% for tumor size, 1.161–96.8% for x location, 1.086–97.1% for y location, and 0.954–96.7% for z location. This study indicates that the combination of surface thermography and deep learning is a convenient tool for predicting breast tumor parameters.
{"title":"CNN-Based Approach for Non-Invasive Estimation of Breast Tumor Size and Location Using Thermographic Images","authors":"Zakaryae Khomsi, Mohamed El Fezazi, L. Bellarbi","doi":"10.3991/ijoe.v20i04.46387","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.46387","url":null,"abstract":"The characterization of tumors is crucial for guiding appropriate treatment strategies and enhancing patient survival rates. Surface thermography shows promise in the non-invasive detection of thermal patterns associated with the existence of breast tumors. Nevertheless, the precise prediction of both tumor size and location using temperature characteristics presents a critical challenge. This is due to the limited availability of thermal images labeled with the corresponding tumor size and location. This work proposes a deep learning approach based on convolutional neural networks (CNN) in combination with thermographic images for estimating breast tumor size and location. Successive COMSOL-based simulations are conducted, including a 3D breast model with various tumor scenarios. Thus, different noise levels were included in the development of the thermographic image dataset. Every image was accordingly labeled with the corresponding tumor location and size to train the CNN model. Mean absolute error (MAE) and the coefficient of determination (R²) were considered as evaluation metrics. The results show that the proposed CNN model achieved a reasonable prediction performance with MAE–R² values of 0.872–98.6% for tumor size, 1.161–96.8% for x location, 1.086–97.1% for y location, and 0.954–96.7% for z location. This study indicates that the combination of surface thermography and deep learning is a convenient tool for predicting breast tumor parameters.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"7 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.45429
Hector Espinoza Villavicencio, Javier Gamboa-Cruzado, Jefferson López-Goycochea, Luis Soto Soto
Artificial intelligence (AI) has significantly transformed the medical field, especially in the diagnosis, treatment, and management of oncological diseases. It has had a profound impact on clinical decision-making and has enhanced the quality of life for various populations. This study aims to comprehensively assess the inherent relationship between AI and medicine and to uncover both its positive and negative implications. To achieve a comprehensive understanding, a thorough systematic review of articles was conducted, examining a total of 80 papers published between 2017 and 2023. These articles were carefully selected from well-known open-access databases, such as Scopus, IOPscience, IEEE Xplore, Google Scholar, ResearchGate, and ProQuest. A key finding from this review is that the majority of research on this topic has been published in scientific journals ranked in the first-quartile (Q1), underscoring the importance and high quality of research in this field. The United States, China, India, the United Kingdom, and Canada are the foremost countries in publishing on this topic. Most of the research is published in first-quartile (Q1) journals, representing 51% of the studies. Only 1% of articles appear in third-quartile (Q3) journals. IEEE Xplore is renowned as the primary database for accessing high-impact studies in this field. Future research should prioritize investigating the long-term impact of AI on patient clinical outcomes. International collaborative research could promote innovation and fairness in the implementation of artificial intelligence (AI) in oncology.
{"title":"The Role of Artificial Intelligence in the Diagnosis of Neoplastic Diseases: A Systematic and Bibliometric Review","authors":"Hector Espinoza Villavicencio, Javier Gamboa-Cruzado, Jefferson López-Goycochea, Luis Soto Soto","doi":"10.3991/ijoe.v20i04.45429","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.45429","url":null,"abstract":"Artificial intelligence (AI) has significantly transformed the medical field, especially in the diagnosis, treatment, and management of oncological diseases. It has had a profound impact on clinical decision-making and has enhanced the quality of life for various populations. This study aims to comprehensively assess the inherent relationship between AI and medicine and to uncover both its positive and negative implications. To achieve a comprehensive understanding, a thorough systematic review of articles was conducted, examining a total of 80 papers published between 2017 and 2023. These articles were carefully selected from well-known open-access databases, such as Scopus, IOPscience, IEEE Xplore, Google Scholar, ResearchGate, and ProQuest. A key finding from this review is that the majority of research on this topic has been published in scientific journals ranked in the first-quartile (Q1), underscoring the importance and high quality of research in this field. The United States, China, India, the United Kingdom, and Canada are the foremost countries in publishing on this topic. Most of the research is published in first-quartile (Q1) journals, representing 51% of the studies. Only 1% of articles appear in third-quartile (Q3) journals. IEEE Xplore is renowned as the primary database for accessing high-impact studies in this field. Future research should prioritize investigating the long-term impact of AI on patient clinical outcomes. International collaborative research could promote innovation and fairness in the implementation of artificial intelligence (AI) in oncology.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"20 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.44511
David Mauricio, Walter Bendita, Ronaldo Flores, Pedro Segundo Castañeda Vargas, Roberth Chuquimbalqui-Maslucán, L. Rojas-Mezarina, Nelson Maculan
Currently, telehealth services in rural regions of Peru primarily rely on telephone and text message communication between rural physicians and specialists based in cities, leading to delays in accessing specialized healthcare services. To overcome this limitation, we propose an information and communication technology (ICT) model for asynchronous teleconsultation in rural areas of Peru. This model, implemented through a system called SITEA, coordinates city-based specialists with treating physicians in rural areas and integrates care phases along with electronic clinical records. A case study conducted in a rural Peruvian healthcare facility, which had limited Internet connectivity and lacked teleconsultation services, revealed significant outcomes. Within 23 days of implementing SITEA, the facility began offering specialized care services, leading to a 60% reduction in patient transfers to specialized urban healthcare facilities. Furthermore, a satisfaction survey conducted with 50 patients resulted in overwhelmingly positive feedback regarding the quality of medical care and future expectations for healthcare services. These positive outcomes can be attributed to the implementation of specialized services, the shift from physical to electronic records, and improved diagnostic accuracy. Importantly, healthcare personnel found the system easy to navigate and highly beneficial, despite the area’s connectivity limitations.
{"title":"AT: Asynchronous Teleconsultation for Health Centers in Rural Areas of Peru","authors":"David Mauricio, Walter Bendita, Ronaldo Flores, Pedro Segundo Castañeda Vargas, Roberth Chuquimbalqui-Maslucán, L. Rojas-Mezarina, Nelson Maculan","doi":"10.3991/ijoe.v20i04.44511","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.44511","url":null,"abstract":"Currently, telehealth services in rural regions of Peru primarily rely on telephone and text message communication between rural physicians and specialists based in cities, leading to delays in accessing specialized healthcare services. To overcome this limitation, we propose an information and communication technology (ICT) model for asynchronous teleconsultation in rural areas of Peru. This model, implemented through a system called SITEA, coordinates city-based specialists with treating physicians in rural areas and integrates care phases along with electronic clinical records. A case study conducted in a rural Peruvian healthcare facility, which had limited Internet connectivity and lacked teleconsultation services, revealed significant outcomes. Within 23 days of implementing SITEA, the facility began offering specialized care services, leading to a 60% reduction in patient transfers to specialized urban healthcare facilities. Furthermore, a satisfaction survey conducted with 50 patients resulted in overwhelmingly positive feedback regarding the quality of medical care and future expectations for healthcare services. These positive outcomes can be attributed to the implementation of specialized services, the shift from physical to electronic records, and improved diagnostic accuracy. Importantly, healthcare personnel found the system easy to navigate and highly beneficial, despite the area’s connectivity limitations.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"27 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.46465
Chayapol Ruengdech, S. Howimanporn, Thanasan Intarakumthornchai, S. Chookaew
Maintaining health and safety is essential for workers’ quality of life, and thus, this has become one of the main priorities for industrial enterprises. Electric welders want required safety precautions to be implemented during work in industries with safety risks, especially muscle injuries. This challenge needs to be addressed by the safety officer, who should suggest a way to decrease the risk for workers. However, traditional assessment based on human evaluation and the need for expertise and accuracy in risk assessment have produced muscle injuries. Thus, using artificial intelligence (AI) technology to mitigate risk assessment is cost-effective and accurate. This study proposed a risk assessment system for muscle injuries (RASMI) with AI technology to assess electric welder postures with rapid entire body assessment (REBA) standards to identify the cause of muscle injuries and to warn electric welders when their pose may be a risk. The findings showed that the system can effectively and precisely evaluate the risk assessment of electric welders’ muscle injuries. Additional results showed that they perceive using AI technology to enhance wellness positively in terms of working with warnings for posture adjustment or behavior that can significantly affect an operator’s long-term health and well-being.
{"title":"Implementing a Risk Assessment System of Electric Welders’ Muscle Injuries for Working Posture Detection with AI Technology","authors":"Chayapol Ruengdech, S. Howimanporn, Thanasan Intarakumthornchai, S. Chookaew","doi":"10.3991/ijoe.v20i04.46465","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.46465","url":null,"abstract":"Maintaining health and safety is essential for workers’ quality of life, and thus, this has become one of the main priorities for industrial enterprises. Electric welders want required safety precautions to be implemented during work in industries with safety risks, especially muscle injuries. This challenge needs to be addressed by the safety officer, who should suggest a way to decrease the risk for workers. However, traditional assessment based on human evaluation and the need for expertise and accuracy in risk assessment have produced muscle injuries. Thus, using artificial intelligence (AI) technology to mitigate risk assessment is cost-effective and accurate. This study proposed a risk assessment system for muscle injuries (RASMI) with AI technology to assess electric welder postures with rapid entire body assessment (REBA) standards to identify the cause of muscle injuries and to warn electric welders when their pose may be a risk. The findings showed that the system can effectively and precisely evaluate the risk assessment of electric welders’ muscle injuries. Additional results showed that they perceive using AI technology to enhance wellness positively in terms of working with warnings for posture adjustment or behavior that can significantly affect an operator’s long-term health and well-being.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"16 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.3991/ijoe.v20i04.45413
D. Bhende, Gopal Sakarkar, Punam Khandar, Satyajit S. Uparkar, Arvind Bhave
Early-stage prediction of a disease is an important and challenging task. The application of machine learning techniques is playing an important role in this era. Thyroid is one of the chronic endocrine diseases, and approximately 42 million people in India are affected by this disease. This paper presents a comprehensive investigation into the enhancement of classification performance through the novel ‘FeatureBoostThyro’ (FBT) model. The study evaluates various machine learning algorithms, including stochastic gradient descent (SGD), K nearest neighbor (KNN), logistic regression (LR), naive bayes (NB), and support vector machine (SVM), in conjunction with diverse feature selection methods. The research systematically explores the impact of feature selection techniques such as information gain, relief F, chi-square, gini index, forward selection, backward selection, recursive feature elimination, and LASSO on model performance across the chosen algorithms. The analysis reveals notable variations in performance metrics, including accuracy, precision, recall, and F1-score, providing valuable insights into the interplay between algorithm and feature selection. One main contribution of this research is the introduction of the FBT model, which consistently outperforms other models across various feature selection methods, making it a promising tool for addressing complex classification tasks. The findings contribute to a broader understanding of model selection and optimization in machine learning applications. The proposed model undergoes evaluation using two distinct datasets: the primary dataset acquired from Lata Mangeshkar Hospital in Nagpur and the secondary dataset obtained from the UCI dataset.
{"title":"Enhancing Classification Performance through FeatureBoostThyro: A Comparative Study of Machine Learning Algorithms and Feature Selection","authors":"D. Bhende, Gopal Sakarkar, Punam Khandar, Satyajit S. Uparkar, Arvind Bhave","doi":"10.3991/ijoe.v20i04.45413","DOIUrl":"https://doi.org/10.3991/ijoe.v20i04.45413","url":null,"abstract":"Early-stage prediction of a disease is an important and challenging task. The application of machine learning techniques is playing an important role in this era. Thyroid is one of the chronic endocrine diseases, and approximately 42 million people in India are affected by this disease. This paper presents a comprehensive investigation into the enhancement of classification performance through the novel ‘FeatureBoostThyro’ (FBT) model. The study evaluates various machine learning algorithms, including stochastic gradient descent (SGD), K nearest neighbor (KNN), logistic regression (LR), naive bayes (NB), and support vector machine (SVM), in conjunction with diverse feature selection methods. The research systematically explores the impact of feature selection techniques such as information gain, relief F, chi-square, gini index, forward selection, backward selection, recursive feature elimination, and LASSO on model performance across the chosen algorithms. The analysis reveals notable variations in performance metrics, including accuracy, precision, recall, and F1-score, providing valuable insights into the interplay between algorithm and feature selection. One main contribution of this research is the introduction of the FBT model, which consistently outperforms other models across various feature selection methods, making it a promising tool for addressing complex classification tasks. The findings contribute to a broader understanding of model selection and optimization in machine learning applications. The proposed model undergoes evaluation using two distinct datasets: the primary dataset acquired from Lata Mangeshkar Hospital in Nagpur and the secondary dataset obtained from the UCI dataset.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"20 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-27DOI: 10.3991/ijoe.v20i03.44507
David Mauricio, Paulo César Llanos-Colchado, Leandro Sebastián Cutipa-Salazar, Pedro Castañeda, Roberth Chuquimbalqui-Maslucán, L. Rojas-Mezarina, J. Castillo-Sequera
In Peru, there is currently no integrated electronic health record (EHR) system that can be automatically shared between healthcare facilities. This leads to increased service costs due to duplicated examinations and records, as well as additional time required to manage patients’ clinical information. One alternative for ensuring the secure interoperability of EHRs while preserving data privacy is the use of blockchain technology. However, existing works consider a pre-established format for exchanging EHRs, which is not applicable when systems have different formats, as is the case in Peru. This work proposes an architecture and a web application for exchanging EHRs in heterogeneous systems. The proposed system includes the homologation of an EHR with rapid interoperability resources for medical attention using FHIR HL7, and vice versa, to achieve interoperability. Additionally, it utilizes blockchain technology to ensure data security and privacy. The web application was tested using a case simulation to demonstrate EHR interoperability between clinics in a clear, secure, and efficient manner. In addition, a survey was conducted with 30 patients regarding adoption, and another survey was conducted with 10 doctors from a public hospital in Peru regarding usability. The results demonstrate a very high level of adoption and usability for them all. Unlike other studies, the proposal does not necessitate alterations to existing EHR systems for interoperability. In other words, the proposal presents a feasible and cost-effective alternative to addressing the EHR interoperability issue in clinics and hospitals in Peru.
{"title":"Electronic Health Record Interoperability System in Peru Using Blockchain","authors":"David Mauricio, Paulo César Llanos-Colchado, Leandro Sebastián Cutipa-Salazar, Pedro Castañeda, Roberth Chuquimbalqui-Maslucán, L. Rojas-Mezarina, J. Castillo-Sequera","doi":"10.3991/ijoe.v20i03.44507","DOIUrl":"https://doi.org/10.3991/ijoe.v20i03.44507","url":null,"abstract":"In Peru, there is currently no integrated electronic health record (EHR) system that can be automatically shared between healthcare facilities. This leads to increased service costs due to duplicated examinations and records, as well as additional time required to manage patients’ clinical information. One alternative for ensuring the secure interoperability of EHRs while preserving data privacy is the use of blockchain technology. However, existing works consider a pre-established format for exchanging EHRs, which is not applicable when systems have different formats, as is the case in Peru. This work proposes an architecture and a web application for exchanging EHRs in heterogeneous systems. The proposed system includes the homologation of an EHR with rapid interoperability resources for medical attention using FHIR HL7, and vice versa, to achieve interoperability. Additionally, it utilizes blockchain technology to ensure data security and privacy. The web application was tested using a case simulation to demonstrate EHR interoperability between clinics in a clear, secure, and efficient manner. In addition, a survey was conducted with 30 patients regarding adoption, and another survey was conducted with 10 doctors from a public hospital in Peru regarding usability. The results demonstrate a very high level of adoption and usability for them all. Unlike other studies, the proposal does not necessitate alterations to existing EHR systems for interoperability. In other words, the proposal presents a feasible and cost-effective alternative to addressing the EHR interoperability issue in clinics and hospitals in Peru.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"14 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140425536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-27DOI: 10.3991/ijoe.v20i03.46765
Hernando Gonzalez, Silvia Hernández, Oscar Calderón
This paper describes the results obtained from the design and validation of translation gloves for Colombian sign language (LSC) to natural language. The MPU6050 sensors capture finger movements, and the TCA9548a card enables data multiplexing. Additionally, an Arduino Uno board preprocesses the data, and the Raspberry Pi interprets it using central tendency statistics, principal component analysis (PCA), and a neural network structure for pattern recognition. Finally, the sign is reproduced in audio format. The methodology developed below focuses on translating specific preselected words, achieving an average classification accuracy of 88.97%.
本文介绍了从哥伦比亚手语（LSC）到自然语言的翻译手套的设计和验证结果。MPU6050 传感器捕捉手指动作，TCA9548a 卡实现数据复用。此外，Arduino Uno 板会对数据进行预处理，Raspberry Pi 会使用中心倾向统计、主成分分析 (PCA) 和模式识别神经网络结构对数据进行解释。最后，符号以音频格式再现。下面开发的方法侧重于翻译特定的预选单词，平均分类准确率达到 88.97%。
{"title":"Design of a Sign Language-to-Natural Language Translator Using Artificial Intelligence","authors":"Hernando Gonzalez, Silvia Hernández, Oscar Calderón","doi":"10.3991/ijoe.v20i03.46765","DOIUrl":"https://doi.org/10.3991/ijoe.v20i03.46765","url":null,"abstract":"This paper describes the results obtained from the design and validation of translation gloves for Colombian sign language (LSC) to natural language. The MPU6050 sensors capture finger movements, and the TCA9548a card enables data multiplexing. Additionally, an Arduino Uno board preprocesses the data, and the Raspberry Pi interprets it using central tendency statistics, principal component analysis (PCA), and a neural network structure for pattern recognition. Finally, the sign is reproduced in audio format. The methodology developed below focuses on translating specific preselected words, achieving an average classification accuracy of 88.97%.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"38 27","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140425625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：