Int. J. Online Biomed. Eng.最新文献

{"title":"Clinical Text Classification with Word Representation Features and Machine Learning Algorithms","authors":"L. Almazaydeh, Mohammed A. Abuhelaleh, Arar Al Tawil, K. Elleithy","doi":"10.3991/ijoe.v19i04.36099","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.36099","url":null,"abstract":"Clinical text classification of electronic medical records is a challenging task. Existing electronic records suffer from irrelevant text, misspellings, semantic ambiguity, and abbreviations. The approach reported in this paper elaborates on machine learning techniques to develop an intelligent framework for classification of the medical transcription dataset. The proposed approach is based on four main phases: the text preprocessing phase, word representation phase, features reduction phase and classification phase. We have used four machine learning algorithms, support vector machines, naïve bayes, logistic regression and k-nearest neighbors in combination with different word representation models. We have applied the four algorithms to the bag of words, to TF-IDF, to word2vec.  Experimental results were evaluated based on precision, recall, accuracy and F1 score. The best results were obtained with the combination of the k-NN classifier, and the word represented by Word2vec achieving an accuracy of 92% to correctly classify the medical specialties based on the transcription text.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133555928","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}

{"title":"Swin Transformer-Based Segmentation and Multi-Scale Feature Pyramid Fusion Module for Alzheimer's Disease with Machine Learning","authors":"Nasr Y. Gharaibeh, Ashraf A. Abu-Ein, Obaida M. Al-hazaimeh, K. M. Nahar, W. Abu-Ain, Malek M. Al-Nawashi","doi":"10.3991/ijoe.v19i04.37677","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.37677","url":null,"abstract":"Alzheimer Disease (AD) is the ordinary type of dementia which does not have any proper and efficient medication. Accurate classification and detection of AD helps to diagnose AD in an earlier stage, for that purpose machine learning and deep learning techniques are used in AD detection which observers both normal and abnormal brain and accurately detect AD in an early. For accurate detection of AD, we proposed a novel approach for detecting AD using MRI images. The proposed work includes three processes such as tri-level pre-processing, swin transfer based segmentation, and multi-scale feature pyramid fusion module-based AD detection.In pre-processing, noises are removed from the MRI images using Hybrid Kuan Filter and Improved Frost Filter (HKIF) algorithm, skull stripping is performed by Geodesic Active Contour (GAC) algorithm which removes the non-brain tissues that increases detection accuracy. Here, bias field correction is performed by Expectation-Maximization (EM) algorithm which removes the intensity non-uniformity. After completed pre-processing, we initiate segmentation process using Swin Transformer based Segmentation using Modified U-Net and Generative Adversarial Network (ST-MUNet) algorithm which segments the gray matter, white matter, and cerebrospinal fluid from the brain images by considering cortical thickness, color, texture, and boundary information which increases segmentation accuracy. After that, multi-scale feature extraction is performed by Multi-Scale Feature Pyramid Fusion Module using VGG16 (MSFP-VGG16) which extract the features in multi-scale which increases the detection and classification accuracy, based on the extracted features the brain image is classified into three classes such as Alzheimer Disease (AD), Mild Cognitive Impairment, and Normal. The simulation of this research is conducted by Matlab R2020a simulation tool, and the performance of this research is evaluated by ADNI dataset in terms of accuracy, specificity, sensitivity, confusion matrix, and positive predictive value. \u0000 ","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207769","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}

{"title":"Virtual Laboratory Application of Direct Current Electric Motor: An Expert-Based Evaluation","authors":"R. Badarudin, D. Hariyanto, Edy Supriyadi, I. W. Djatmiko, M. Triyono, G. Kassymova, U. Urazaliyeva","doi":"10.3991/ijoe.v19i04.36749","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.36749","url":null,"abstract":"This research aims to validate the virtual laboratory application of a direct current motor based on expert judgment. There are two aspects of the assessment. The first is the electrical machine content aspect, and the second is the computer-based media content aspect. The instrument was developed based on scientific studies related to multimedia quality criteria. The instrument was declared valid through a content validity test and evaluation by an evaluation expert. Evaluating the virtual laboratory application media was conducted by two groups of experts: the material content expert in electrical machinery and the computer-based media content expert. The assessment results showed that the virtual laboratory application media was declared Very Appropriate for all dimensions of the assessment of material and media content.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127336494","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}

{"title":"Deep Learning and Transfer Learning Methods to Effectively Diagnose Cervical Cancer from Liquid-Based Cytology Pap Smear Images","authors":"L. Wong, Andrés Ccopa, Elmer Diaz, Sergio Valcarcel, David Mauricio, V. Villoslada","doi":"10.3991/ijoe.v19i04.37437","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.37437","url":null,"abstract":"As cervical cancer is considered one of the leading causes of death for women globally, different screening techniques have emerged. As the Papanicolaou technique generates high numbers of false negatives due to only testing 20% of a sample, the liquid-based cytology technique was developed to test 100% of the sample and improve accuracy. However, as the larger sample size has made it difficult to detect the lesion images through a microscope, studies have looked for ways to intelligently analyze sample. The aim of this study is to develop an artificial intelligence image recognition system that detects the lesion level of cervical cancer of liquid-based Pap smears under the Bethesda classification of cancer (NI/LSIEL/HSIEL/SCC). For this purpose, six activities were carried out: dataset selection, data augmentation, optimization, model development, evaluation and system construction. A dataset built from publicly available Pap smear images and passed through data augmentation algorithms generated a total of 2,676 images. Two models, ResNet50V2 and ResNet101V2, were developed under Deep Learning and Transfer Learning protocols. The evaluation showed that the ResNet50V2 model obtained better performance, where the classification of HSIL and SCC type images obtained a precision of 0.98 and achieved an accuracy of 0.97. Finally, the system based on the ResNet50V2 model was built and its performance was validated.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133242558","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}

{"title":"Optimizing Multi-Layer Perceptron using Variable Step Size Firefly Optimization Algorithm for Diabetes Data Classification","authors":"M. Behera, Archana Sarangi, Debahuti Mishra, Shubhendu Kumar Sarangi","doi":"10.3991/ijoe.v19i04.36543","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.36543","url":null,"abstract":"According to a survey conducted by the International Diabetes Federation, the proportion of people living with diabetes is gradually rising. Diabetes mellitus is a chronic disorder caused by elevated blood sugar levels. For the early diagnosis and treatment of diabetes patients, efficient machine-learning methods are needed. Data Classification is a significant subject in many areas of life, and it is also a very challenging job in data mining. Clinical data mining has recently gained attention in complicated healthcare challenges relying on healthcare datasets.  The principal objective of classification is to classify all data in a given dataset to a certain class label. In the healthcare field, classification is commonly employed in much research articles. A hybrid method for diabetes data classification is suggested by integrating multilayer perceptron with a modified firefly optimization algorithm for diabetes data classification. The performance of the proposed hybrid multilayer perceptron variable step size firefly algorithm is compared with other hybrid models such as the hybrid multilayer perceptron particle swarm optimization algorithm, hybrid multilayer perceptron differential evolution algorithm, and hybrid multilayer perceptron firefly optimization algorithm. The performance of these models is calculated based on accuracy, precision, recall, F1 score, and mean square error. In comparison to other models, the proposed hybrid model produces superior outcomes for diabetes data classification.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132930656","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}

{"title":"Effect of Changing Targeted Layers of the Deep Dream Technique Using VGG-16 Model","authors":"Lafta R. Al-khazraji, A. Abbas, A. S. Jamil","doi":"10.3991/ijoe.v19i03.37235","DOIUrl":"https://doi.org/10.3991/ijoe.v19i03.37235","url":null,"abstract":"The deep dream is one of the most recent techniques in deep learning. It is used in many applications, such as decorating and modifying images with motifs and simulating the patients' hallucinations. This study presents a deep dream model that generates deep dream images using a convolutional neural network (CNN). Firstly, we survey the layers of each block in the network, then choose the required layers, and extract their features to maximize it. This process repeats several iterations as needed, computes the total loss, and extracts the final deep dream images. We apply this operation on different layers two times; the former is on the low-level layers, and the latter is on the high-level layers. The results of applying this operation are different, where the resulting image from applying deep dream on the high-level layers are clearer than those resulting from low-level layers. Also, the loss of the images of low-level layers ranges between 31.1435 and 31.1435, while the loss of the images of upper layers ranges between 20.0704 and 32.1625.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127437906","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}

{"title":"The Performance Analysis of Machine Learning Algorithms for Credit Card Fraud Detection","authors":"Muhammad Zohaib Khan, S. Shaikh, Muneer Ahmed Shaikh, Kamlesh Kumar Khatri, Mahira Abdul Rauf, Ayesha Kalhoro, Muhammad Adnan","doi":"10.3991/ijoe.v19i03.35331","DOIUrl":"https://doi.org/10.3991/ijoe.v19i03.35331","url":null,"abstract":"This paper studies the performance analysis of machine learning (ML) and data mining techniques for anomaly detection in credit cards. As the usage of digital money or plastic money grows in developing nations, so does the risk of fraud. To counter these scams, we need a sophisticated fraud detection method that not only identifies the fraud but also detects it before it occurs efficiently. We have introduced the notion of credit card fraud and its many variants in this research. Numerous ML fraud detection approaches are studied in this paper including Principal Component Analysis (PCA) data mining and the Fuzzy C-Means methodologies, as well as the Logistic Regression (LR), Decision Tree (DT), and Naive Bayes (NB) algorithms. The existing and proposed models for credit card fraud detection have been thoroughly reviewed, and these strategies have been compared using quantitative metrics including accuracy rate and characteristics curves. This paper discusses the shortcomings of existing models and proposes an efficient technique to analyze the fraud detection.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129404560","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}

{"title":"Information Cardiac Platform to Support Healthcare","authors":"G. Georgieva-Tsaneva, Evgeniya Gospodinova, Galina Bogdanova, Diana Dimitrova","doi":"10.3991/ijoe.v19i03.35217","DOIUrl":"https://doi.org/10.3991/ijoe.v19i03.35217","url":null,"abstract":"The article presents a software information platform for storing, processing, researching, and protecting cardiology information obtained during the study of patients with various cardiovascular diseases and a healthy control group. The information platform contains non-confidential data about the research subjects, which is freely available; as well as a confidential part; cardiological data, containing information about the biomedical tests carried out; as well as the parametric and graphical results of the mathematical analyzes obtained based on the registered cardiac data. The created integrated information platform can be used by cardiology specialists to evaluate the results of cardiac examinations and assist cardiologists in making a correct diagnosis and prescribing effective treatment. The platform is a tool with a user-friendly interface and can be useful for cardiac data researchers as well.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134206920","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}

{"title":"Creating a Digital 3D Model of the Dental Cast Using Structure-from-Motion Photogrammetry Technique","authors":"Reem Al-Tameemi, S. Hamandi, Akmam H. Al-Mahdi","doi":"10.3991/ijoe.v19i03.36289","DOIUrl":"https://doi.org/10.3991/ijoe.v19i03.36289","url":null,"abstract":"Photogrammetry is a technique used to obtain a reliable database of any physical object, by creating a digital 3d model using multiple photos taken at different angles around the object. Recently, several fields have used this technique to build digital 3D models, such as topography, architecture, engineering, and medicine.  Many recent dentistry studies have used the Structure-from-motion (SfM) Photogrammetry technique to reconstruct a digital three-dimensional (3D) model of a dental cast as an alternative to conventional scanning. In this research, the dental casts are constructed by applying the SfM Photogrammetry technique in which a guide to stepwise workflow is provided by utilizing simple tools which are: a smartphone camera, homemade photo studio setup, and Agisoft Metashape software. The agreements between the generated models and the reference dental casts are assessed using the Bland Altman method by calculating the mean value differences. All the calculated differences are not statistically significant (P-value >0.05), and they are also clinically accepted as the range of the mean differences (-0.042 to 0.355) is less than 0.5mm. this demonstrates that the resulted 3D models closely approximate the overall geometry of the dental casts. ","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125779860","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}

{"title":"Design and Evaluation of Web-Based Information Systems for the Medical Laboratory","authors":"H. Sritart, Tanachawan Phudin, P. Tosranon, Somchat Taertulakarn","doi":"10.3991/ijoe.v19i03.36505","DOIUrl":"https://doi.org/10.3991/ijoe.v19i03.36505","url":null,"abstract":"In the medical laboratory, equipment and material management is well real-ized as one of the high-priority tasks in handling of information about the periodic quality inspection and maintenance of test equipment and other in-strument monitoring in the laboratory. Lack of managing and neglecting the equipment can result into malfunction that ends up costing more time and resources. This paper proposed a designed web-based information system in order to address the issues of managing the expensive medical equipment (ME) and various consumable medical materials (CMM) in the laboratories. In regard to data administration improvement of medical laboratories' day-to-day operations, the objective of this study is to design to complete the func-tionality and evaluate the information system based on the user specifica-tion. More than 200 initiate materials list and 50 medical equipment records were collected and transferred into the system. Three independent laborato-ries utilized the developed ME/CMM information system to evaluate its per-formance compared to the traditional system. The t-test statistical analysis was used to assess feedback surveys. The finding shows that the system pro-vides users convenience and effectiveness in handling ME and CMM; thus, our system significantly reduces the workload of staffs and inefficient costs.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121475913","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}