2 March 2024 in Sustainable Machine Intelligence Journal
Depression has become the disease of the times and has caused suffering and disruption in the lives of millions of people around the world of all ages. Method: We obtained 16,581 Arabic tweets, whether they express depression or not, and the symptoms they contain for 1439 Arab Twitter users. We classified whether the user is depressed or not. We used many machine learning algorithms: DT, RF, Mutational Naïve Bayes, and AdaBoost , we also used feature extraction like BOW and TF-IDF. The result: Our experiments showed that Mutational Naïve Bayes with TF-IDF had the highest accuracy of 86% when rating tweets. Conclusion: Caring for the mental health of people is very important, as some measures must be taken to maintain the mental health of people in the early stages of infection.
31 January 2024 in Information Sciences with Applications
Accurate bone fracture identification remains critical in medical diagnostics, motivating researchers to investigate deep-learning systems to address this difficulty. The performance of convolutional neural networks (CNN) and region-based convolutional neural networks (RCNN) in fracture diagnosis is investigated in this paper. Algorithmic efficacy was investigated using a complete set of experiments involving various epochs, batch sizes, and optimization techniques (Adam and SGD). As discussed in the discussion, the results continuously highlight the superiority of the RCNN algorithm, which demonstrated amazing performance across many experimental settings. Algorithms trained using the Adam optimizer regularly demonstrated high levels of accuracy, precision, recall, and F1 score. Nonetheless, the effect of epoch counts and batch size on performance variability was seen, necessitating careful consideration to avoid overfitting and ensure generalization. These findings support careful algorithm selection guided by optimization techniques and fine-tuned hyperparameters. The RCNN algorithm's impressive results, proven by its constant superiority, underline its potential to revolutionize bone fracture diagnosis. Further research should focus on hyperparameter tuning and comprehensive validation across several datasets, fostering accurate and efficient solutions for bone fracture diagnoses in medical practice.
13 March 2024 in Multicriteria Algorithms with Applications
Background: Recently, a body of evidence has emerged that patients who participate in the healthcare process have better health outcomes and lower treatment costs. Therefore, healthcare institutions have tended to use strategies for better patient engagement in the healthcare process, by educating them about their health conditions and fully involving the patient in making decisions about their healthcare. Objectives: This paper presents a systematic study of the recent literature on determining the outcomes and benefits of patient engagement in the healthcare process, through which we provide a comprehensive review, analysis, and synthesis of research published in the past five years. Methodology: We collected relevant literature published between 2018 and 2023 and reviewed the approved issues, research problems, manuscript scopes, research methodologies, and main findings. 28 studies yielded our final extracted cohort. Conclusions: Using the objective analysis of the extracted studies, we present a research typology that summarizes the major outcomes and the benefits of patient engagement in the healthcare process of relevant recent research in this field.
2 March 2024 in Sustainable Machine Intelligence Journal
In this study, we proposed a novel Multi-Fused Residual Convolutional Neural Network (MFR-CNN) with Auxiliary Fusing Layers (AuxFL) to diagnose various types of brain tumor MRI images. The MFR-CNN was designed to handle four specific cases, namely glioma, meningioma, pituitary, and healthy brain images, obtained from reliable Kaggle databases. Our proposed model integrated three state-of-the-art models into a single feature extraction pipeline, incorporating partially frozen and truncated layers. This strategic fusion enabled the propagation of robust features and improved diagnostic performance without incurring significant computing costs, unlike most existing state-of-the-art models. Moreover, the MFR-CNN effectively mitigated overfitting and performance saturation issues, providing a notable advantage over models lacking these components. Upon evaluation, our proposed model achieved an outstanding accuracy of 94%, surpassing the efficiency and accuracy of conventionally trained DCNNs. Notably, the MFR-CNN demonstrated potential in enhancing brain tumor diagnosis more cost-efficiently than ensembles and outperforming conventional pre-trained and fine-tuned DCNNs. In conclusion, the proposed MFR-CNN with AuxFL and FuRB exhibits promising capabilities to improve the diagnosis of brain tumors, offering better cost-efficiency and accuracy compared to existing methods.
11 March 2024 in Information Sciences with Applications
Background: The COVID-19 pandemic is the greatest pandemic the world has witnessed in the modern era. This has caused suffering, disruption in the lives of millions of people. Method: We got 16581 Arab tweets, whether they express depression or not, and what symptoms they contain while keeping the time series of the tweets to monitor the 1439 Arab Twitter users during the two years 2019 and 2020. We determined whether the user was depressed or not, once in 2019 and again in 2020 during the COVID-19 pandemic period; to determine the impact of COVID-19 on depression for each user. Result: We have found that approximately 1.18% of users were classified with depression during the year 2019, compared to 36.69% of users who were classified with depression during the 2020 "during the COVID-19 pandemic," from a database of 1439 Arab users. Conclusion: Taking care of people’s mental health during this difficult period is very important, as some measures must be taken to preserve people’s mental health in countries affected by COVID-19. Feelings of fear related to COVID-19 can affect and harm mental health, causing depression.
13 March 2024 in Multicriteria Algorithms with Applications
Background: Recently, there has been a great development in healthcare services, and in the future, it is expected to evolve even more. The incorporation of the latest technologies, such as modern sensors, networks and cloud computing, has revolutionized the traditional healthcare system, one of the most important of these Updates electronic medical records that are a substitute for paper records. Objectives: This paper presents a systematic study of the recent literature on privacy issues faced by electronic medical records (EMR), through which we provide a comprehensive review, analysis and synthesis of research published in the past five years. Methodology: We collected relevant literature published between 2016 and 2021 and reviewed the approved issues, research problems, manuscript scopes, research methodologies, and main findings. 29 studies yielded our final extracted cohort. Conclusions: Using the objective analysis of the extracted cohort, we present a research typology that summarizes the major EMR privacy issues of relevant recent research in this field.