Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100154
Huiqiang Li , Xiaozhao Li , Juntao Feng
Background
Due to the complexity of airways and the limitation of experiments, the production mechanism of the lung sounds in airways has not been fully understood, which often confuses diagnosis.
Method
A 3D geometrical model of human airways (G5-G8) has been developed based on Weibel's model. Simulation on transient airflow and the noise production during exhalation under different breathing intensities (Q = 15, 30, 45, 60, 75, 90 L/min) has been carried out with Direct Noise Computation (DNC) and Ffowcs Williams-Hawkings (FW-H) method.
Results
(1) The junctions between airways are most likely to produce lung sounds, and the peak value is located in the junction between G7 and G6 at the middle of exhalation (about 0.75 s). (2) With the increase in breathing intensity, the average sound pressure level first increases, reaches the peak value at 70–75 L/min, and then drops. (3) Higher breathing intensity is helpful to produce the feature of wheezing, namely a comparatively higher sound pressure level in the range of 200–500 Hz. Moreover, this feature is prominent with the increase in breathing intensity.
{"title":"Numerical study on normal lung sounds in bronchial airways under different breathing intensities","authors":"Huiqiang Li , Xiaozhao Li , Juntao Feng","doi":"10.1016/j.cmpbup.2024.100154","DOIUrl":"https://doi.org/10.1016/j.cmpbup.2024.100154","url":null,"abstract":"<div><h3>Background</h3><p>Due to the complexity of airways and the limitation of experiments, the production mechanism of the lung sounds in airways has not been fully understood, which often confuses diagnosis.</p></div><div><h3>Method</h3><p>A 3D geometrical model of human airways (G5-G8) has been developed based on Weibel's model. Simulation on transient airflow and the noise production during exhalation under different breathing intensities (<em>Q</em> = 15, 30, 45, 60, 75, 90 L/min) has been carried out with Direct Noise Computation (DNC) and Ffowcs Williams-Hawkings (FW-H) method.</p></div><div><h3>Results</h3><p>(1) The junctions between airways are most likely to produce lung sounds, and the peak value is located in the junction between G7 and G6 at the middle of exhalation (about 0.75 s). (2) With the increase in breathing intensity, the average sound pressure level first increases, reaches the peak value at 70–75 L/min, and then drops. (3) Higher breathing intensity is helpful to produce the feature of wheezing, namely a comparatively higher sound pressure level in the range of 200–500 Hz. Moreover, this feature is prominent with the increase in breathing intensity.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000211/pdfft?md5=6b1cdf9b1b9d99f91f6def14fe7bffab&pid=1-s2.0-S2666990024000211-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140604780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100146
Mohamed Khalifa , Mona Albadawy
Introduction
This review evaluates the role of Artificial Intelligence (AI) in transforming diagnostic imaging in healthcare. AI has the potential to enhance accuracy and efficiency of interpreting medical images like X-rays, MRIs, and CT scans.
Methods
A comprehensive literature search across databases like PubMed, Embase, and Google Scholar was conducted, focusing on articles published in peer-reviewed journals in English language since 2019. Inclusion criteria targeted studies on AI's application in diagnostic imaging, while exclusion criteria filtered out irrelevant or empirically unsupported studies.
Results and discussion
Through 30 included studies, the review identifies four AI domains and eight functions in diagnostic imaging: 1) In the area of Image Analysis and Interpretation, AI capabilities enhanced image analysis, spotting minor discrepancies and anomalies, and by reducing human error, maintaining accuracy and mitigating the impact of fatigue or oversight, 2) The Operational Efficiency is enhanced by AI through efficiency and speed, which accelerates the diagnostic process, and cost-effectiveness, reducing healthcare costs by improving efficiency and accuracy, 3) Predictive and Personalised Healthcare benefit from AI through predictive analytics, leveraging historical data for early diagnosis, and personalised medicine, which employs patient-specific data for tailored diagnostic approaches, 4) Lastly, in Clinical Decision Support, AI assists in complex procedures by providing precise imaging support and integrates with other technologies like electronic health records for enriched health insights, showcasing ai's transformative potential in diagnostic imaging. The review also discusses challenges in AI integration, such as ethical concerns, data privacy, and the need for technology investments and training.
Conclusion
AI is revolutionising diagnostic imaging by improving accuracy, efficiency, and personalised healthcare delivery. Recommendations include continued investment in AI, establishment of ethical guidelines, training for healthcare professionals, and ensuring patient-centred AI development. The review calls for collaborative efforts to integrate AI in clinical practice effectively and address healthcare disparities.
{"title":"AI in diagnostic imaging: Revolutionising accuracy and efficiency","authors":"Mohamed Khalifa , Mona Albadawy","doi":"10.1016/j.cmpbup.2024.100146","DOIUrl":"10.1016/j.cmpbup.2024.100146","url":null,"abstract":"<div><h3>Introduction</h3><p>This review evaluates the role of Artificial Intelligence (AI) in transforming diagnostic imaging in healthcare. AI has the potential to enhance accuracy and efficiency of interpreting medical images like X-rays, MRIs, and CT scans.</p></div><div><h3>Methods</h3><p>A comprehensive literature search across databases like PubMed, Embase, and Google Scholar was conducted, focusing on articles published in peer-reviewed journals in English language since 2019. Inclusion criteria targeted studies on AI's application in diagnostic imaging, while exclusion criteria filtered out irrelevant or empirically unsupported studies.</p></div><div><h3>Results and discussion</h3><p>Through 30 included studies, the review identifies four AI domains and eight functions in diagnostic imaging: 1) In the area of Image Analysis and Interpretation, AI capabilities enhanced image analysis, spotting minor discrepancies and anomalies, and by reducing human error, maintaining accuracy and mitigating the impact of fatigue or oversight, 2) The Operational Efficiency is enhanced by AI through efficiency and speed, which accelerates the diagnostic process, and cost-effectiveness, reducing healthcare costs by improving efficiency and accuracy, 3) Predictive and Personalised Healthcare benefit from AI through predictive analytics, leveraging historical data for early diagnosis, and personalised medicine, which employs patient-specific data for tailored diagnostic approaches, 4) Lastly, in Clinical Decision Support, AI assists in complex procedures by providing precise imaging support and integrates with other technologies like electronic health records for enriched health insights, showcasing ai's transformative potential in diagnostic imaging. The review also discusses challenges in AI integration, such as ethical concerns, data privacy, and the need for technology investments and training.</p></div><div><h3>Conclusion</h3><p>AI is revolutionising diagnostic imaging by improving accuracy, efficiency, and personalised healthcare delivery. Recommendations include continued investment in AI, establishment of ethical guidelines, training for healthcare professionals, and ensuring patient-centred AI development. The review calls for collaborative efforts to integrate AI in clinical practice effectively and address healthcare disparities.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000132/pdfft?md5=dc2a7d25e2ce178c93e675f9e58901e5&pid=1-s2.0-S2666990024000132-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140084641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
COVID-19 is the first pandemic in history in which technology and social media are being used for people to be informed and be safe. Thus, digital health literacy skills affect the way people will protect and promote their health.
Methods
A cross-sectional web-based study was conducted with a convenience sample among university students (N=604) from one of the Universities located in Attica (Greece) during May - June 2020. The COVID-HL university students survey questionnaire was used for collecting the data.
Results
In regards to information search, 28 % of the university students indicated that they found it very difficult/difficult to find the exact information they were looking for and 20.4 % to make a choice from all the information they found. Additionally, 45.1 % of the participants found it very difficult/difficult to decide whether the information retrieved via online search is reliable or not.
Conclusion
The results indicate a need for the promotion of digital health literacy among university students and therefore, health education interventions need to optimize students’ seeking skills and critical thinking. Health educators should consider the results of this study and involve the university students in any intervention they plan in order to address the students’ specific needs. It is also suggested that these health education interventions should be integrated throughout all academic activities.
{"title":"Digital health literacy and information-seeking on the internet in relation to COVID-19 among university students in Greece","authors":"Evanthia Sakellari , Orkan Okan , Kevin Dadaczynski , Kostantinos Koutentakis , Areti Lagiou","doi":"10.1016/j.cmpbup.2024.100139","DOIUrl":"10.1016/j.cmpbup.2024.100139","url":null,"abstract":"<div><h3>Background</h3><p>COVID-19 is the first pandemic in history in which technology and social media are being used for people to be informed and be safe. Thus, digital health literacy skills affect the way people will protect and promote their health.</p></div><div><h3>Methods</h3><p>A cross-sectional web-based study was conducted with a convenience sample among university students (<em>N</em>=604) from one of the Universities located in Attica (Greece) during May - June 2020. The COVID-HL university students survey questionnaire was used for collecting the data.</p></div><div><h3>Results</h3><p>In regards to information search, 28 % of the university students indicated that they found it very difficult/difficult to find the exact information they were looking for and 20.4 % to make a choice from all the information they found. Additionally, 45.1 % of the participants found it very difficult/difficult to decide whether the information retrieved via online search is reliable or not.</p></div><div><h3>Conclusion</h3><p>The results indicate a need for the promotion of digital health literacy among university students and therefore, health education interventions need to optimize students’ seeking skills and critical thinking. Health educators should consider the results of this study and involve the university students in any intervention they plan in order to address the students’ specific needs. It is also suggested that these health education interventions should be integrated throughout all academic activities.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000065/pdfft?md5=7424d30d38ac13d3fb171812c2d3fc89&pid=1-s2.0-S2666990024000065-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139638316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100165
Background and Objective:
Accurate classification of liver disease stages provides crucial insights into patient prognosis, aiding in the prediction of disease outcomes and influencing clinical decision-making. There is an urgent need for non-invasive methods to diagnose various stages of liver dysfunction and uncover hidden pattern based on individual disease characteristics.
Method:
One popular and effective approach is collecting serum biomarker samples. The study was conducted on collected serum biomaker samples of 81 patients with Inflammatory Bowel Disease (IBD) of Changhua Christian Hospital in China, including 36 with Crohn’s disease (CD) and 45 with Ulcerative Colitis (UC) using Latent Semantic Analysis(LSA) and machine learning (ML) techniques.Machine Learning algorithms Random Forest (RF), Logistic Regression (LR), XGBoost (XGB), and Support Vector Classifier (SVC), were utilized to predict liver risk associated with conditions including Hepatitis, Autoimmune Hepatitis (AIH), Alcoholic Liver Disease (ALD), and Non-Alcoholic Fatty Liver Disease (NAFLD). Models’ accuracy was assessed using K-Fold Cross-Validation (CV).Distinct pattern were identified using Latent Semantic Analysis(LSA). Furthermore, SHAP plots were utilized for enhanced interpretability, highlighting essential features for liver dysfunction levels.
Results:
The inflammatory profile, mixed disease profile, and healthy profile were the three distinct clusters were identified with LSA. The RF model achieved high accuracy of . Serum Glutamate Pyruvate Transaminase (GPT), Age at Diagnosis (AAD), Erythrocyte Sedimentation Rate (ESR), C-reactive protein (CRP) were found the most key important features in liver disease staging increment.
Conclusion:
The research significantly contributes to the fields of biomedical informatics and clinical decision-making. The developed model offers valuable decision-making tools for clinicians, enabling early and targeted interventions.
{"title":"Deciphering the complex links between inflammatory bowel diseases and NAFLD through advanced statistical and machine learning analysis","authors":"","doi":"10.1016/j.cmpbup.2024.100165","DOIUrl":"10.1016/j.cmpbup.2024.100165","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Accurate classification of liver disease stages provides crucial insights into patient prognosis, aiding in the prediction of disease outcomes and influencing clinical decision-making. There is an urgent need for non-invasive methods to diagnose various stages of liver dysfunction and uncover hidden pattern based on individual disease characteristics.</div></div><div><h3>Method:</h3><div>One popular and effective approach is collecting serum biomarker samples. The study was conducted on collected serum biomaker samples of 81 patients with Inflammatory Bowel Disease (IBD) of Changhua Christian Hospital in China, including 36 with Crohn’s disease (CD) and 45 with Ulcerative Colitis (UC) using Latent Semantic Analysis(LSA) and machine learning (ML) techniques.Machine Learning algorithms Random Forest (RF), Logistic Regression (LR), XGBoost (XGB), and Support Vector Classifier (SVC), were utilized to predict liver risk associated with conditions including Hepatitis, Autoimmune Hepatitis (AIH), Alcoholic Liver Disease (ALD), and Non-Alcoholic Fatty Liver Disease (NAFLD). Models’ accuracy was assessed using K-Fold Cross-Validation (CV).Distinct pattern were identified using Latent Semantic Analysis(LSA). Furthermore, SHAP plots were utilized for enhanced interpretability, highlighting essential features for liver dysfunction levels.</div></div><div><h3>Results:</h3><div>The inflammatory profile, mixed disease profile, and healthy profile were the three distinct clusters were identified with LSA. The RF model achieved high accuracy of <span><math><mrow><mn>0</mn><mo>.</mo><mn>94</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>06</mn></mrow></math></span>. Serum Glutamate Pyruvate Transaminase (GPT), Age at Diagnosis (AAD), Erythrocyte Sedimentation Rate (ESR), C-reactive protein (CRP) were found the most key important features in liver disease staging increment.</div></div><div><h3>Conclusion:</h3><div>The research significantly contributes to the fields of biomedical informatics and clinical decision-making. The developed model offers valuable decision-making tools for clinicians, enabling early and targeted interventions.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100145
Mohamed Khalifa , Mona Albadawy
Background
Academic writing is an essential component of research, characterized by structured expression of ideas, data-driven arguments, and logical reasoning. However, it poses challenges such as handling vast amounts of information and complex ideas. The integration of Artificial Intelligence (AI) into academic writing has become increasingly important, offering solutions to these challenges. This review aims to explore specific domains where AI significantly supports academic writing.
Methods
A systematic review of literature from databases like PubMed, Embase, and Google Scholar, published since 2019, was conducted. Studies were included based on relevance to AI's application in academic writing and research, focusing on writing assistance, grammar improvement, structure optimization, and other related aspects.
Results
The search identified 24 studies through which six core domains were identified where AI helps academic writing and research: 1) facilitating idea generation and research design, 2) improving content and structuring, 3) supporting literature review and synthesis, 4) enhancing data management and analysis, 5) supporting editing, review, and publishing, and 6) assisting in communication, outreach, and ethical compliance. ChatGPT has shown substantial potential in these areas, though challenges like maintaining academic integrity and balancing AI use with human insight remain.
Conclusion and recommendations
AI significantly revolutionises academic writing and research across various domains. Recommendations include broader integration of AI tools in research workflows, emphasizing ethical and transparent use, providing adequate training for researchers, and maintaining a balance between AI utility and human insight. Ongoing research and development are essential to address emerging challenges and ethical considerations in AI's application in academia.
{"title":"Using artificial intelligence in academic writing and research: An essential productivity tool","authors":"Mohamed Khalifa , Mona Albadawy","doi":"10.1016/j.cmpbup.2024.100145","DOIUrl":"https://doi.org/10.1016/j.cmpbup.2024.100145","url":null,"abstract":"<div><h3>Background</h3><p>Academic writing is an essential component of research, characterized by structured expression of ideas, data-driven arguments, and logical reasoning. However, it poses challenges such as handling vast amounts of information and complex ideas. The integration of Artificial Intelligence (AI) into academic writing has become increasingly important, offering solutions to these challenges. This review aims to explore specific domains where AI significantly supports academic writing.</p></div><div><h3>Methods</h3><p>A systematic review of literature from databases like PubMed, Embase, and Google Scholar, published since 2019, was conducted. Studies were included based on relevance to AI's application in academic writing and research, focusing on writing assistance, grammar improvement, structure optimization, and other related aspects.</p></div><div><h3>Results</h3><p>The search identified 24 studies through which six core domains were identified where AI helps academic writing and research: 1) facilitating idea generation and research design, 2) improving content and structuring, 3) supporting literature review and synthesis, 4) enhancing data management and analysis, 5) supporting editing, review, and publishing, and 6) assisting in communication, outreach, and ethical compliance. ChatGPT has shown substantial potential in these areas, though challenges like maintaining academic integrity and balancing AI use with human insight remain.</p></div><div><h3>Conclusion and recommendations</h3><p>AI significantly revolutionises academic writing and research across various domains. Recommendations include broader integration of AI tools in research workflows, emphasizing ethical and transparent use, providing adequate training for researchers, and maintaining a balance between AI utility and human insight. Ongoing research and development are essential to address emerging challenges and ethical considerations in AI's application in academia.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000120/pdfft?md5=69cd44e1ee12e7efa2147c0319eb0030&pid=1-s2.0-S2666990024000120-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140062690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100136
Hurmat Ali Shah, Mowafa Househ
Public health surveillance (PHS) systems are an important tool to map the distribution and burden of disease as well as enable efficient distribution of resources to fight a disease. The surveillance systems are used to detect, report, track a disease as well as assess the response to the disease and people's attitudes. PHS systems are changing with the rapid change in technology and are becoming more real-time responsive with availability of new type of data such as online content and social media data. This review presents the basics of surveillance systems and develop from it to show the evolution of surveillance systems. The different forms of data available, surveillance methods and surveillance types are also reviewed such as social media based, web-based and clinical data based PHS maps. This review provide comprehensive details of the surveillance systems in terms of data types used, source of data and purpose of the surveillance system.
{"title":"Concepts, objectives and analysis of public health surveillance systems","authors":"Hurmat Ali Shah, Mowafa Househ","doi":"10.1016/j.cmpbup.2024.100136","DOIUrl":"10.1016/j.cmpbup.2024.100136","url":null,"abstract":"<div><p>Public health surveillance (PHS) systems are an important tool to map the distribution and burden of disease as well as enable efficient distribution of resources to fight a disease. The surveillance systems are used to detect, report, track a disease as well as assess the response to the disease and people's attitudes. PHS systems are changing with the rapid change in technology and are becoming more real-time responsive with availability of new type of data such as online content and social media data. This review presents the basics of surveillance systems and develop from it to show the evolution of surveillance systems. The different forms of data available, surveillance methods and surveillance types are also reviewed such as social media based, web-based and clinical data based PHS maps. This review provide comprehensive details of the surveillance systems in terms of data types used, source of data and purpose of the surveillance system.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266699002400003X/pdfft?md5=c7174d19610aa51e76061c94d0b56e24&pid=1-s2.0-S266699002400003X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139456573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2023.100133
Chukwuebuka Joseph Ejiyi , Zhen Qin , Ann O Nnani , Fuhu Deng , Thomas Ugochukwu Ejiyi , Makuachukwu Bennedith Ejiyi , Victor Kwaku Agbesi , Olusola Bamisile
Pulmonary tuberculosis (TB), the most prevalent form of TB, remains a major global public health concern, contributing to more than a million deaths each year. The accurate and timely diagnosis of this disease is of paramount importance for effective control and treatment. Chest X-ray (CXR) images have emerged as a valuable tool for screening lung diseases, including TB, owing to their cost-effectiveness and non-invasiveness. Despite advancements in technology, the challenges associated with interpreting CXR images persist, primarily due to the scarcity of trained radiologists. This underscores the pressing need for an automated and cost-effective computer-aided system capable of diagnosing TB, assisting medical practitioners in distinguishing between TB-positive and negative CXR scans. In response to this need, we introduce an innovative approach called ResNet-fused External Attention Network (ResfEANet). This network excels in accurately classifying TB from CXR images, achieving remarkable levels of accuracy and sensitivity. ResfEANet is built upon ResNet and incorporates an External Attention mechanism, albeit with fewer residual network blocks than ResNet-50 resulting in a relatively shallow network with fewer layers. This approach proves highly effective in feature extraction and yields competitive results in the classification of TB. Our method was employed to train a model that demonstrated an impressive accuracy rate of 97.59% and a remarkable sensitivity of 100% in binary classification tasks with optimal computational cost. These outcomes suggest that our proposed approach has the potential to serve as a valuable secondary tool in clinical decision-making, providing crucial assistance to radiologists and healthcare professionals.
{"title":"ResfEANet: ResNet-fused External Attention Network for Tuberculosis Diagnosis using Chest X-ray Images","authors":"Chukwuebuka Joseph Ejiyi , Zhen Qin , Ann O Nnani , Fuhu Deng , Thomas Ugochukwu Ejiyi , Makuachukwu Bennedith Ejiyi , Victor Kwaku Agbesi , Olusola Bamisile","doi":"10.1016/j.cmpbup.2023.100133","DOIUrl":"10.1016/j.cmpbup.2023.100133","url":null,"abstract":"<div><p>Pulmonary tuberculosis (TB), the most prevalent form of TB, remains a major global public health concern, contributing to more than a million deaths each year. The accurate and timely diagnosis of this disease is of paramount importance for effective control and treatment. Chest X-ray (CXR) images have emerged as a valuable tool for screening lung diseases, including TB, owing to their cost-effectiveness and non-invasiveness. Despite advancements in technology, the challenges associated with interpreting CXR images persist, primarily due to the scarcity of trained radiologists. This underscores the pressing need for an automated and cost-effective computer-aided system capable of diagnosing TB, assisting medical practitioners in distinguishing between TB-positive and negative CXR scans. In response to this need, we introduce an innovative approach called ResNet-fused External Attention Network (ResfEANet). This network excels in accurately classifying TB from CXR images, achieving remarkable levels of accuracy and sensitivity. ResfEANet is built upon ResNet and incorporates an External Attention mechanism, albeit with fewer residual network blocks than ResNet-50 resulting in a relatively shallow network with fewer layers. This approach proves highly effective in feature extraction and yields competitive results in the classification of TB. Our method was employed to train a model that demonstrated an impressive accuracy rate of 97.59% and a remarkable sensitivity of 100% in binary classification tasks with optimal computational cost. These outcomes suggest that our proposed approach has the potential to serve as a valuable secondary tool in clinical decision-making, providing crucial assistance to radiologists and healthcare professionals.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990023000411/pdfft?md5=81aecaa858595c69800e5427f5591e96&pid=1-s2.0-S2666990023000411-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139193821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dengue fever is a vital public health concern that affects about 40% of the world’s population. To address the dynamics of dengue disease, a mathematical model was formulated by incorporating three control strategies: vector control, treatment, and mass awareness. A stability analysis of the disease-free equilibrium (DFE) was conducted using the Jacobian matrix. The DFE was found to be locally and globally asymptotically stable when the effective reproductive number was less than one; otherwise, it was unstable. Additionally, an endemic equilibrium point (EEP) was identified. The global stability analysis of the EEP, performed using the Lyapunov method, showed that it is globally asymptotically stable whenever ; otherwise, it is unstable. Bifurcation analysis revealed that the model system exhibits a forward bifurcation. Furthermore, sensitivity analysis of the effective reproduction number revealed that the most sensitive parameters are the biting rate () and insecticide efficacy (). Therefore, the results suggest that, in order to reduce new dengue cases, intervention strategies that decrease the biting rate, such as mosquito repellents and the use of insecticides to kill mosquitoes, should be implemented. Moreover, simulations were conducted for the extended model with vector control, treatment, and mass awareness. The results showed that the combination of vector control, treatment, and mass awareness has a more positive impact on the control of dengue fever than any single or paired intervention. Thus, for effective control of dengue fever, the three control measures should be implemented simultaneously, especially in endemic areas.
{"title":"Mathematical modeling of the effects of vector control, treatment and mass awareness on the transmission dynamics of dengue fever","authors":"Boniface Zacharia Naaly , Theresia Marijani , Augustino Isdory , Jufren Zakayo Ndendya","doi":"10.1016/j.cmpbup.2024.100159","DOIUrl":"https://doi.org/10.1016/j.cmpbup.2024.100159","url":null,"abstract":"<div><p>Dengue fever is a vital public health concern that affects about 40% of the world’s population. To address the dynamics of dengue disease, a mathematical model was formulated by incorporating three control strategies: vector control, treatment, and mass awareness. A stability analysis of the disease-free equilibrium (DFE) was conducted using the Jacobian matrix. The DFE was found to be locally and globally asymptotically stable when the effective reproductive number was less than one; otherwise, it was unstable. Additionally, an endemic equilibrium point (EEP) was identified. The global stability analysis of the EEP, performed using the Lyapunov method, showed that it is globally asymptotically stable whenever <span><math><mrow><msub><mrow><mi>R</mi></mrow><mrow><mi>e</mi></mrow></msub><mo>></mo><mn>1</mn></mrow></math></span>; otherwise, it is unstable. Bifurcation analysis revealed that the model system exhibits a forward bifurcation. Furthermore, sensitivity analysis of the effective reproduction number revealed that the most sensitive parameters are the biting rate (<span><math><mi>b</mi></math></span>) and insecticide efficacy (<span><math><mi>δ</mi></math></span>). Therefore, the results suggest that, in order to reduce new dengue cases, intervention strategies that decrease the biting rate, such as mosquito repellents and the use of insecticides to kill mosquitoes, should be implemented. Moreover, simulations were conducted for the extended model with vector control, treatment, and mass awareness. The results showed that the combination of vector control, treatment, and mass awareness has a more positive impact on the control of dengue fever than any single or paired intervention. Thus, for effective control of dengue fever, the three control measures should be implemented simultaneously, especially in endemic areas.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000260/pdfft?md5=58dbf14090021c1ebf275bc2a8944acb&pid=1-s2.0-S2666990024000260-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141480951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2024.100164
Background
The global increase in an aging population has led to more common age-related health challenges, particularly multimorbidity and frailty, but there is a significant gap.
Methods
This cross-sectional study utilized data from the National Health and Nutrition Examination Survey (1999–2018). The association between age and frailty was assessed using a restricted cubic spline (RCS) model, while weighted adjusted multivariable logistic regression evaluated the effect of diseases to frailty. And in machine learning process, feature selection for the frailty prediction model involved three algorithms. The model's performance was optimized using nested cross-validation and tested with various algorithms including decision tree, Logistic Regression, k-Nearest Neighbor, Random Forest, Recursive Partitioning and Regression Trees, and eXtreme Gradient Boosting (XGBoost). We used areas under the receiver operating characteristic curve (AUC) and area under the precision-recall curve (AU-PRC) to evaluate six algorithms, select the optimal model, and test the discrimination and consistency of the optimal model.
Results
The study included 46,187 participants, with 6,009 cases of frailty. RCS analysis showed a non-linear association between age and frailty, with a turning point at 49 years. Key impacting variables identified are Anemia, Arthritis, Diabetes Mellitus, Coronary Heart Disease, and Hypertension. In the machine learning process, we selected the optimal data set by feature selection, including 13 variables. Through nested cross-validation, a total of 31,900 models were built using 6 algorithms. And the XGBoost model showed the highest performance (AUC = 0.8828 and AU-PRC = 0.624), and clear proficiency in both discrimination and calibration.
Conclusions
We found 49 years maintain the balance of physiological reserve and external aggression. In addition, chronic diseases are trigger factor of frailty, while acute diseases are contributing factor that exacerbates the body's rapid decline. Last, the XGBoost frailty prediction model, with its simplicity, high performance and high clinical value holds potential for clinical application.
{"title":"Machine learning approaches for predicting frailty base on multimorbidities in US adults using NHANES data (1999–2018)","authors":"","doi":"10.1016/j.cmpbup.2024.100164","DOIUrl":"10.1016/j.cmpbup.2024.100164","url":null,"abstract":"<div><h3>Background</h3><p>The global increase in an aging population has led to more common age-related health challenges, particularly multimorbidity and frailty, but there is a significant gap.</p></div><div><h3>Methods</h3><p>This cross-sectional study utilized data from the National Health and Nutrition Examination Survey (1999–2018). The association between age and frailty was assessed using a restricted cubic spline (RCS) model, while weighted adjusted multivariable logistic regression evaluated the effect of diseases to frailty. And in machine learning process, feature selection for the frailty prediction model involved three algorithms. The model's performance was optimized using nested cross-validation and tested with various algorithms including decision tree, Logistic Regression, k-Nearest Neighbor, Random Forest, Recursive Partitioning and Regression Trees, and eXtreme Gradient Boosting (XGBoost). We used areas under the receiver operating characteristic curve (AUC) and area under the precision-recall curve (AU-PRC) to evaluate six algorithms, select the optimal model, and test the discrimination and consistency of the optimal model.</p></div><div><h3>Results</h3><p>The study included 46,187 participants, with 6,009 cases of frailty. RCS analysis showed a non-linear association between age and frailty, with a turning point at 49 years. Key impacting variables identified are Anemia, Arthritis, Diabetes Mellitus, Coronary Heart Disease, and Hypertension. In the machine learning process, we selected the optimal data set by feature selection, including 13 variables. Through nested cross-validation, a total of 31,900 models were built using 6 algorithms. And the XGBoost model showed the highest performance (AUC = 0.8828 and AU-PRC = 0.624), and clear proficiency in both discrimination and calibration.</p></div><div><h3>Conclusions</h3><p>We found 49 years maintain the balance of physiological reserve and external aggression. In addition, chronic diseases are trigger factor of frailty, while acute diseases are contributing factor that exacerbates the body's rapid decline. Last, the XGBoost frailty prediction model, with its simplicity, high performance and high clinical value holds potential for clinical application.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666990024000314/pdfft?md5=b2ac2f1faea71ce864789e43929be852&pid=1-s2.0-S2666990024000314-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1016/j.cmpbup.2023.100132
Elisabetta Gentili , Giorgia Franchini , Riccardo Zese , Marco Alberti , Maria Ferrara , Ilaria Domenicano , Luigi Grassi
Imbalanced datasets can impair the learning performance of many Machine Learning techniques. Nevertheless, many real-world datasets, especially in the healthcare field, are inherently imbalanced. For instance, in the medical domain, the classes representing a specific disease are typically the minority of the total cases. This challenge justifies the substantial research effort spent in the past decades to tackle data imbalance at the data and algorithm levels. In this paper, we describe the strategies we used to deal with an imbalanced classification task on data extracted from a database generated from the Electronic Health Records of the Mental Health Service of the Ferrara Province, Italy. In particular, we applied balancing techniques to the original data, such as random undersampling and oversampling, and Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC). In order to assess the effectiveness of the balancing techniques on the classification task at hand, we applied different Machine Learning algorithms. We employed cost-sensitive learning as well and compared its results with those of the balancing methods. Furthermore, a feature selection analysis was conducted to investigate the relevance of each feature. Results show that balancing can help find the best setting to accomplish classification tasks. Since real-world imbalanced datasets are increasingly becoming the core of scientific research, further studies are needed to improve already existing techniques.
{"title":"Machine learning from real data: A mental health registry case study","authors":"Elisabetta Gentili , Giorgia Franchini , Riccardo Zese , Marco Alberti , Maria Ferrara , Ilaria Domenicano , Luigi Grassi","doi":"10.1016/j.cmpbup.2023.100132","DOIUrl":"10.1016/j.cmpbup.2023.100132","url":null,"abstract":"<div><p>Imbalanced datasets can impair the learning performance of many Machine Learning techniques. Nevertheless, many real-world datasets, especially in the healthcare field, are inherently imbalanced. For instance, in the medical domain, the classes representing a specific disease are typically the minority of the total cases. This challenge justifies the substantial research effort spent in the past decades to tackle data imbalance at the data and algorithm levels. In this paper, we describe the strategies we used to deal with an imbalanced classification task on data extracted from a database generated from the Electronic Health Records of the Mental Health Service of the Ferrara Province, Italy. In particular, we applied balancing techniques to the original data, such as random undersampling and oversampling, and Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC). In order to assess the effectiveness of the balancing techniques on the classification task at hand, we applied different Machine Learning algorithms. We employed cost-sensitive learning as well and compared its results with those of the balancing methods. Furthermore, a feature selection analysis was conducted to investigate the relevance of each feature. Results show that balancing can help find the best setting to accomplish classification tasks. Since real-world imbalanced datasets are increasingly becoming the core of scientific research, further studies are needed to improve already existing techniques.</p></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266699002300040X/pdfft?md5=fca4123f44f99c83994cc13701771f05&pid=1-s2.0-S266699002300040X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139190322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}