INTRODUCTION: This piece of work provides the description of integrated intelligent computing models for the interpretation of cognitive-based neurological diseases in children. These diseases can have a significant impact on children's cognitive and developmental functioning. OBJECTIVES: The research work review the current diagnosis and treatment methods for cognitive based neurological diseases and discusses the potential of machine learning, deep learning, Natural language processing, speech recognition, brain imaging, and signal processing techniques in interpreting the diseases. METHODS: A survey of recent research on integrated intelligent computing models for cognitive-based neurological disease interpretation in children is presented, highlighting the benefits and limitations of these models. RESULTS: The significant of this work provide important implications for healthcare practice and policy, with strengthen diagnosis and treatment of cognitive-based neurological diseases in children. CONCLUSION: This research paper concludes with a discussion of the ethical and legal considerations surrounding the use of intelligent computing models in healthcare, as well as future research directions in this area.
{"title":"Integrated Intelligent Computing Models for Cognitive-Based Neurological Disease Interpretation in Children: A Survey","authors":"Archana Tandon, B. Mazumdar, Manoj Kumar Pal","doi":"10.4108/eetpht.10.5541","DOIUrl":"https://doi.org/10.4108/eetpht.10.5541","url":null,"abstract":"INTRODUCTION: This piece of work provides the description of integrated intelligent computing models for the interpretation of cognitive-based neurological diseases in children. These diseases can have a significant impact on children's cognitive and developmental functioning. \u0000OBJECTIVES: The research work review the current diagnosis and treatment methods for cognitive based neurological diseases and discusses the potential of machine learning, deep learning, Natural language processing, speech recognition, brain imaging, and signal processing techniques in interpreting the diseases. \u0000METHODS: A survey of recent research on integrated intelligent computing models for cognitive-based neurological disease interpretation in children is presented, highlighting the benefits and limitations of these models. \u0000RESULTS: The significant of this work provide important implications for healthcare practice and policy, with strengthen diagnosis and treatment of cognitive-based neurological diseases in children. \u0000CONCLUSION: This research paper concludes with a discussion of the ethical and legal considerations surrounding the use of intelligent computing models in healthcare, as well as future research directions in this area.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"11 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140381530","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}
INTRODUCTION: Parkinson's Disease (PD), a progressively debilitating neurological disorder impacting a substantial global population, stands as a significant challenge in modern healthcare. The gradual onset of motor and non-motor symptoms underscores the criticality of early detection for optimal treatment outcomes. In response to this urgency, novel avenues for early diagnosis are being explored, where the amalgamation of biomedical voice analysis and advanced machine learning techniques holds immense promise. Individuals afflicted by PD experience a nuanced deterioration of bodily functions, necessitating interventions that are most effective when initiated at an early stage. The potential of biomedical voice measurements to encode subtle health indicators presents an enticing opportunity. The human voice, an intricate interplay of frequencies and patterns, might offer insights into the underlying health condition. OBJECTIVES: This research embarks on a comprehensive journey to delve into the intricate connections between voice attributes and the presence of PD, with the aim of expediting its detection and treatment. METHODS: At the heart of this exploration is the Support Vector Machine (SVM) model, a versatile machine learning tool [1-2]. Functioning as a virtual detective, the SVM model learns from historical data to decipher the intricate patterns that differentiate healthy individuals from those with PD [3-4]. RESULTS: Through the power of pattern recognition, the SVM becomes a predictive instrument, a potential catalyst in unravelling the latent manifestations of PD using the unique patterns harbored within the human voice. Embedded within this research are the practical demonstrations showcased through code snippets [5-7]. By synergizing the intricate voice measurements with the SVM model, we envision the emergence of a diagnostic paradigm where early PD detection becomes both accessible and efficient. This study not only epitomizes the synergy of voice and machine interactions but also attests to the transformative potential of technology within the domain of healthcare. . CONCLUSION: Ultimately, this research strives to harness the intricate layers of voice data, as exemplified through the provided model code [8-11], to contribute to the evolution of an advanced tool for PD prediction. By amalgamating the principles of machine learning and biomedical analysis, we aspire to expedite early PD diagnosis, thereby catalyzing more efficacious treatment strategies. In traversing this multidimensional exploration, we aspire to pave the path toward a future where technology plays an instrumental role in enhancing healthcare outcomes for individuals navigating the challenges of PD, ultimately advancing the pursuit of early diagnosis and intervention.
{"title":"Predictive Modelling for Parkinson's Disease Diagnosis using Biomedical Voice Measurements","authors":"Ruby Dahiya, Virendra Kumar Dahiya, Deepakshi, Nidhi Agarwal, L. Maguluri, Elangovan Muniyandy","doi":"10.4108/eetpht.10.5519","DOIUrl":"https://doi.org/10.4108/eetpht.10.5519","url":null,"abstract":"INTRODUCTION: Parkinson's Disease (PD), a progressively debilitating neurological disorder impacting a substantial global population, stands as a significant challenge in modern healthcare. The gradual onset of motor and non-motor symptoms underscores the criticality of early detection for optimal treatment outcomes. In response to this urgency, novel avenues for early diagnosis are being explored, where the amalgamation of biomedical voice analysis and advanced machine learning techniques holds immense promise. Individuals afflicted by PD experience a nuanced deterioration of bodily functions, necessitating interventions that are most effective when initiated at an early stage. The potential of biomedical voice measurements to encode subtle health indicators presents an enticing opportunity. The human voice, an intricate interplay of frequencies and patterns, might offer insights into the underlying health condition. \u0000OBJECTIVES: This research embarks on a comprehensive journey to delve into the intricate connections between voice attributes and the presence of PD, with the aim of expediting its detection and treatment. \u0000METHODS: At the heart of this exploration is the Support Vector Machine (SVM) model, a versatile machine learning tool [1-2]. Functioning as a virtual detective, the SVM model learns from historical data to decipher the intricate patterns that differentiate healthy individuals from those with PD [3-4]. \u0000RESULTS: Through the power of pattern recognition, the SVM becomes a predictive instrument, a potential catalyst in unravelling the latent manifestations of PD using the unique patterns harbored within the human voice. Embedded within this research are the practical demonstrations showcased through code snippets [5-7]. By synergizing the intricate voice measurements with the SVM model, we envision the emergence of a diagnostic paradigm where early PD detection becomes both accessible and efficient. This study not only epitomizes the synergy of voice and machine interactions but also attests to the transformative potential of technology within the domain of healthcare. . \u0000CONCLUSION: Ultimately, this research strives to harness the intricate layers of voice data, as exemplified through the provided model code [8-11], to contribute to the evolution of an advanced tool for PD prediction. By amalgamating the principles of machine learning and biomedical analysis, we aspire to expedite early PD diagnosis, thereby catalyzing more efficacious treatment strategies. In traversing this multidimensional exploration, we aspire to pave the path toward a future where technology plays an instrumental role in enhancing healthcare outcomes for individuals navigating the challenges of PD, ultimately advancing the pursuit of early diagnosis and intervention.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140219624","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}
INTRODUCTION: The transformation in the lifestyle and other societal and economic factors during modern times have led to rise in the cases of infertility among young generation. Apart from these factors infertility may also be attributed to different medical conditions among both men and women. This rise in the cases of infertility is a matter of huge concern to the mankind and should be seriously pondered upon. However, the unprecedented advancements in the field of healthcare have led to In Vitro fertilization as a rescue to this devastating condition. Although the In Vitro fertilization has the potential to unfurl the happiness, it has associated challenges also in terms of physical and emotional health. Also, the success rate of In Vitro fertilization may vary from person to person. OBJECTIVES: To predict the success rate of In Vitro fertilization. METHODS: Machine Learning Models. RESULTS: It has been observed that Adaboost outperforms all other machine learning models by yielding an accuracy of 97.5%. CONCLUSION: During the result analysis, it is concluded that if age > 36, there is a negative propensity for clinical pregnancy and if age >40, the probability of a clinical pregnancy dramatically declines. Further, the propensity of clinical pregnancy is positively correlated to the count of embryos transferred in the same IVF cycle.
{"title":"Machine Learning Based Assessment and Predictive Analysis of In-Vitro Fertilization Success Rate","authors":"Vaishali Mehta, M. Mangla, Nonita Sharma, Manik Rakhra, Tanupriya Choudhury, Garigipati Rama Krishna","doi":"10.4108/eetpht.10.5511","DOIUrl":"https://doi.org/10.4108/eetpht.10.5511","url":null,"abstract":"INTRODUCTION: The transformation in the lifestyle and other societal and economic factors during modern times have led to rise in the cases of infertility among young generation. Apart from these factors infertility may also be attributed to different medical conditions among both men and women. This rise in the cases of infertility is a matter of huge concern to the mankind and should be seriously pondered upon. However, the unprecedented advancements in the field of healthcare have led to In Vitro fertilization as a rescue to this devastating condition. Although the In Vitro fertilization has the potential to unfurl the happiness, it has associated challenges also in terms of physical and emotional health. Also, the success rate of In Vitro fertilization may vary from person to person. \u0000OBJECTIVES: To predict the success rate of In Vitro fertilization. \u0000METHODS: Machine Learning Models. \u0000RESULTS: It has been observed that Adaboost outperforms all other machine learning models by yielding an accuracy of 97.5%. \u0000CONCLUSION: During the result analysis, it is concluded that if age > 36, there is a negative propensity for clinical pregnancy and if age >40, the probability of a clinical pregnancy dramatically declines. Further, the propensity of clinical pregnancy is positively correlated to the count of embryos transferred in the same IVF cycle.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140217756","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}
Shagufta Rasheed, G. Kiran Kumar, D. Rani, M. V. V. Prasad Kantipudi, Anila M
INTRODUCTION: This study explores machine learning algorithms (SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest) for heart disease prediction, utilizing comprehensive cardiovascular and clinical data. Our research enables early detection, aiding timely interventions and preventive measures. Hyperparameter tuning via GridSearchCV enhances model accuracy, reducing heart disease's burdens. Methodology includes preprocessing, feature engineering, model training, and cross-validation. Results favor Random Forest for heart disease prediction, promising clinical applications. This work advances predictive healthcare analytics, highlighting machine learning's pivotal role. Our findings have implications for healthcare and policy, advocating efficient predictive models for early heart disease management. Advanced analytics can save lives, cut costs, and elevate care quality. OBJECTIVES: Evaluate the models to enable early detection, timely interventions, and preventive measures. METHODS: Utilize GridSearchCV for hyperparameter tuning to enhance model accuracy. Employ preprocessing, feature engineering, model training, and cross-validation methodologies. Evaluate the performance of SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest algorithms. RESULTS: The study reveals Random Forest as the favored algorithm for heart disease prediction, showing promise for clinical applications. Advanced analytics and hyperparameter tuning contribute to improved model accuracy, reducing the burden of heart disease. CONCLUSION: The research underscores machine learning's pivotal role in predictive healthcare analytics, advocating efficient models for early heart disease management.
{"title":"Heart Disease Prediction Using GridSearchCV and Random Forest","authors":"Shagufta Rasheed, G. Kiran Kumar, D. Rani, M. V. V. Prasad Kantipudi, Anila M","doi":"10.4108/eetpht.10.5523","DOIUrl":"https://doi.org/10.4108/eetpht.10.5523","url":null,"abstract":"INTRODUCTION: This study explores machine learning algorithms (SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest) for heart disease prediction, utilizing comprehensive cardiovascular and clinical data. Our research enables early detection, aiding timely interventions and preventive measures. Hyperparameter tuning via GridSearchCV enhances model accuracy, reducing heart disease's burdens. Methodology includes preprocessing, feature engineering, model training, and cross-validation. Results favor Random Forest for heart disease prediction, promising clinical applications. This work advances predictive healthcare analytics, highlighting machine learning's pivotal role. Our findings have implications for healthcare and policy, advocating efficient predictive models for early heart disease management. Advanced analytics can save lives, cut costs, and elevate care quality. \u0000OBJECTIVES: Evaluate the models to enable early detection, timely interventions, and preventive measures. \u0000METHODS: Utilize GridSearchCV for hyperparameter tuning to enhance model accuracy. Employ preprocessing, feature engineering, model training, and cross-validation methodologies. Evaluate the performance of SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest algorithms. \u0000RESULTS: The study reveals Random Forest as the favored algorithm for heart disease prediction, showing promise for clinical applications. Advanced analytics and hyperparameter tuning contribute to improved model accuracy, reducing the burden of heart disease. \u0000CONCLUSION: The research underscores machine learning's pivotal role in predictive healthcare analytics, advocating efficient models for early heart disease management.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 36","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140213228","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}
INTRODUCTION: Depression is one of the leading psychological problems in the modern tech era where every single person has a social media account that has wide space for the creation of depressed feelings. Since depression can escalate to the point of suicidal thoughts or behavior spotting it early can be vitally important. Traditionally, psychologists rely on patient interviews and questionnaires to gauge the severity of depression. OBJECTIVES: The objective of this paper is earlier depression detection as well as treatment can greatly improve the probability of living a healthy and full life free of depression. METHODS: This paper introduces the utilization of BERT, a novel deep-learning, transformers approach that can detect levels of depression using textual data as input. RESULTS: The main result obtained in this paper is the extensive dataset consists of a total of 20,000 samples, which are categorized into 5 classes and further divided into training, testing, and validation sets, with respective sizes of 16,000, 2,000, and 2,000. This paper has achieved a remarkable result with a training accuracy of 95.5% and validation accuracy of 92.2% with just 5 epochs. CONCLUSION: These are the conclusions of this paper, Deep learning has a lot of potential for use in mental health applications, as seen by the study's outstanding results, which included training accuracy of 95.5%. But the path towards comprehensive and morally sound AI-based mental health support continues into the future.
{"title":"Depressonify: BERT a deep learning approach of detection of depression","authors":"Meena Kumari, Gurpreet Singh, S. Pande","doi":"10.4108/eetpht.10.5513","DOIUrl":"https://doi.org/10.4108/eetpht.10.5513","url":null,"abstract":"INTRODUCTION: Depression is one of the leading psychological problems in the modern tech era where every single person has a social media account that has wide space for the creation of depressed feelings. Since depression can escalate to the point of suicidal thoughts or behavior spotting it early can be vitally important. Traditionally, psychologists rely on patient interviews and questionnaires to gauge the severity of depression. \u0000OBJECTIVES: The objective of this paper is earlier depression detection as well as treatment can greatly improve the probability of living a healthy and full life free of depression. \u0000METHODS: This paper introduces the utilization of BERT, a novel deep-learning, transformers approach that can detect levels of depression using textual data as input. \u0000RESULTS: The main result obtained in this paper is the extensive dataset consists of a total of 20,000 samples, which are categorized into 5 classes and further divided into training, testing, and validation sets, with respective sizes of 16,000, 2,000, and 2,000. This paper has achieved a remarkable result with a training accuracy of 95.5% and validation accuracy of 92.2% with just 5 epochs. \u0000CONCLUSION: These are the conclusions of this paper, Deep learning has a lot of potential for use in mental health applications, as seen by the study's outstanding results, which included training accuracy of 95.5%. But the path towards comprehensive and morally sound AI-based mental health support continues into the future.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140217052","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}
Nidhi Agarwal, Deepakshi, J. Harikiran, Yampati Bhagya Lakshmi, Aylapogu Pramod Kumar, Elangovan Muniyandy, Amit Verma
INTRODUCTION: Cardiovascular diseases, including heart disease, remain a significant cause of morbidity and mortality worldwide. Timely and accurate diagnosis of heart disease is crucial for effective intervention and patient care. With the emergence of machine learning techniques, there is a growing interest in leveraging these methods to enhance diagnostic accuracy and predict disease outcomes. OBJECTIVES: This study evaluates the performance of three machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors in predicting heart disease based on patient attributes. METHODS: In this study, we explore the application of three prominent machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors (kNN)—to predict the presence of heart disease based on a set of patient attributes. RESULTS: Using a dataset of 303 patient records with 14 attributes, including age, sex, and cholesterol levels, the data is pre-processed, scaled, and split into training and test sets. Each classifier is trained on the training set and evaluated on the test set. Results reveal that Naive Bayes and k-Nearest Neighbors classifiers outperform Logistic Regression in terms of accuracy, precision, recall, and area under the ROC curve (AUC). CONCLUSION: This study underscores the promising role of machine learning in medical diagnosis, showcasing the potential of Naive Bayes and k-Nearest Neighbors classifiers in improving heart disease prediction accuracy. Future work could explore advanced classifiers and feature selection techniques to enhance predictive accuracy and generalize findings to larger datasets.
{"title":"Predictive Modelling for Heart Disease Diagnosis: A Comparative Study of Classifiers","authors":"Nidhi Agarwal, Deepakshi, J. Harikiran, Yampati Bhagya Lakshmi, Aylapogu Pramod Kumar, Elangovan Muniyandy, Amit Verma","doi":"10.4108/eetpht.10.5518","DOIUrl":"https://doi.org/10.4108/eetpht.10.5518","url":null,"abstract":"INTRODUCTION: Cardiovascular diseases, including heart disease, remain a significant cause of morbidity and mortality worldwide. Timely and accurate diagnosis of heart disease is crucial for effective intervention and patient care. With the emergence of machine learning techniques, there is a growing interest in leveraging these methods to enhance diagnostic accuracy and predict disease outcomes. \u0000OBJECTIVES: This study evaluates the performance of three machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors in predicting heart disease based on patient attributes. \u0000METHODS: In this study, we explore the application of three prominent machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors (kNN)—to predict the presence of heart disease based on a set of patient attributes. \u0000RESULTS: Using a dataset of 303 patient records with 14 attributes, including age, sex, and cholesterol levels, the data is pre-processed, scaled, and split into training and test sets. Each classifier is trained on the training set and evaluated on the test set. Results reveal that Naive Bayes and k-Nearest Neighbors classifiers outperform Logistic Regression in terms of accuracy, precision, recall, and area under the ROC curve (AUC). \u0000CONCLUSION: This study underscores the promising role of machine learning in medical diagnosis, showcasing the potential of Naive Bayes and k-Nearest Neighbors classifiers in improving heart disease prediction accuracy. Future work could explore advanced classifiers and feature selection techniques to enhance predictive accuracy and generalize findings to larger datasets.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140214415","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}
P. N. S. Prakash, S. Sudharson, Venkat Amith Woonna, Sai Venkat, Teja Bacham
INTRODUCTION: The paper introduces a novel approach for the early detection of cataracts using images captured using smartphones. Cataracts are a significant global eye disease that can lead to vision impairment in individuals aged 40 and above. In this article, we proposed a deep convolution neural network (CataractsNET) trained using an open dataset available in Github which includes images collected through google searches and images generated using standard augmentation mechanism. OBJECTIVES: The main objective of this paper is to design and implement a lightweight network model for cataract identification that outperforms other state-of-the-art network models in terms of accuracy, precision, recall, and F1 Score. METHODS: The proposed neural network model comprises nine layers, guaranteeing the extraction of significant details from the input images and achieving precise classification. The dataset primarily comprises cataract images sourced from a standardized dataset that is publicly available on GitHub, with 8000 training images and 1600 testing images. RESULTS: The proposed CataractsNET model achieved an accuracy of 96.20%, precision of 96.1%, recall of 97.6%, and F1 score of 96.1%. These results demonstrate that the proposed method outperforms other deep learning models like ResNet50 and VGG19. CONCLUSION: The paper concludes that identifying cataracts in the earlier stages is crucial for effective treatment and reducing the likelihood of experiencing blindness. The widespread use of smartphones makes this approach accessible to a broad audience, allowing individuals to check for cataracts and seek timely consultation with ophthalmologists for further diagnosis.
{"title":"Effective Cataract Identification System using Deep Convolution Neural Network","authors":"P. N. S. Prakash, S. Sudharson, Venkat Amith Woonna, Sai Venkat, Teja Bacham","doi":"10.4108/eetpht.10.5525","DOIUrl":"https://doi.org/10.4108/eetpht.10.5525","url":null,"abstract":"INTRODUCTION: The paper introduces a novel approach for the early detection of cataracts using images captured using smartphones. Cataracts are a significant global eye disease that can lead to vision impairment in individuals aged 40 and above. In this article, we proposed a deep convolution neural network (CataractsNET) trained using an open dataset available in Github which includes images collected through google searches and images generated using standard augmentation mechanism. \u0000OBJECTIVES: The main objective of this paper is to design and implement a lightweight network model for cataract identification that outperforms other state-of-the-art network models in terms of accuracy, precision, recall, and F1 Score. \u0000METHODS: The proposed neural network model comprises nine layers, guaranteeing the extraction of significant details from the input images and achieving precise classification. The dataset primarily comprises cataract images sourced from a standardized dataset that is publicly available on GitHub, with 8000 training images and 1600 testing images. \u0000RESULTS: The proposed CataractsNET model achieved an accuracy of 96.20%, precision of 96.1%, recall of 97.6%, and F1 score of 96.1%. These results demonstrate that the proposed method outperforms other deep learning models like ResNet50 and VGG19. \u0000CONCLUSION: The paper concludes that identifying cataracts in the earlier stages is crucial for effective treatment and reducing the likelihood of experiencing blindness. The widespread use of smartphones makes this approach accessible to a broad audience, allowing individuals to check for cataracts and seek timely consultation with ophthalmologists for further diagnosis.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140215905","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}
Vaishali Mehta, N. Batra, Poonam, Sonali Goyal, Amandeep Kaur, K. V. Dudekula, Ganta Jacob Victor
INTRODUCTION: This research paper presents an exploratory data analysis (EDA) approach to diagnose Chronic Kidney Disease (CKD) using machine learning algorithms. OBJECTIVES: This paper focuses on early and accurate detection of CKD using a comprehensive dataset of clinical and laboratory parameters to minimize the risk of patients’ health complications with timely intervention through appropriate medications. METHODS: Machine Learning based prediction models including Naive Bayes, KNN, Logistic regression, decision tree, ensemble modelling, Random Forest and Ada Boost. RESULTS: The results indicate that the Naive Bayes algorithm achieved highest accuracy and sensitivity in detecting CKD. CONCLUSION: For reduced features and for binary class classification, Naive Bayes classifier gives best performance in terms of accuracy and computational cost. Other algorithms are good for multi-class classification but for binary class, they are little expensive than Naive Bayes.
{"title":"Machine Learning based Exploratory Data Analysis (EDA) and Diagnosis of Chronic Kidney Disease (CKD)","authors":"Vaishali Mehta, N. Batra, Poonam, Sonali Goyal, Amandeep Kaur, K. V. Dudekula, Ganta Jacob Victor","doi":"10.4108/eetpht.10.5512","DOIUrl":"https://doi.org/10.4108/eetpht.10.5512","url":null,"abstract":"INTRODUCTION: This research paper presents an exploratory data analysis (EDA) approach to diagnose Chronic Kidney Disease (CKD) using machine learning algorithms. \u0000OBJECTIVES: This paper focuses on early and accurate detection of CKD using a comprehensive dataset of clinical and laboratory parameters to minimize the risk of patients’ health complications with timely intervention through appropriate medications. \u0000METHODS: Machine Learning based prediction models including Naive Bayes, KNN, Logistic regression, decision tree, ensemble modelling, Random Forest and Ada Boost. \u0000RESULTS: The results indicate that the Naive Bayes algorithm achieved highest accuracy and sensitivity in detecting CKD. \u0000CONCLUSION: For reduced features and for binary class classification, Naive Bayes classifier gives best performance in terms of accuracy and computational cost. Other algorithms are good for multi-class classification but for binary class, they are little expensive than Naive Bayes.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140217291","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}
Shrey Shah, M. Mangla, Nonita Sharma, Tanupriya Choudhury, Maganti Syamala
INTRODUCTION: This study compares and contrasts various machine learning algorithms for predicting diabetes. The study of current research work is to analyse the effectiveness of various machine learning algorithms for diabetes prediction. OBJECTIVES: To compare the efficacy of various machine learning algorithms for diabetic prediction. METHODS: For the same, a diabetic dataset was subjected to the application of various well-known machine learning algorithms. Unbalanced data was handled by pre-processing the dataset. The models were subsequently trained and assessed using different performance metrics namely F1-score, accuracy, sensitivity, and specificity. RESULTS: The experimental results show that the Decision Tree and ensemble model outperforms all other comparative models in terms of accuracy and other evaluation metrics. CONCLUSION: This study can help healthcare practitioners and researchers to choose the best machine learning model for diabetes prediction based on their specific needs and available data.
简介：本研究对预测糖尿病的各种机器学习算法进行了比较和对比。当前研究工作的目的是分析各种机器学习算法在预测糖尿病方面的有效性。目标比较各种机器学习算法在预测糖尿病方面的功效。方法：为此，对一个糖尿病数据集采用了各种著名的机器学习算法。通过预处理数据集来处理不平衡数据。随后对模型进行训练，并使用不同的性能指标（即 F1 分数、准确率、灵敏度和特异性）进行评估。结果：实验结果表明，决策树和集合模型在准确率和其他评估指标方面优于所有其他比较模型。结论：这项研究可以帮助医疗从业人员和研究人员根据自己的具体需求和可用数据，为糖尿病预测选择最佳的机器学习模型。
{"title":"Modelling of Diabetic Cases for Effective Prevalence Classification","authors":"Shrey Shah, M. Mangla, Nonita Sharma, Tanupriya Choudhury, Maganti Syamala","doi":"10.4108/eetpht.10.5514","DOIUrl":"https://doi.org/10.4108/eetpht.10.5514","url":null,"abstract":"INTRODUCTION: This study compares and contrasts various machine learning algorithms for predicting diabetes. The study of current research work is to analyse the effectiveness of various machine learning algorithms for diabetes prediction. \u0000OBJECTIVES: To compare the efficacy of various machine learning algorithms for diabetic prediction. \u0000METHODS: For the same, a diabetic dataset was subjected to the application of various well-known machine learning algorithms. Unbalanced data was handled by pre-processing the dataset. The models were subsequently trained and assessed using different performance metrics namely F1-score, accuracy, sensitivity, and specificity. \u0000RESULTS: The experimental results show that the Decision Tree and ensemble model outperforms all other comparative models in terms of accuracy and other evaluation metrics. \u0000CONCLUSION: This study can help healthcare practitioners and researchers to choose the best machine learning model for diabetes prediction based on their specific needs and available data.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140219933","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}
INTRODUCTION: The goal of this study, titled ”Integrated System for Detecting Diabetes Mellitus using Various Machine Learning and Deep Learning Algorithms,” is to increase the precision and usability of diabetes diagnosis through the investigation and application of a wide range of machine learning and deep learning techniques. OBJECTIVES: The objective of the study was to establish a comprehensive system for identifying diabetes mellitus by combining several machine learning and deep learning methods METHODS: The methodology included every phase, from data gathering and preprocessing through advanced model development and performance assessment. The experiment demonstrated how combining several machine learning and deep learning techniques might completely transform diabetes detection. While praising accomplishments, the methodology also highlighted flaws in the data collection process. The goal of the roadmap for future improvements was to use technology to better detect and treat diabetes, which would ultimately help people of all ages and backgrounds. RESULTS: The project’s remarkable results demonstrate the legitimacy of the methodology chosen while also highlighting its potential to completely transform the diagnosis and treatment of diabetes CONCLUSION: The conclusion of this project lays the ground for next developments, such as improved user interfaces and the expansion of dataset scope. Through these initiatives, the long-term objective of providing more precise and accessible diabetes diagnoses becomes a real possibility, providing significant advantages to people from a variety of age groups and demographics[6].
{"title":"Integrated Embedded system for detecting diabetes mellitus using various machine learning techniques","authors":"Rishita Konda, Anuraag Ramineni, Jayashree J, Niharika Singavajhala, Sai Akshaj Vanka","doi":"10.4108/eetpht.10.5497","DOIUrl":"https://doi.org/10.4108/eetpht.10.5497","url":null,"abstract":" \u0000INTRODUCTION: The goal of this study, titled ”Integrated System for Detecting Diabetes Mellitus using Various Machine Learning and Deep Learning Algorithms,” is to increase the precision and usability of diabetes diagnosis through the investigation and application of a wide range of machine learning and deep learning techniques. \u0000OBJECTIVES: The objective of the study was to establish a comprehensive system for identifying diabetes mellitus by combining several machine learning and deep learning methods \u0000METHODS: The methodology included every phase, from data gathering and preprocessing through advanced model development and performance assessment. The experiment demonstrated how combining several machine learning and deep learning techniques might completely transform diabetes detection. While praising accomplishments, the methodology also highlighted flaws in the data collection process. The goal of the roadmap for future improvements was to use technology to better detect and treat diabetes, which would ultimately help people of all ages and backgrounds. \u0000RESULTS: The project’s remarkable results demonstrate the legitimacy of the methodology chosen while also highlighting its potential to completely transform the diagnosis and treatment of diabetes \u0000CONCLUSION: The conclusion of this project lays the ground for next developments, such as improved user interfaces and the expansion of dataset scope. Through these initiatives, the long-term objective of providing more precise and accessible diabetes diagnoses becomes a real possibility, providing significant advantages to people from a variety of age groups and demographics[6].","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"53 3‐4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140223425","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：