Pub Date : 2024-01-30DOI: 10.3390/biomedinformatics4010018
Pentti Nieminen
Multivariable statistical analysis involves the dichotomy of modeling and predicting [...]
多变量统计分析涉及建模和预测的二分法 [...]
{"title":"Research on the Application and Interpretability of Predictive Statistical Data Analysis Methods in Medicine","authors":"Pentti Nieminen","doi":"10.3390/biomedinformatics4010018","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010018","url":null,"abstract":"Multivariable statistical analysis involves the dichotomy of modeling and predicting [...]","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140481325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-26DOI: 10.3390/biomedinformatics4010017
J. Carreras, Yara Yukie Kikuti, M. Miyaoka, Saya Miyahara, Giovanna Roncador, R. Hamoudi, Naoya Nakamura
Diffuse large B-cell lymphoma is one of the most frequent mature B-cell hematological neoplasms and non-Hodgkin lymphomas. Despite advances in diagnosis and treatment, clinical evolution is unfavorable in a subset of patients. Using molecular techniques, several pathogenic models have been proposed, including cell-of-origin molecular classification; Hans’ classification and derivates; and the Schmitz, Chapuy, Lacy, Reddy, and Sha models. This study introduced different machine learning techniques and their classification. Later, several machine learning techniques and artificial neural networks were used to predict the DLBCL subtypes with high accuracy (100–95%), including Germinal center B-cell like (GCB), Activated B-cell like (ABC), Molecular high-grade (MHG), and Unclassified (UNC), in the context of the data released by the REMoDL-B trial. In order of accuracy (MHG vs. others), the techniques were XGBoost tree (100%); random trees (99.9%); random forest (99.5%); and C5, Bayesian network, SVM, logistic regression, KNN algorithm, neural networks, LSVM, discriminant analysis, CHAID, C&R tree, tree-AS, Quest, and XGBoost linear (99.4–91.1%). The inputs (predictors) were all the genes of the array and a set of 28 genes related to DLBCL-Burkitt differential expression. In summary, artificial intelligence (AI) is a useful tool for predictive analytics using gene expression data.
弥漫大 B 细胞淋巴瘤是最常见的成熟 B 细胞血液肿瘤和非霍奇金淋巴瘤之一。尽管在诊断和治疗方面取得了进步，但仍有一部分患者的临床进展不佳。人们利用分子技术提出了几种致病模型，包括原发细胞分子分类、汉斯分类及其衍生模型，以及施密茨、查普伊、莱西、雷迪和沙模型。这项研究介绍了不同的机器学习技术及其分类方法。随后，研究人员结合 REMoDL-B 试验发布的数据，使用几种机器学习技术和人工神经网络对 DLBCL 亚型进行了高准确率（100%-95%）预测，包括类生殖中心 B 细胞（GCB）、类活化 B 细胞（ABC）、分子高级别（MHG）和未分类（UNC）。按准确率（MHG 与其他）排序，这些技术依次为 XGBoost 树（100%）、随机树（99.9%）、随机森林（99.5%）以及 C5、贝叶斯网络、SVM、逻辑回归、KNN 算法、神经网络、LSVM、判别分析、CHAID、C&R 树、tree-AS、Quest 和 XGBoost 线性（99.4%-91.1%）。输入（预测因子）是阵列的所有基因和一组与 DLBCL-Burkitt 差异表达相关的 28 个基因。总之，人工智能（AI）是利用基因表达数据进行预测分析的有用工具。
{"title":"Artificial Intelligence Analysis and Reverse Engineering of Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using Gene Expression Data","authors":"J. Carreras, Yara Yukie Kikuti, M. Miyaoka, Saya Miyahara, Giovanna Roncador, R. Hamoudi, Naoya Nakamura","doi":"10.3390/biomedinformatics4010017","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010017","url":null,"abstract":"Diffuse large B-cell lymphoma is one of the most frequent mature B-cell hematological neoplasms and non-Hodgkin lymphomas. Despite advances in diagnosis and treatment, clinical evolution is unfavorable in a subset of patients. Using molecular techniques, several pathogenic models have been proposed, including cell-of-origin molecular classification; Hans’ classification and derivates; and the Schmitz, Chapuy, Lacy, Reddy, and Sha models. This study introduced different machine learning techniques and their classification. Later, several machine learning techniques and artificial neural networks were used to predict the DLBCL subtypes with high accuracy (100–95%), including Germinal center B-cell like (GCB), Activated B-cell like (ABC), Molecular high-grade (MHG), and Unclassified (UNC), in the context of the data released by the REMoDL-B trial. In order of accuracy (MHG vs. others), the techniques were XGBoost tree (100%); random trees (99.9%); random forest (99.5%); and C5, Bayesian network, SVM, logistic regression, KNN algorithm, neural networks, LSVM, discriminant analysis, CHAID, C&R tree, tree-AS, Quest, and XGBoost linear (99.4–91.1%). The inputs (predictors) were all the genes of the array and a set of 28 genes related to DLBCL-Burkitt differential expression. In summary, artificial intelligence (AI) is a useful tool for predictive analytics using gene expression data.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140493679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-19DOI: 10.3390/biomedinformatics4010016
Ping Lu, Zihao Wang, Hai Duong Ha Thi, Ho Bich Hai, Louise Thwaites, David A. Clifton
Tetanus, a life-threatening bacterial infection prevalent in low- and middle-income countries like Vietnam, impacts the nervous system, causing muscle stiffness and spasms. Severe tetanus often involves dysfunction of the autonomic nervous system (ANS). Timely detection and effective ANS dysfunction management require continuous vital sign monitoring, traditionally performed using bedside monitors. However, wearable electrocardiogram (ECG) sensors offer a more cost-effective and user-friendly alternative. While machine learning-based ECG analysis can aid in tetanus severity classification, existing methods are excessively time-consuming. Our previous studies have investigated the improvement of tetanus severity classification using ECG time series imaging. In this study, our aim is to explore an alternative method using ECG data without relying on time series imaging as an input, with the aim of achieving comparable or improved performance. To address this, we propose a novel approach using a 1D-Vision Transformer, a pioneering method for classifying tetanus severity by extracting crucial global information from 1D ECG signals. Compared to 1D-CNN, 2D-CNN, and 2D-CNN + Dual Attention, our model achieves better results, boasting an F1 score of 0.77 ± 0.06, precision of 0.70 ± 0. 09, recall of 0.89 ± 0.13, specificity of 0.78 ± 0.12, accuracy of 0.82 ± 0.06 and AUC of 0.84 ± 0.05.
{"title":"Tetanus Severity Classification in Low-Middle Income Countries through ECG Wearable Sensors and a 1D-Vision Transformer","authors":"Ping Lu, Zihao Wang, Hai Duong Ha Thi, Ho Bich Hai, Louise Thwaites, David A. Clifton","doi":"10.3390/biomedinformatics4010016","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010016","url":null,"abstract":"Tetanus, a life-threatening bacterial infection prevalent in low- and middle-income countries like Vietnam, impacts the nervous system, causing muscle stiffness and spasms. Severe tetanus often involves dysfunction of the autonomic nervous system (ANS). Timely detection and effective ANS dysfunction management require continuous vital sign monitoring, traditionally performed using bedside monitors. However, wearable electrocardiogram (ECG) sensors offer a more cost-effective and user-friendly alternative. While machine learning-based ECG analysis can aid in tetanus severity classification, existing methods are excessively time-consuming. Our previous studies have investigated the improvement of tetanus severity classification using ECG time series imaging. In this study, our aim is to explore an alternative method using ECG data without relying on time series imaging as an input, with the aim of achieving comparable or improved performance. To address this, we propose a novel approach using a 1D-Vision Transformer, a pioneering method for classifying tetanus severity by extracting crucial global information from 1D ECG signals. Compared to 1D-CNN, 2D-CNN, and 2D-CNN + Dual Attention, our model achieves better results, boasting an F1 score of 0.77 ± 0.06, precision of 0.70 ± 0. 09, recall of 0.89 ± 0.13, specificity of 0.78 ± 0.12, accuracy of 0.82 ± 0.06 and AUC of 0.84 ± 0.05.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139612311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-18DOI: 10.3390/biomedinformatics4010015
Hadrien T. Gayap, Moulay A. Akhloufi
Deep learning has emerged as a powerful tool for medical image analysis and diagnosis, demonstrating high performance on tasks such as cancer detection. This literature review synthesizes current research on deep learning techniques applied to lung cancer screening and diagnosis. This review summarizes the state-of-the-art in deep learning for lung cancer detection, highlighting key advances, limitations, and future directions. We prioritized studies utilizing major public datasets, such as LIDC, LUNA16, and JSRT, to provide a comprehensive overview of the field. We focus on deep learning architectures, including 2D and 3D convolutional neural networks (CNNs), dual-path networks, Natural Language Processing (NLP) and vision transformers (ViT). Across studies, deep learning models consistently outperformed traditional machine learning techniques in terms of accuracy, sensitivity, and specificity for lung cancer detection in CT scans. This is attributed to the ability of deep learning models to automatically learn discriminative features from medical images and model complex spatial relationships. However, several challenges remain to be addressed before deep learning models can be widely deployed in clinical practice. These include model dependence on training data, generalization across datasets, integration of clinical metadata, and model interpretability. Overall, deep learning demonstrates great potential for lung cancer detection and precision medicine. However, more research is required to rigorously validate models and address risks. This review provides key insights for both computer scientists and clinicians, summarizing progress and future directions for deep learning in medical image analysis.
{"title":"Deep Machine Learning for Medical Diagnosis, Application to Lung Cancer Detection: A Review","authors":"Hadrien T. Gayap, Moulay A. Akhloufi","doi":"10.3390/biomedinformatics4010015","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010015","url":null,"abstract":"Deep learning has emerged as a powerful tool for medical image analysis and diagnosis, demonstrating high performance on tasks such as cancer detection. This literature review synthesizes current research on deep learning techniques applied to lung cancer screening and diagnosis. This review summarizes the state-of-the-art in deep learning for lung cancer detection, highlighting key advances, limitations, and future directions. We prioritized studies utilizing major public datasets, such as LIDC, LUNA16, and JSRT, to provide a comprehensive overview of the field. We focus on deep learning architectures, including 2D and 3D convolutional neural networks (CNNs), dual-path networks, Natural Language Processing (NLP) and vision transformers (ViT). Across studies, deep learning models consistently outperformed traditional machine learning techniques in terms of accuracy, sensitivity, and specificity for lung cancer detection in CT scans. This is attributed to the ability of deep learning models to automatically learn discriminative features from medical images and model complex spatial relationships. However, several challenges remain to be addressed before deep learning models can be widely deployed in clinical practice. These include model dependence on training data, generalization across datasets, integration of clinical metadata, and model interpretability. Overall, deep learning demonstrates great potential for lung cancer detection and precision medicine. However, more research is required to rigorously validate models and address risks. This review provides key insights for both computer scientists and clinicians, summarizing progress and future directions for deep learning in medical image analysis.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139615776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-12DOI: 10.3390/biomedinformatics4010014
Safaa Dafrallah, Moulay A. Akhloufi
Hospital readmission involves the unplanned emergency admission of patients within 30 days from discharge after the previous admission. According to the Canadian Health Institute (CIHI), 1 in 11 patients were readmitted within 30 days of leaving the hospital in 2021. In the USA, nearly 20% of Medicare patients were readmitted after discharge, where the average cost of readmission was approximately USD 15,000, as reported by the Agency for Healthcare Research and Quality (AHQR) in 2018. To tackle this issue, we first conducted a descriptive analysis study to understand the risk factors associated with hospital readmission, and then we applied machine learning approaches to predict hospital readmission by using patients’ demographic and clinical data extracted from the Electronic Health Record of the MIMIC-III clinical database. The results showed that the number of previous admissions during the last 12 months, hyperosmolar imbalance and comorbidity index were the top three significant factors for hospital readmission. The predictive model achieved a performance of 95.6% AP and an AUC = 97.3% using the Gradient Boosting algorithm trained on all features.
{"title":"Factors Associated with Unplanned Hospital Readmission after Discharge: A Descriptive and Predictive Study Using Electronic Health Record Data","authors":"Safaa Dafrallah, Moulay A. Akhloufi","doi":"10.3390/biomedinformatics4010014","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010014","url":null,"abstract":"Hospital readmission involves the unplanned emergency admission of patients within 30 days from discharge after the previous admission. According to the Canadian Health Institute (CIHI), 1 in 11 patients were readmitted within 30 days of leaving the hospital in 2021. In the USA, nearly 20% of Medicare patients were readmitted after discharge, where the average cost of readmission was approximately USD 15,000, as reported by the Agency for Healthcare Research and Quality (AHQR) in 2018. To tackle this issue, we first conducted a descriptive analysis study to understand the risk factors associated with hospital readmission, and then we applied machine learning approaches to predict hospital readmission by using patients’ demographic and clinical data extracted from the Electronic Health Record of the MIMIC-III clinical database. The results showed that the number of previous admissions during the last 12 months, hyperosmolar imbalance and comorbidity index were the top three significant factors for hospital readmission. The predictive model achieved a performance of 95.6% AP and an AUC = 97.3% using the Gradient Boosting algorithm trained on all features.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139624945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-11DOI: 10.3390/biomedinformatics4010011
Orly Yariv, K. Camphausen, Andra V. Krauze
Radiation-induced gastrointestinal (GI) dose constraints are still a matter of concern with the ongoing evolution of patient outcomes and treatment-related toxicity in the era of image-guided intensity-modulated radiation therapy (IMRT), stereotactic ablative radiotherapy (SABR), and novel systemic agents. Small bowel (SB) dose constraints in pelvic radiotherapy (RT) are a critical aspect of treatment planning, and prospective data to support them are scarce. Previous and current guidelines are based on retrospective data and experts’ opinions. Patient-related factors, including genetic, biological, and clinical features and systemic management, modulate toxicity. Omic and microbiome alterations between patients receiving RT to the SB may aid in the identification of patients at risk and real-time identification of acute and late toxicity. Actionable biomarkers may represent a pragmatic approach to translating findings into personalized treatment with biologically optimized dose escalation, given the mitigation of the understood risk. Biomarkers grounded in the genome, transcriptome, proteome, and microbiome should undergo analysis in trials that employ, R.T. Bioinformatic templates will be needed to help advance data collection, aggregation, and analysis, and eventually, decision making with respect to dose constraints in the modern RT era.
{"title":"Small Bowel Dose Constraints in Radiation Therapy—Where Omics-Driven Biomarkers and Bioinformatics Can Take Us in the Future","authors":"Orly Yariv, K. Camphausen, Andra V. Krauze","doi":"10.3390/biomedinformatics4010011","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010011","url":null,"abstract":"Radiation-induced gastrointestinal (GI) dose constraints are still a matter of concern with the ongoing evolution of patient outcomes and treatment-related toxicity in the era of image-guided intensity-modulated radiation therapy (IMRT), stereotactic ablative radiotherapy (SABR), and novel systemic agents. Small bowel (SB) dose constraints in pelvic radiotherapy (RT) are a critical aspect of treatment planning, and prospective data to support them are scarce. Previous and current guidelines are based on retrospective data and experts’ opinions. Patient-related factors, including genetic, biological, and clinical features and systemic management, modulate toxicity. Omic and microbiome alterations between patients receiving RT to the SB may aid in the identification of patients at risk and real-time identification of acute and late toxicity. Actionable biomarkers may represent a pragmatic approach to translating findings into personalized treatment with biologically optimized dose escalation, given the mitigation of the understood risk. Biomarkers grounded in the genome, transcriptome, proteome, and microbiome should undergo analysis in trials that employ, R.T. Bioinformatic templates will be needed to help advance data collection, aggregation, and analysis, and eventually, decision making with respect to dose constraints in the modern RT era.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139533479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-11DOI: 10.3390/biomedinformatics4010012
A. M. Pavone, Antonio Giulio Giannone, Daniela Cabibi, Simona D’Aprile, Simona Denaro, G. Salvaggio, R. Parenti, Anthony Yezzi, A. Comelli
In the era of digitalization, the biomedical sector has been affected by the spread of artificial intelligence. In recent years, the possibility of using deep and machine learning methods for clinical diagnostic and therapeutic interventions has been emerging as an essential resource for biomedical imaging. Digital pathology represents innovation in a clinical world that looks for faster and better-performing diagnostic methods, without losing the accuracy of current human-guided analyses. Indeed, artificial intelligence has played a key role in a wide variety of applications that require the analysis of a massive amount of data, including segmentation processes in medical imaging. In this context, artificial intelligence enables the improvement of image segmentation methods, moving towards the development of fully automated systems of analysis able to support pathologists in decision-making procedures. The aim of this review is to aid biologists and clinicians in discovering the most common segmentation open-source tools, including ImageJ (v. 1.54), CellProfiler (v. 4.2.5), Ilastik (v. 1.3.3) and QuPath (v. 0.4.3), along with their customized implementations. Additionally, the tools’ role in the histological imaging field is explored further, suggesting potential application workflows. In conclusion, this review encompasses an examination of the most commonly segmented tissues and their analysis through open-source deep and machine learning tools.
{"title":"Digital Pathology: A Comprehensive Review of Open-Source Histological Segmentation Software","authors":"A. M. Pavone, Antonio Giulio Giannone, Daniela Cabibi, Simona D’Aprile, Simona Denaro, G. Salvaggio, R. Parenti, Anthony Yezzi, A. Comelli","doi":"10.3390/biomedinformatics4010012","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010012","url":null,"abstract":"In the era of digitalization, the biomedical sector has been affected by the spread of artificial intelligence. In recent years, the possibility of using deep and machine learning methods for clinical diagnostic and therapeutic interventions has been emerging as an essential resource for biomedical imaging. Digital pathology represents innovation in a clinical world that looks for faster and better-performing diagnostic methods, without losing the accuracy of current human-guided analyses. Indeed, artificial intelligence has played a key role in a wide variety of applications that require the analysis of a massive amount of data, including segmentation processes in medical imaging. In this context, artificial intelligence enables the improvement of image segmentation methods, moving towards the development of fully automated systems of analysis able to support pathologists in decision-making procedures. The aim of this review is to aid biologists and clinicians in discovering the most common segmentation open-source tools, including ImageJ (v. 1.54), CellProfiler (v. 4.2.5), Ilastik (v. 1.3.3) and QuPath (v. 0.4.3), along with their customized implementations. Additionally, the tools’ role in the histological imaging field is explored further, suggesting potential application workflows. In conclusion, this review encompasses an examination of the most commonly segmented tissues and their analysis through open-source deep and machine learning tools.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139533992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-11DOI: 10.3390/biomedinformatics4010013
Alfred Ultsch, J. Hoffmann, M. Röhnert, M. von Bonin, U. Oelschlägel, Cornelia Brendel, Michael C. Thrun
Typical state-of-the-art flow cytometry data samples typically consist of measures of 10 to 30 features of more than 100,000 cell “events”. Artificial intelligence (AI) systems are able to diagnose such data with almost the same accuracy as human experts. However, such systems face one central challenge: their decisions have far-reaching consequences for the health and lives of people. Therefore, the decisions of AI systems need to be understandable and justifiable by humans. In this work, we present a novel explainable AI (XAI) method called algorithmic population descriptions (ALPODS), which is able to classify (diagnose) cases based on subpopulations in high-dimensional data. ALPODS is able to explain its decisions in a form that is understandable to human experts. For the identified subpopulations, fuzzy reasoning rules expressed in the typical language of domain experts are generated. A visualization method based on these rules allows human experts to understand the reasoning used by the AI system. A comparison with a selection of state-of-the-art XAI systems shows that ALPODS operates efficiently on known benchmark data and on everyday routine case data.
{"title":"An Explainable AI System for the Diagnosis of High-Dimensional Biomedical Data","authors":"Alfred Ultsch, J. Hoffmann, M. Röhnert, M. von Bonin, U. Oelschlägel, Cornelia Brendel, Michael C. Thrun","doi":"10.3390/biomedinformatics4010013","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010013","url":null,"abstract":"Typical state-of-the-art flow cytometry data samples typically consist of measures of 10 to 30 features of more than 100,000 cell “events”. Artificial intelligence (AI) systems are able to diagnose such data with almost the same accuracy as human experts. However, such systems face one central challenge: their decisions have far-reaching consequences for the health and lives of people. Therefore, the decisions of AI systems need to be understandable and justifiable by humans. In this work, we present a novel explainable AI (XAI) method called algorithmic population descriptions (ALPODS), which is able to classify (diagnose) cases based on subpopulations in high-dimensional data. ALPODS is able to explain its decisions in a form that is understandable to human experts. For the identified subpopulations, fuzzy reasoning rules expressed in the typical language of domain experts are generated. A visualization method based on these rules allows human experts to understand the reasoning used by the AI system. A comparison with a selection of state-of-the-art XAI systems shows that ALPODS operates efficiently on known benchmark data and on everyday routine case data.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139534259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-09DOI: 10.3390/biomedinformatics4010010
Osama A. Omer, Mostafa Salah, A. Hassan, Mohamed Abdel-Nasser, Norihiro Sugita, Y. Saijo
One of the most significant indicators of heart and cardiovascular health is blood pressure (BP). Blood pressure (BP) has gained great attention in the last decade. Uncontrolled high blood pressure increases the risk of serious health problems, including heart attack and stroke. Recently, machine/deep learning has been leveraged for learning a BP from photoplethysmography (PPG) signals. Hence, continuous BP monitoring can be introduced, based on simple wearable contact sensors or even remotely sensed from a proper camera away from the clinical setup. However, the available training dataset imposes many limitations besides the other difficulties related to the PPG time series as high-dimensional data. This work presents beat-by-beat continuous PPG-based BP monitoring while accounting for the aforementioned limitations. For a better exploration of beats’ features, we propose to use wavelet scattering transform as a better descriptive domain to cope with the limitation of the training dataset and to help the deep learning network accurately learn the relationship between the morphological shapes of PPG beats and the BP. A long short-term memory (LSTM) network is utilized to demonstrate the superiority of the wavelet scattering transform over other domains. The learning scenarios are carried out on a beat basis where the input corresponding PPG beat is used for predicting BP in two scenarios; (1) Beat-by-beat arterial blood pressure (ABP) estimation, and (2) Beat-by-beat estimation of the systolic and diastolic blood pressure values. Different transformations are used to extract the features of the PPG beats in different domains including time, discrete cosine transform (DCT), discrete wavelet transform (DWT), and wavelet scattering transform (WST) domains. The simulation results show that using the WST domain outperforms the other domains in the sense of root mean square error (RMSE) and mean absolute error (MAE) for both of the suggested two scenarios.
{"title":"Blood Pressure Estimation from Photoplythmography Using Hybrid Scattering–LSTM Networks","authors":"Osama A. Omer, Mostafa Salah, A. Hassan, Mohamed Abdel-Nasser, Norihiro Sugita, Y. Saijo","doi":"10.3390/biomedinformatics4010010","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010010","url":null,"abstract":"One of the most significant indicators of heart and cardiovascular health is blood pressure (BP). Blood pressure (BP) has gained great attention in the last decade. Uncontrolled high blood pressure increases the risk of serious health problems, including heart attack and stroke. Recently, machine/deep learning has been leveraged for learning a BP from photoplethysmography (PPG) signals. Hence, continuous BP monitoring can be introduced, based on simple wearable contact sensors or even remotely sensed from a proper camera away from the clinical setup. However, the available training dataset imposes many limitations besides the other difficulties related to the PPG time series as high-dimensional data. This work presents beat-by-beat continuous PPG-based BP monitoring while accounting for the aforementioned limitations. For a better exploration of beats’ features, we propose to use wavelet scattering transform as a better descriptive domain to cope with the limitation of the training dataset and to help the deep learning network accurately learn the relationship between the morphological shapes of PPG beats and the BP. A long short-term memory (LSTM) network is utilized to demonstrate the superiority of the wavelet scattering transform over other domains. The learning scenarios are carried out on a beat basis where the input corresponding PPG beat is used for predicting BP in two scenarios; (1) Beat-by-beat arterial blood pressure (ABP) estimation, and (2) Beat-by-beat estimation of the systolic and diastolic blood pressure values. Different transformations are used to extract the features of the PPG beats in different domains including time, discrete cosine transform (DCT), discrete wavelet transform (DWT), and wavelet scattering transform (WST) domains. The simulation results show that using the WST domain outperforms the other domains in the sense of root mean square error (RMSE) and mean absolute error (MAE) for both of the suggested two scenarios.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139441624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-09DOI: 10.3390/biomedinformatics4010009
Eirini Banou, Aristidis G. Vrahatis, Marios G. Krokidis, Vlamos
(1) Background: Parkinson’s disease (PD) is a progressively worsening neurodegenerative disorder affecting movement, mental well-being, sleep, and pain. While no cure exists, treatments like hyperbaric oxygen therapy (HBOT) offer potential relief. However, the molecular biology perspective, especially when intertwined with machine learning dynamics, remains underexplored. (2) Methods: We employed machine learning techniques to analyze single-cell RNA-seq data from human PD cell samples. This approach aimed to identify pivotal genes associated with PD and understand their relationship with HBOT. (3) Results: Our analysis indicated genes such as MAP2, CAP2, and WSB1, among others, as being crucially linked with Parkinson’s disease (PD) and showed their significant correlation with Hyperbaric oxygen therapy (HBOT) indicatively. This suggests that certain genomic factors might influence the efficacy of HBOT in PD treatment. (4) Conclusions: HBOT presents promising therapeutic potential for Parkinson’s disease, with certain genomic factors playing a pivotal role in its efficacy. Our findings emphasize the need for further machine learning-driven research harnessing diverse omics data to better understand and treat PD.
{"title":"Machine Learning Analysis of Genomic Factors Influencing Hyperbaric Oxygen Therapy in Parkinson’s Disease","authors":"Eirini Banou, Aristidis G. Vrahatis, Marios G. Krokidis, Vlamos","doi":"10.3390/biomedinformatics4010009","DOIUrl":"https://doi.org/10.3390/biomedinformatics4010009","url":null,"abstract":"(1) Background: Parkinson’s disease (PD) is a progressively worsening neurodegenerative disorder affecting movement, mental well-being, sleep, and pain. While no cure exists, treatments like hyperbaric oxygen therapy (HBOT) offer potential relief. However, the molecular biology perspective, especially when intertwined with machine learning dynamics, remains underexplored. (2) Methods: We employed machine learning techniques to analyze single-cell RNA-seq data from human PD cell samples. This approach aimed to identify pivotal genes associated with PD and understand their relationship with HBOT. (3) Results: Our analysis indicated genes such as MAP2, CAP2, and WSB1, among others, as being crucially linked with Parkinson’s disease (PD) and showed their significant correlation with Hyperbaric oxygen therapy (HBOT) indicatively. This suggests that certain genomic factors might influence the efficacy of HBOT in PD treatment. (4) Conclusions: HBOT presents promising therapeutic potential for Parkinson’s disease, with certain genomic factors playing a pivotal role in its efficacy. Our findings emphasize the need for further machine learning-driven research harnessing diverse omics data to better understand and treat PD.","PeriodicalId":72394,"journal":{"name":"BioMedInformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139442888","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：