Pub Date : 2024-08-01eCollection Date: 2024-09-01DOI: 10.1007/s41666-024-00169-2
Soheila Molaei, Nima Ghanbari Bousejin, Ghadeer O Ghosheh, Anshul Thakur, Vinod Kumar Chauhan, Tingting Zhu, David A Clifton
Electronic Health Records (EHRs) play a crucial role in shaping predictive are models, yet they encounter challenges such as significant data gaps and class imbalances. Traditional Graph Neural Network (GNN) approaches have limitations in fully leveraging neighbourhood data or demanding intensive computational requirements for regularisation. To address this challenge, we introduce CliqueFluxNet, a novel framework that innovatively constructs a patient similarity graph to maximise cliques, thereby highlighting strong inter-patient connections. At the heart of CliqueFluxNet lies its stochastic edge fluxing strategy - a dynamic process involving random edge addition and removal during training. This strategy aims to enhance the model's generalisability and mitigate overfitting. Our empirical analysis, conducted on MIMIC-III and eICU datasets, focuses on the tasks of mortality and readmission prediction. It demonstrates significant progress in representation learning, particularly in scenarios with limited data availability. Qualitative assessments further underscore CliqueFluxNet's effectiveness in extracting meaningful EHR representations, solidifying its potential for advancing GNN applications in healthcare analytics.
{"title":"CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks.","authors":"Soheila Molaei, Nima Ghanbari Bousejin, Ghadeer O Ghosheh, Anshul Thakur, Vinod Kumar Chauhan, Tingting Zhu, David A Clifton","doi":"10.1007/s41666-024-00169-2","DOIUrl":"10.1007/s41666-024-00169-2","url":null,"abstract":"<p><p>Electronic Health Records (EHRs) play a crucial role in shaping predictive are models, yet they encounter challenges such as significant data gaps and class imbalances. Traditional Graph Neural Network (GNN) approaches have limitations in fully leveraging neighbourhood data or demanding intensive computational requirements for regularisation. To address this challenge, we introduce CliqueFluxNet, a novel framework that innovatively constructs a patient similarity graph to maximise cliques, thereby highlighting strong inter-patient connections. At the heart of CliqueFluxNet lies its stochastic edge fluxing strategy - a dynamic process involving random edge addition and removal during training. This strategy aims to enhance the model's generalisability and mitigate overfitting. Our empirical analysis, conducted on MIMIC-III and eICU datasets, focuses on the tasks of mortality and readmission prediction. It demonstrates significant progress in representation learning, particularly in scenarios with limited data availability. Qualitative assessments further underscore CliqueFluxNet's effectiveness in extracting meaningful EHR representations, solidifying its potential for advancing GNN applications in healthcare analytics.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11310186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141918532","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 : 2024-02-22DOI: 10.1007/s41666-024-00161-w
L. Gargioni, D. Fogli, Pietro Baroni
{"title":"A Systematic Review on Pill and Medication Dispensers from a Human-Centered Perspective","authors":"L. Gargioni, D. Fogli, Pietro Baroni","doi":"10.1007/s41666-024-00161-w","DOIUrl":"https://doi.org/10.1007/s41666-024-00161-w","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140441532","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: 10.1007/s41666-023-00136-3
Ayush Singh, Saranya Krishnamoorthy, John E. Ortega
{"title":"NeighBERT: Medical Entity Linking Using Relation-Induced Dense Retrieval","authors":"Ayush Singh, Saranya Krishnamoorthy, John E. Ortega","doi":"10.1007/s41666-023-00136-3","DOIUrl":"https://doi.org/10.1007/s41666-023-00136-3","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","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":"139525949","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 : 2024-01-16DOI: 10.1007/s41666-023-00158-x
Jon Harris, Mohammed J. Zaki
{"title":"Neural Models for Generating Natural Language Summaries from Temporal Personal Health Data","authors":"Jon Harris, Mohammed J. Zaki","doi":"10.1007/s41666-023-00158-x","DOIUrl":"https://doi.org/10.1007/s41666-023-00158-x","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139527961","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 : 2024-01-05DOI: 10.1007/s41666-023-00155-0
Cathy Shyr, Yan Hu, L. Bastarache, Alex Cheng, Rizwan Hamid, Paul Harris, Hua Xu
{"title":"Identifying and Extracting Rare Diseases and Their Phenotypes with Large Language Models","authors":"Cathy Shyr, Yan Hu, L. Bastarache, Alex Cheng, Rizwan Hamid, Paul Harris, Hua Xu","doi":"10.1007/s41666-023-00155-0","DOIUrl":"https://doi.org/10.1007/s41666-023-00155-0","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139381790","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 : 2024-01-03DOI: 10.1007/s41666-023-00157-y
Dinithi Vithanage, Ping Yu, Lei Wang, Chao Deng
{"title":"Contextual Word Embedding for Biomedical Knowledge Extraction: a Rapid Review and Case Study","authors":"Dinithi Vithanage, Ping Yu, Lei Wang, Chao Deng","doi":"10.1007/s41666-023-00157-y","DOIUrl":"https://doi.org/10.1007/s41666-023-00157-y","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139389543","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 : 2023-12-12DOI: 10.1007/s41666-023-00145-2
Ronak Etemadpour, Sonali Shintree, A. D. Shereen
{"title":"Brain Activity is Influenced by How High Dimensional Data are Represented: An EEG Study of Scatterplot Diagnostic (Scagnostics) Measures","authors":"Ronak Etemadpour, Sonali Shintree, A. D. Shereen","doi":"10.1007/s41666-023-00145-2","DOIUrl":"https://doi.org/10.1007/s41666-023-00145-2","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139009866","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 : 2023-11-14DOI: 10.1007/s41666-023-00153-2
Ban Al-Sahab, Alan Leviton, Tobias Loddenkemper, Nigel Paneth, Bo Zhang
{"title":"Biases in Electronic Health Records Data for Generating Real-World Evidence: An Overview","authors":"Ban Al-Sahab, Alan Leviton, Tobias Loddenkemper, Nigel Paneth, Bo Zhang","doi":"10.1007/s41666-023-00153-2","DOIUrl":"https://doi.org/10.1007/s41666-023-00153-2","url":null,"abstract":"","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134902772","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 : 2023-10-13DOI: 10.1007/s41666-023-00151-4
Tomas M. Bosschieter, Zifei Xu, Hui Lan, Benjamin J. Lengerich, Harsha Nori, Ian Painter, Vivienne Souter, Rich Caruana
Although most pregnancies result in a good outcome, complications are not uncommon and can be associated with serious implications for mothers and babies. Predictive modeling has the potential to improve outcomes through better understanding of risk factors, heightened surveillance for high risk patients, and more timely and appropriate interventions, thereby helping obstetricians deliver better care. We identify and study the most important risk factors for four types of pregnancy complications: (i) severe maternal morbidity, (ii) shoulder dystocia, (iii) preterm preeclampsia, and (iv) antepartum stillbirth. We use an Explainable Boosting Machine (EBM), a high-accuracy glass-box learning method, for prediction and identification of important risk factors. We undertake external validation and perform an extensive robustness analysis of the EBM models. EBMs match the accuracy of other black-box ML methods such as deep neural networks and random forests, and outperform logistic regression, while being more interpretable. EBMs prove to be robust. The interpretability of the EBM models reveals surprising insights into the features contributing to risk (e.g. maternal height is the second most important feature for shoulder dystocia) and may have potential for clinical application in the prediction and prevention of serious complications in pregnancy.
{"title":"Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes","authors":"Tomas M. Bosschieter, Zifei Xu, Hui Lan, Benjamin J. Lengerich, Harsha Nori, Ian Painter, Vivienne Souter, Rich Caruana","doi":"10.1007/s41666-023-00151-4","DOIUrl":"https://doi.org/10.1007/s41666-023-00151-4","url":null,"abstract":"Although most pregnancies result in a good outcome, complications are not uncommon and can be associated with serious implications for mothers and babies. Predictive modeling has the potential to improve outcomes through better understanding of risk factors, heightened surveillance for high risk patients, and more timely and appropriate interventions, thereby helping obstetricians deliver better care. We identify and study the most important risk factors for four types of pregnancy complications: (i) severe maternal morbidity, (ii) shoulder dystocia, (iii) preterm preeclampsia, and (iv) antepartum stillbirth. We use an Explainable Boosting Machine (EBM), a high-accuracy glass-box learning method, for prediction and identification of important risk factors. We undertake external validation and perform an extensive robustness analysis of the EBM models. EBMs match the accuracy of other black-box ML methods such as deep neural networks and random forests, and outperform logistic regression, while being more interpretable. EBMs prove to be robust. The interpretability of the EBM models reveals surprising insights into the features contributing to risk (e.g. maternal height is the second most important feature for shoulder dystocia) and may have potential for clinical application in the prediction and prevention of serious complications in pregnancy.","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135858010","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号