相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Information Systems
Sicen Liu et al.
Summary: The study aims to explore the interactions between structured and unstructured data in electronic health records (EHR) and propose a Medical Multimodal Pre-trained Language Model (MedM-PLM) to learn enhanced EHR representations. The model is trained on the MIMIC-III dataset and shows superior performance compared to state-of-the-art methods in medication recommendation, 30-day readmission prediction, and ICD coding tasks.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Yikuan Li et al.
Summary: Electronic health records (EHR) provide an overview of patients' trajectories and have potential for developing accurate risk prediction models. However, current deep learning models have limitations in processing long sequences, which is crucial in healthcare and EHR. To address this, Hi-BEHRT, a hierarchical Transformer-based model, is introduced, which surpasses existing models in predicting heart failure, diabetes, chronic kidney disease, and stroke risks. Furthermore, Hi-BEHRT utilizes an effective end-to-end contrastive pre-training strategy to enhance its transferability.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Review
Mathematical & Computational Biology
Ashir Javeed et al.
Summary: Heart disease is one of the leading causes of deaths globally, and traditional diagnostic methods have cost and health concerns. Therefore, researchers have developed automated diagnostic systems based on machine learning and data mining techniques, providing affordable, efficient, and reliable solutions for heart disease detection.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2022)
Review
Computer Science, Interdisciplinary Applications
Feng Xie et al.
Summary: This study systematically examines deep learning solutions for temporal data representation in electronic health records (EHRs). The study identifies challenges in representing temporal data, such as irregularity, heterogeneity, sparsity, and model opacity. It explores how deep learning techniques address these challenges and discusses open challenges in the field. The study concludes that deep learning solutions can partially address the challenges of temporal EHR data, but future research should focus on designing comprehensive and integrated solutions and incorporating clinical domain knowledge and model interpretability.
JOURNAL OF BIOMEDICAL INFORMATICS
(2022)
Review
Cardiac & Cardiovascular Systems
Marco Penso et al.
Summary: This review examines the application of deep learning techniques in the management of heart failure. While image and signal processing have achieved high performance, there is still room for improvement in electronic health record and multisource data prediction. Deep learning has the potential to provide more efficient care and improve patient outcomes, but there are current limitations.
CURRENT HEART FAILURE REPORTS
(2022)
Article
Computer Science, Interdisciplinary Applications
Ke Niu et al.
Summary: The goal of this study is to design an accurate and robust predictive model for mortality prediction based on patients' previous EHR. The challenges lie in handling the sequential, multivariate, sparse, and irregular nature of EHR data, as well as the insufficient information of patients with rare diseases. To address these challenges, a new model called SeMO is proposed, which learns reasonable embeddings for medical concepts from sequential and irregular visits and improves prediction performance by integrating multivariate features.
JOURNAL OF BIOMEDICAL INFORMATICS
(2022)
Article
Medicine, General & Internal
Jennifer Chen et al.
MEDICAL CLINICS OF NORTH AMERICA
(2022)
Article
Cardiac & Cardiovascular Systems
David P. Kao
HEART FAILURE CLINICS
(2022)
Review
Cardiac & Cardiovascular Systems
Saeed Amal et al.
Summary: Today's digital health revolution aims to improve the efficiency of healthcare delivery and make care more personalized and timely. Data fusion techniques enable the integration of multiple modalities, providing deeper insights specific to the field of cardiovascular medicine and advancing the diagnosis and treatment of cardiovascular diseases.
FRONTIERS IN CARDIOVASCULAR MEDICINE
(2022)
Article
Cardiac & Cardiovascular Systems
Martha M. O. McGilvray et al.
Summary: This study developed deep learning models based on commonly-available electronic health record (EHR) variables to assist clinicians in identifying HF medical therapy nonresponders. The models showed high accuracy in predicting 1-year all-cause death or referral for HF surgical therapy, supporting their clinical relevance.
JACC-HEART FAILURE
(2022)
Review
Biochemistry & Molecular Biology
Mikolaj Blaziak et al.
Summary: Heart failure is a major cause of mortality and hospitalization worldwide. Machine learning models have shown higher accuracy in predicting outcomes in heart failure patients and may play an important role in management.
Article
Health Care Sciences & Services
Benjamin Shickel et al.
Summary: Transformer models have brought revolutionary progress to the field of natural language processing and continue to achieve state-of-the-art results in text-based applications. This study proposes a dynamic method for tokenizing patient data and utilizes a Transformer model for predicting clinical outcomes, resulting in more accurate predictions compared to traditional machine learning models.
FRONTIERS IN DIGITAL HEALTH
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Bo Li et al.
Summary: This paper proposes a new method called MTSSP, which combines missing value filling and time series classification to improve the prediction of mortality in electronic health records. Experimental results demonstrate that this approach significantly outperforms other methods.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Article
Peripheral Vascular Disease
Ikram U. Haq et al.
Summary: Artificial intelligence, specifically machine learning algorithms, are increasingly used in various aspects of cardiovascular medicine to enhance diagnostic capabilities, clinical decision-making, and patient care. However, further validation through multicenter, prospective clinical trials is needed.
VASCULAR HEALTH AND RISK MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
P. Priyanga et al.
Summary: Heart disease, also known as Cardio Vascular Disease, is a major cause of morbidity and mortality globally. Assessing risk factors and early diagnosis are crucial in the management of heart disease. Machine learning techniques are valuable in providing decision support and predictive analytics in clinical settings for heart disease.
COMPUTATIONAL INTELLIGENCE
(2021)
Article
Oncology
Lisa M. Hess et al.
Summary: The study revealed that patients with RET fusions have more favorable overall survival rates, but after adjusting for baseline covariates, there were no significant differences in either OS or PFS based on RET status among patients treated with standard therapy.
Article
Computer Science, Information Systems
Shreyesh Doppalapudi et al.
Summary: In this study, deep learning models were used to predict survival periods of lung cancer patients, outperforming traditional machine learning models. Feature importance analysis was conducted to understand the factors impacting survival periods, providing a baseline for early cancer diagnosis.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2021)
Article
Health Care Sciences & Services
Haichen Lv et al.
Summary: This study developed machine learning models to predict 1-year in-hospital mortality, use of positive inotropic agents, and 1-year all-cause readmission rate for patients with heart failure. The results showed that machine learning algorithms improved the performance of predictive models and a decision tree of mortality risk was created to help guide better clinical risk assessment and decision making.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Mathematical & Computational Biology
Ashwath Radhachandran et al.
Summary: This study developed models for predicting seven-day mortality among AHF patients by applying machine learning techniques to retrospective patient data. A model using only four clinical variables outperformed the commonly used EHMRG model in predicting seven-day mortality in AHF, showing potential for assisting clinicians in making critical decisions about patient disposition in ED settings.
Article
Cardiac & Cardiovascular Systems
Hua Wang et al.
Summary: The study revealed an increasing prevalence and incidence of HF with age in China, posing a considerable burden on the country's health systems.
CIRCULATION-HEART FAILURE
(2021)
Article
Computer Science, Artificial Intelligence
Lu Men et al.
Summary: A deep learning approach utilizing LSTM and time-aware, attention-based mechanisms was proposed for multi-disease prediction based on clinical visit records. The approach outperformed traditional and deep learning methods in predicting future disease diagnoses using a large clinical record dataset.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Andrew P. Reimer et al.
Summary: This study assessed the feasibility of developing a schema to identify and subclassify all structured diagnosis codes for a patient encounter. By merging structured diagnosis codes with additional EHR data and secondary data sources, it provided additional information to understand the role of diagnosis throughout a clinical encounter and improved predictive model performance.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Eunji Jun et al.
Summary: Electronic health records are complex data characterized by sparseness, noise, and heterogeneity, making it challenging to learn patterns within them. Existing methods have attempted to address the sparseness issue caused by missing values through defining secondary imputation problems. However, the fidelity or confidence of imputed values is often overlooked, which can lead to difficulties in modeling and performance degradation. Our novel variational recurrent network aims to estimate the distribution of missing variables, update hidden states based on fidelity to imputed values, and predict in-hospital mortality, demonstrating improved performance compared to state-of-the-art methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Cardiac & Cardiovascular Systems
Sebastian Koenig et al.
Summary: This study aimed to develop a reliable algorithm to compute in-hospital mortality rates in heart failure (HF) patients using machine learning models. By comparing different ML algorithms, the study found that they outperformed traditional regression analysis in predicting mortality. The models demonstrated good performance and could potentially improve future care for HF patients.
Proceedings Paper
Computer Science, Artificial Intelligence
Mingquan Lin et al.
Summary: The study developed a deep learning model using multimodal data to predict ICU-mortality, achieving a high average C-index compared to traditional methods. Results show the potential of deep learning models with multimodal information to enhance ICU-mortality prediction, outperforming traditional methods in this field. The study's findings are publicly available for further research and implementation.
2021 IEEE 9TH INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI 2021)
(2021)
Article
Cardiac & Cardiovascular Systems
Eric D. Adler et al.
EUROPEAN JOURNAL OF HEART FAILURE
(2020)
Article
Cardiac & Cardiovascular Systems
Suveen Angraal et al.
JACC-HEART FAILURE
(2020)
Article
Medical Informatics
Davide Chicco et al.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2020)
Article
Computer Science, Artificial Intelligence
Yi Zheng et al.
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS
(2020)
Article
Computer Science, Interdisciplinary Applications
Zhe Wang et al.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2020)
Article
Computer Science, Information Systems
Guangyuan Zheng et al.
TSINGHUA SCIENCE AND TECHNOLOGY
(2020)
Article
Computer Science, Interdisciplinary Applications
Jiebin Chu et al.
JOURNAL OF BIOMEDICAL INFORMATICS
(2020)
Editorial Material
Ophthalmology
Kurt K. Benke
JAMA OPHTHALMOLOGY
(2019)
Article
Engineering, Biomedical
Jinsung Yoon et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2019)
Article
Medical Informatics
Tong Ruan et al.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2019)
Article
Multidisciplinary Sciences
Alistair E. W. Johnson et al.
Article
Medicine, General & Internal
Jerry H. Gurwitz et al.
AMERICAN JOURNAL OF MEDICINE
(2013)
Article
Computer Science, Artificial Intelligence
A Ross et al.
PATTERN RECOGNITION LETTERS
(2003)
