4.5 Review

Disease Prediction Using Graph Machine Learning Based on Electronic Health Data: A Review of Approaches and Trends

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

A survey of graph neural networks in various learning paradigms: methods, applications, and challenges

Lilapati Waikhom et al.

Summary: This article introduces recent advances in applying deep learning to graph-based tasks, known as Graph Neural Networks (GNNs). It covers different learning paradigms, including supervised, unsupervised, semi-supervised, self-supervised, and few-shot or meta-learning. The methods for each learning task are analyzed from theoretical and empirical perspectives, and general guidelines for building GNN models are provided, along with applications and benchmark datasets.

ARTIFICIAL INTELLIGENCE REVIEW (2023)

Article Computer Science, Artificial Intelligence

A disease network-based recommender system framework for predictive risk modelling of chronic diseases and their comorbidities

Haohui Lu et al.

Summary: This study predicts chronic diseases and their comorbidities using administrative health data and applies graph theory and content-based recommender system approaches. The models with network features show better performance in predicting chronic diseases and their latent comorbidities.

APPLIED INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

A patient network-based machine learning model for disease prediction: The case of type 2 diabetes mellitus

Haohui Lu et al.

Summary: The study utilized real-world healthcare data and developed a model for predicting chronic diseases, specifically type 2 diabetes, by combining patient networks and machine learning methods to accurately assess the risk of developing such conditions.

APPLIED INTELLIGENCE (2022)

Article Multidisciplinary Sciences

Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction

Shahadat Uddin et al.

Summary: This paper studies different variants of the k-nearest neighbour (KNN) algorithm and compares their performance in disease prediction. By implementing and experimenting on eight datasets, the study found that accuracy values ranged from 64.22% to 83.62%, with Hassanaat KNN showing the highest accuracy. The study also proposes a relative performance index based on accuracy, precision, and recall measures, identifying Hassanaat KNN as the best performing variant.

SCIENTIFIC REPORTS (2022)

Article Computer Science, Artificial Intelligence

Early prediction of high-cost inpatients with ischemic heart disease using network analytics and machine learning

Ping Yang et al.

Summary: This study aimed to predict high-cost inpatients with ischemic heart disease (IHD) at an early stage of admission by integrating network analytics with machine learning. Two networks were constructed based on hospital discharge records, and three novel network features were generated. Six machine learning models were developed and compared, with LightGBM achieving the best performance. Network features were found to be the most significant, and the proposed approach showed potential value in the healthcare field.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Article Computer Science, Artificial Intelligence

Network analytics and machine learning for predictive risk modelling of cardiovascular disease in patients with type 2 diabetes

Ekramul Hossain et al.

Summary: The study proposed a risk prediction model utilizing administrative data to assess the risk of cardiovascular diseases in type 2 diabetes patients, achieving classifiers accuracy ranging from 79% to 88%. The model shows potential for medical practice and stakeholders to develop health management programs for high-risk patients developing chronic diseases.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Article Computer Science, Information Systems

Disease Prediction via Graph Neural Networks

Zhenchao Sun et al.

Summary: With the increasing availability of electronic medical records (EMRs), disease prediction has received significant research attention. This study introduces an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment EMR data and accurately predicts both general and rare diseases.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Article Multidisciplinary Sciences

A weighted patient network-based framework for predicting chronic diseases using graph neural networks

Haohui Lu et al.

Summary: The article presents a framework based on Graph Neural Networks for predicting patients with chronic diseases. By extracting the latent relationships among patients and building prediction models using GNN techniques, the accuracy of chronic disease prediction was successfully improved.

SCIENTIFIC REPORTS (2021)

Review Biochemical Research Methods

Use of Electronic Health Data for Disease Prediction: A Comprehensive Literature Review

Md Ekramul Hossain et al.

Summary: Disease prediction using electronic health data can benefit stakeholders by identifying at-risk patients and improving quality of care to avoid hospital admissions. Various models have been proposed utilizing large-scale electronic health databases, different methods, and healthcare variables, with the goal to discuss different risk prediction models based on electronic health data.

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS (2021)

Article Biology

COVID-19 and Artificial Intelligence: An Approach to Forecast the Severity of Diagnosis

Anca Loredana Udristoiu et al.

Summary: This study accurately predicted the severity of COVID-19 in positive-tested patients by integrating clinical and biological data with chest X-ray images using deep learning methods.

LIFE-BASEL (2021)

Article Computer Science, Information Systems

Transgender data collection in the electronic health record: Current concepts and issues

Clair A. Kronk et al.

Summary: Researchers present recommendations for collecting sex- and gender-related data in electronic health records, as well as common pitfalls. Collaborations and open inclusion of transgender and gender-diverse individuals are crucial for shifting the paradigm in transgender and gender-diverse health.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2021)

Review Chemistry, Analytical

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

David Ahmedt-Aristizabal et al.

Summary: This survey thoroughly reviews different types of graph architectures and their applications in healthcare, organized by functional connectivity, anatomical structure, and electrical-based analysis. The study highlights the limitations of existing techniques and discusses potential directions for future research. Graph neural networks have attracted attention for exploiting implicit information in biological systems through interacting nodes connected by edges with weights determined by temporal associations or anatomical junctions.

SENSORS (2021)

Article Genetics & Heredity

Graph Neural Networks and Their Current Applications in Bioinformatics

Xiao-Meng Zhang et al.

Summary: This study presents a systematic survey of the application of graph neural networks (GNNs) in bioinformatics, introducing basic principles and common models of GNNs, and discussing their applications in tasks such as node classification, link prediction, and graph generation. It also categorizes and discusses related studies based on different omics data applications, pointing out the current shortcomings and future prospects of GNN research in biological tasks.

FRONTIERS IN GENETICS (2021)

Proceedings Paper Computer Science, Interdisciplinary Applications

A Meta-Path-Based Prediction Method for Disease Comorbidities

Eduardo P. Garcia del Valle et al.

Summary: The co-occurrence of diseases worsens patient prognosis and treatment difficulty. Utilizing clinical information and heterogeneous information networks can reveal hidden disease relationships, with meta-paths capturing complex semantics in the networks. Using these approaches, a system was proposed to predict disease comorbidities, resulting in improved predictions supported by medical literature and publicly accessible data and models.

2021 IEEE 34TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS) (2021)

Article Medicine, General & Internal

Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods

Corina Maria Vasile et al.

Summary: A novel ensemble method combining two deep learning models was developed to classify ultrasound thyroidal images, achieving excellent results and validated by physicians.

MEDICINA-LITHUANIA (2021)

Article Biochemical Research Methods

Graph embedding on biomedical networks: methods, applications and evaluations

Xiang Yue et al.

BIOINFORMATICS (2020)

Article Computer Science, Artificial Intelligence

Directed disease networks to facilitate multiple-disease risk assessment modeling

Tingyan Wang et al.

DECISION SUPPORT SYSTEMS (2020)

Article Biochemical Research Methods

A Cancer Survival Prediction Method Based on Graph Convolutional Network

Chunyu Wang et al.

IEEE TRANSACTIONS ON NANOBIOSCIENCE (2020)

Article Computer Science, Interdisciplinary Applications

Graph Neural Network-Based Diagnosis Prediction

Yang Li et al.

BIG DATA (2020)

Proceedings Paper Computer Science, Information Systems

MGNN: A Multimodal Graph Neural Network for Predicting the Survival of Cancer Patients

Jianliang Gao et al.

PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20) (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Drug-Disease Graph: Predicting Adverse Drug Reaction Signals via Graph Neural Network with Clinical Data

Heeyoung Kwak et al.

ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2020, PT II (2020)

Proceedings Paper Computer Science, Theory & Methods

Graph-based Deep Learning in Natural Language Processing

Shikhar Vashishth et al.

PROCEEDINGS OF THE 7TH ACM IKDD CODS AND 25TH COMAD (CODS-COMAD 2020) (2020)

Review Biochemistry & Molecular Biology

Constructing knowledge graphs and their biomedical applications

David N. Nicholson et al.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2020)

Review Biochemical Research Methods

Graph convolutional networks for computational drug development and discovery

Mengying Sun et al.

BRIEFINGS IN BIOINFORMATICS (2020)

Article Medical Informatics

Comparing different supervised machine learning algorithms for disease prediction

Shahadat Uddin et al.

BMC MEDICAL INFORMATICS AND DECISION MAKING (2019)

Article Computer Science, Artificial Intelligence

Chronic disease prediction using administrative data and graph theory: The case of type 2 diabetes

Arif Khan et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Article Computer Science, Theory & Methods

Big data in healthcare: management, analysis and future prospects

Sabyasachi Dash et al.

JOURNAL OF BIG DATA (2019)

Article Computer Science, Theory & Methods

Privacy preservation techniques in big data analytics: a survey

P. Ram Mohan Rao et al.

JOURNAL OF BIG DATA (2018)

Editorial Material Engineering, Electrical & Electronic

Geometric Deep Learning Going beyond Euclidean data

Michael M. Bronstein et al.

IEEE SIGNAL PROCESSING MAGAZINE (2017)

Proceedings Paper Computer Science, Artificial Intelligence

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

Yuxiao Dong et al.

KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (2017)

Proceedings Paper Computer Science, Artificial Intelligence

GRAM: Graph-based Attention Model for Healthcare Representation Learning

Edward Choi et al.

KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (2017)

Article Computer Science, Interdisciplinary Applications

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

Nima Tajbakhsh et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Article Multidisciplinary Sciences

MIMIC-III, a freely accessible critical care database

Alistair E. W. Johnson et al.

SCIENTIFIC DATA (2016)

Article Computer Science, Artificial Intelligence

The Graph Neural Network Model

Franco Scarselli et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2009)

Article Computer Science, Information Systems

The link-prediction problem for social networks

David Liben-Nowell et al.

JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY (2007)

Article Multidisciplinary Sciences

Using the principle of entropy maximization to infer genetic interaction networks from gene expression patterns

Timothy R. Lezon et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2006)