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

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Haohui Lu ◽  
Shahadat Uddin
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Cardiovascular Disease ◽  
Chronic Disease ◽  
Pulmonary Disease ◽  
Chronic Diseases ◽  
Prediction Models ◽  
Disease Prediction ◽  
Chronic Pulmonary Disease ◽  
Graph Neural Networks

AbstractChronic disease prediction is a critical task in healthcare. Existing studies fulfil this requirement by employing machine learning techniques based on patient features, but they suffer from high dimensional data problems and a high level of bias. We propose a framework for predicting chronic disease based on Graph Neural Networks (GNNs) to address these issues. We begin by projecting a patient-disease bipartite graph to create a weighted patient network (WPN) that extracts the latent relationship among patients. We then use GNN-based techniques to build prediction models. These models use features extracted from WPN to create robust patient representations for chronic disease prediction. We compare the output of GNN-based models to machine learning methods by using cardiovascular disease and chronic pulmonary disease. The results show that our framework enhances the accuracy of chronic disease prediction. The model with attention mechanisms achieves an accuracy of 93.49% for cardiovascular disease prediction and 89.15% for chronic pulmonary disease prediction. Furthermore, the visualisation of the last hidden layers of GNN-based models shows the pattern for the two cohorts, demonstrating the discriminative strength of the framework. The proposed framework can help stakeholders improve health management systems for patients at risk of developing chronic diseases and conditions.

scholarly journals Machine Learning for Integrating Social Determinants in Cardiovascular Disease Prediction Models: A Systematic Review

2020 ◽  
Author(s):  
Yuan Zhao ◽  
Erica P Wood ◽  
Nicholas Mirin ◽  
Rajesh Vedanthan ◽  
Stephanie H Cook ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Cardiovascular Disease ◽  
Social Determinants ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Complex Nature ◽  
Disease Prediction ◽  
Causal Pathway

Background: Cardiovascular disease (CVD) is the number one cause of death worldwide, and CVD burden is increasing in low-resource settings and for lower socioeconomic groups worldwide. Machine learning (ML) algorithms are rapidly being developed and incorporated into clinical practice for CVD prediction and treatment decisions. Significant opportunities for reducing death and disability from cardiovascular disease worldwide lie with addressing the social determinants of cardiovascular outcomes. We sought to review how social determinants of health (SDoH) and variables along their causal pathway are being included in ML algorithms in order to develop best practices for development of future machine learning algorithms that include social determinants. Methods: We conducted a systematic review using five databases (PubMed, Embase, Web of Science, IEEE Xplore and ACM Digital Library). We identified English language articles published from inception to April 10, 2020, which reported on the use of machine learning for cardiovascular disease prediction, that incorporated SDoH and related variables. We included studies that used data from any source or study type. Studies were excluded if they did not include the use of any machine learning algorithm, were developed for non-humans, the outcomes were bio-markers, mediators, surgery or medication of CVD, rehabilitation or mental health outcomes after CVD or cost-effective analysis of CVD, the manuscript was non-English, or was a review or meta-analysis. We also excluded articles presented at conferences as abstracts and the full texts were not obtainable. The study was registered with PROSPERO (CRD42020175466). Findings: Of 2870 articles identified, 96 were eligible for inclusion. Most studies that compared ML and regression showed increased performance of ML, and most studies that compared performance with or without SDoH/related variables showed increased performance with them. The most frequently included SDoH variables were race/ethnicity, income, education and marital status. Studies were largely from North America, Europe and China, limiting the diversity of included populations and variance in social determinants. Interpretation: Findings show that machine learning models, as well as SDoH and related variables, improve CVD prediction model performance. The limited variety of sources and data in studies emphasize that there is opportunity to include more SDoH variables, especially environmental ones, that are known CVD risk factors in machine learning CVD prediction models. Given their flexibility, ML may provide opportunity to incorporate and model the complex nature of social determinants. Such data should be recorded in electronic databases to enable their use.

More Eggs, Less Sugar: A Sneak Peek into the Latest Dietary Guidelines for Americans

2018 ◽  
Vol 7 (1) ◽  
pp. 22-24
Author(s):  
Darlene Zimmerman
Keyword(s):  
Cardiovascular Disease ◽  
Chronic Disease ◽  
Chronic Diseases ◽  
Dietary Guidelines ◽  
Healthy Diet ◽  
Dietary Guidelines For Americans

ABSTRACT The 2015 – 2020 Dietary Guidelines for Americans provides guidance for choosing a healthy diet. There is a focus on preventing and alleviating the effects of diet-related chronic diseases. These include obesity, diabetes, cardiovascular disease, and stroke, among others. This article briefly reviews the primary guideline items that can be used to teach patients with respect to improving their diet. Clinical exercise physiologists who work with patients with chronic disease can use these guidelines for general discussions regarding a heart-healthy diet.

scholarly journals Cardiovascular disease prediction: do pulmonary disease-related chest CT features have added value?

2015 ◽  
Vol 25 (6) ◽  
pp. 1646-1654
Author(s):  
Pushpa M. Jairam ◽  
◽  
Pim A. de Jong ◽  
Willem P. Th. M. Mali ◽  
Ivana Isgum ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Pulmonary Disease ◽  
Chest Ct ◽  
Added Value ◽  
Disease Prediction ◽  
Ct Features

Reviewing the use and quality of machine learning in developing clinical prediction models for cardiovascular disease

2021 ◽  
pp. postgradmedj-2020-139352
Author(s):  
Simon Allan ◽  
Raphael Olaiya ◽  
Rasan Burhan
Keyword(s):  
Machine Learning ◽  
Cardiovascular Disease ◽  
Prediction Models ◽  
Bone Fractures ◽  
Statin Treatment ◽  
Computer Algorithms ◽  
Clinical Prediction ◽  
Clinical Prediction Models ◽  
Heart Attacks

Cardiovascular disease (CVD) is one of the leading causes of death across the world. CVD can lead to angina, heart attacks, heart failure, strokes, and eventually, death; among many other serious conditions. The early intervention with those at a higher risk of developing CVD, typically with statin treatment, leads to better health outcomes. For this reason, clinical prediction models (CPMs) have been developed to identify those at a high risk of developing CVD so that treatment can begin at an earlier stage. Currently, CPMs are built around statistical analysis of factors linked to developing CVD, such as body mass index and family history. The emerging field of machine learning (ML) in healthcare, using computer algorithms that learn from a dataset without explicit programming, has the potential to outperform the CPMs available today. ML has already shown exciting progress in the detection of skin malignancies, bone fractures and many other medical conditions. In this review, we will analyse and explain the CPMs currently in use with comparisons to their developing ML counterparts. We have found that although the newest non-ML CPMs are effective, ML-based approaches consistently outperform them. However, improvements to the literature need to be made before ML should be implemented over current CPMs.

scholarly journals Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Dejun Jiang ◽  
Zhenxing Wu ◽  
Chang-Yu Hsieh ◽  
Guangyong Chen ◽  
Ben Liao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Computational Efficiency ◽  
Domain Knowledge ◽  
Prediction Models ◽  
Computational Cost ◽  
Large Dataset ◽  
Predictive Capacity ◽  
Classification Tasks ◽  
Graph Neural Networks ◽  
Public Datasets

AbstractGraph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various property endpoints, the predictive capacity and computational efficiency of the prediction models developed by eight machine learning (ML) algorithms, including four descriptor-based models (SVM, XGBoost, RF and DNN) and four graph-based models (GCN, GAT, MPNN and Attentive FP), were extensively tested and compared. The results demonstrate that on average the descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency. SVM generally achieves the best predictions for the regression tasks. Both RF and XGBoost can achieve reliable predictions for the classification tasks, and some of the graph-based models, such as Attentive FP and GCN, can yield outstanding performance for a fraction of larger or multi-task datasets. In terms of computational cost, XGBoost and RF are the two most efficient algorithms and only need a few seconds to train a model even for a large dataset. The model interpretations by the SHAP method can effectively explore the established domain knowledge for the descriptor-based models. Finally, we explored use of these models for virtual screening (VS) towards HIV and demonstrated that different ML algorithms offer diverse VS profiles. All in all, we believe that the off-the-shelf descriptor-based models still can be directly employed to accurately predict various chemical endpoints with excellent computability and interpretability.

scholarly journals Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques

2020 ◽  
Author(s):  
Georgios Kantidakis ◽  
Hein Putter ◽  
Carlo Lancia ◽  
Jacob de Boer ◽  
Andries E Braat ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Liver Transplantation ◽  
Prediction Models ◽  
Machine Learning Techniques ◽  
Brier Score ◽  
Survival Prediction ◽  
Cox Models ◽  
Learning Techniques ◽  
Random Survival Forest

Abstract Background: Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians.Methods: In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques.Results: Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years.Conclusion: In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables.

scholarly journals Benchmarking Graph Neural Networks for Materials Chemistry

2021 ◽  
Author(s):  
Victor Fung ◽  
Jiaxin Zhang ◽  
Eric Juarez ◽  
Bobby Sumpter
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Materials Chemistry ◽  
Learning Models ◽  
High Data ◽  
Hyperparameter Selection ◽  
Computational Materials ◽  
Conventional Models ◽  
Graph Neural Networks ◽  
Machine Learning Models

Graph neural networks (GNNs) have received intense interest as a rapidly expanding class of machine learning models remarkably well-suited for materials applications. To date, a number of successful GNNs have been proposed and demonstrated for systems ranging from crystal stability to electronic property prediction and to surface chemistry and heterogeneous catalysis. However, a consistent benchmark of these models remains lacking, hindering the development and consistent evaluation of new models in the materials field. Here, we present a workflow and testing platform, MatDeepLearn, for quickly and reproducibly assessing and comparing GNNs and other machine learning models. We use this platform to optimize and evaluate a selection of top performing GNNs on several representative datasets in computational materials chemistry. From our investigations we note the importance of hyperparameter selection and find roughly similar performances for the top models once optimized. We identify several strengths in GNNs over conventional models in cases with compositionally diverse datasets and in its overall flexibility with respect to inputs, due to learned rather than defined representations. Meanwhile several weaknesses of GNNs are also observed including high data requirements, and suggestions for further improvement for applications in materials chemistry are proposed.

Sign in / Sign up

Export Citation Format

Share Document