Prediction of coronary atherosclerosis progression using dynamic Bayesian networks

Risk Prediction Using Bayesian Networks: An Immunotherapy Case Study in Patients With Metastatic Renal Cell Carcinoma

To address the need for more accurate risk stratification models for cancer immuno-oncology, this study aimed to develop a machine-learned Bayesian network model (BNM) for predicting outcomes in patients with metastatic renal cell carcinoma (mRCC) being treated with immunotherapy.

StoCast: Stochastic Disease Forecasting With Progression Uncertainty

Forecasting patients' disease progressions with rich longitudinal clinical data has drawn much attention in recent years due to its impactful application in healthcare and the medical field. Researchers have tackled this problem by leveraging traditional machine learning, statistical techniques and deep learning based models. However, existing methods suffer from either deterministic internal structures or over-simplified stochastic components, failing to deal with complex uncertain scenarios such as progression uncertainty (i.e., multiple possible trajectories) and data uncertainty (i.e., imprecise observations and misdiagnosis). To overcome these major uncertainty issues, we propose a novel deep generative model, Stochastic Disease Forecasting Model (StoCast), along with an associated neural network architecture StoCastNet, that can be trained efficiently via stochastic optimization techniques. Our StoCast model uses internal stochastic components to deal with departures of observed data from patients' true health states, and more importantly, is able to produce a comprehensive estimate of future disease progression trajectories. Based on two public datasets related to Alzheimer's disease and Parkinson's disease, we demonstrate how our StoCast model achieves robust and superior performance than deterministic baseline approaches, and conveys richer information that can potentially assist doctors to make decisions with greater confidence in a complex uncertain scenario.

Probabilistic Graphical Modeling for Estimating Risk of Coronary Artery Disease: Applications of a Flexible Machine-Learning Method

Objectives. Coronary artery disease (CAD) is the leading cause of death and disease burden worldwide, causing 1 in 7 deaths in the United States alone. Risk prediction models that can learn the complex causal relationships that give rise to CAD from data, instead of merely predicting the risk of disease, have the potential to improve transparency and efficacy of personalized CAD diagnosis and therapy selection for physicians, patients, and other decision makers. Methods. We use Bayesian networks (BNs) to model the risk of CAD using the Z-Alizadehsani data set-a published real-world observational data set of 303 Iranian patients at risk for CAD. We also describe how BNs can be used for incorporation of background knowledge, individual risk prediction, handling missing observations, and adaptive decision making under uncertainty. Results. BNs performed on par with machine-learning classifiers at predicting CAD and showed better probability calibration. They achieved a mean 10-fold area under the receiver-operating characteristic curve (AUC) of 0.93 ± 0.04, which was comparable with the performance of logistic regression with L1 or L2 regularization (AUC: 0.92 ± 0.06), support vector machine (AUC: 0.92 ± 0.06), and artificial neural network (AUC: 0.91 ± 0.05). We describe the use of BNs to predict with missing data and to adaptively calculate prognostic values of individual variables under uncertainty. Conclusion. BNs are powerful and versatile tools for risk prediction and health outcomes research that can complement traditional statistical techniques and are particularly useful in domains in which information is uncertain or incomplete and in which interpretability is important, such as medicine.

Association of traditional risk factors with coronary artery disease in nonagenarians: the primary role of hypertension

BACKGROUND

Previous studies have shown different relationships between traditional cardiovascular risk factors for coronary artery disease (CAD) in very elderly people. Although new associations with CAD have been reported, there is also evidence of the possibility of new therapeutic strategies for the treatment or prevention of CAD.

DESIGN

This article retrospectively examines the possible association of traditional cardiovascular risk factors with CAD in very elderly people aged >90 years. This study represents the hypothesis that the elderly aged >90 years have a different cardiovascular profile with respect to CAD than patients <90 years old.

METHODS

Data on all patients aged >90 years who received a cardiac catheterization were collected from hospital charts from the Department of Internal Medicine, Saarland University Medical Center, Germany, within the study period of 2004-2013. The cardiovascular risk profiles were compared in patients aged >90 years with and without CAD after cardiac catheterization.

RESULTS

One hundred and six out of 67,976 (0.2%, mean age 91.6±1.8 years, 40 female [37.7%]; 95% confidence interval [CI]: 0.1-0.2), and out of a total of 114 of the very elderly patients, were found to have CAD. From the results of this study, the author could establish only a causal relationship between hypertension and CAD in very elderly people (P=0.005). At best, this is just an association with a higher risk of CAD in this age group. Several studies with similar outcomes are needed to establish causality.

CONCLUSION

This study could find no link between CAD and traditional risk factors, except for hypertension.

Weak prediction power of the Framingham Risk Score for coronary artery disease in nonagenarians

Background

Coronary artery disease (CAD) is caused by an acute myocardial infarction and is still feared as a life-threatening heart disease worldwide. In order to identify patients at high risk for CAD, previous studies have proposed various risk assessment scores for the prevention of CAD. The most commonly used risk assessment score for CAD worldwide is the Framingham Risk Score (FRS). The FRS is used for middle-aged people; hence, its appropriateness has not been demonstrated to predict the likelihood of CAD occurrence in very elderly people. This article examines the possible predictive value of FRS for CAD in very elderly people over 90 years of age.

Methods

Data on all patients over 90 years of age who received a cardiac catheter were collected from hospital charts from the Department of Internal Medicine, Saarland University Medical Center, and HELIOS Hospital Wuppertal, Witten/Herdecke University Medical Center, Germany, within a study period from 2004 to 2013. The FRSs and cardiovascular risk profiles of patients over 90 years of age with and without CAD after cardiac catheterization were compared.

Results

One hundred and seventy-five (91.15%, mean age 91.51±1.80 years, 74 females [42.29%]; 95% confidence interval [CI], 0.87–0.95) of a total 192 of the very elderly patients were found to have CAD. Based on the results of our study, the FRS seems to provide weak predictive ability for CAD in very elderly people (P = 0.3792).

Conclusion

We found weak prediction power of FRS for CAD in nonagenarians.