A dynamic Bayesian network for diagnosing ventilator-associated pneumonia in ICU patients

Charitos, Theodore; Gaag, Linda C. van der; Visscher, Stefan; Schurink, Karin; Lucas, Peter

doi:10.1016/j.eswa.2007.11.065

Cited by 45 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…DBNs have been applied to finding gene regulatory networks [86], inferring neural connectivity networks from spike train data [87], and developing prognostic and diagnostic models [88, 89]; and there are a number of software packages for inferring them [90, 91]. Recent work has also extended DBNs to the case of non-stationary time series, where there are so-called changepoints when the structure of the system (how the variables are connected) changes.…”

Section: Causal Inference and Explanationmentioning

confidence: 99%

A review of causal inference for biomedical informatics

Kleinberg

Hripcsak

2011

Journal of Biomedical Informatics

149

View full text Add to dashboard Cite

Causality is an important concept throughout the health sciences and is particularly vital for informatics work such as finding adverse drug events or risk factors for disease using electronic health records. While philosophers and scientists working for centuries on formalizing what makes something a cause have not reached a consensus, new methods for inference show that we can make progress in this area in many practical cases. This article reviews core concepts in understanding and identifying causality and then reviews current computational methods for inference and explanation, focusing on inference from large-scale observational data. While the problem is not fully solved, we show that graphical models and Granger causality provide useful frameworks for inference and that a more recent approach based on temporal logic addresses some of the limitations of these methods.

show abstract

Section: Causal Inference and Explanationmentioning

confidence: 99%

A review of causal inference for biomedical informatics

Kleinberg

Hripcsak

2011

Journal of Biomedical Informatics

149

View full text Add to dashboard Cite

show abstract

“…26–31 In 2010, the FDA released a guidance for the use of Bayesian statistics in medical device clinical trials. 32 In 2013, United Network for Organ Sharing proposed the adoption of a new Bayesian methodology to better identify those transplant programs that may be underperforming in the area of patient and graft survival.…”

Section: Discussionmentioning

confidence: 99%

A New Bayesian Network-Based Risk Stratification Model for Prediction of Short-Term and Long-Term LVAD Mortality

et al. 2015

View full text Add to dashboard Cite

Existing risk assessment tools for patient selection for left ventricular assist devices (LVADs) such as the Destination Therapy Risk Score (DTRS) and HeartMate II Risk Score (HMRS) have limited predictive ability. This study aims to overcome the limitations of traditional statistical methods by performing the first application of Bayesian analysis to the comprehensive INTERMACS dataset and comparing it to HMRS. We retrospectively analyzed 8,050 continuous flow (CF) LVAD patients and 226 pre-implant variables. We then derived Bayesian models for mortality at each of five time endpoints post-implant (30 day, 90 day, 6 month, 1 year, and 2 year), achieving accuracies of 95, 90, 90, 83, and 78%, Kappa values of 0.43, 0.37, 0.37, 0.45, and 0.43, and area under the ROC of 91, 82, 82, 80 and 81% respectively. This was in comparison to the HMRS with an ROC of 57 and 60% at 90-days and 1-year, respectively. Pre-implant interventions such as dialysis, ECMO, and ventilators were major contributing risk markers. Bayesian models have the ability to reliably represent the complex causal relationships of multiple variables on clinical outcomes. Their potential to develop a reliable risk stratification tool for use in clinical decision making on LVAD patients encourages further investigation.

show abstract

“…DBNs, as well as Bayesian networks (BNs), are increasingly being used in clinical screening and treatment decision making. For example, DBNs and BNs have been used in the domain of nosocomial infections [21], pneumonia [22], cardiac surgery [23], gait analysis [24], osteoporosis [25], oral cancer [26], colon cancer [27], cervical cancer [28], and breast cancer [29, 30, 31, 32]. Notably, [33] proposed a Bayesian network for lung cancer built from both physical and biological data (biomarkers) for the prediction of local failure in non-small cell lung cancer (NSCLC) after radiotherapy.…”

Section: Introductionmentioning

confidence: 99%

Prediction of lung cancer incidence on the low-dose computed tomography arm of the National Lung Screening Trial: A dynamic Bayesian network

Petousis

Han

Aberle

et al. 2016

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Introduction Identifying high-risk lung cancer individuals at an early disease stage is the most effective way of improving survival. The landmark National Lung Screening Trial (NLST) demonstrated the utility of low-dose computed tomography (LDCT) imaging to reduce mortality (relative to x-ray screening). As a result of the NLST and other studies, imaging-based lung cancer screening programs are now being implemented. However, LDCT interpretation results in a high number of false positives. A set of dynamic Bayesian networks (DBN) were designed and evaluated to provide insight into how longitudinal data can be used to help inform lung cancer screening decisions. Methods The LDCT arm of the NLST dataset was used to build and explore five DBNs for high-risk individuals. Three of these DBNs were built using a backward construction process, and two using structure learning methods. All models employ demographic, smoking status, cancer history, family lung cancer history, exposure risk factors, comorbidities related to lung cancer, and LDCT screening outcome information. Given the uncertainty arising from lung cancer screening, a cancer state-space model based on lung cancer staging was utilized to characterize the cancer status of an individual over time. The models were evaluated on balanced training and test sets of cancer and non-cancer cases to deal with data imbalance and overfitting. Results Results were comparable to expert decisions. The average area under the curve (AUC) of the receiver operating characteristic (ROC) for the three intervention points of the NLST trial was higher than 0.75 for all models. Evaluation of the models on the complete LDCT arm of the NLST dataset (N = 25, 486) demonstrated satisfactory generalization. Consensus of predictions over similar cases is reported in concordance statistics between the models’ and the physicians’ predictions. The models’ predictive ability with respect to missing data was also evaluated with the sample of cases that missed the second screening exam of the trial (N = 417). The DBNs outperformed comparison models such as logistic regression and naïve Bayes. Conclusion The lung cancer screening DBNs demonstrated high discrimination and predictive power with the majority of cancer and non-cancer cases.

show abstract

A dynamic Bayesian network for diagnosing ventilator-associated pneumonia in ICU patients

Cited by 45 publications

References 8 publications

A review of causal inference for biomedical informatics

A review of causal inference for biomedical informatics

A New Bayesian Network-Based Risk Stratification Model for Prediction of Short-Term and Long-Term LVAD Mortality

Prediction of lung cancer incidence on the low-dose computed tomography arm of the National Lung Screening Trial: A dynamic Bayesian network

Contact Info

Product

Resources

About