Risk stratification in pulmonary arterial hypertension using Bayesian analysis

Abstract

Background: Current risk stratification tools in pulmonary arterial hypertension (PAH) are limited in their discriminatory abilities, partly due to the assumption that prognostic clinical variables have an independent and linear relationship to clinical outcomes. We sought to demonstrate the utility of Bayesian network-based machine learning in enhancing the predictive ability of an existing state-of-the-art risk stratification tool, REVEAL 2.0.

Methods: We derived a tree-augmented naïve Bayes model (titled PHORA) to predict 1-year survival in PAH patients included in the REVEAL registry, using the same variables and cut-points found in REVEAL 2.0. PHORA models were validated internally (within the REVEAL registry) and externally (in the COMPERA and PHSANZ registries). Patients were classified as low-, intermediate- and high-risk (<5%, 5-20% and >10% 12-month mortality, respectively) based on the 2015 European Society of Cardiology/European Respiratory Society guidelines.

Results: PHORA had an area under the curve (AUC) of 0.80 for predicting 1-year survival, which was an improvement over REVEAL 2.0 (AUC 0.76). When validated in the COMPERA and PHSANZ registries, PHORA demonstrated an AUC of 0.74 and 0.80, respectively. 1-year survival rates predicted by PHORA were greater for patients with lower risk scores and poorer for those with higher risk scores (p<0.001), with excellent separation between low-, intermediate- and high-risk groups in all three registries.

Conclusion: Our Bayesian network-derived risk prediction model, PHORA, demonstrated an improvement in discrimination over existing models. This is reflective of the ability of Bayesian network-based models to account for the interrelationships between clinical variables on outcome, and tolerance to missing data elements when calculating predictions.

Conflict of interest statement

Conflict of interest: M.K. Kanwar reports grants from NIH/NHBLI, during the conduct of the study. Conflict of interest: M. Gomberg-Maitland reports consultancy/steering committee, data monitoring board work for Acceleron, Actelion, Complexa, Gossamer Bio, Reata, and Neuroderm; George Washington School of Medicine and Health Sciences has received grants for research from Altavant and United Therapeutics; and is a member of the scientific advisory board for United Therapeutics, outside the submitted work. Conflict of interest: M. Hoeper reports personal fees from Actelion, Bayer, MSD and Pfizer, outside the submitted work. Conflict of interest: C. Pausch has nothing to disclose. Conflict of interest: D. Pittrow reports personal fees from Actelion, Bayer, Amgen, Boehringer Ingelheim, Sanofi, MSD and Biogen, outside the submitted work. Conflict of interest: G. Strange reports grants from Actelion Pharmaceuticals, GlaxoSmithKline and Bayer Pharmaceuticals, during the conduct of the study. Conflict of interest: J.J. Anderson reports grants from GlaxoSmithKline, non-financial support from Actelion and Bayer, personal fees from AstraZeneca, outside the submitted work. Conflict of interest: C. Zhao is an employee of Actelion Pharmaceuticals US, Inc., a Janssen Pharmaceutical Company of Johnson & Johnson. Conflict of interest: J.V. Scott has nothing to disclose. Conflict of interest: M.J. Druzdzel is a partner at BayesFusion, LLC. Conflict of interest: J. Kraisangka has nothing to disclose. Conflict of interest: L. Lohmueller has nothing to disclose. Conflict of interest: J. Antaki reports grants from NIH/NHLBI (R01 HL134673), during the conduct of the study. Conflict of interest: R.L. Benza reports grants from NIH/NHLBI (R01 HL134673), Actelion, United Therapeutics and Bayer, during the conduct of the study.

Copyright ©ERS 2020.

Figures

Figure 1:

Structure of the Pulmonary Hypertension Outcomes Risk Assessment (PHORA) Bayesian network (BN) model, with conditional probability table (CPT) for survival

Figure 2:

Performance of the BN algorithm when internally validated in REVEAL (PHORA, AUC 0.80), and externally in PHSANZ (AUC 0.80) and COMPERA (AUC 0.74) registries

Figure 3:

Kaplan-Meier curves demonstrating PHORA’s risk stratification abilities into low, intermediate and high risk of 12-month mortality based on the 2015 ESC/ERS guidelines in REVEAL (A), COMPERA (B), and PHSANZ (C) registries

Figure 4

(A) Example of a PHORA model when some variables (highlighted in blue) are observed at baseline assessment. The values of these variables are noted in the dotted line box adjacent to each node. Variables in orange are yet to be reported as patient is undergoing work-up. (B) Updated PHORA model when additional parameters (previously in orange) are now available. Note change in the predicted outcome (survival at 12 months, green box) as additional data is input.

Figure 4

(A) Example of a PHORA model when some variables (highlighted in blue) are observed at baseline assessment. The values of these variables are noted in the dotted line box adjacent to each node. Variables in orange are yet to be reported as patient is undergoing work-up. (B) Updated PHORA model when additional parameters (previously in orange) are now available. Note change in the predicted outcome (survival at 12 months, green box) as additional data is input.

Figure 5

A screenshot of the webpage that will demonstrate the predicted clinical outcome (survival at 12 months). Outcomes as predicted by PHORA are shown as a blue bar, as predicted by REVEAL 2.0 as a red bar at 1 and 5 years, COMPERA risk stratification is shown in yellow and French non-invasive score as green. The clinical variables are shown at the bottom