Kanwar Manreet K, Gomberg-Maitland Mardi, Hoeper Marius, Pausch Christine, Pittrow David, Strange Geoff, Anderson James J, Zhao Carol, Scott Jacqueline V, Druzdzel Marek J, Kraisangka Jidapa, Lohmueller Lisa, Antaki James, Benza Raymond L
Cardiovascular Institute at Allegheny Health Network, Pittsburgh, PA, USA.
George Washington School of Medicine and Health Sciences, Washington, DC, USA.
Eur Respir J. 2020 Aug 27;56(2). doi: 10.1183/13993003.00008-2020. Print 2020 Aug.
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.
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.
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.
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.
肺动脉高压（PAH）当前的风险分层工具在区分能力方面存在局限性，部分原因在于假定预后临床变量与临床结局具有独立且线性的关系。我们试图证明基于贝叶斯网络的机器学习在增强现有先进风险分层工具REVEAL 2.0的预测能力方面的效用。
我们推导了一个树增强朴素贝叶斯模型（名为PHORA），以使用REVEAL 2.0中相同的变量和切点来预测REVEAL注册研究中PAH患者的1年生存率。PHORA模型在内部（在REVEAL注册研究中）和外部（在COMPERA和PHSANZ注册研究中）进行了验证。根据2015年欧洲心脏病学会/欧洲呼吸学会指南，将患者分为低、中、高风险组（12个月死亡率分别<5%、5 - 20%和>10%）。
PHORA预测1年生存率的曲线下面积（AUC）为0.80，优于REVEAL 2.0（AUC为0.76）。在COMPERA和PHSANZ注册研究中进行验证时，PHORA的AUC分别为0.74和0.80。PHORA预测的1年生存率在风险评分较低的患者中更高，在风险评分较高的患者中更低（p<0.001），在所有三个注册研究中，低、中、高风险组之间有良好的区分度。
我们基于贝叶斯网络得出的风险预测模型PHORA在区分能力上优于现有模型。这反映了基于贝叶斯网络的模型能够考虑临床变量与结局之间的相互关系，以及在计算预测时对缺失数据元素的耐受性。
