Prognostic importance of Kidney, Heart and Interstitial lung diseases (KHI triad) in PH: A machine learning study.

ABSTRACT

BACKGROUND: Pulmonary hypertension (PH) is a heterogeneous, severe and progressive disease with an impact on quality of life and life-expectancy despite specific therapies. AIMS: (i) to compare prognosis significance of each PH subgroup in a cohort from a referral center, (ii) to identify phenotypically distinct high-risk PH patient using machine learning. METHODS: Patients with PH were included from 2002 to 2019 and routinely followed-up. We collected clinical, laboratory, imaging and hemodynamic variables. Four-year survival rate of each subgroups was then compared. Next, phenotypic domains were imputed with 5 eigenvectors for missing values and filtered if the Pearson correlation coefficient was>0.6. Thereafter, agglomerative hierarchical clustering was used for grouping phenotypic variables and patients a heat map was generated and participants were separated using Penalized Model-Based Clustering. P<0.05 was considered significant. RESULTS: 328 patients were prospectively included (mean age 63±18 yo, 46% male). PH secondary to left heart disease (PH-LHD) and lung disease (PH-LD) had a significantly increased mortality compared to pulmonary arterial hypertension (PAH) patients HR=2.43, 95%CI=(1.24-4.73) and 2.95, 95%CI=(1.43-6.07) respectively. 25 phenotypic domains were pinpointed and 3 phenogroups identified. Phenogroup 3 had a significantly increased mortality (log-rank P=0.046) compared to the others and was remarkable for predominant pulmonary disease in older male, accumulating cardiovascular risk factors, and simultaneous three major comorbidities coronary artery disease, chronic kidney disease and interstitial lung disease. CONCLUSION: PH-LHD and PH-LD has 2-fold and 3-fold increase in mortality, respectively compared with PAH. PH patients with simultaneous kidney-cardiac-pulmonary comorbidities were identified as having high-risk of mortality. Specific targeted therapy in this phenogroup should be prospectively evaluated.