Prediction of clinical risk assessment and survival in chronic obstructive pulmonary disease with pulmonary hypertension

Abstract

Background: Patients with pulmonary hypertension (PH) and chronic obstructive pulmonary disease (COPD) have an increased risk of disease exacerbation and decreased survival. We aimed to develop and validate a non-invasive nomogram for predicting COPD associated with severe PH and a prognostic nomogram for patients with COPD and concurrent PH (COPD-PH).

Methods: This study included 535 patients with COPD-PH from six hospitals. A multivariate logistic regression analysis was used to analyse the risk factors for severe PH in patients with COPD and a multivariate Cox regression was used for the prognostic factors of COPD-PH. Performance was assessed using calibration, the area under the receiver operating characteristic curve and decision analysis curves. Kaplan-Meier curves were used for a survival analysis. The nomograms were developed as online network software.

Results: Tricuspid regurgitation velocity, right ventricular diameter, N-terminal pro-brain natriuretic peptide (NT-proBNP), the red blood cell count, New York Heart Association functional class and sex were non-invasive independent variables of severe PH in patients with COPD. These variables were used to construct a risk assessment nomogram with good discrimination. NT-proBNP, mean pulmonary arterial pressure, partial pressure of arterial oxygen, the platelet count and albumin were independent prognostic factors for COPD-PH and were used to create a predictive nomogram of overall survival rates.

Conclusions: The proposed nomograms based on a large sample size of patients with COPD-PH could be used as non-invasive clinical tools to enhance the risk assessment of severe PH in patients with COPD and for the prognosis of COPD-PH. Additionally, the online network has the potential to provide artificial intelligence-assisted diagnosis and treatment.

Highlights: A multicentre study with a large sample of chronic obstructive pulmonary disease (COPD) patients diagnosed with PH through right heart catheterisation. A non-invasive online clinical tool for assessing severe pulmonary hypertension (PH) in COPD. The first risk assessment tool was established for Chinese patients with COPD-PH.

Keywords: COPD; nomogram; pulmonary hypertension; survival.

FIGURE 1

Development and validation of the non‐invasive nomogram. (A) The nomogram incorporates six variables, with points allocated according to the scale for each variable. A total score could be easily calculated by adding each single score, and the total score would then be used to calculate the predicted probability of severe PH in COPD. (B (a, b)) Calibration curves for the non‐invasive nomogram in the training (a) and validation (b) cohorts. The calibration plot illustrates the accuracy of the original prediction (‘Apparent’; light dotted line) and bootstrap models (‘Bias‐corrected’; solid line) in predicting the probability of severe PH in COPD. The 45° straight line represents the perfect match between the actual and nomogram‐predicted probabilities. A closer distance between the two curves indicates higher accuracy. (C (a, b)) ROC curves of the non‐invasive nomogram, red blood cell count, tricuspid regurgitation velocity, NT‐proBNP, right ventricular diameter, sex and NYHA functional class in the training (a) and validation (b) cohorts. Red represents the non‐invasive nomogram, yellow represents red blood cell count, green represents tricuspid regurgitation velocity, dark blue represents NT‐proBNP, blue represents right ventricular diameter, purple represents sex and brown represents NYHA functional class. (D (a, b)) Violin plot analysis comparing the distribution of risk prediction probabilities for non‐severe PH versus severe PH in COPD groups in the training (a) and validation (b) cohorts. The predicted risk probabilities for severe PH groups in both cohorts were much higher than those for non‐severe PH groups. A violin plot and the depicted data are shown. Three lines within the plot show the first and third quartiles and the median of the dataset, whereas the width of the violin body indicates the density of data along the Y‐axis. The edges of the violins represent the minimum and maximum values of the dataset. COPD, chronic obstructive pulmonary disease; NT‐proBNP, N‐terminal pro‐brain natriuretic peptide; NYHA, New York Heart Association; PH, pulmonary hypertension.

FIGURE 2

Development and validation of the prognostic nomogram. (A) The nomogram incorporates five variables, with points allocated according to the scale for each variable. A total score could be easily calculated by adding each single score, and the total score was then used to calculate the predicted 1‐, 5‐ and 7‐year OS of COPD–PH. (B (a, b)) ROC curve of the 1‐, 5‐ and 7‐year survival prediction in the follow‐up (a) and validation cohorts (b). (C (a–c)) Calibration curves of the 1‐, 5‐ and 7‐year OS for COPD–PH in the follow‐up cohort. (D (a–c)) Calibration curves of the 1‐, 5‐ and 7‐year OS for COPD–PH in validation cohort. The light blue line indicates the ideal reference line where predicted probabilities would match the observed survival rates. The red dots are calculated by bootstrapping (resample: 1000) and represent the performance of the nomogram. The closer the solid red line is to the light blue line, the more accurately the model predicts survival. AUC, area under the curve; COPD, chronic obstructive pulmonary disease; NT‐proBNP, N‐terminal pro‐brain natriuretic peptide; OS, overall survival; PH, pulmonary hypertension; ROC, receiver operating characteristic.

FIGURE 3

Clinical usefulness of the prognostic nomogram. (A, B) The distribution plot of the risk score in the follow‐up (A) and validation cohorts (B). Patients are arranged from left to right in increasing order of risk score (a). The survival status of each patient (b). The Y‐axis represents the overall survival time. The colour code: blue for alive cases and red for dead cases. Heatmap of the expression levels of the five variables (c). (C, D) Decision curve analysis for the prognostic nomogram in the follow‐up (C) and validation cohorts (D). The Y‐axis indicates the net benefit, which is calculated by summing the benefits (true positives) and subtracting the harms (false positives). The X‐axis indicates the threshold probability. (E (a, b)) Kaplan–Meier overall survival curves for the low‐risk, middle‐risk and high‐risk COPD–PH patients stratified by the prognostic nomogram in the follow‐up (a) and validation cohorts (b). COPD, chronic obstructive pulmonary disease; mPAP, mean pulmonary arterial pressure; M, month; NT‐proBNP, N‐terminal pro‐brain natriuretic peptide; OS, overall survival; PaO₂, partial pressure of arterial oxygen; PH, pulmonary hypertension.