A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis

Justin K Lui; Kari R Gillmeyer; Ruchika A Sangani; Robert J Smyth; Deepa M Gopal; Marcin A Trojanowski; Andreea M Bujor; Renda Soylemez Wiener; Michael P LaValley; Elizabeth S Klings

doi:10.1002/acr.24969

Back

A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis

Journal article

Peer reviewed

A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis

Justin K Lui, Kari R Gillmeyer, Ruchika A Sangani, Robert J Smyth, Deepa M Gopal, Marcin A Trojanowski, Andreea M Bujor, Renda Soylemez Wiener, Michael P LaValley and Elizabeth S Klings

Arthritis care & research (2010), Vol.75(7), pp.1462-1468

07/2023

DOI: 10.1002/acr.24969

PMCID: PMC9732142

PMID: 35678779

Files and links (1)

url

https://pmc.ncbi.nlm.nih.gov/articles/PMC9732142/pdf/nihms-1814768.pdfView

Open Access

Abstract

Diagnosis of pulmonary hypertension (PH) in systemic sclerosis (SSc) requires an invasive right heart catheterization (RHC), often based on an elevated estimated pulmonary artery systolic pressure on screening echocardiography. However, because of the poor specificity of echocardiography, a greater number of patients undergo RHC than necessary, exposing patients to potentially avoidable complication risks. The development of improved prediction models for PH in SSc may inform decision-making for RHC in these patients. We conducted a retrospective study of 130 patients with SSc; 66 (50.8%) were diagnosed with PH by RHC. We used data from pulmonary function testing, electrocardiography, echocardiography, and computed tomography to identify and compare the performance characteristics of 3 models predicting the presence of PH: 1) random forest, 2) classification and regression tree, and 3) logistic regression. For each model, we generated receiver operating curves and calculated sensitivity and specificity. We internally validated models using a train-test split of the data. The random forest model performed best with an area under the curve of 0.92 (95% confidence interval [95% CI] 0.83-1.00), sensitivity of 0.95 (95% CI 0.75-1.00), and specificity of 0.80 (95% CI 0.56-0.94). The 2 most important variables in our random forest model were pulmonary artery diameter on chest computed tomography and diffusing capacity for carbon monoxide on pulmonary function testing. In patients with SSc, a random forest model can aid in the detection of PH with high sensitivity and specificity and may allow for better patient selection for RHC, thereby minimizing patient risk.

Cardiac Catheterization - adverse effects

Humans

Hypertension, Pulmonary - diagnosis

Hypertension, Pulmonary - etiology

Pulmonary Artery - diagnostic imaging

Retrospective Studies

Scleroderma, Systemic - complications

Scleroderma, Systemic - diagnosis

Sensitivity and Specificity

Details

Title: Subtitle: A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis
Creators: Justin K Lui - Boston University
Kari R Gillmeyer - Boston University
Ruchika A Sangani - Boston University
Robert J Smyth - Boston University
Deepa M Gopal - Boston University
Marcin A Trojanowski - Boston University
Andreea M Bujor - Boston University
Renda Soylemez Wiener - Boston University
Michael P LaValley - Boston University
Elizabeth S Klings - Boston University
Resource Type: Journal article
Publication Details: Arthritis care & research (2010), Vol.75(7), pp.1462-1468
DOI: 10.1002/acr.24969
PMID: 35678779
PMCID: PMC9732142
NLM abbreviation: Arthritis Care Res (Hoboken)
ISSN: 2151-464X
eISSN: 2151-4658
Grant note: P30 AR072571 / NIAMS NIH HHS 5F32-HL-14923602 / NHLBI NIH HHS U1-EMC-78640800 / HRSA HHS R01 HL155955 / NHLBI NIH HHS F32 HL156614 / NHLBI NIH HHS F32 HL149236 / NHLBI NIH HHS UL1 TR001430 / NCATS NIH HHS 1R01-HL-15595501A1 / NHLBI NIH HHS 1F32-HL-15661401 / NHLBI NIH HHS 2UL-1-TR-00143005-A1 / NCATS NIH HHS T32 HL007035 / NHLBI NIH HHS 1UG3-HL-14319201A1 / NHLBI NIH HHS UG3 HL143192 / NHLBI NIH HHS
Language: English
Date published: 07/2023
Academic Unit: Pulmonary, Critical Care, and Occupational Medicine; Internal Medicine
Record Identifier: 9984695685702771

Metrics

13 Record Views

6 Times Cited - Web of Science