Search

A blood test identifying patients at increased risk of pulmonary hypertension (PH) could streamline the investigative pathway. The prospective, multicenter CIPHER study aimed to develop a microRNA-based signature for detecting PH in breathless patients and enrolled adults with a high suspicion of PH who had undergone right heart catheterization (RHC). The CIPHER-MRI study was added to assess the performance of this CIPHER signature in a population with low probability of having PH who underwent cardiac magnetic resonance imaging (cMRI) instead of RHC. The microRNA signature was developed using a penalized linear regression (LASSO) model. Data were modeled both with and without N-terminal pro-brain natriuretic peptide (NT-proBNP). Signature performance was assessed against predefined thresholds (lower 98.7% CI bound of ≥0.73 for sensitivity and ≥0.53 for specificity, based on a meta-analysis of echocardiographic data), using RHC as the true diagnosis. Overall, 926 CIPHER participants were screened and 888 were included in the analysis. Of 688 RHC-confirmed PH cases, approximately 40% were already receiving PH treatment. Fifty microRNA (from 311 investigated) were algorithmically selected to be included in the signature. Sensitivity [97.5% CI] of the signature was 0.85 [0.80-0.89] for microRNA-alone and 0.90 [0.86-0.93] for microRNA+NT-proBNP, and the corresponding specificities were 0.33 [0.24-0.44] and 0.28 [0.20-0.39]. Of 80 CIPHER-MRI participants with evaluable data, 7 were considered PH-positive by cMRI whereas 52 were considered PH-positive by the microRNA signature. Due to low specificity, the CIPHER miRNA-based signature for PH (either with or without NT-proBNP in model) did not meet the prespecified diagnostic threshold for the primary analysis., Competing Interests: Luke Howard has served as a member of the CIPHER steering committee for Janssen pharmaceutical companies of Johnson & Johnson, Gossamer Bio, and Lung Biotechnology; has received consulting fees from Altavant; has received research grants from Janssen pharmaceutical companies of Johnson & Johnson; has received speaker fees from Bayer PLC, Janssen pharmaceutical companies of Johnson & Johnson, and Merck; has received support for attending meetings and/or travel from Janssen pharmaceutical companies of Johnson & Johnson; has been a member of an advisory board for Acceleron, Janssen pharmaceutical companies of Johnson & Johnson, and Merck; and is a shareholder in iOWNA and Circular. David G. Kiely has served as a member of the CIPHER steering committee for Janssen pharmaceutical companies of Johnson & Johnson and his institution has received support from the National Institute of Health Research Sheffield Biomedical Research Centre as part of the support for the present manuscript. He has received consulting fees and honoraria for lectures, presentations, speakers bureaus, manuscript writing or educational events from Janssen pharmaceutical companies of Johnson & Johnson, Ferrer, Altavant, MSD, United Therapeutics, Gossamer, and Liquidia; has received support for attending meetings and/or travel from Janssen pharmaceutical companies of Johnson & Johnson, Ferrer, MSD and United Therapeutics; has participated on a Data Safety Monitoring Board of Advisory Board for Janssen pharmaceutical companies of Johnson & Johnson and MSD; is a member of the Clinical Reference Group for Specialized Respiratory Medicine (NHS England, unpaid); and is the lead of the UK National Audit of Pulmonary Hypertension (paid). David G. Kiely's institution has received grants or contracts from Janssen pharmaceutical companies of Johnson & Johnson, National Institute of Health Research Sheffield Biomedical Research Centre and Ferrer. Allan Lawrie has served has received payment for serving as a steering committee member for Janssen pharmaceutical companies of Johnson & Johnson (as part of the support for the present manuscript), has received support for attending meetings and/or travel from Janssen pharmaceutical companies of Johnson & Johnson. He receives funding from the British Heart Foundation through a Senior Basic Science Research Fellowship (FS/18/52/33808), the Imperial British Heart Foundation Imperial Centre for Research Excellence (RE/18/4/34215), Alexion Pharmaceuticals, and Apple Inc (Investigator Awards). Bradley A. Maron has served as a member of the CIPHER steering committee for Janssen pharmaceutical companies of Johnson & Johnson; and has received consultancy fees from Actelion Pharmaceuticals, Tenax, and Regeneron and grants from Deerfield, Boston Biomedical Innovation Center and the Cardiovascular Medical Research Education Foundation, He has two patents pending and one patent issued relevant to the submitted work. He has served as PI or co‐PI on various projects: 5R01HL139613‐03: PI on NIH R01 award focusing on molecular mechanisms that regulate vascular fibrosis in PAH ($1,748,134); NIH R01HL163960: Co‐PI on NIH R01 award using network medicine to prognosticate patients with PH ($286,861); U54HL119145 and Boston Biomedical Innovation Center (BBIC): PI on NIH‐funded project to develop an antibody therapeutic for CTEPH ($341,589); Brigham IGNITE award: PI on project to develop an antibody therapeutic for CTEPH ($50,000); NIH R01HL153502: PI on NIH‐funded project to clarify the mechanisms regulating NEDD9‐SMAD3 interactions in thrombotic vascular disease ($864,664); NIH R01HL155096‐01: PI on NIH‐funded project to clarify individualize the pathophenotype of patients with PH ($809,353). Ioana R. Preston has served as a member of the CIPHER steering committee for Janssen pharmaceutical companies of Johnson & Johnson, Merck, Liquidia; she has received consulting fees and honoraria for lectures, presentations, manuscript writing or educational events from Janssen pharmaceutical companies of Johnson & Johnson, Altavant, Gossamer, and United Therapeutics; has received support for attending meetings and/or travel from Janssen pharmaceutical companies of Johnson & Johnson, Merck, and United Therapeutics; Ioana Preston's institution has received grants or contracts from Janssen pharmaceutical companies of Johnson & Johnson, Merck, United Therapeutics, Respira, Bellerophon. Stephan Rosenkranz has served as a steering committee member for Janssen pharmaceutical companies of Johnson & Johnson (as part of the support for the present manuscript), has received remunerations for lectures and/or consultancy from Abbott, Acceleron, Actelion, Aerovate, Altavant, AOP, AstraZeneca, Bayer, Boehringer‐Ingelheim, Edwards, Ferrer, Gossamer, Janssen, Lilly, MSD, United Therapeutics, Vifor. His institution has received research grants from Actelion, AstraZeneca, Bayer, Janssen pharmaceutical companies of Johnson & Johnson, and Lempo. Mark Toshner has served as a steering committee member for Janssen pharmaceutical companies of Johnson & Johnson (as part of the support for the present manuscript), has received support for attending meetings and/or travel from Janssen pharmaceutical companies of Johnson & Johnson & GSK and has been a member of an advisory board for MorphogenIX. Martin R Wilkins has served as a member of the CIPHER steering committee for Janssen pharmaceutical companies of Johnson & Johnson and his institution received clinical research facility and Biomedical Research Centre infrastructure support from the National Institute of Health Research Sheffield Biomedical Research Centre as part of the support for the present manuscript. Martin R. Wilkins has received consulting fees from MorphogenIX, VIVUS, Janssen pharmaceutical companies of Johnson & Johnson, Kindaset, Chiesi, Aerami and BenevolentAI and has patents planned, issued and/or pending with Imperial Innovations (patent submitted for prognostic protein model and diagnostic miRNA model and patent for ZIP12 as a drug target); has participated in an adjudication committee for three clinical trials for Acceleron and in a study safety committee for GSK. Martin R. Wilkins institute has received grants or contracts from the British Heart Foundation (RE/18/4/34215 center support). Yiu‐Lian Fong was an employee of Janssen Pharmaceuticals Inc. at the time of study, and owns shares of stock/stock options in Johnson & Johnson. Cynthia Gargano is an employee of Janssen Pharmaceuticals Inc. and owns shares of stock/stock options in Johnson & Johnson. Debbie Quinn, Dimitri Stamatiadis, and Xavier Gitton are employees of Actelion Pharmaceuticals Ltd, a Janssen pharmaceutical company of Johnson & Johnson, and own shares of stock/stock options in Johnson & Johnson. Kelly M Chin has received payment for work on steering, advisory, or adjudication committee work with Arena, Bayer, Gossamer Bio, Janssen Pharmaceuticals of Johnson & Johnson, and Merck, payment for consulting work with Altavant, and her institution has received research support for clinical studies overseen by her from Altavant, Gossamer Bio, Janssen pharmaceutical companies of Johnson & Johnson, Merck, Pfizer, and United Therapeutics. Cheng He, Li Zhou, and Lihan Zhou are employees of MiRXES Lab and received support from Janssen Pharmaceuticals of Johnson & Johnson during the conduct of this study., (© 2024 The Author(s). Pulmonary Circulation published by John Wiley & Sons Ltd on behalf of Pulmonary Vascular Research Institute.)

Background: Pulmonary hypertension (PH) is life-threatening, and often diagnosed late in its course. We aimed to evaluate if a deep learning approach using electrocardiogram (ECG) data alone can detect PH and clinically important subtypes. We asked: does an automated deep learning approach to ECG interpretation detect PH and its clinically important subtypes?, Methods and Results: Adults with right heart catheterization or an echocardiogram within 90 days of an ECG at the University of California, San Francisco (2012-2019) were retrospectively identified as PH or non-PH. A deep convolutional neural network was trained on patients' 12-lead ECG voltage data. Patients were divided into training, development, and test sets in a ratio of 7:1:2. Overall, 5016 PH and 19,454 patients without PH were used in the study. The mean age at the time of ECG was 62.29 ± 17.58 years and 49.88% were female. The mean interval between ECG and right heart catheterization or echocardiogram was 3.66 and 2.23 days for patients with PH and patients without PH, respectively. In the test dataset, the model achieved an area under the receiver operating characteristic curve, sensitivity, and specificity, respectively of 0.89, 0.79, and 0.84 to detect PH; 0.91, 0.83, and 0.84 to detect precapillary PH; 0.88, 0.81, and 0.81 to detect pulmonary arterial hypertension, and 0.80, 0.73, and 0.76 to detect group 3 PH. We additionally applied the trained model on ECGs from participants in the test dataset that were obtained from up to 2 years before diagnosis of PH; the area under the receiver operating characteristic curve was 0.79 or greater., Conclusions: A deep learning ECG algorithm can detect PH and PH subtypes around the time of diagnosis and can detect PH using ECGs that were done up to 2 years before right heart catheterization/echocardiogram diagnosis. This approach has the potential to decrease diagnostic delays in PH., (Copyright © 2023 Elsevier Inc. All rights reserved.)