1
|
Jia H, Liao S, Zhu X, Liu W, Xu Y, Ge R, Zhu Y. Deep learning prediction of survival in patients with heart failure using chest radiographs. THE INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING 2024:10.1007/s10554-024-03177-w. [PMID: 38969836 DOI: 10.1007/s10554-024-03177-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Accepted: 06/28/2024] [Indexed: 07/07/2024]
Abstract
Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.
Collapse
Affiliation(s)
- Han Jia
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, Jiangsu, China
| | - Shengen Liao
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, Jiangsu, China
| | - Xiaomei Zhu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, Jiangsu, China
| | - Wangyan Liu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, Jiangsu, China
| | - Yi Xu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, Jiangsu, China.
| | - Rongjun Ge
- School of Instrument Science and Engineering, Southeast University, Nanjing, 210029, Jiangsu, China.
| | - Yinsu Zhu
- Department of Radiology, Jiangsu Institute of Cancer Research, Jiangsu Cancer Hospital, The Affiliated Cancer Hospital of Nanjing Medical University, 42 Baiziting, Nanjing, 210009, China.
| |
Collapse
|
2
|
DuBrock HM, Wagner TE, Carlson K, Carpenter CL, Awasthi S, Attia ZI, Frantz RP, Friedman PA, Kapa S, Annis J, Brittain EL, Hemnes AR, Asirvatham SJ, Babu M, Prasad A, Yoo U, Barve R, Selej M, Agron P, Kogan E, Quinn D, Dunnmon P, Khan N, Soundararajan V. An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension. Eur Respir J 2024; 64:2400192. [PMID: 38936966 PMCID: PMC11269769 DOI: 10.1183/13993003.00192-2024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2021] [Accepted: 05/19/2024] [Indexed: 06/29/2024]
Abstract
BACKGROUND Early diagnosis of pulmonary hypertension (PH) is critical for effective treatment and management. We aimed to develop and externally validate an artificial intelligence algorithm that could serve as a PH screening tool, based on analysis of a standard 12-lead ECG. METHODS The PH Early Detection Algorithm (PH-EDA) is a convolutional neural network developed using retrospective ECG voltage-time data, with patients classified as "PH-likely" or "PH-unlikely" (controls) based on right heart catheterisation or echocardiography. In total, 39 823 PH-likely patients and 219 404 control patients from Mayo Clinic were randomly split into training (48%), validation (12%) and test (40%) sets. ECGs taken within 1 month of PH diagnosis (diagnostic dataset) were used to train the PH-EDA at Mayo Clinic. Performance was tested on diagnostic ECGs within the test sets from Mayo Clinic (n=16 175/87 998 PH-likely/controls) and Vanderbilt University Medical Center (VUMC; n=6045/24 256 PH-likely/controls). In addition, performance was tested on ECGs taken 6-18 months (pre-emptive dataset), and up to 5 years prior to a PH diagnosis at both sites. RESULTS Performance testing yielded an area under the receiver operating characteristic curve (AUC) of 0.92 and 0.88 in the diagnostic test sets at Mayo Clinic and VUMC, respectively, and 0.86 and 0.81, respectively, in the pre-emptive test sets. The AUC remained a minimum of 0.79 at Mayo Clinic and 0.73 at VUMC up to 5 years before diagnosis. CONCLUSION The PH-EDA can detect PH at diagnosis and 6-18 months prior, demonstrating the potential to accelerate diagnosis and management of this debilitating disease.
Collapse
Affiliation(s)
- Hilary M DuBrock
- Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA
- Co-first authors
| | - Tyler E Wagner
- nference, Cambridge, MA, USA
- Anumana, Cambridge, MA, USA
- Co-first authors
| | | | | | - Samir Awasthi
- nference, Cambridge, MA, USA
- Anumana, Cambridge, MA, USA
| | - Zachi I Attia
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA
| | - Robert P Frantz
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA
| | - Paul A Friedman
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA
| | - Suraj Kapa
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA
| | - Jeffrey Annis
- Division of Cardiovascular Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Institute for Clinical and Translational Research, Nashville, TN, USA
| | - Evan L Brittain
- Division of Cardiovascular Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Anna R Hemnes
- Division of Allergy, Pulmonary and Critical Care Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | | | - Melwin Babu
- Anumana, Cambridge, MA, USA
- nference Labs, Bangalore, India
| | - Ashim Prasad
- Anumana, Cambridge, MA, USA
- nference Labs, Bangalore, India
| | | | - Rakesh Barve
- Anumana, Cambridge, MA, USA
- nference Labs, Bangalore, India
| | - Mona Selej
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | - Peter Agron
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | - Emily Kogan
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | - Deborah Quinn
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | - Preston Dunnmon
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | - Najat Khan
- Janssen Research and Development, LLC, a Johnson and Johnson company, Raritan, NJ, USA
| | | |
Collapse
|
3
|
Becerra-Muñoz VM, Gómez Sáenz JT, Escribano Subías P. The importance of data in Pulmonary Arterial Hypertension: from international registries to Machine Learning. Med Clin (Barc) 2024; 162:591-598. [PMID: 38383269 DOI: 10.1016/j.medcli.2023.12.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Revised: 12/03/2023] [Accepted: 12/05/2023] [Indexed: 02/23/2024]
Abstract
Real-world registries have been critical to building the scientific knowledge of rare diseases, including Pulmonary Arterial Hypertension (PAH). In the past 4 decades, a considerable number of registries on this condition have allowed to improve the pathology and its subgroupś definition, to advance in the understanding of its pathophysiology, to elaborate prognostic scales and to check the transferability of the results from clinical trials to clinical practice. However, in a moment where a huge amount of data from multiple sources is available, they are not always taken into account by the registries. For that reason, Machine Learning (ML) offer a unique opportunity to manage all these data and, finally, to obtain tools that may help to get an earlier diagnose, to help to deduce the prognosis and, in the end, to advance in Personalized Medicine. Thus, we present a narrative revision with the aims of, in one hand, summing up the aspects in which data extraction is important in rare diseases -focusing on the knowledge gained from PAH real-world registries- and, on the other hand, describing some of the achievements and the potential use of the ML techniques on PAH.
Collapse
Affiliation(s)
- Víctor Manuel Becerra-Muñoz
- Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, España; Servicio de Cardiología, Instituto de Investigación Biomédica de Málaga (IBIMA), Málaga, España; Hospital Universitario Virgen de la Victoria, Universidad de Málaga (UMA), Málaga, España.
| | - José Tomás Gómez Sáenz
- Centro de Salud de Nájera, La Rioja, España; Sociedad Española de Médicos de Atención Primaria (SEMERGEN), Madrid, España
| | - Pilar Escribano Subías
- Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, España; Hospital Universitario 12 de Octubre, Madrid, España
| |
Collapse
|
4
|
Stamate E, Piraianu AI, Ciobotaru OR, Crassas R, Duca O, Fulga A, Grigore I, Vintila V, Fulga I, Ciobotaru OC. Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years. Diagnostics (Basel) 2024; 14:1103. [PMID: 38893630 PMCID: PMC11172021 DOI: 10.3390/diagnostics14111103] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2024] [Revised: 05/12/2024] [Accepted: 05/23/2024] [Indexed: 06/21/2024] Open
Abstract
BACKGROUND Artificial intelligence (AI) can radically change almost every aspect of the human experience. In the medical field, there are numerous applications of AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, this fact being supported by the exponential increase in the number of publications in which the algorithms play an important role in data analysis, pattern discovery, identification of anomalies, and therapeutic decision making. Furthermore, with technological development, there have appeared new models of machine learning (ML) and deep learning (DP) that are capable of exploring various applications of AI in cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional cardiology, and many others. In this sense, the present article aims to provide a general vision of the current state of AI use in cardiology. RESULTS We identified and included a subset of 200 papers directly relevant to the current research covering a wide range of applications. Thus, this paper presents AI applications in cardiovascular imaging, arithmology, clinical or emergency cardiology, cardiovascular prevention, and interventional procedures in a summarized manner. Recent studies from the highly scientific literature demonstrate the feasibility and advantages of using AI in different branches of cardiology. CONCLUSIONS The integration of AI in cardiology offers promising perspectives for increasing accuracy by decreasing the error rate and increasing efficiency in cardiovascular practice. From predicting the risk of sudden death or the ability to respond to cardiac resynchronization therapy to the diagnosis of pulmonary embolism or the early detection of valvular diseases, AI algorithms have shown their potential to mitigate human error and provide feasible solutions. At the same time, limits imposed by the small samples studied are highlighted alongside the challenges presented by ethical implementation; these relate to legal implications regarding responsibility and decision making processes, ensuring patient confidentiality and data security. All these constitute future research directions that will allow the integration of AI in the progress of cardiology.
Collapse
Affiliation(s)
- Elena Stamate
- Department of Cardiology, Emergency University Hospital of Bucharest, 050098 Bucharest, Romania; (E.S.); (V.V.)
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
| | - Alin-Ionut Piraianu
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
| | - Oana Roxana Ciobotaru
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Railway Hospital Galati, 800223 Galati, Romania
| | - Rodica Crassas
- Emergency County Hospital Braila, 810325 Braila, Romania;
| | - Oana Duca
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Emergency County Hospital Braila, 810325 Braila, Romania;
| | - Ana Fulga
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei Street, 800578 Galati, Romania
| | - Ionica Grigore
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Emergency County Hospital Braila, 810325 Braila, Romania;
| | - Vlad Vintila
- Department of Cardiology, Emergency University Hospital of Bucharest, 050098 Bucharest, Romania; (E.S.); (V.V.)
- Clinical Department of Cardio-Thoracic Pathology, University of Medicine and Pharmacy “Carol Davila” Bucharest, 37 Dionisie Lupu Street, 4192910 Bucharest, Romania
| | - Iuliu Fulga
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei Street, 800578 Galati, Romania
| | - Octavian Catalin Ciobotaru
- Faculty of Medicine and Pharmacy, University “Dunarea de Jos” of Galati, 35 AI Cuza Street, 800010 Galati, Romania; (O.D.); (A.F.); (I.G.); (I.F.); (O.C.C.)
- Railway Hospital Galati, 800223 Galati, Romania
| |
Collapse
|
5
|
Hirata Y, Tsuji T, Kotoku J, Sata M, Kusunose K. Echocardiographic artificial intelligence for pulmonary hypertension classification. Heart 2024; 110:586-593. [PMID: 38296266 DOI: 10.1136/heartjnl-2023-323320] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Accepted: 11/30/2023] [Indexed: 03/24/2024] Open
Abstract
OBJECTIVE The classification of pulmonary hypertension (PH) is crucial for determining the appropriate therapeutic strategy. We investigated whether machine learning (ML) algorithms may assist in echocardiographic PH prediction, where current guidelines recommend integrating several different parameters. METHODS We obtained physical and echocardiographic data from 885 patients who underwent right heart catheterisation (RHC). Patients were classified into three groups: non-PH, precapillary PH and postcapillary PH, based on values obtained from RHC. Using 24 parameters, we created predictive models employing four different classifiers and selected the one with the highest area under the curve. We then calculated the macro-average classification accuracy for PH on the derivation cohort (n=720) and prospective validation data set (n=165), comparing the results with guideline-based echocardiographic assessment obtained from each cohort. RESULTS Logistic regression with elastic net regularisation had the highest classification accuracy, with areas under the curves of 0.789, 0.766 and 0.742 for normal, precapillary PH and postcapillary PH, respectively. The ML model demonstrated significantly better predictive accuracy than the guideline-based echocardiographic assessment in the derivation cohort (59.4% vs 51.6%, p<0.01). In the independent validation data set, the ML model's accuracy was comparable to the guideline-based PH classification (59.4% vs 57.8%, p=0.638). CONCLUSIONS This preliminary study suggests promising potential for our ML model in predicting echocardiographic PH. Further research and validation are needed to fully assess its clinical utility in PH diagnosis and treatment decision-making.
Collapse
Affiliation(s)
- Yukina Hirata
- Ultrasound Examination center, Tokushima University Hospital, Tokushima, Japan
| | - Takumasa Tsuji
- Department of Radiological Technology, Teikyo University, Itabashi-ku, Tokyo, Japan
| | - Jun'ichi Kotoku
- Department of Radiological Technology, Teikyo University, Itabashi-ku, Tokyo, Japan
| | - Masataka Sata
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| | - Kenya Kusunose
- Department of Cardiovascular Medicine, Nephrology, and Neurology, University of the Ryukyus, Uehara, Okinawa, Japan
| |
Collapse
|
6
|
Singh N, Mehta S. Artificial intelligence to improve the diagnosis of pulmonary hypertension: promises and pitfalls. Heart 2024; 110:541-542. [PMID: 38360056 DOI: 10.1136/heartjnl-2023-323693] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/17/2024] Open
Affiliation(s)
- Namisha Singh
- Southwest Ontario PH Clinic, Medicine/Respirology, London Health Sciences Centre, University of Western Ontario, London, Ontario, Canada
| | - Sanjay Mehta
- Southwest Ontario PH Clinic, Medicine/Respirology, London Health Sciences Centre, University of Western Ontario, London, Ontario, Canada
- Pulmonary Hypertension Association of Canada, Vancouver, British Columbia, Canada
| |
Collapse
|
7
|
Imai S, Sakao S, Nagata J, Naito A, Sekine A, Sugiura T, Shigeta A, Nishiyama A, Yokota H, Shimizu N, Sugawara T, Nomi T, Honda S, Ogaki K, Tanabe N, Baba T, Suzuki T. Artificial intelligence-based model for predicting pulmonary arterial hypertension on chest x-ray images. BMC Pulm Med 2024; 24:101. [PMID: 38413932 PMCID: PMC10898025 DOI: 10.1186/s12890-024-02891-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Accepted: 02/01/2024] [Indexed: 02/29/2024] Open
Abstract
BACKGROUND Pulmonary arterial hypertension is a serious medical condition. However, the condition is often misdiagnosed or a rather long delay occurs from symptom onset to diagnosis, associated with decreased 5-year survival. In this study, we developed and tested a deep-learning algorithm to detect pulmonary arterial hypertension using chest X-ray (CXR) images. METHODS From the image archive of Chiba University Hospital, 259 CXR images from 145 patients with pulmonary arterial hypertension and 260 CXR images from 260 control patients were identified; of which 418 were used for training and 101 were used for testing. Using the testing dataset for each image, the algorithm outputted a numerical value from 0 to 1 (the probability of the pulmonary arterial hypertension score). The training process employed a binary cross-entropy loss function with stochastic gradient descent optimization (learning rate parameter, α = 0.01). In addition, using the same testing dataset, the algorithm's ability to identify pulmonary arterial hypertension was compared with that of experienced doctors. RESULTS The area under the curve (AUC) of the receiver operating characteristic curve for the detection ability of the algorithm was 0.988. Using an AUC threshold of 0.69, the sensitivity and specificity of the algorithm were 0.933 and 0.982, respectively. The AUC of the algorithm's detection ability was superior to that of the doctors. CONCLUSION The CXR image-derived deep-learning algorithm had superior pulmonary arterial hypertension detection capability compared with that of experienced doctors.
Collapse
Affiliation(s)
- Shun Imai
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan.
- Pulmonary Hypertension Center, Chibaken Saiseikai Narashino Hospital, Chiba, Japan.
| | - Seiichiro Sakao
- Department of Pulmonary Medicine, School of Medicine, International University of Health and Welfare (IUHW), Chiba, Japan
| | - Jun Nagata
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
- Pulmonary Hypertension Center, Chibaken Saiseikai Narashino Hospital, Chiba, Japan
| | - Akira Naito
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
| | - Ayumi Sekine
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
| | - Toshihiko Sugiura
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
- Pulmonary Hypertension Center, Chibaken Saiseikai Narashino Hospital, Chiba, Japan
| | - Ayako Shigeta
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
| | - Akira Nishiyama
- Department of Radiology, Tsudanuma Central General Hospital, Chiba, Japan
| | - Hajime Yokota
- Diagnostic Radiology and Radiation Oncology, Graduate School of Medicine, Chiba University, Chiba, Japan
| | | | - Takeshi Sugawara
- Chiba University Hospital Translational Research and Development Center, Chiba, Japan
| | | | | | | | - Nobuhiro Tanabe
- Pulmonary Hypertension Center, Chibaken Saiseikai Narashino Hospital, Chiba, Japan
| | - Takayuki Baba
- Department of Ophthalmology and Visual Science, Graduate School of Medicine, Chiba University, Chiba, Japan
| | - Takuji Suzuki
- Department of Respirology, Graduate School of Medicine, Chiba University, Chiba, Japan
| |
Collapse
|
8
|
Ragnarsdottir H, Ozkan E, Michel H, Chin-Cheong K, Manduchi L, Wellmann S, Vogt JE. Deep Learning Based Prediction of Pulmonary Hypertension in Newborns Using Echocardiograms. Int J Comput Vis 2024; 132:2567-2584. [PMID: 38911323 PMCID: PMC11186939 DOI: 10.1007/s11263-024-01996-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Accepted: 01/04/2024] [Indexed: 06/25/2024]
Abstract
Pulmonary hypertension (PH) in newborns and infants is a complex condition associated with several pulmonary, cardiac, and systemic diseases contributing to morbidity and mortality. Thus, accurate and early detection of PH and the classification of its severity is crucial for appropriate and successful management. Using echocardiography, the primary diagnostic tool in pediatrics, human assessment is both time-consuming and expertise-demanding, raising the need for an automated approach. Little effort has been directed towards automatic assessment of PH using echocardiography, and the few proposed methods only focus on binary PH classification on the adult population. In this work, we present an explainable multi-view video-based deep learning approach to predict and classify the severity of PH for a cohort of 270 newborns using echocardiograms. We use spatio-temporal convolutional architectures for the prediction of PH from each view, and aggregate the predictions of the different views using majority voting. Our results show a mean F1-score of 0.84 for severity prediction and 0.92 for binary detection using 10-fold cross-validation and 0.63 for severity prediction and 0.78 for binary detection on the held-out test set. We complement our predictions with saliency maps and show that the learned model focuses on clinically relevant cardiac structures, motivating its usage in clinical practice. To the best of our knowledge, this is the first work for an automated assessment of PH in newborns using echocardiograms.
Collapse
Affiliation(s)
- Hanna Ragnarsdottir
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, 8092 Zürich, Switzerland
| | - Ece Ozkan
- Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, 43 Vassar Street, Cambridge, MA 02139 USA
| | - Holger Michel
- Department of Neonatology, University Children’s Hospital Regensburg (KUNO), Hospital St. Hedwig of the Order of St. John, University of Regensburg, Regensburg, Germany
| | - Kieran Chin-Cheong
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, 8092 Zürich, Switzerland
| | - Laura Manduchi
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, 8092 Zürich, Switzerland
| | - Sven Wellmann
- Department of Neonatology, University Children’s Hospital Regensburg (KUNO), Hospital St. Hedwig of the Order of St. John, University of Regensburg, Regensburg, Germany
| | - Julia E. Vogt
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, 8092 Zürich, Switzerland
| |
Collapse
|
9
|
Averjanovaitė V, Gumbienė L, Zeleckienė I, Šileikienė V. Unmasking a Silent Threat: Improving Pulmonary Hypertension Screening Methods for Interstitial Lung Disease Patients. MEDICINA (KAUNAS, LITHUANIA) 2023; 60:58. [PMID: 38256318 PMCID: PMC10820938 DOI: 10.3390/medicina60010058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Revised: 12/23/2023] [Accepted: 12/26/2023] [Indexed: 01/24/2024]
Abstract
This article provides a comprehensive overview of the latest literature on the diagnostics and treatment of pulmonary hypertension (PH) associated with interstitial lung disease (ILD). Heightened suspicion for PH arises when the advancement of dyspnoea in ILD patients diverges from the expected pattern of decline in pulmonary function parameters. The complexity of PH associated with ILD (PH-ILD) diagnostics is emphasized by the limitations of transthoracic echocardiography in the ILD population, necessitating the exploration of alternative diagnostic approaches. Cardiac magnetic resonance imaging (MRI) emerges as a promising tool, offering insights into hemodynamic parameters and providing valuable prognostic information. The potential of biomarkers, alongside pulmonary function and cardiopulmonary exercise tests, is explored for enhanced diagnostic and prognostic precision. While specific treatments for PH-ILD remain limited, recent studies on inhaled treprostinil provide new hope for improved patient outcomes.
Collapse
Affiliation(s)
| | - Lina Gumbienė
- Clinic of Cardiac and Vascular Diseases, Faculty of Medicine, Institute of Clinical Medicine, Vilnius University, LT-03101 Vilnius, Lithuania;
| | | | - Virginija Šileikienė
- Clinic of Chest Diseases, Immunology and Allergology, Faculty of Medicine, Institute of Clinical Medicine, Vilnius University, LT-03101 Vilnius, Lithuania;
| |
Collapse
|
10
|
Farina JM, Pereyra M, Mahmoud AK, Scalia IG, Abbas MT, Chao CJ, Barry T, Ayoub C, Banerjee I, Arsanjani R. Artificial Intelligence-Based Prediction of Cardiovascular Diseases from Chest Radiography. J Imaging 2023; 9:236. [PMID: 37998083 PMCID: PMC10672462 DOI: 10.3390/jimaging9110236] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Revised: 10/18/2023] [Accepted: 10/24/2023] [Indexed: 11/25/2023] Open
Abstract
Chest radiography (CXR) is the most frequently performed radiological test worldwide because of its wide availability, non-invasive nature, and low cost. The ability of CXR to diagnose cardiovascular diseases, give insight into cardiac function, and predict cardiovascular events is often underutilized, not clearly understood, and affected by inter- and intra-observer variability. Therefore, more sophisticated tests are generally needed to assess cardiovascular diseases. Considering the sustained increase in the incidence of cardiovascular diseases, it is critical to find accessible, fast, and reproducible tests to help diagnose these frequent conditions. The expanded focus on the application of artificial intelligence (AI) with respect to diagnostic cardiovascular imaging has also been applied to CXR, with several publications suggesting that AI models can be trained to detect cardiovascular conditions by identifying features in the CXR. Multiple models have been developed to predict mortality, cardiovascular morphology and function, coronary artery disease, valvular heart diseases, aortic diseases, arrhythmias, pulmonary hypertension, and heart failure. The available evidence demonstrates that the use of AI-based tools applied to CXR for the diagnosis of cardiovascular conditions and prognostication has the potential to transform clinical care. AI-analyzed CXRs could be utilized in the future as a complimentary, easy-to-apply technology to improve diagnosis and risk stratification for cardiovascular diseases. Such advances will likely help better target more advanced investigations, which may reduce the burden of testing in some cases, as well as better identify higher-risk patients who would benefit from earlier, dedicated, and comprehensive cardiovascular evaluation.
Collapse
Affiliation(s)
- Juan M. Farina
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Milagros Pereyra
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Ahmed K. Mahmoud
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Isabel G. Scalia
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Mohammed Tiseer Abbas
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Chieh-Ju Chao
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Timothy Barry
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Chadi Ayoub
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| | - Imon Banerjee
- Department of Radiology, Mayo Clinic, Phoenix, AZ 85054, USA;
| | - Reza Arsanjani
- Department of Cardiovascular Medicine, Mayo Clinic, Phoenix, AZ 85054, USA (M.P.); (M.T.A.); (T.B.)
| |
Collapse
|
11
|
Tsuji T, Hirata Y, Kusunose K, Sata M, Kumagai S, Shiraishi K, Kotoku J. Classification of chest X-ray images by incorporation of medical domain knowledge into operation branch networks. BMC Med Imaging 2023; 23:62. [PMID: 37161392 PMCID: PMC10169130 DOI: 10.1186/s12880-023-01019-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 05/02/2023] [Indexed: 05/11/2023] Open
Abstract
BACKGROUND This study was conducted to alleviate a common difficulty in chest X-ray image diagnosis: The attention region in a convolutional neural network (CNN) does not often match the doctor's point of focus. The method presented herein, which guides the area of attention in CNN to a medically plausible region, can thereby improve diagnostic capabilities. METHODS The model is based on an attention branch network, which has excellent interpretability of the classification model. This model has an additional new operation branch that guides the attention region to the lung field and heart in chest X-ray images. We also used three chest X-ray image datasets (Teikyo, Tokushima, and ChestX-ray14) to evaluate the CNN attention area of interest in these fields. Additionally, after devising a quantitative method of evaluating improvement of a CNN's region of interest, we applied it to evaluation of the proposed model. RESULTS Operation branch networks maintain or improve the area under the curve to a greater degree than conventional CNNs do. Furthermore, the network better emphasizes reasonable anatomical parts in chest X-ray images. CONCLUSIONS The proposed network better emphasizes the reasonable anatomical parts in chest X-ray images. This method can enhance capabilities for image interpretation based on judgment.
Collapse
Affiliation(s)
- Takumasa Tsuji
- Graduate School of Medical Care and Technology, Teikyo University, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan
| | - Yukina Hirata
- Ultrasound Examination Center, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Kenya Kusunose
- Department of Cardiovascular Medicine, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Masataka Sata
- Department of Cardiovascular Medicine, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Shinobu Kumagai
- Central Radiology Division, Teikyo University Hospital, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8606, Japan
| | - Kenshiro Shiraishi
- Department of Radiology, Teikyo University School of Medicine, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan
| | - Jun'ichi Kotoku
- Graduate School of Medical Care and Technology, Teikyo University, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan.
- Central Radiology Division, Teikyo University Hospital, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8606, Japan.
| |
Collapse
|
12
|
Lou YS, Lin CS, Fang WH, Lee CC, Lin C. Extensive deep learning model to enhance electrocardiogram application via latent cardiovascular feature extraction from identity identification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 231:107359. [PMID: 36738606 DOI: 10.1016/j.cmpb.2023.107359] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/21/2022] [Revised: 12/22/2022] [Accepted: 01/17/2023] [Indexed: 06/18/2023]
Abstract
BACKGROUND AND OBJECTIVE Deep learning models (DLMs) have been successfully applied in biomedicine primarily using supervised learning with large, annotated databases. However, scarce training resources limit the potential of DLMs for electrocardiogram (ECG) analysis. METHODS We have developed a novel pre-training strategy for unsupervised identity identification with an area under the receiver operating characteristic curve (AUC) >0.98. Accordingly, a DLM pre-trained with identity identification can be applied to 70 patient characteristic predictions using transfer learning (TL). These ECG-based patient characteristics were then used for cardiovascular disease (CVD) risk prediction. The DLMs were trained using 507,729 ECGs from 222,473 patients and validated using two independent validation sets (n = 27,824/31,925). RESULTS The DLMs using our method exhibited better performance than directly trained DLMs. Additionally, our DLM performed better than those of previous studies in terms of gender (AUC [internal/external] = 0.982/0.968), age (correlation = 0.886/0.892), low ejection fraction (AUC = 0.942/0.951), and critical markers not addressed previously, including high B-type natriuretic peptide (AUC = 0.921/0.899). Additionally, approximately 50% of the ECG-based characteristics provided significantly more prediction information for cardiovascular risk than real characteristics. CONCLUSIONS This is the first study to use identity identification as a pre-training task for TL in ECG analysis. An extensive exploration of the relationship between ECG and 70 patient characteristics was conducted. Our DLM-enhanced ECG interpretation system extensively advanced ECG-related patient characteristic prediction and mortality risk management for cardiovascular diseases.
Collapse
Affiliation(s)
- Yu-Sheng Lou
- Graduate Institutes of Life Sciences, National Defense Medical Center, Taipei, Taiwan; School of Public Health, National Defense Medical Center, Taipei, Taiwan
| | - Chin-Sheng Lin
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.; Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C
| | - Wen-Hui Fang
- Department of Family and Community Medicine, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C
| | - Chia-Cheng Lee
- Department of Medical Informatics, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.; Division of Colorectal Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C
| | - Chin Lin
- Graduate Institutes of Life Sciences, National Defense Medical Center, Taipei, Taiwan; School of Public Health, National Defense Medical Center, Taipei, Taiwan; Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C.; School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C..
| |
Collapse
|
13
|
Mamalakis M, Dwivedi K, Sharkey M, Alabed S, Kiely D, Swift AJ. A transparent artificial intelligence framework to assess lung disease in pulmonary hypertension. Sci Rep 2023; 13:3812. [PMID: 36882484 PMCID: PMC9990015 DOI: 10.1038/s41598-023-30503-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Accepted: 02/24/2023] [Indexed: 03/09/2023] Open
Abstract
Recent studies have recognized the importance of characterizing the extent of lung disease in pulmonary hypertension patients by using Computed Tomography. The trustworthiness of an artificial intelligence system is linked with the depth of the evaluation in functional, operational, usability, safety and validation dimensions. The safety and validation of an artificial tool is linked to the uncertainty estimation of the model's prediction. On the other hand, the functionality, operation and usability can be achieved by explainable deep learning approaches which can verify the learning patterns and use of the network from a generalized point of view. We developed an artificial intelligence framework to map the 3D anatomical models of patients with lung disease in pulmonary hypertension. To verify the trustworthiness of the framework we studied the uncertainty estimation of the network's prediction, and we explained the learning patterns of the network. Therefore, a new generalized technique combining local explainable and interpretable dimensionality reduction approaches (PCA-GradCam, PCA-Shape) was developed. Our open-source software framework was evaluated in unbiased validation datasets achieving accurate, robust and generalized results.
Collapse
Affiliation(s)
- Michail Mamalakis
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK.
- Department of Computer Science, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK.
- Insigneo Institute for in silico Medicine, University of Sheffield, The Pam Liversidge Building, Sheffield, S1 3JD, UK.
| | - Krit Dwivedi
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK
- Insigneo Institute for in silico Medicine, University of Sheffield, The Pam Liversidge Building, Sheffield, S1 3JD, UK
| | - Michael Sharkey
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK
| | - Samer Alabed
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK
- Insigneo Institute for in silico Medicine, University of Sheffield, The Pam Liversidge Building, Sheffield, S1 3JD, UK
| | - David Kiely
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK
- Department of Cardiology, University of Sheffield, Sheffield Teaching Hospitals Sheffield, Sheffield, S5 7AU, UK
| | - Andrew J Swift
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Beech Hill Rd, Sheffield, S10 2RX, UK.
- Insigneo Institute for in silico Medicine, University of Sheffield, The Pam Liversidge Building, Sheffield, S1 3JD, UK.
| |
Collapse
|
14
|
Langlais EL, Avram R. Overcoming Diagnostic Delays in Pulmonary Hypertension with Deep Learning ECG Analysis. J Card Fail 2023:S1071-9164(23)00063-5. [PMID: 36878352 DOI: 10.1016/j.cardfail.2023.02.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Accepted: 02/08/2023] [Indexed: 03/07/2023]
Key Words
- 95% CI, 95(th) percentile confidence interval
- AI, artificial intelligence
- AUC, area under the receiver operating characteristic curve
- ECG, electrocardiogram
- ICD, International Classification of Disease
- NPV, negative predictive value
- PH, pulmonary hypertension
- PPV, positive predictive value
- RHC, right heart catheterization
- mPAP, mean pulmonary arterial pressure
Collapse
Affiliation(s)
- Elodie Labrecque Langlais
- Division of Cardiology, Department of Medicine, Montreal Heart Institute, University of Montreal, QC, Canada
| | - Robert Avram
- Département de Génie Biomédical, Polytechnique Montréal, Montréal, QC, Canada.
| |
Collapse
|
15
|
Kogan E, Didden EM, Lee E, Nnewihe A, Stamatiadis D, Mataraso S, Quinn D, Rosenberg D, Chehoud C, Bridges C. A machine learning approach to identifying patients with pulmonary hypertension using real-world electronic health records. Int J Cardiol 2023; 374:95-99. [PMID: 36528138 DOI: 10.1016/j.ijcard.2022.12.016] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/24/2022] [Revised: 12/06/2022] [Accepted: 12/08/2022] [Indexed: 12/15/2022]
Abstract
BACKGROUND This study aimed to develop a machine learning (ML) model to identify patients who are likely to have pulmonary hypertension (PH), using a large patient-level US-based electronic health record (EHR) database. METHODS A gradient boosting model, XGBoost, was developed using data from Optum's US-based de-identified EHR dataset (2007-2019). PH and disease control adult patients were identified using diagnostic, treatment and procedure codes and were randomly split into the training (90%) or test set (10%). Model features included patient demographics, physician visits, diagnoses, procedures, prescriptions, and laboratory test results. SHapley Additive exPlanations values were used to determine feature importance. RESULTS We identified 11,279,478 control and 115,822 PH patients (mean age, respectively: 62 and 68 years, both 53% female). The final model used 165 features, with the most important predictive features including diagnosis of heart failure, shortness of breath and atrial fibrillation. The model predicted PH with an area under the receiver operating characteristic curve (AUROC) of 0.92. AUROC remained above 0.80 for the prediction of PH up to and beyond 18 months before diagnosis. Among the PH patients, we also identified 955 pulmonary arterial hypertension (PAH) and 1432 chronic thromboembolic pulmonary hypertension (CTEPH) patients, and the range of AUROCs obtained for these cohorts was 0.79-0.90 and 0.87-0.96, respectively. CONCLUSIONS This model to detect PH based on patients' EHR records is viable and performs well in subgroups of PAH and CTEPH patients. This approach has the potential to improve patient outcomes by reducing diagnostic delay in PH.
Collapse
Affiliation(s)
- Emily Kogan
- Janssen Pharmaceuticals Inc., Spring House, PA, USA.
| | - Eva-Maria Didden
- Actelion Pharmaceuticals Ltd, a Janssen Pharmaceutical Company of Johnson & Johnson, Allschwil, Switzerland, Global Epidemiology Department
| | - Eileen Lee
- Janssen Pharmaceuticals Inc., Spring House, PA, USA
| | | | - Dimitri Stamatiadis
- Actelion Pharmaceuticals Ltd, a Janssen Pharmaceutical Company of Johnson & Johnson, Allschwil, Switzerland, Global R&D Department
| | | | | | - Daniel Rosenberg
- Actelion Pharmaceuticals Ltd, a Janssen Pharmaceutical Company of Johnson & Johnson, Allschwil, Switzerland, Global Epidemiology Department
| | | | | |
Collapse
|
16
|
Didden E, Lee E, Wyckmans J, Quinn D, Perchenet L. Time to diagnosis of pulmonary hypertension and diagnostic burden: A retrospective analysis of nationwide US healthcare data. Pulm Circ 2023; 13:e12188. [PMID: 36694845 PMCID: PMC9843478 DOI: 10.1002/pul2.12188] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Revised: 12/21/2022] [Accepted: 12/26/2022] [Indexed: 01/09/2023] Open
Abstract
The main aim of this analysis was to investigate time from symptom onset (chronic unexplained dyspnoea [CUD]) to diagnosis of Group 1 pulmonary hypertension (PH)-pulmonary arterial hypertension (PAH)-and to characterize healthcare resource utilization leading up to diagnosis using a nationwide US claims and an electronic health record (EHR) database from Optum©. Eligible patients were ≥18 years old at first CUD diagnosis (index event) and had a PAH diagnosis on or after index date. Based on administrative codes, PAH was defined as right heart catheterization (RHC), ≥ 2 PAH diagnoses (1 within a year of RHC), and ≥1 post-RHC prescription for PAH treatment. All values are median (1st quartile-3rd quartile) unless otherwise stated. Of 854,722 patients with CUD in the claims database, 582 (0.1%) had PAH. Time from CUD to PAH diagnosis was 2.26 (0.73-4.22) years. PAH patients experienced 3 (2-4) transthoracic echocardiograms (TTEs), 6 (3-12) specialist visits, and 2 (1-4) hospitalizations during the diagnostic interval. Almost one-third of patients (29%) waited 10 months or more to have a TTE. Findings from the EHR database were broadly similar. Resource utilization during the diagnostic interval was also analyzed in an overall PH cohort: findings were generally similar to the PAH cohort (2 [1-3] TTEs, 4 [2-9] specialist visits and 2 [1-4] hospitalizations). These data indicate a delay in the diagnostic pathway for PAH, and illustrate the burden associated with PAH diagnosis.
Collapse
Affiliation(s)
| | - Eileen Lee
- Janssen Research & DevelopmentSpring HousePennsylvaniaUSA
| | | | | | | |
Collapse
|
17
|
van der Bijl P, Bax JJ. Using deep learning to diagnose pulmonary hypertension. Eur Heart J Cardiovasc Imaging 2022; 23:1457-1458. [PMID: 35906842 DOI: 10.1093/ehjci/jeac148] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Pieter van der Bijl
- Department of Cardiology, Heart Lung Centre, Leiden University Medical Centre, Albinusdreef 2, 2300 RC, Leiden, The Netherlands
| | - Jeroen J Bax
- Department of Cardiology, Heart Lung Centre, Leiden University Medical Centre, Albinusdreef 2, 2300 RC, Leiden, The Netherlands.,Heart Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, FI-20520, Turku, Finland
| |
Collapse
|
18
|
Kusunose K, Hirata Y, Yamaguchi N, Kosaka Y, Tsuji T, Kotoku J, Sata M. Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images. Front Cardiovasc Med 2022; 9:891703. [PMID: 35783826 PMCID: PMC9240342 DOI: 10.3389/fcvm.2022.891703] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Accepted: 05/12/2022] [Indexed: 11/28/2022] Open
Abstract
Background Stress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment. Objective We evaluated the usefulness of a deep learning (DL) approach based on a chest X-ray (CXR) to predict EIPH in 6-min walk stress echocardiography. Methods The study enrolled 142 patients with scleroderma or mixed connective tissue disease with scleroderma features who performed a 6-min walk stress echocardiographic test. EIPH was defined by abnormal cardiac output (CO) responses that involved an increase in mean pulmonary artery pressure (mPAP). We used the previously developed AI model to predict PH and calculated PH probability in this cohort. Results EIPH defined as ΔmPAP/ΔCO >3.3 and exercise mPAP >25 mmHg was observed in 52 patients, while non-EIPH was observed in 90 patients. The patients with EIPH had a higher mPAP at rest than those without EIPH. The probability of PH based on the DL model was significantly higher in patients with EIPH than in those without EIPH. Multivariate analysis showed that gender, mean PAP at rest, and the probability of PH based on the DL model were independent predictors of EIPH. A model based on baseline parameters (age, gender, and mPAP at rest) was improved by adding the probability of PH predicted by the DL model (AUC: from 0.65 to 0.74; p = 0.046). Conclusion Applying the DL model based on a CXR may have a potential for detection of EIPH in the clinical setting.
Collapse
Affiliation(s)
- Kenya Kusunose
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
- *Correspondence: Kenya Kusunose,
| | - Yukina Hirata
- Ultrasound Examination Center, Tokushima University Hospital, Tokushima, Japan
| | - Natsumi Yamaguchi
- Ultrasound Examination Center, Tokushima University Hospital, Tokushima, Japan
| | - Yoshitaka Kosaka
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| | - Takumasa Tsuji
- Department of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, Japan
| | - Jun’ichi Kotoku
- Department of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, Japan
| | - Masataka Sata
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| |
Collapse
|
19
|
Schlesinger DE, Diamant N, Raghu A, Reinertsen E, Young K, Batra P, Pomerantsev E, Stultz CM. A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram. JACC. ADVANCES 2022; 1:100003. [PMID: 38939079 PMCID: PMC11198366 DOI: 10.1016/j.jacadv.2022.100003] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 12/28/2021] [Accepted: 01/19/2022] [Indexed: 06/29/2024]
Abstract
Background Central hemodynamic parameters are typically measured via pulmonary artery catherization-an invasive procedure that involves some risk to the patient and is not routinely available in all settings. Objectives This study sought to develop a noninvasive method to identify elevated mean pulmonary capillary wedge pressure (mPCWP). Methods We leveraged data from 248,955 clinical records at the Massachusetts General Hospital to develop a deep learning model that can infer when the mPCWP >15 mmHg using the 12-lead electrocardiogram (ECG). Of these data, 242,216 records were used to pre-train a model that generates useful ECG representations. The remaining 6,739 records contain encounters with direct measurements of the mPCWP. Eighty percent of these data were used for model development and testing (5,390), and the remaining records comprise a holdout set (1,349) that was used to evaluate the model. We developed an associated unreliability score that identifies when model predictions are likely to be untrustworthy. Results The model achieves an area under the receiver operating characteristic curve (AUC) of 0.80 ± 0.02 (test set) and 0.79 ± 0.01 (holdout set). Model performance varies as a function of the unreliability, where patients with high unreliability scores correspond to a subgroup where model performance is poor: for example, patients in the holdout set with unreliability scores in the highest decile have a reduced AUC of 0.70 ± 0.06. Conclusions The mPCWP can be inferred from the ECG, and the reliability of this inference can be measured. When invasive monitoring cannot be expeditiously performed, deep learning models may provide information that can inform clinical care.
Collapse
Affiliation(s)
- Daphne E. Schlesinger
- Harvard-MIT Division of Health Sciences and Technology, MIT, Cambridge, Massachusetts, USA
- Institute for Medical Engineering and Science, MIT, Cambridge, Massachusetts, USA
- Research Laboratory of Electronics, Computer Science & Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
| | | | - Aniruddh Raghu
- Research Laboratory of Electronics, Computer Science & Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
- Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, USA
| | - Erik Reinertsen
- Research Laboratory of Electronics, Computer Science & Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
- Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Katherine Young
- Harvard-MIT Division of Health Sciences and Technology, MIT, Cambridge, Massachusetts, USA
| | - Puneet Batra
- Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA
| | - Eugene Pomerantsev
- Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Collin M. Stultz
- Harvard-MIT Division of Health Sciences and Technology, MIT, Cambridge, Massachusetts, USA
- Institute for Medical Engineering and Science, MIT, Cambridge, Massachusetts, USA
- Research Laboratory of Electronics, Computer Science & Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
- Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, USA
- Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts, USA
| |
Collapse
|
20
|
Hsiang CW, Lin C, Liu WC, Lin CS, Chang WC, Hsu HH, Huang GS, Lou YS, Lee CC, Wang CH, Fang WH. Detection of left ventricular systolic dysfunction using an artificial intelligence-enabled chest X-ray. Can J Cardiol 2022; 38:763-773. [PMID: 35007705 DOI: 10.1016/j.cjca.2021.12.019] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2021] [Revised: 12/16/2021] [Accepted: 12/18/2021] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Assessment of left ventricular systolic dysfunction provides essential information related to the prognosis and management of cardiovascular diseases. The aim of this study is to develop a deep-learning model (DLM) to identify LVEF≤35% via chest X-ray (CXR-EF≤35%) features and investigate the performance and clinical implications. METHODS This study collected 90,547 CXRs with the corresponding LVEF by transthoracic echocardiogram from the outpatient department in an academic medical center. Among these, 77,227 CXRs were used to develop a CXR-EF≤35%. Another 13,320 CXRs were used to validate the performance, which was evaluated by the area under the receiver operating characteristic curve (AUC). Furthermore, CXR-EF≤35% was tested to assess the long-term risks of developing LVEF≤35% and cardiovascular outcomes, which were evaluated by Kaplan-Meier survival analysis and the Cox proportional hazards model. RESULTS The AUCs of CXR-EF≤35% for the detection of LVEF≤35% were 0.888 and 0.867 in internal and external validation cohort. Patients with baseline LVEF>50%, detected as LVEF≤35% by CXR-EF≤35% were at higher risk of long-term developing LVEF≤35% (HRi:3.91, 95% CI, 2.98-5.14; HRe:2.49, 95%CI, 1.89-3.27). Furthermore, patients detected as LVEF≤35% by CXR-EF≤35% had significantly higher future risks of all-cause mortality (HRi:1.40, 95%CI, 1.15-1.71; HRe:1.38, 95%CI, 1.15-1.66), cardiovascular mortality (HRi:3.02, 95%CI, 1.84-4.98; HRe:2.60, 95%CI, 1.77-3.82), and new-onset atrial fibrillation (HRi:2.81, 95%CI, 2.15-3.66; HRe:2.93, 95%CI, 2.34-3.67) compared to those detected as no LVEF≤35%. CONCLUSION CXR-EF≤35% may serve as a screening tool for early detecting LVEF≤35% and independently contribute to predictions of long-term developing LVEF≤35% and cardiovascular outcomes. Further prospective studies are needed to confirm the model performance.
Collapse
Affiliation(s)
- Chih-Weim Hsiang
- Department of Radiology, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Chin Lin
- Graduate Institute of Life Sciences, National Defense Medical Centre, Taipei, Taiwan; School of Public Health, National Defense Medical Centre, Taipei, Taiwan; Medical Technology Education Center, School of Medicine, National Defense Medical Centre, Taipei, Taiwan
| | - Wen-Cheng Liu
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Chin-Sheng Lin
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan; Graduate Institute of Medical Sciences, National Defense Medical Centre, Taipei, Taiwan
| | - Wei-Chou Chang
- Department of Radiology, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan; Graduate Institute of Medical Sciences, National Defense Medical Centre, Taipei, Taiwan
| | - Hsian-He Hsu
- Department of Radiology, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Guo-Shu Huang
- Department of Radiology, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Yu-Sheng Lou
- Graduate Institute of Life Sciences, National Defense Medical Centre, Taipei, Taiwan; School of Public Health, National Defense Medical Centre, Taipei, Taiwan
| | - Chia-Cheng Lee
- Department of Medical Informatics, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Chih-Hung Wang
- Graduate Institute of Medical Sciences, National Defense Medical Centre, Taipei, Taiwan; Department of Otolaryngology-Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan
| | - Wen-Hui Fang
- Department of Family and Community Medicine, Tri-Service General Hospital, National Defense Medical Centre, Taipei, Taiwan.
| |
Collapse
|
21
|
Çallı E, Sogancioglu E, van Ginneken B, van Leeuwen KG, Murphy K. Deep learning for chest X-ray analysis: A survey. Med Image Anal 2021; 72:102125. [PMID: 34171622 DOI: 10.1016/j.media.2021.102125] [Citation(s) in RCA: 98] [Impact Index Per Article: 32.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2021] [Revised: 05/17/2021] [Accepted: 05/27/2021] [Indexed: 12/14/2022]
Abstract
Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs published before March 2021, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Detailed descriptions of all publicly available datasets are included and commercial systems in the field are described. A comprehensive discussion of the current state of the art is provided, including caveats on the use of public datasets, the requirements of clinically useful systems and gaps in the current literature.
Collapse
Affiliation(s)
- Erdi Çallı
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands.
| | - Ecem Sogancioglu
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Bram van Ginneken
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Kicky G van Leeuwen
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Keelin Murphy
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| |
Collapse
|
22
|
Kusunose K. Reply to Higaki-Next Steps in Artificial Intelligence for Cardiovascular Hemodynamics. Can J Cardiol 2021; 37:1299. [PMID: 33722661 DOI: 10.1016/j.cjca.2021.03.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2021] [Accepted: 03/07/2021] [Indexed: 11/25/2022] Open
|
23
|
Higaki A. Can Artificial Intelligence Substitute Right-Heart Catheterization With Chest X-Rays? Can J Cardiol 2021; 37:1298. [PMID: 33711477 DOI: 10.1016/j.cjca.2021.03.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2021] [Revised: 03/01/2021] [Accepted: 03/04/2021] [Indexed: 11/18/2022] Open
|
24
|
Hirata Y, Kusunose K, Tsuji T, Fujimori K, Kotoku J, Sata M. Deep Learning for Detection of Elevated Pulmonary Artery Wedge Pressure Using Standard Chest X-Ray. Can J Cardiol 2021; 37:1198-1206. [PMID: 33609716 DOI: 10.1016/j.cjca.2021.02.007] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2020] [Revised: 02/04/2021] [Accepted: 02/11/2021] [Indexed: 12/27/2022] Open
Abstract
BACKGROUND To accurately diagnose and control heart failure (HF), it is important to carry out a simple assessment of elevated pulmonary arterial wedge pressure (PAWP). The aim of this study was to develop and validate an objective method for detecting elevated PAWP by applying deep learning (DL) to a chest x-ray (CXR). METHODS We enrolled 1013 consecutive patients with a right-heart catheter between October 2009 and February 2020. We developed a convolutional neural network to identify patients with elevated PAWP (> 18 mm Hg) as the actual value of PAWP to be used in the dataset for training. In the prospective validation dataset used to detect elevated PAWP, the area under the receiver operating characteristic curve (AUC) was calculated using the DL model that evaluated the CXR. RESULTS In the prospective validation dataset, the AUC of the DL model with CXR was not significantly different from the AUC produced by brain natriuretic peptide (BNP) and the echocardiographic left-ventricular diastolic dysfunction (DD) algorithm (DL model: 0.77 vs BNP: 0.77 vs DD algorithm: 0.70; respectively; P = NS for all comparisons); it was, however, significantly higher than the AUC of the cardiothoracic ratio (DL model vs cardiothoracic ratio [CTR]: 0.66, P = 0.044). The model based on 3 parameters (BNP, DD algorithm, and CTR) was improved by adding the DL model (AUC: from 0.80 to 0.86; P = 0.041). CONCLUSIONS Applying the DL model based on a CXR (a classical, universal, and low-cost test) is useful for screening for elevated PAWP.
Collapse
Affiliation(s)
- Yukina Hirata
- Ultrasound Examination Center, Tokushima University Hospital, Tokushima, Japan
| | - Kenya Kusunose
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan.
| | - Takumasa Tsuji
- Department of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, Japan
| | - Kohei Fujimori
- Department of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, Japan
| | - Jun'ichi Kotoku
- Department of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, Japan
| | - Masataka Sata
- Ultrasound Examination Center, Tokushima University Hospital, Tokushima, Japan; Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| |
Collapse
|