1
|
Chao CJ, Jeong J, Arsanjani R, Kim K, Tsai YL, Yu WC, Farina JM, Mahmoud AK, Ayoub C, Grogan M, Kane GC, Banerjee I, Oh JK. Echocardiography-Based Deep Learning Model to Differentiate Constrictive Pericarditis and Restrictive Cardiomyopathy. JACC Cardiovasc Imaging 2024; 17:349-360. [PMID: 37943236 DOI: 10.1016/j.jcmg.2023.09.011] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Revised: 09/07/2023] [Accepted: 09/25/2023] [Indexed: 11/10/2023]
Abstract
BACKGROUND Constrictive pericarditis (CP) is an uncommon but reversible cause of diastolic heart failure if appropriately identified and treated. However, its diagnosis remains a challenge for clinicians. Artificial intelligence may enhance the identification of CP. OBJECTIVES The authors proposed a deep learning approach based on transthoracic echocardiography to differentiate CP from restrictive cardiomyopathy. METHODS Patients with a confirmed diagnosis of CP and cardiac amyloidosis (CA) (as the representative disease of restrictive cardiomyopathy) at Mayo Clinic Rochester from January 2003 to December 2021 were identified to extract baseline demographics. The apical 4-chamber view from transthoracic echocardiography studies was used as input data. The patients were split into a 60:20:20 ratio for training, validation, and held-out test sets of the ResNet50 deep learning model. The model performance (differentiating CP and CA) was evaluated in the test set with the area under the curve. GradCAM was used for model interpretation. RESULTS A total of 381 patients were identified, including 184 (48.3%) CP, and 197 (51.7%) CA cases. The mean age was 68.7 ± 11.4 years, and 72.8% were male. ResNet50 had a performance with an area under the curve of 0.97 to differentiate the 2-class classification task (CP vs CA). The GradCAM heatmap showed activation around the ventricular septal area. CONCLUSIONS With a standard apical 4-chamber view, our artificial intelligence model provides a platform to facilitate the detection of CP, allowing for improved workflow efficiency and prompt referral for more advanced evaluation and intervention of CP.
Collapse
Affiliation(s)
- Chieh-Ju Chao
- Mayo Clinic Rochester, Rochester, Minnesota, USA; Mayo Clinic Arizona, Scottsdale, Arizona, USA
| | - Jiwoong Jeong
- Mayo Clinic Arizona, Scottsdale, Arizona, USA; Arizona State University, Tempe, Arizona, USA
| | | | - Kihong Kim
- Mayo Clinic Rochester, Rochester, Minnesota, USA
| | - Yi-Lin Tsai
- Taipei Veterans General Hospital, Taipei, Taiwan
| | - Wen-Chung Yu
- Taipei Veterans General Hospital, Taipei, Taiwan
| | | | | | - Chadi Ayoub
- Mayo Clinic Arizona, Scottsdale, Arizona, USA
| | | | | | - Imon Banerjee
- Mayo Clinic Arizona, Scottsdale, Arizona, USA; Arizona State University, Tempe, Arizona, USA
| | - Jae K Oh
- Mayo Clinic Rochester, Rochester, Minnesota, USA.
| |
Collapse
|
2
|
Ojurongbe TA, Afolabi HA, Bashiru KA, Sule WF, Akinde SB, Ojurongbe O, Adegoke NA. Prediction of malaria positivity using patients' demographic and environmental features and clinical symptoms to complement parasitological confirmation before treatment. Trop Dis Travel Med Vaccines 2023; 9:24. [PMID: 38098124 PMCID: PMC10722830 DOI: 10.1186/s40794-023-00208-7] [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: 04/25/2023] [Accepted: 09/28/2023] [Indexed: 12/17/2023] Open
Abstract
BACKGROUND Current malaria diagnosis methods that rely on microscopy and Histidine Rich Protein-2 (HRP2)-based rapid diagnostic tests (RDT) have drawbacks that necessitate the development of improved and complementary malaria diagnostic methods to overcome some or all these limitations. Consequently, the addition of automated detection and classification of malaria using laboratory methods can provide patients with more accurate and faster diagnosis. Therefore, this study used a machine-learning model to predict Plasmodium falciparum (Pf) antigen positivity (presence of malaria) based on sociodemographic behaviour, environment, and clinical features. METHOD Data from 200 Nigerian patients were used to develop predictive models using nested cross-validation and sequential backward feature selection (SBFS), with 80% of the dataset randomly selected for training and optimisation and the remaining 20% for testing the models. Outcomes were classified as Pf-positive or Pf-negative, corresponding to the presence or absence of malaria, respectively. RESULTS Among the three machine learning models examined, the penalised logistic regression model had the best area under the receiver operating characteristic curve for the training set (AUC = 84%; 95% confidence interval [CI]: 75-93%) and test set (AUC = 83%; 95% CI: 63-100%). Increased odds of malaria were associated with higher body weight (adjusted odds ratio (AOR) = 4.50, 95% CI: 2.27 to 8.01, p < 0.0001). Even though the association between the odds of having malaria and body temperature was not significant, patients with high body temperature had higher odds of testing positive for the Pf antigen than those who did not have high body temperature (AOR = 1.40, 95% CI: 0.99 to 1.91, p = 0.068). In addition, patients who had bushes in their surroundings (AOR = 2.60, 95% CI: 1.30 to 4.66, p = 0.006) or experienced fever (AOR = 2.10, 95% CI: 0.88 to 4.24, p = 0.099), headache (AOR = 2.07; 95% CI: 0.95 to 3.95, p = 0.068), muscle pain (AOR = 1.49; 95% CI: 0.66 to 3.39, p = 0.333), and vomiting (AOR = 2.32; 95% CI: 0.85 to 6.82, p = 0.097) were more likely to experience malaria. In contrast, decreased odds of malaria were associated with age (AOR = 0.62, 95% CI: 0.41 to 0.90, p = 0.012) and BMI (AOR = 0.47, 95% CI: 0.26 to 0.80, p = 0.006). CONCLUSION Newly developed routinely collected baseline sociodemographic, environmental, and clinical features to predict Pf antigen positivity may be a valuable tool for clinical decision-making.
Collapse
Affiliation(s)
| | | | | | | | | | - Olusola Ojurongbe
- Department of Medical Microbiology and Parasitology, Ladoke Akintola University of Technology, Ogbomoso, Nigeria
- Center for Emerging and Re-emerging Infectious Diseases, Ladoke Akintola University of Technology, Ogbomoso, Nigeria
| | - Nurudeen A Adegoke
- Melanoma Institute Australia, The University of Sydney, Sydney, Australia
| |
Collapse
|
3
|
Kusunose K. Revolution of echocardiographic reporting: the new era of artificial intelligence and natural language processing. J Echocardiogr 2023; 21:99-104. [PMID: 37312003 DOI: 10.1007/s12574-023-00611-1] [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: 05/29/2023] [Revised: 05/29/2023] [Accepted: 06/06/2023] [Indexed: 06/15/2023]
Abstract
Artificial intelligence (AI) has been making a significant impact on cardiovascular imaging, transforming everything from data capture to report generation. In the field of echocardiography, AI offers the potential to enhance accuracy, speed up reporting, and reduce the workload of physicians. This is an advantage because, compared to computed tomography and magnetic resonance imaging, echocardiograms tend to exhibit higher observer variability in interpretation. This review takes a comprehensive viewpoint at AI-based reporting systems and their application in echocardiography, emphasizing the need for automated diagnoses. The integration of natural language processing (NLP) technologies, including ChatGPT, could provide revolutionary advancements. One of the exciting prospects of AI integration is its potential to accelerate reporting, thereby improving patient outcomes and access to treatment, while also mitigating physician burnout. However, AI introduces new challenges like ensuring data quality, managing potential over-reliance on AI, addressing legal and ethical concerns, and balancing significant costs against benefits. As we navigate these complexities, it's important for cardiologists to stay updated with AI advancements and learn to utilize them effectively. AI has the potential to be integrated into daily clinical practice, becoming a valuable tool for healthcare professionals dealing with heart diseases, provided it's approached with careful consideration.
Collapse
Affiliation(s)
- Kenya Kusunose
- Department of Cardiovascular Medicine, Nephrology, and Neurology, Graduate School of Medicine, University of the Ryukyus, 207 Uehara, Nishihara Town, Okinawa, Japan.
| |
Collapse
|
4
|
Yamaguchi N, Kosaka Y, Haga A, Sata M, Kusunose K. Artificial intelligence-assisted interpretation of systolic function by echocardiogram. Open Heart 2023; 10:e002287. [PMID: 37460267 DOI: 10.1136/openhrt-2023-002287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 06/30/2023] [Indexed: 07/20/2023] Open
Abstract
OBJECTIVE Precise and reliable echocardiographic assessment of left ventricular ejection fraction (LVEF) is needed for clinical decision-making. Recently, artificial intelligence (AI) models have been developed to estimate LVEF accurately. The aim of this study was to evaluate whether an AI model could estimate an expert read of LVEF and reduce the interinstitutional variability of level 1 readers with the AI-LVEF displayed on the echocardiographic screen. METHODS This prospective, multicentre echocardiographic study was conducted by five cardiologists of level 1 echocardiographic skill (minimum level of competency to interpret images) from different hospitals. Protocol 1: Visual LVEFs for the 48 cases were measured without input from the AI-LVEF. Protocol 2: the 48 cases were again shown to all readers with inclusion of AI-LVEF data. To assess the concordance and accuracy with or without AI-LVEF, each visual LVEF measurement was compared with an average of the estimates by five expert readers as a reference. RESULTS A good correlation was found between AI-LVEF and reference LVEF (r=0.90, p<0.001) from the expert readers. For the classification LVEF, the area under the curve was 0.95 on heart failure with preserved EF and 0.96 on heart failure reduced EF. For the precision, the SD was reduced from 6.1±2.3 to 2.5±0.9 (p<0.001) with AI-LVEF. For the accuracy, the root-mean squared error was improved from 7.5±3.1 to 5.6±3.2 (p=0.004) with AI-LVEF. CONCLUSIONS AI can assist with the interpretation of systolic function on an echocardiogram for level 1 readers from different institutions.
Collapse
Affiliation(s)
- Natsumi Yamaguchi
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| | - Yoshitaka Kosaka
- Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, Japan
| | - Akihiko Haga
- Graduate School of Biomedical Sciences, Tokushima University, Tokushima, 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, Okinawa, Japan
| |
Collapse
|
6
|
Goto S, Solanki D, John JE, Yagi R, Homilius M, Ichihara G, Katsumata Y, Gaggin HK, Itabashi Y, MacRae CA, Deo RC. Multinational Federated Learning Approach to Train ECG and Echocardiogram Models for Hypertrophic Cardiomyopathy Detection. Circulation 2022; 146:755-769. [PMID: 35916132 PMCID: PMC9439630 DOI: 10.1161/circulationaha.121.058696] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
Abstract
BACKGROUND Novel targeted treatments increase the need for prompt hypertrophic cardiomyopathy (HCM) detection. However, its low prevalence (0.5%) and resemblance to common diseases present challenges that may benefit from automated machine learning-based approaches. We aimed to develop machine learning models to detect HCM and to differentiate it from other cardiac conditions using ECGs and echocardiograms, with robust generalizability across multiple cohorts. METHODS Single-institution HCM ECG models were trained and validated on external data. Multi-institution models for ECG and echocardiogram were trained on data from 3 academic medical centers in the United States and Japan using a federated learning approach, which enables training on distributed data without data sharing. Models were validated on held-out test sets for each institution and from a fourth academic medical center and were further evaluated for discrimination of HCM from aortic stenosis, hypertension, and cardiac amyloidosis. Last, automated detection was compared with manual interpretation by 3 cardiologists on a data set with a realistic HCM prevalence. RESULTS We identified 74 376 ECGs for 56 129 patients and 8392 echocardiograms for 6825 patients at the 4 academic medical centers. Although ECG models trained on data from each institution displayed excellent discrimination of HCM on internal test data (C statistics, 0.88-0.93), the generalizability was limited, most notably for a model trained in Japan and tested in the United States (C statistic, 0.79-0.82). When trained in a federated manner, discrimination of HCM was excellent across all institutions (C statistics, 0.90-0.96 and 0.90-0.96 for ECG and echocardiogram model, respectively), including for phenotypic subgroups. The models further discriminated HCM from hypertension, aortic stenosis, and cardiac amyloidosis (C statistics, 0.84, 0.83, and 0.88, respectively, for ECG and 0.93, 0.94, 0.85, respectively, for echocardiogram). Analysis of electrocardiography-echocardiography paired data from 11 823 patients from an external institution indicated a higher sensitivity of automated HCM detection at a given positive predictive value compared with cardiologists (0.98 versus 0.81 at a positive predictive value of 0.01 for ECG and 0.78 versus 0.59 at a positive predictive value of 0.24 for echocardiogram). CONCLUSIONS Federated learning improved the generalizability of models that use ECGs and echocardiograms to detect and differentiate HCM from other causes of hypertrophy compared with training within a single institution.
Collapse
Affiliation(s)
- Shinichi Goto
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.).,Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)
| | - Divyarajsinhji Solanki
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)
| | - Jenine E. John
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)
| | - Ryuichiro Yagi
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)
| | - Max Homilius
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)
| | - Genki Ichihara
- Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)
| | - Yoshinori Katsumata
- Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)
| | - Hanna K. Gaggin
- Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.).,Division of Cardiology, Massachusetts General Hospital, Boston (H.K.G.)
| | - Yuji Itabashi
- Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)
| | - Calum A. MacRae
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)
| | - Rahul C. Deo
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.).,Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.).,Center for Digital Health Innovation and Department of Medicine, University of California San Francisco (R.C.D.)
| |
Collapse
|