{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["6(2)"],"submitter":["Kishikawa R"],"pubmed_abstract":["<h4>Aims</h4>Delayed diagnosis of pulmonary hypertension (PH) is a known cause of poor patient prognosis. We aimed to develop an artificial intelligence (AI) model, using ensemble learning method to detect PH using electrocardiography (ECG), chest X-ray (CXR), and brain natriuretic peptide (BNP), facilitating accurate detection and prompting further examinations.<h4>Methods and results</h4>We developed a convolutional neural network model using ECG data to predict PH, labelled by ECG from seven institutions. Logistic regression was used for the BNP prediction model. We referenced a CXR deep learning model using ResNet18. Outputs from each of the three models were integrated into a three-layer fully connected multimodal model. Ten cardiologists participated in an interpretation test, detect"],"journal":["European heart journal. Digital health"],"pagination":["209-217"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11914732"],"repository":["biostudies-literature"],"pubmed_title":["An ensemble learning model for detection of pulmonary hypertension using electrocardiogram, chest X-ray, and brain natriuretic peptide."],"pmcid":["PMC11914732"],"pubmed_authors":["Takeda N","Ishida J","Kishikawa R","Shinohara H","Setoguchi N","Akazawa H","Fujita H","Nanasato M","Ando J","Kushida S","Minatsuki S","Fujiu K","Kodera S","Maki H","Sawano S","Nakanishi K","Tanabe K","Kato N","Watanabe H","Sawada N","Sato M","Morita H","Takahashi M"],"additional_accession":[]},"is_claimable":false,"name":"An ensemble learning model for detection of pulmonary hypertension using electrocardiogram, chest X-ray, and brain natriuretic peptide.","description":"<h4>Aims</h4>Delayed diagnosis of pulmonary hypertension (PH) is a known cause of poor patient prognosis. We aimed to develop an artificial intelligence (AI) model, using ensemble learning method to detect PH using electrocardiography (ECG), chest X-ray (CXR), and brain natriuretic peptide (BNP), facilitating accurate detection and prompting further examinations.<h4>Methods and results</h4>We developed a convolutional neural network model using ECG data to predict PH, labelled by ECG from seven institutions. Logistic regression was used for the BNP prediction model. We referenced a CXR deep learning model using ResNet18. Outputs from each of the three models were integrated into a three-layer fully connected multimodal model. Ten cardiologists participated in an interpretation test, detect","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Mar","modification":"2025-04-04T00:08:22.026Z","creation":"2025-04-04T00:08:22.026Z"},"accession":"S-EPMC11914732","cross_references":{"pubmed":["40110214"],"doi":["10.1093/ehjdh/ztae097"]}}