Zhusi Zhong, Helen Zhang, Fayez H Fayad, Andrew C Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collins, Colin F Greineder, Sun H Ahn, Harrison X Bai, Zhicheng Jiao, Michael K Atalay
{"title":"基于计算机断层血管造影和临床数据的肺栓塞生存预测的多模式学习。","authors":"Zhusi Zhong, Helen Zhang, Fayez H Fayad, Andrew C Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collins, Colin F Greineder, Sun H Ahn, Harrison X Bai, Zhicheng Jiao, Michael K Atalay","doi":"10.1097/RTI.0000000000000831","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using computed tomography pulmonary angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE survival.</p><p><strong>Materials and methods: </strong>In total, 918 patients (median age 64 y, range 13 to 99 y, 48% male) with 3978 CTPAs were identified via retrospective review across 3 institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and clinical variables were then incorporated into independent DL models to predict survival outcomes. Cross-modal fusion CoxPH models were used to develop multimodal models from combinations of DL models and calculated PESI scores. Five multimodal models were developed as follows: (1) using CTPA imaging features only, (2) using clinical variables only, (3) using both CTPA and clinical variables, (4) using CTPA and PESI score, and (5) using CTPA, clinical variables, and PESI score. Performance was evaluated using the concordance index (c-index). Kaplan-Meier analysis was performed to stratify patients into high-risk and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction.</p><p><strong>Results: </strong>For both data sets, the multimodal models incorporating CTPA features, clinical variables, and PESI score achieved higher c-indices than PESI alone. Following the stratification of patients into high-risk and low-risk groups by models, survival outcomes differed significantly (both P<0.001). A strong correlation was found between high-risk grouping and RV dysfunction.</p><p><strong>Conclusions: </strong>Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.</p>","PeriodicalId":49974,"journal":{"name":"Journal of Thoracic Imaging","volume":" ","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pulmonary Embolism Survival Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data.\",\"authors\":\"Zhusi Zhong, Helen Zhang, Fayez H Fayad, Andrew C Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collins, Colin F Greineder, Sun H Ahn, Harrison X Bai, Zhicheng Jiao, Michael K Atalay\",\"doi\":\"10.1097/RTI.0000000000000831\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using computed tomography pulmonary angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE survival.</p><p><strong>Materials and methods: </strong>In total, 918 patients (median age 64 y, range 13 to 99 y, 48% male) with 3978 CTPAs were identified via retrospective review across 3 institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and clinical variables were then incorporated into independent DL models to predict survival outcomes. Cross-modal fusion CoxPH models were used to develop multimodal models from combinations of DL models and calculated PESI scores. Five multimodal models were developed as follows: (1) using CTPA imaging features only, (2) using clinical variables only, (3) using both CTPA and clinical variables, (4) using CTPA and PESI score, and (5) using CTPA, clinical variables, and PESI score. Performance was evaluated using the concordance index (c-index). Kaplan-Meier analysis was performed to stratify patients into high-risk and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction.</p><p><strong>Results: </strong>For both data sets, the multimodal models incorporating CTPA features, clinical variables, and PESI score achieved higher c-indices than PESI alone. Following the stratification of patients into high-risk and low-risk groups by models, survival outcomes differed significantly (both P<0.001). A strong correlation was found between high-risk grouping and RV dysfunction.</p><p><strong>Conclusions: </strong>Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.</p>\",\"PeriodicalId\":49974,\"journal\":{\"name\":\"Journal of Thoracic Imaging\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2025-04-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Thoracic Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/RTI.0000000000000831\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Thoracic Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/RTI.0000000000000831","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Pulmonary Embolism Survival Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data.
Purpose: Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using computed tomography pulmonary angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE survival.
Materials and methods: In total, 918 patients (median age 64 y, range 13 to 99 y, 48% male) with 3978 CTPAs were identified via retrospective review across 3 institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and clinical variables were then incorporated into independent DL models to predict survival outcomes. Cross-modal fusion CoxPH models were used to develop multimodal models from combinations of DL models and calculated PESI scores. Five multimodal models were developed as follows: (1) using CTPA imaging features only, (2) using clinical variables only, (3) using both CTPA and clinical variables, (4) using CTPA and PESI score, and (5) using CTPA, clinical variables, and PESI score. Performance was evaluated using the concordance index (c-index). Kaplan-Meier analysis was performed to stratify patients into high-risk and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction.
Results: For both data sets, the multimodal models incorporating CTPA features, clinical variables, and PESI score achieved higher c-indices than PESI alone. Following the stratification of patients into high-risk and low-risk groups by models, survival outcomes differed significantly (both P<0.001). A strong correlation was found between high-risk grouping and RV dysfunction.
Conclusions: Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.
期刊介绍:
Journal of Thoracic Imaging (JTI) provides authoritative information on all aspects of the use of imaging techniques in the diagnosis of cardiac and pulmonary diseases. Original articles and analytical reviews published in this timely journal provide the very latest thinking of leading experts concerning the use of chest radiography, computed tomography, magnetic resonance imaging, positron emission tomography, ultrasound, and all other promising imaging techniques in cardiopulmonary radiology.
Official Journal of the Society of Thoracic Radiology:
Japanese Society of Thoracic Radiology
Korean Society of Thoracic Radiology
European Society of Thoracic Imaging.