Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review
Background: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other ha...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IMR Press
2022-12-01
|
| Series: | Reviews in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.imrpress.com/journal/RCM/23/12/10.31083/j.rcm2312402 |
| _version_ | 1797975831211933696 |
|---|---|
| author | Lies Dina Liastuti Bambang Budi Siswanto Renan Sukmawan Wisnu Jatmiko Yosilia Nursakina Rindayu Yusticia Indira Putri Grafika Jati Aqsha Azhary Nur |
| author_facet | Lies Dina Liastuti Bambang Budi Siswanto Renan Sukmawan Wisnu Jatmiko Yosilia Nursakina Rindayu Yusticia Indira Putri Grafika Jati Aqsha Azhary Nur |
| author_sort | Lies Dina Liastuti |
| collection | DOAJ |
| description | Background: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other hand, studies have shown that artificial intelligence (AI) is highly potential in complementing the work of clinicians to diagnose heart failure accurately and rapidly. Methods: We systematically searched Europe PMC, ProQuest, Science Direct, PubMed, and IEEE following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and our inclusion and exclusion criteria. The 14 selected works of literature were then assessed for their quality and risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). Results: A total of 2105 studies were retrieved, and 14 were included in the analysis. Five studies posed risks of bias. Nearly all studies included datasets in the form of 3D (three dimensional) or 2D (two dimensional) images, along with apical four-chamber (A4C) and apical two-chamber (A2C) being the most common echocardiography views used. The machine learning algorithm for each study differs, with the convolutional neural network as the most common method used. The accuracy varies from 57% to 99.3%. Conclusions: To conclude, current evidence suggests that the application of AI leads to a better and faster diagnosis of left heart failure through echocardiography. However, the presence of clinicians is still irreplaceable during diagnostic processes and overall clinical care; thus, AI only serves as complementary assistance for clinicians. |
| first_indexed | 2024-04-11T04:41:41Z |
| format | Article |
| id | doaj.art-d128661eb02546f9a3742a96be0163d6 |
| institution | Directory Open Access Journal |
| issn | 1530-6550 |
| language | English |
| last_indexed | 2024-04-11T04:41:41Z |
| publishDate | 2022-12-01 |
| publisher | IMR Press |
| record_format | Article |
| series | Reviews in Cardiovascular Medicine |
| spelling | doaj.art-d128661eb02546f9a3742a96be0163d62022-12-28T05:34:20ZengIMR PressReviews in Cardiovascular Medicine1530-65502022-12-01231240210.31083/j.rcm2312402S1530-6550(22)00728-1Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic ReviewLies Dina Liastuti0Bambang Budi Siswanto1Renan Sukmawan2Wisnu Jatmiko3Yosilia Nursakina4Rindayu Yusticia Indira Putri5Grafika Jati6Aqsha Azhary Nur7Department of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, National Cardiovascular Center Harapan Kita Hospital, 15810 Jakarta, IndonesiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, National Cardiovascular Center Harapan Kita Hospital, 15810 Jakarta, IndonesiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, National Cardiovascular Center Harapan Kita Hospital, 15810 Jakarta, IndonesiaDepartment of Computer Science, Faculty of Computer Science Universitas Indonesia, 16424 Depok, IndonesiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, Dr. Cipto Mangunkusumo Hospital, 10430 Jakarta, IndonesiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, National Cardiovascular Center Harapan Kita Hospital, 15810 Jakarta, IndonesiaDepartment of Computer Science, Faculty of Computer Science Universitas Indonesia, 16424 Depok, IndonesiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine Universitas Indonesia, Dr. Cipto Mangunkusumo Hospital, 10430 Jakarta, IndonesiaBackground: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other hand, studies have shown that artificial intelligence (AI) is highly potential in complementing the work of clinicians to diagnose heart failure accurately and rapidly. Methods: We systematically searched Europe PMC, ProQuest, Science Direct, PubMed, and IEEE following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and our inclusion and exclusion criteria. The 14 selected works of literature were then assessed for their quality and risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). Results: A total of 2105 studies were retrieved, and 14 were included in the analysis. Five studies posed risks of bias. Nearly all studies included datasets in the form of 3D (three dimensional) or 2D (two dimensional) images, along with apical four-chamber (A4C) and apical two-chamber (A2C) being the most common echocardiography views used. The machine learning algorithm for each study differs, with the convolutional neural network as the most common method used. The accuracy varies from 57% to 99.3%. Conclusions: To conclude, current evidence suggests that the application of AI leads to a better and faster diagnosis of left heart failure through echocardiography. However, the presence of clinicians is still irreplaceable during diagnostic processes and overall clinical care; thus, AI only serves as complementary assistance for clinicians.https://www.imrpress.com/journal/RCM/23/12/10.31083/j.rcm2312402heart failureechocardiographymachine learning |
| spellingShingle | Lies Dina Liastuti Bambang Budi Siswanto Renan Sukmawan Wisnu Jatmiko Yosilia Nursakina Rindayu Yusticia Indira Putri Grafika Jati Aqsha Azhary Nur Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review Reviews in Cardiovascular Medicine heart failure echocardiography machine learning |
| title | Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review |
| title_full | Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review |
| title_fullStr | Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review |
| title_full_unstemmed | Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review |
| title_short | Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review |
| title_sort | detecting left heart failure in echocardiography through machine learning a systematic review |
| topic | heart failure echocardiography machine learning |
| url | https://www.imrpress.com/journal/RCM/23/12/10.31083/j.rcm2312402 |
| work_keys_str_mv | AT liesdinaliastuti detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT bambangbudisiswanto detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT renansukmawan detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT wisnujatmiko detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT yosilianursakina detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT rindayuyusticiaindiraputri detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT grafikajati detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview AT aqshaazharynur detectingleftheartfailureinechocardiographythroughmachinelearningasystematicreview |