| Abstract | Objectives: Congenital heart diseases (CHD) are a significant cause of neonatal mortality and morbidity. Detecting these abnormalities during pregnancy increases survival rates, enhances prognosis, and im-proves pregnancy management and quality of life for the affected families. Foetal echocardiography can be considered an accurate method for detecting CHDs. However, the detection of CHDs can be limited by factors such as the sonographer's skill, expertise and patient specific variables. Using artificial intelligence (AI) has the potential to address these challenges, increasing antenatal CHD detection during prenatal care. A scoping review was conducted using Google Scholar, PubMed, and ScienceDirect databases, employing keywords, Boolean operators, and inclusion and exclusion criteria to identify peer-reviewed studies. Thematic mapping and synthesis of the found literature were conducted to review key concepts, research methods and findings. Key findings: A total of n = 233 articles were identified, after exclusion criteria, the focus was narrowed to n = 7 that met the inclusion criteria. Themes in the literature identified the potential of AI to assist clinicians and trainees, alongside emerging new ethical limitations in ultrasound imaging. Conclusion: AI-based tools in ultrasound imaging offer great potential in assisting sonographers and doctors with decision-making in CHD diagnosis. However, due to the paucity of data and small sample sizes, further research and technological advancements are needed to improve reliability and integrate AI into routine clinical practice. Implications for practice: This scoping review identified the reported accuracy and limitations of AI based tools within foetal cardiac ultrasound imaging. AI has the potential to aid in reducing missed diagnoses, enhance training, and improve pregnancy management. There is a need to understand and address the ethical and legal considerations involved with this new paradigm in imaging. |
|---|
| References | References1. Day TG, Matthew J, Budd SF, Farruggia A, Venturini L, Wright R, et al. Artificialintelligence to assist in the screening fetal anomaly ultrasound scan (PRO-METHEUS): a Randomised Controlled trial. medRxiv. 2024:2024–2025. https://
doi.org/10.1101/2024.05.23.24307329.2. NHS England. NCARDRS congenital anomaly official statistics report. 2024, 2021,
London.L. Norris and P. Lockwood Radiography 31 (2025) 10317073. Khan K, Ullah F, Syed I, Ali H. Accurately assessing congenital heart diseaseusing artificial intelligence. PeerJ Comput Sci. 2024;10:e2535.4. Horgan R, Nehme L, Abuhamad A. Artificial intelligence in obstetric ultra-sound: a scoping review. Prenat Diagn. 2023;43(9):1176–1219. https://doi.org/10.1002/pd.6411.5. Zhang J, Xiao S, Zhu Y, Zhang Z, Cao H, Xie M, et al. Advances in the applicationof artificial intelligence in fetal echocardiography. J Am Soc Echocardiogr.2024;37(5):550–561. https://doi.org/10.1016/j.echo.2023.12.013.6. Liu H, Zhou J, Feng Q-L, Gu H-T, Wan G, Zhang H-M, et al. Fetal echocardi-ography for congenital heart disease diagnosis: a meta-analysis, power anal-ysis and missing data analysis. Eur J Prev Cardiol. 2015;22(12):1531–1547.https://doi.org/10.1177/2047487314551547.7. AlZubi AA, Alkhanifer A. Study on the prediction of congenital cardiac ab-normalities using various Machine learning models. J King Saud Univ Sci.2024;36(11):103555. https://doi.org/10.1016/j.jksus.2024.103555.8. Aveyard H. Doing a Literature Review in Health and Social Care: A Practical Guide5e. 2023.9. Morrison A, Polisena J, Husereau D, Moulton K, Clark M, Fiander M, et al. Theeffect of English-language restriction on systematic review-based meta-ana-lyses: a systematic review of empirical studies. Int J Technol Assess Health Care.2012;28(2):138–144. https://doi.org/10.1017/S0266462312000086.10. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al.The PRISMA 2020 statement: an updated guideline for reporting systematicreviews. Bmj. 2021;372. https://doi.org/10.1136/bmj.n71.11. Su F, Zhang X, Han J, Wang J, Li L, Kong D, et al. Application of computer-aideddiagnosis of congenital heart disease in four-chamber view of fetal heart basicscreening. Chin Med J (Engl). 2022;135(24):3010–3012. https://doi.org/10.1097/CM9.0000000000002274.12. Athalye C, van Nisselrooij A, Rizvi S, Haak MC, Moon-Grady AJ, Arnaout R.Deep-learning model for prenatal congenital heart disease screeninggeneralizes to community setting and outperforms clinical detection. Ul-trasound Obstet Gynecol. 2024;63(1):44–52. https://doi.org/10.1002/uog.27503.13. Taksøe-Vester CA, Mikolaj K, Petersen OBB, Vejlstrup NG, Christensen AN,Feragen A, et al. Role of artificial-intelligence-assisted automated cardiacbiometrics in prenatal screening for coarctation of aorta. Ultrasound ObstetGynecol. 2024;64(1):36–43. https://doi.org/10.1002/uog.27608.14. Li F, Li P, Liu Z, Liu S, Zeng P, Song H, et al. Application of artificial intelligencein VSD prenatal diagnosis from fetal heart ultrasound images. BMC PregnancyChildbirth. 2024;24(1):758. https://doi.org/10.1186/s12884-024-06916-y.15. Reddy CD, Van den Eynde J, Kutty S. Artificial intelligence in perinatal diag-nosis and management of congenital heart disease. Seminars in perinatology.2022;46:151588. Elsevier.16. Liu X, Zhang Y, Zhu H, Jia B, Wang J, He Y, et al. Applications of artificial intelligence-powered prenatal diagnosis for congenital heart disease. Front Cardiovasc Med.2024;11:1345761. https://doi.org/10.3389/fcvm.2024.1345761.17. Drukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligencein ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol.2020;56(4):498–505. https://doi.org/10.1002/UOG.22122.18. Drukker L. The Holy Grail of obstetric ultrasound: can artificial intelligencedetect hard-to-identify fetal cardiac anomalies? Ultrasound Obstet Gynecol.2024:5–9. https://doi.org/10.1002/uog.27703.19. Jone P-N, Gearhart A, Lei H, Xing F, Nahar J, Lopez-Jimenez F, et al. Artificialintelligence in congenital heart disease: current state and prospects. JACC (JAm Coll Cardiol): Advances. 2022;1(5):100153. https://doi.org/10.1016/j.jacadv.2022.100153.20. Faber J, Fonseca LM. How sample size influences research outcomes. DentalPress J Orthod. 2014;19:27–29. https://doi.org/10.1590/2176-9451.19.4.027-029.ebo.21. Riva A, Guerra M, Di Gangi S, Veronese P, Vida VL. Artificial intelligence for theprenatal ultrasound diagnosis of congenital heart disease: a narrative review.Clin Exp Obstet Gynecol. 2024;51(11):244.22. American College of Cardiology. Congenital Heart Disease. Cardio Smart. p1.Available from: https://www.cardiosmart.org/topics/congenital-heart-disease/overview [accessed June 9, 2025].23. Tariq A, Gill A, Hussain HK, Jiwani N, Logeshwaran J. The smart earlier pre-diction of conginental heart disease in pregnancy using deep learning model.In: 2023 IEEE technology & Engineering management conference-asia Pacific(TEMSCON-ASPAC). IEEE; 2023:1–7.24. Ginsberg G, Drukker L, Pollak U, Brezis M. Cost-utility analysis of prenataldiagnosis of congenital cardiac diseases using deep learning. Authorea Pre-prints. 2024. https://doi.org/10.22541/au.171045405.59757841/v1 |
|---|