- 1Department of Surgery, Division of Pediatric Surgery, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
- 2Department of Neonatology, Beatrix Children’s Hospital, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
Editorial on the Research Topic
Artificial intelligence and machine learning in pediatric surgery
1 Introduction
Cutting-edge technologies are leading to a profound transformation of healthcare (1, 2). Among the most promising advancements is the integration of artificial intelligence (AI) into the delicate and critical domain of pediatrics (3–5). We find ourselves at the threshold of a new frontier, envisioning how AI might revolutionize every step of the pediatric patient journey. In this Research Topic, we embark on an exploration of how AI may shape the future of pediatrics and pediatric surgery in particular.
2 Artificial intelligence and machine learning in pediatrics
The term “artificial intelligence” was coined by John McCarthy in 1955, defining it as “the science and engineering to make intelligent machines” (6). Over the years, AI has evolved into a vast field of computer science, levering technologies like machine learning to perform tasks that were once thought to require human intelligence, such as problem-solving, pattern recognition, and decision-making (7). In pediatrics, where healthcare providers often face intricate tasks demanding advanced human intelligence, AI has emerged as a transformative ally. The most recent technologies brought forward by AI can provide valuable support by analyzing extensive patient data and offering predictive insights which can be incorporated into early warning systems (8). Moreover, AI holds the potential to assist medical professionals in making precise diagnoses and suggesting personalized treatment recommendations (9–11). Beyond this, AI's capabilities extend into the operating theatre, where it can provide real-time information, robotic assistance, and procedural guidance, further advancing the field of pediatric surgery (12).
3 AI throughout the pediatric patient journey
This Research Topic delves into AI's potential future role in pediatrics, stretching even to the prenatal phase with Lin et al. exploring AI's potential in the detection of genomic mutations in congenital surgical diseases Lin et al. By navigating through a number of innovative deep learning models that identify and prioritize variations from big genomic data, they showed that AI can help to detect and understand the potential impact of mutations on disease development. This proactive approach enables timely interventions including preventive or corrective measures before or shortly after birth.
As we progress through the patient journey, AI's influence expands into the childbirth process, assisting healthcare professionals in monitoring and optimizing maternal and neonatal care. For instance, AI can play a pivotal role in analyzing progression data to predict the necessity of procedures like caesarean sections (13, 14). Post-birth, high-risk neonates undergo a series of diagnostic tests, including imaging scans and laboratory tests. Ongoing research into computer vision algorithms, utilizing convolutional neural networks for the analysis of medical images, holds the promise of more accurate diagnoses (15, 16). Future developments may even witness integration of sophisticated multi-modal algorithms, combining diverse data sources for highly precise predictions of specific medical conditions (17).
Where preventative measures fall short and critical diseases manifest, AI can step in to facilitate informed decision-making. An interesting example lies in the use of Behavioral Artificial Intelligence Technology, showcased in the study by Van Varsseveld et al. illustrating its potential in supporting physicians with end-of-life decision-making for preterm infants with surgical necrotizing enterocolitis.
Within the operating theatre, AI's potential in guiding surgical procedures becomes increasingly evident. While technologies like the use of indocyanine green fluorescence have proven successful in open-surgery Esposito et al., envisioning an AI-driven iteration might involve the integration of augmented reality (AR) technologies (18, 19). These would enable the visualization of crucial landmarks and surgical paths, providing invaluable guidance to surgeons. Another notable example highlighted in this Research Topic involves machine learning algorithms distinguishing between ventral and dorsal roots during selective dorsal rhizotomy using electro-neurophysiological characteristics Jiang et al. Furthermore, robotic-assisted surgery is not untouched by AI's transformative impact, offering surgeons greater precision, facilitating minimally invasive surgeries, and contributing to reduced incisions, pain, and faster recovery times for pediatric patients (20–22). Natural language processing might allow for automatic surgery reporting, streamlining documentation by extracting key information from the surgical procedure and generating detailed reports (23).
In postoperative care, AI can play a pivotal role by analyzing patient data to predict and prevent complications, optimizing recovery strategies, and personalizing rehabilitation plans. Moreover, it can streamline healthcare processes by optimizing appointment planning and enhancing overall efficiency in healthcare facilities. In essence, AI's integration into pediatrics encompasses a spectrum of technologies and applications, revolutionizing surgical practices and ultimately improving outcomes for pediatric patients and their families.
4 Ethical, legal and societal aspects (ELSA) of applying AI throughout the patient journey
Integration of AI in pediatrics and pediatric surgery brings along a great deal of interconnected ethical, legal, and social concerns, which are of particular relevance when caring for preterm and critically ill newborns and children.
As the article by Till et al. in this Research Topic explained, optimization of the developed algorithms can have a significant impact on its usability Till et al. By performing a thorough pre-processing procedure, they significantly improved the radiological detection of wrist fractures. Hence, before implementation, it is imperative to carry out iterative development and testing procedures to ensure optimal performance and clinical relevance of the model. While doing so, factors like algorithm bias and transparency must be meticulously considered to prevent disproportionate impacts on the vulnerable pediatric populations (24–26). Additionally, robust safeguards are essential to protect patient privacy. Taking a societal perspective, the deployment of AI-tools must transcend socio-economic boundaries, advocating for equal access to these transformative technologies (27). Simultaneously, a proactive approach to education is essential, empowering individuals with the knowledge necessary to use the tools optimally (28). The seamless integration of AI in pediatrics also necessitates the cultivation of trust, ensuring its acceptance as valuable aid rather than a potential source of apprehension (29, 30). On the legal front, AI prompts a reevaluation of medical liability and responsibility (31–33). Still, by navigating the social and legal dimensions conscientiously, a seamless integration of AI into pediatrics can be achieved, fostering advancements that benefit patients while upholding ethical, social, and legal standards.
5 Conclusion
In this Research Topic, we provide a glimpse of how AI could be possibly integrated into the pediatric patient journey. AI has the potential to be incorporated at any stage of this journey, catering to the specific needs and preferences of healthcare professionals, parents and patients alike. As we navigate the opportunities and challenges in this transformative era, the continuous evolution of AI holds the key to a future where technology becomes an even more indispensable ally in the pursuit of optimal pediatric care.
Author contributions
RV: Writing – original draft, Writing – review & editing. JH: Supervision, Writing – original draft, Writing – review & editing.
Funding
The author(s) declare that financial support was received for the research, authorship, and/or publication of this article.
This Editorial was supported by the For Wis(h)dom Foundation (Project 9, 02/02/2022, Baarn, The Netherlands).
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. (2019) 25(1):44–56. doi: 10.1038/s41591-018-0300-7
2. Bohr A, Memarzadeh K. Chapter 2 - The rise of artificial intelligence in healthcare applications. In: Bohr A, Memarzadeh K, editors. Artificial Intelligence in Healthcare. Academic Press (2020). p. 25–60. doi: 10.1016/B978-0-12-818438-7.00002-2
3. Matsushita FY, Krebs VLJ, Carvalho WB. Artificial intelligence and machine learning in pediatrics and neonatology healthcare. Rev Assoc Med Bras (1992). (2022) 68(6):745–50. doi: 10.1590/1806-9282.20220177
4. Malhotra A, Molloy EJ, Bearer CF, Mulkey SB. Emerging role of artificial intelligence, big data analysis and precision medicine in pediatrics. Pediatr Res. (2023) 93(2):281–3. doi: 10.1038/s41390-022-02422-z
5. Shah N, Arshad A, Mazer MB, Carroll CL, Shein SL, Remy KE. The use of machine learning and artificial intelligence within pediatric critical care. Pediatr Res. (2023) 93(2):405–12. doi: 10.1038/s41390-022-02380-6
6. McCarthy J. A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence. (1955). Available online at: http://www-formal.stanford.edu/jmc/history/dartmouth/dartmouth.html
7. Korteling JEH, van de Boer-Visschedijk GC, Blankendaal RAM, Boonekamp RC, Eikelboom AR. Human- versus artificial intelligence. Front Artif Intell. (2021) 4:622364. doi: 10.3389/frai.2021.622364
8. Smith JD, Smith AR, Smith LP, Allen RW, Smith CJ. Predictive analytics in healthcare using machine learning algorithms: a review. IEEE Access. (2020) 8:134783–814. doi: 10.1109/ACCESS.2020.3012618
9. Shen J, Zhang CJP, Jiang B, Chen J, Song J, Liu Z, et al. Artificial intelligence versus clinicians in disease diagnosis: systematic review. JMIR Med Inform. (2019) 7(3):e10010. doi: 10.2196/10010
10. Ng CKC. Diagnostic performance of artificial intelligence-based computer-aided detection and diagnosis in pediatric radiology: a systematic review. Children (Basel). (2023) 10(3):525. doi: 10.3390/children10030525
11. Ashton JJ, Young A, Johnson MJ, Beattie RM. Using machine learning to impact on long-term clinical care: principles, challenges, and practicalities. Pediatr Res. (2023) 93(2):324–33. doi: 10.1038/s41390-022-02194-6
12. Mithany RH, Aslam S, Abdallah S, Abdelmaseeh M, Gerges F, Mohamed MS, et al. Advancements and challenges in the application of artificial intelligence in surgical arena: a literature review. Cureus. (2023) 15(10):e47924. doi: 10.7759/cureus.47924
13. Guedalia J, Lipschuetz M, Novoselsky-Persky M, Cohen SM, Rottenstreich A, Levin G, et al. Real-time data analysis using a machine learning model significantly improves prediction of successful vaginal deliveries. Am J Obstet Gynecol. (2020) 223(3):437.e1–437.e15. doi: 10.1016/j.ajog.2020.05.025
14. Guedalia J, Sompolinsky Y, Novoselsky Persky M, Cohen SM, Kabiri D, Yagel S, et al. Prediction of severe adverse neonatal outcomes at the second stage of labour using machine learning: a retrospective cohort study. BJOG. (2021) 128(11):1824–32. doi: 10.1111/1471-0528.16700
15. Yu H, Yang LT, Zhang Q, Armstrong D, Deen MJ. Convolutional neural networks for medical image analysis: state-of-the-art, comparisons, improvement and perspectives. Neurocomputing. (2021) 444:92–110. doi: 10.1016/j.neucom.2020.04.157
16. Yadav SS, Jadhav SM. Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data. (2019) 6(1):1–18. doi: 10.1186/s40537-019-0276-2
17. Yan K, Li T, Marques JAL, Gao J, Fong SJ. A review on multimodal machine learning in medical diagnostics. Math Biosci Eng. (2023) 20(5):8708–26. doi: 10.3934/mbe.2023382
18. Fida B, Cutolo F, di Franco G, Ferrari M, Ferrari V. Augmented reality in open surgery. Updates Surg. (2018) 70(3):389–400. doi: 10.1007/s13304-018-0567-8
19. Dennler C, Bauer DE, Scheibler AG, Spirig J, Götschi T, Fürnstahl P, et al. Augmented reality in the operating room: a clinical feasibility study. BMC Musculoskelet Disord. (2021) 22(1):451. doi: 10.1186/s12891-021-04339-w
20. Mirnezami R, Ahmed A. Surgery 3.0, artificial intelligence and the next-generation surgeon. Br J Surg. (2018) 105(5):463–5. doi: 10.1002/bjs.10860
21. Peters BS, Armijo PR, Krause C, Choudhury SA, Oleynikov D. Review of emerging surgical robotic technology. Surg Endosc. (2018) 32(4):1636–55. doi: 10.1007/s00464-018-6079-2
22. Bhandari M, Zeffiro T, Reddiboina M. Artificial intelligence and robotic surgery: current perspective and future directions. Curr Opin Urol. (2020) 30(1):48–54. doi: 10.1097/MOU.0000000000000692
23. Bieck R, Wildfeuer V, Kunz V, Sorge M, Pirlich M, Rockstroh M, et al. Generation of surgical reports using keyword-augmented next sequence prediction. Curr Dir Biomed Eng. (2021) 7:387–90. doi: 10.1515/cdbme-2021-2098
24. Abràmoff MD, Tarver ME, Loyo-Berrios N, Trujillo S, Char D, Obermeyer Z, et al. Considerations for addressing bias in artificial intelligence for health equity. NPJ Digit Med. (2023) 6(1):170. doi: 10.1038/s41746-023-00913-9
25. McCradden MD, Joshi S, Mazwi M, Anderson JA. Ethical limitations of algorithmic fairness solutions in health care machine learning. Lancet Digit Health. (2020) 2(5):e221–3. doi: 10.1016/S2589-7500(20)30065-0
26. Boch S, Sezgin E, Lin Linwood S. Ethical artificial intelligence in paediatrics. The Lancet Child & Adolescent Health. (2022) 6(12):833–5. doi: 10.1016/S2352-4642(22)00243-7
27. McCoy LG, Banja JD, Ghassemi M, Celi LA. Ensuring machine learning for healthcare works for all. BMJ Health Care Inform. (2020) 27(3):e100237. doi: 10.1136/bmjhci-2020-100237
28. Tucci V, Saary J, Doyle TE. Factors influencing trust in medical artificial intelligence for healthcare professionals: a narrative review. J Med Artif Intell. (2022) 5:4. doi: 10.21037/jmai-21-25
29. Zhang J, Zhang ZM. Ethics and governance of trustworthy medical artificial intelligence. BMC Med Inform Decis Mak. (2023) 23(1):7. doi: 10.1186/s12911-023-02103-9
30. Rojas JC, Teran M, Umscheid CA. Clinician trust in artificial intelligence: what is known and how trust can be facilitated. Crit Care Clin. (2023) 39(4):769–82. doi: 10.1016/j.ccc.2023.02.004
31. Naik N, Hameed BMZ, Shetty DK, Swain D, Shah M, Paul R, et al. Legal and ethical consideration in artificial intelligence in healthcare: who takes responsibility? Front Surg. (2022) 9:862322. doi: 10.3389/fsurg.2022.862322
32. O'Sullivan S, Nevejans N, Allen C, Blyth A, Leonard S, Pagallo U, et al. Legal, regulatory, and ethical frameworks for development of standards in artificial intelligence (AI) and autonomous robotic surgery. Int J Med Robot. (2019) 15(1):e1968. doi: 10.1002/rcs.1968
Keywords: artificial intelligence, machine learning, deep learning, pediatric surgery, neonatal and pediatric care, ELSA, surgical innovation
Citation: Verhoeven R and Hulscher JBF (2024) Editorial: Artificial intelligence and machine learning in pediatric surgery. Front. Pediatr. 12:1404600. doi: 10.3389/fped.2024.1404600
Received: 21 March 2024; Accepted: 1 April 2024;
Published: 9 April 2024.
Edited and Reviewed by: Simone Frediani, Bambino Gesù Children’s Hospital (IRCCS), Italy
© 2024 Verhoeven and Hulscher. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Rosa Verhoeven r.verhoeven@umcg.nl