Newborn Time - improved newborn care based on video and artificial intelligence - study protocol

Springer Science and Business Media LLC
Kjersti Engan1, Øyvind Meinich-Bache1, Stefanie Brunner2, Helge Myklebust2, Chunming Rong1,3, Jorge García-Torres1, Hege Ersdal4, Anders Johannessen2, Hanne Markhus Pike5, Siren Rettedal4
1Department of Electrical Engineering and Computer Science, University of Stavanger, Stavanger, Norway
2Laerdal Medical AS, Stavanger, Norway
3BitYoga, Stavanger, Norway
4Faculty of Health Sciences, University of Stavanger, Stavanger, Norway
5Department of Pediatrics, Stavanger University Hospital, Stavanger, Norway

Tóm tắt

Abstract Background Approximately 3-8% of all newborns do not breathe spontaneously at birth, and require time critical resuscitation. Resuscitation guidelines are mostly based on best practice, and more research on newborn resucitation is highly sought for. Methods The NewbornTime project will develop artificial intelligence (AI) based solutions for activity recognition during newborn resuscitations based on both visible light spectrum videos and infrared spectrum (thermal) videos. In addition, time-of-birth detection will be developed using thermal videos from the delivery rooms. Deep Neural Network models will be developed, focusing on methods for limited supervision and solutions adapting to on-site environments. A timeline description of the video analysis output enables objective analysis of resuscitation events. The project further aims to use machine learning to find patterns in large amount of such timeline data to better understand how newborn resuscitation treatment is given and how it can be improved. The automatic video analysis and timeline generation will be developed for on-site usage, allowing for data-driven simulation and clinical debrief for health-care providers, and paving the way for automated real-time feedback. This brings added value to the medical staff, mothers and newborns, and society at large. Discussion The project is a interdisciplinary collaboration, combining AI, image processing, blockchain and cloud technology, with medical expertise, which will lead to increased competences and capacities in these various fields. Trial registration ISRCTNregistry, number ISRCTN12236970

Từ khóa


Tài liệu tham khảo

Wyckoff MH, Wyllie J, Aziz K, de Almeida MF, Fabres J, Fawke J, et al. Neonatal life support: 2020 international consensus on cardiopulmonary resuscitation and emergency cardiovascular care science with treatment recommendations. Circulation. 2020;142(16-suppl-1):S185–221.

Madar J, Roehr CC, Ainsworth S, Ersdal H, Morley C, Ruediger M, et al. European Resuscitation Council Guidelines 2021: Newborn resuscitation and support of transition of infants at birth. Resuscitation. 2021;161:291–326.

Bjorland PA, Øymar K, Ersdal HL, Rettedal SI. Incidence of newborn resuscitative interventions at birth and short-term outcomes: a regional population-based study. BMJ Paediatr Open. 2019;3(1). https://doi.org/10.1136/bmjpo-2019-000592.

World Health Organization (WHO). Children: improving survival and well-being. 2019. https://www.who.int/en/news-room/fact-sheets/detail/children-reducing-mortality. Accessed 2 Jan 2023.

Aslam HM, Saleem S, Afzal R, Iqbal U, Saleem SM, Shaikh MWA, et al. Risk factors of birth asphyxia. Ital J Pediatr. 2014;40(1):1–9.

Save the Children. Ending Newborn Deaths - Ensuring every baby survives. 2014. https://www.savethechildren.net/sites/default/files/libraries/ENDING-NEWBORN-DEATHS.pdf. Accessed 2 Jan 2023.

Manley BJ, Owen LS, Hooper SB, Jacobs SE, Cheong JL, Doyle LW, et al. Towards evidence-based resuscitation of the newborn infant. Lancet. 2017;389(10079):1639–48.

Ersdal HL, Mduma E, Svensen E, Perlman JM. Early initiation of basic resuscitation interventions including face mask ventilation may reduce birth asphyxia related mortality in low-income countries: a prospective descriptive observational study. Resuscitation. 2012;83(7):869–73.

Haug IA, Holte K, Chang CL, Purington C, Eilevstjønn J, Yeconia A, et al. Video analysis of newborn resuscitations after simulation-based helping babies breathe training. Clin Simul Nurs. 2020;44:68–78.

Jones BF, Plassmann P. Digital infrared thermal imaging of human skin. IEEE Eng Med Biol Mag. 2002;21(6):41–8.

Vardasca R, Magalhaes C, Mendes J. Biomedical applications of infrared thermal imaging: current state of machine learning classification. Multidiscip Digit Publ Inst Proc. 2019;27(1):46.

Costello JT, McInerney CD, Bleakley CM, Selfe J, Donnelly AE. The use of thermal imaging in assessing skin temperature following cryotherapy: a review. J Therm Biol. 2012;37(2):103–10.

Topalidou A, Ali N, Sekulic S, Downe S. Thermal imaging applications in neonatal care: a scoping review. BMC Pregnancy Childbirth. 2019;19(1):1–14.

Urakova N, Urakov A. Thermal imaging for increasing the diagnostic accuracy in fetal hypoxia: concept and practice suggestions. In: Ng, E., Etehadtavakol, M. (eds) Application of Infrared to Biomedical Sciences. Series in BioEngineering. Singapore: Springer; 2017. p. 277–89. https://doi.org/10.1007/978-981-10-3147-2_16.

Abbas AK, Heimann K, Jergus K, Orlikowsky T, Leonhardt S. Neonatal non-contact respiratory monitoring based on real-time infrared thermography. Biomed Eng Online. 2011;10(1):1–17.

Ornek AH, Ceylan M, Ervural S. Health status detection of neonates using infrared thermography and deep convolutional neural networks. Infrared Phys Technol. 2019;103:103044.

Knobel RB, Guenther BD, Rice HE. Thermoregulation and thermography in neonatal physiology and disease. Biol Res Nurs. 2011;13(3):274–82.

Center for research in computer vision. UCF101 - Action Recognition Data Set. 2012. https://www.crcv.ucf.edu/data/UCF101.php. Accsessed 2 Jan 2023.

Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T. HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (ICCV). Barcelona: IEEE; 2011. https://doi.org/10.1109/ICCV.2011.6126543.

Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L, Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE; 2009. p. 248–55.

Cheplygina V, de Bruijne M, Pluim JP. Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Med Image Anal. 2019;54:280–96.

Montes A, Salvador A, Pascual S, Giro-i Nieto X. Temporal activity detection in untrimmed videos with recurrent neural networks. 2016. arXiv preprint arXiv:1608.08128.

Gao M, Zhou Y, Xu R, Socher R, Xiong C. WOAD: Weakly supervised online action detection in untrimmed videos. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE; 2021. p. 1915–23. https://doi.org/10.1109/CVPR46437.2021.00195.

Dai R, Das S, Sharma S, Minciullo L, Garattoni L, Bremond F, et al. Toyota smarthome untrimmed: Real-world untrimmed videos for activity detection. IEEE Trans Pattern Anal Mach Intell. 2022;45:2533–50 . https://doi.org/10.1109/TPAMI.2022.3169976.

Gleason J, Schwarcz S, Ranjan R, Castillo CD, Chen JC, Chellappa R. Activity Detection in Untrimmed Videos Using Chunk-based Classifiers. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops. Snowmass: IEEE; 2020. p. 107–16. https://doi.org/10.1109/WACVW50321.2020.9096912.

Yang Y, Zhou DW, Zhan DC, Xiong H, Jiang Y. Adaptive deep models for incremental learning: Considering capacity scalability and sustainability. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM Digital library. 2019. p. 74–82. https://doi.org/10.1145/3292500.3330865.

Safer Births project information. www.saferbirths.com. Accessed 3 Jan 2023.

Laerdal Global Health. Neobeat: Newborn Heart Rate Meter. https://shop.laerdalglobalhealth.com/product/neobeat/. Accessed 3 Jan 2023.

Urdal J, Engan K, Eftestøl T, Naranjo V, Haug IA, Yeconia A, et al. Automatic identification of stimulation activities during newborn resuscitation using ECG and accelerometer signals. Comput Methods Programs Biomed. 2020;193:105445.

Meinich-Bache Ø, Austnes SL, Engan K, Austvoll I, Eftestøl T, Myklebust H, et al. Activity recognition from newborn resuscitation videos. IEEE J Biomed Health Inform. 2020;24(11):3258–67.

García-Torres J, Meinich-Bache Ø, Brunner S, Johannessen A, Rettedal S, Engan K, Towards using Thermal Cameras in Birth Detection. In: 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). Nafplio: IEEE; 2022. https://doi.org/10.1109/IVMSP54334.2022.9816177.

Rettedal S, Kibsgaard A, Eilevstjønn J, Kvaløy JT, Bjorland PA, Pike HM, et al. Impact of immediate and continuous heart rate feedback by dry electrode ECG on time to initiation of ventilation after birth: protocol for a randomised controlled trial. BMJ Open. 2022;12(9):e061839. https://doi.org/10.1136/bmjopen-2022-061839.

Patterson J. An Integrated mHealth Strategy to Improve Newborn Resuscitation in Low and Lower-Middle Income Countries. 2022. https://reporter.nih.gov/search/X-_wWWUTU0WFRnd0xw_60g/project-details/10671832. Accessed 3 Jan 2023.

Bettinger K, Mafuta E, Mackay A, Bose C, Myklebust H, Haug I, et al. Improving newborn resuscitation by making every birth a learning event. Children. 2021;8(12):1194.

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Thông tin tác giả