Machine Learning-Based Automatic Classification of Video Recorded Neonatal Manipulations and Associated Physiological Parameters: A Feasibility Study
- 주제(키워드) CNN , electronic medical records , IoT , LSTM , machine learning , neonatal intensive care units , physiological deviations , physiological parameters , streaming server , video monitoring
- 주제(기타) Pediatrics
- 설명문(일반) [Singh, Harpreet; Gupta, Shubham; Kalra, Jayant; Kaur, Ravneet; Das, Ritu] Child Hlth Imprints CHIL Pte Ltd, Singapore 048545, Singapore; [Kusuda, Satoshi] Kyorin Univ, Dept Pediat, Tokyo 1818612, Japan; [McAdams, Ryan M.] Univ Wisconsin, Dept Pediat, Sch Med & Publ Hlth, Madison, WI 53726 USA; [Anand, Saket] Indraprastha Inst Informat Technol, Dept Comp Sci & Engn, New Delhi 110020, India; [Pandey, Ashish Kumar] Indraprastha Inst Informat Technol, Dept Math, New Delhi 110020, India; [Cho, Su Jin] Ewha Womans Univ Seoul, Coll Med, Seoul 03760, South Korea; [Saluja, Satish] Sir Ganga Ram Hosp, Dept Neonatol, New Delhi 110060, India; [Boutilier, Justin J.] Univ Wisconsin, Coll Engn, Dept Ind & Syst Engn, Madison, WI 53706 USA; [Saria, Suchi] Johns Hopkins Univ, Machine Learning & Healthcare Lab, 3400 N Charles St, Baltimore, MD 21218 USA; [Palma, Jonathan] Stanford Univ, Dept Pediat, Stanford, CA 94305 USA; [Kaur, Avneet] Apollo Cradle Hosp, Dept Neonatol, New Delhi 110015, India; [Yadav, Gautam] Kalawati Hosp, Dept Pediat, Rewari 123401, India; [Sun, Yao] Univ Calif San Francisco, Div Neonatol, San Francisco, CA 92521 USA
- 등재 SCIE
- OA유형 Green Published, gold
- 발행기관 MDPI
- 발행년도 2021
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000175480
- 본문언어 영어
- Published As http://dx.doi.org/10.3390/children8010001
- PubMed https://pubmed.ncbi.nlm.nih.gov/33375101
초록/요약
Our objective in this study was to determine if machine learning (ML) can automatically recognize neonatal manipulations, along with associated changes in physiological parameters. A retrospective observational study was carried out in two Neonatal Intensive Care Units (NICUs) between December 2019 to April 2020. Both the video and physiological data (heart rate (HR) and oxygen saturation (SpO(2))) were captured during NICU hospitalization. The proposed classification of neonatal manipulations was achieved by a deep learning system consisting of an Inception-v3 convolutional neural network (CNN), followed by transfer learning layers of Long Short-Term Memory (LSTM). Physiological signals prior to manipulations (baseline) were compared to during and after manipulations. The validation of the system was done using the leave-one-out strategy with input of 8 s of video exhibiting manipulation activity. Ten neonates were video recorded during an average length of stay of 24.5 days. Each neonate had an average of 528 manipulations during their NICU hospitalization, with the average duration of performing these manipulations varying from 28.9 s for patting, 45.5 s for a diaper change, and 108.9 s for tube feeding. The accuracy of the system was 95% for training and 85% for the validation dataset. In neonates <32 weeks' gestation, diaper changes were associated with significant changes in HR and SpO(2), and, for neonates >= 32 weeks' gestation, patting and tube feeding were associated with significant changes in HR. The presented system can classify and document the manipulations with high accuracy. Moreover, the study suggests that manipulations impact physiological parameters.
more