Machine learning model for predicting immediate postoperative desaturation using spirometry signal data
Abstract Postoperative desaturation is a common post-surgery pulmonary complication. The real-time prediction of postoperative desaturation can become a preventive measure, and real-time changes in spirometry data can provide valuable information on respiratory mechanics. However, there is a lack of...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-49062-9 |
_version_ | 1797388341170143232 |
---|---|
author | Youmin Shin Yoon Jung Kim Juseong Jin Seung-Bo Lee Hee-Soo Kim Young-Gon Kim |
author_facet | Youmin Shin Yoon Jung Kim Juseong Jin Seung-Bo Lee Hee-Soo Kim Young-Gon Kim |
author_sort | Youmin Shin |
collection | DOAJ |
description | Abstract Postoperative desaturation is a common post-surgery pulmonary complication. The real-time prediction of postoperative desaturation can become a preventive measure, and real-time changes in spirometry data can provide valuable information on respiratory mechanics. However, there is a lack of related research, specifically on using spirometry signals as inputs to machine learning (ML) models. We developed an ML model and postoperative desaturation prediction index (DPI) by analyzing intraoperative spirometry signals in patients undergoing laparoscopic surgery. We analyzed spirometry data from patients who underwent laparoscopic, robot-assisted gynecologic, or urologic surgery, identifying postoperative desaturation as a peripheral arterial oxygen saturation level below 95%, despite facial oxygen mask usage. We fitted the ML model on two separate datasets collected during different periods. (Datasets A and B). Dataset A (Normal 133, Desaturation 74) was used for the entire experimental process, including ML model fitting, statistical analysis, and DPI determination. Dataset B (Normal 20, Desaturation 4) was only used for verify the ML model and DPI. Four feature categories—signal property, inter-/intra-position correlation, peak value/interval variability, and demographics—were incorporated into the ML models via filter and wrapper feature selection methods. In experiments, the ML model achieved an adequate predictive capacity for postoperative desaturation, and the performance of the DPI was unbiased. |
first_indexed | 2024-03-08T22:39:21Z |
format | Article |
id | doaj.art-616e0bbda7ee458b8f21624aca896811 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-08T22:39:21Z |
publishDate | 2023-12-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-616e0bbda7ee458b8f21624aca8968112023-12-17T12:15:07ZengNature PortfolioScientific Reports2045-23222023-12-011311910.1038/s41598-023-49062-9Machine learning model for predicting immediate postoperative desaturation using spirometry signal dataYoumin Shin0Yoon Jung Kim1Juseong Jin2Seung-Bo Lee3Hee-Soo Kim4Young-Gon Kim5Department of Transdisciplinary Medicine, Seoul National University HospitalDepartment of Anesthesiology and Pain Medicine, Seoul National University Hospital, College of Medicine, Seoul National UniversityInterdisciplinary Program in Bio-engineering, Seoul National UniversityDepartment of Medical Informatics, Keimyung University School of MedicineDepartment of Anesthesiology and Pain Medicine, Seoul National University Hospital, College of Medicine, Seoul National UniversityDepartment of Transdisciplinary Medicine, Seoul National University HospitalAbstract Postoperative desaturation is a common post-surgery pulmonary complication. The real-time prediction of postoperative desaturation can become a preventive measure, and real-time changes in spirometry data can provide valuable information on respiratory mechanics. However, there is a lack of related research, specifically on using spirometry signals as inputs to machine learning (ML) models. We developed an ML model and postoperative desaturation prediction index (DPI) by analyzing intraoperative spirometry signals in patients undergoing laparoscopic surgery. We analyzed spirometry data from patients who underwent laparoscopic, robot-assisted gynecologic, or urologic surgery, identifying postoperative desaturation as a peripheral arterial oxygen saturation level below 95%, despite facial oxygen mask usage. We fitted the ML model on two separate datasets collected during different periods. (Datasets A and B). Dataset A (Normal 133, Desaturation 74) was used for the entire experimental process, including ML model fitting, statistical analysis, and DPI determination. Dataset B (Normal 20, Desaturation 4) was only used for verify the ML model and DPI. Four feature categories—signal property, inter-/intra-position correlation, peak value/interval variability, and demographics—were incorporated into the ML models via filter and wrapper feature selection methods. In experiments, the ML model achieved an adequate predictive capacity for postoperative desaturation, and the performance of the DPI was unbiased.https://doi.org/10.1038/s41598-023-49062-9 |
spellingShingle | Youmin Shin Yoon Jung Kim Juseong Jin Seung-Bo Lee Hee-Soo Kim Young-Gon Kim Machine learning model for predicting immediate postoperative desaturation using spirometry signal data Scientific Reports |
title | Machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
title_full | Machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
title_fullStr | Machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
title_full_unstemmed | Machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
title_short | Machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
title_sort | machine learning model for predicting immediate postoperative desaturation using spirometry signal data |
url | https://doi.org/10.1038/s41598-023-49062-9 |
work_keys_str_mv | AT youminshin machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata AT yoonjungkim machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata AT juseongjin machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata AT seungbolee machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata AT heesookim machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata AT younggonkim machinelearningmodelforpredictingimmediatepostoperativedesaturationusingspirometrysignaldata |