Smartphone camera oximetry in an induced hypoxemia study
Abstract Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate bloo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-09-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00665-y |
| _version_ | 1797642354544345088 |
|---|---|
| author | Jason S. Hoffman Varun K. Viswanath Caiwei Tian Xinyi Ding Matthew J. Thompson Eric C. Larson Shwetak N. Patel Edward J. Wang |
| author_facet | Jason S. Hoffman Varun K. Viswanath Caiwei Tian Xinyi Ding Matthew J. Thompson Eric C. Larson Shwetak N. Patel Edward J. Wang |
| author_sort | Jason S. Hoffman |
| collection | DOAJ |
| description | Abstract Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO2) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health. Towards this goal, we performed the first clinical development validation on a smartphone camera-based SpO2 sensing system using a varied fraction of inspired oxygen (FiO2) protocol, creating a clinically relevant validation dataset for solely smartphone-based contact PPG methods on a wider range of SpO2 values (70–100%) than prior studies (85–100%). We built a deep learning model using this data to demonstrate an overall MAE = 5.00% SpO2 while identifying positive cases of low SpO2 < 90% with 81% sensitivity and 79% specificity. We also provide the data in open-source format, so that others may build on this work. |
| first_indexed | 2024-03-11T13:58:52Z |
| format | Article |
| id | doaj.art-2637ce72ffd3438193df03560ee8fbeb |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-11T13:58:52Z |
| publishDate | 2022-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-2637ce72ffd3438193df03560ee8fbeb2023-11-02T05:20:54ZengNature Portfolionpj Digital Medicine2398-63522022-09-015111010.1038/s41746-022-00665-ySmartphone camera oximetry in an induced hypoxemia studyJason S. Hoffman0Varun K. Viswanath1Caiwei Tian2Xinyi Ding3Matthew J. Thompson4Eric C. Larson5Shwetak N. Patel6Edward J. Wang7Paul G. Allen School of Computer Science and Engineering, University of WashingtonDepartment of Electrical and Computer Engineering, University of California San DiegoPaul G. Allen School of Computer Science and Engineering, University of WashingtonDepartment of Computer Science, Southern Methodist UniversityDepartment of Family Medicine, University of WashingtonDepartment of Computer Science, Southern Methodist UniversityPaul G. Allen School of Computer Science and Engineering, University of WashingtonDepartment of Electrical and Computer Engineering, University of California San DiegoAbstract Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO2) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health. Towards this goal, we performed the first clinical development validation on a smartphone camera-based SpO2 sensing system using a varied fraction of inspired oxygen (FiO2) protocol, creating a clinically relevant validation dataset for solely smartphone-based contact PPG methods on a wider range of SpO2 values (70–100%) than prior studies (85–100%). We built a deep learning model using this data to demonstrate an overall MAE = 5.00% SpO2 while identifying positive cases of low SpO2 < 90% with 81% sensitivity and 79% specificity. We also provide the data in open-source format, so that others may build on this work.https://doi.org/10.1038/s41746-022-00665-y |
| spellingShingle | Jason S. Hoffman Varun K. Viswanath Caiwei Tian Xinyi Ding Matthew J. Thompson Eric C. Larson Shwetak N. Patel Edward J. Wang Smartphone camera oximetry in an induced hypoxemia study npj Digital Medicine |
| title | Smartphone camera oximetry in an induced hypoxemia study |
| title_full | Smartphone camera oximetry in an induced hypoxemia study |
| title_fullStr | Smartphone camera oximetry in an induced hypoxemia study |
| title_full_unstemmed | Smartphone camera oximetry in an induced hypoxemia study |
| title_short | Smartphone camera oximetry in an induced hypoxemia study |
| title_sort | smartphone camera oximetry in an induced hypoxemia study |
| url | https://doi.org/10.1038/s41746-022-00665-y |
| work_keys_str_mv | AT jasonshoffman smartphonecameraoximetryinaninducedhypoxemiastudy AT varunkviswanath smartphonecameraoximetryinaninducedhypoxemiastudy AT caiweitian smartphonecameraoximetryinaninducedhypoxemiastudy AT xinyiding smartphonecameraoximetryinaninducedhypoxemiastudy AT matthewjthompson smartphonecameraoximetryinaninducedhypoxemiastudy AT ericclarson smartphonecameraoximetryinaninducedhypoxemiastudy AT shwetaknpatel smartphonecameraoximetryinaninducedhypoxemiastudy AT edwardjwang smartphonecameraoximetryinaninducedhypoxemiastudy |