Applications of deep learning methods in digital biomarker research using noninvasive sensing data
Introduction: Noninvasive digital biomarkers are critical elements in digital healthcare in terms of not only the ease of measurement but also their use of raw data. In recent years, deep learning methods have been put to use to analyze these diverse heterogeneous data; these methods include represe...
| Main Authors: | , , , , , |
|---|---|
| 格式: | Article |
| 語言: | English |
| 出版: |
SAGE Publishing
2022-11-01
|
| 叢編: | Digital Health |
| 在線閱讀: | https://doi.org/10.1177/20552076221136642 |
| _version_ | 1828157011370442752 |
|---|---|
| author | Hoyeon Jeong Yong W Jeong Yeonjae Park Kise Kim Junghwan Park Dae R Kang |
| author_facet | Hoyeon Jeong Yong W Jeong Yeonjae Park Kise Kim Junghwan Park Dae R Kang |
| author_sort | Hoyeon Jeong |
| collection | DOAJ |
| description | Introduction: Noninvasive digital biomarkers are critical elements in digital healthcare in terms of not only the ease of measurement but also their use of raw data. In recent years, deep learning methods have been put to use to analyze these diverse heterogeneous data; these methods include representation learning for feature extraction and supervised learning for the prediction of these biomarkers. Methods: We introduce clinical cases of digital biomarkers and various deep-learning methods applied according to each data type. In addition, deep learning methods for the integrated analysis of multidimensional heterogeneous data are introduced, and the utility of these data as an integrated digital biomarker is presented. The current status of digital biomarker research is examined by surveying research cases applied to various types of data as well as modeling methods. Results: We present a future research direction for using data from heterogeneous sources together by introducing deep learning methods for dimensionality reduction and mode integration from multimodal digital biomarker studies covering related domains. The integration of multimodality has led to advances in research through the improvement of performance and complementarity between modes. Discussion: The integrative digital biomarker will be more useful for research on diseases that require data from multiple sources to be treated together. Since delicate signals from patients are not missed and the interaction effects between signals are also considered, it will be helpful for immediate detection and more accurate prediction of symptoms. |
| first_indexed | 2024-04-11T23:22:23Z |
| format | Article |
| id | doaj.art-962435f6c2064ac689c901b5f49a9af7 |
| institution | Directory Open Access Journal |
| issn | 2055-2076 |
| language | English |
| last_indexed | 2024-04-11T23:22:23Z |
| publishDate | 2022-11-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj.art-962435f6c2064ac689c901b5f49a9af72022-12-22T03:57:25ZengSAGE PublishingDigital Health2055-20762022-11-01810.1177/20552076221136642Applications of deep learning methods in digital biomarker research using noninvasive sensing data Hoyeon Jeong0Yong W Jeong1Yeonjae Park2Kise Kim3Junghwan Park4Dae R Kang5 Department of Biostatistics, , Wonju, Republic of Korea Department of Biostatistics, , Wonju, Republic of Korea Department of Biostatistics, , Wonju, Republic of Korea School of Health and Environmental Science, , Seoul, Republic of Korea MEZOO Co., Ltd., Wonju, Republic of Korea Department of Precision Medicine, , Wonju, Republic of KoreaIntroduction: Noninvasive digital biomarkers are critical elements in digital healthcare in terms of not only the ease of measurement but also their use of raw data. In recent years, deep learning methods have been put to use to analyze these diverse heterogeneous data; these methods include representation learning for feature extraction and supervised learning for the prediction of these biomarkers. Methods: We introduce clinical cases of digital biomarkers and various deep-learning methods applied according to each data type. In addition, deep learning methods for the integrated analysis of multidimensional heterogeneous data are introduced, and the utility of these data as an integrated digital biomarker is presented. The current status of digital biomarker research is examined by surveying research cases applied to various types of data as well as modeling methods. Results: We present a future research direction for using data from heterogeneous sources together by introducing deep learning methods for dimensionality reduction and mode integration from multimodal digital biomarker studies covering related domains. The integration of multimodality has led to advances in research through the improvement of performance and complementarity between modes. Discussion: The integrative digital biomarker will be more useful for research on diseases that require data from multiple sources to be treated together. Since delicate signals from patients are not missed and the interaction effects between signals are also considered, it will be helpful for immediate detection and more accurate prediction of symptoms.https://doi.org/10.1177/20552076221136642 |
| spellingShingle | Hoyeon Jeong Yong W Jeong Yeonjae Park Kise Kim Junghwan Park Dae R Kang Applications of deep learning methods in digital biomarker research using noninvasive sensing data Digital Health |
| title | Applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| title_full | Applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| title_fullStr | Applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| title_full_unstemmed | Applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| title_short | Applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| title_sort | applications of deep learning methods in digital biomarker research using noninvasive sensing data |
| url | https://doi.org/10.1177/20552076221136642 |
| work_keys_str_mv | AT hoyeonjeong applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata AT yongwjeong applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata AT yeonjaepark applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata AT kisekim applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata AT junghwanpark applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata AT daerkang applicationsofdeeplearningmethodsindigitalbiomarkerresearchusingnoninvasivesensingdata |