Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration
Abstract Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological sta...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2020-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-020-79007-5 |
id |
doaj-e942291820ca48d59ab2991c456caf30 |
---|---|
record_format |
Article |
spelling |
doaj-e942291820ca48d59ab2991c456caf302020-12-20T12:32:28ZengNature Publishing GroupScientific Reports2045-23222020-12-0110111010.1038/s41598-020-79007-5Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restorationZengyi Qin0Jiansheng Chen1Zhenyu Jiang2Xumin Yu3Chunhua Hu4Yu Ma5Suhua Miao6Rongsong Zhou7Department of Electronic Engineering, Tsinghua UniversityDepartment of Electronic Engineering, Tsinghua UniversityDepartment of Electronic Engineering, Tsinghua UniversityDepartment of Electronic Engineering, Tsinghua UniversitySchool of Aerospace Engineering, Tsinghua UniversityTsinghua University Yuquan HospitalTsinghua University Yuquan HospitalTsinghua University Yuquan HospitalAbstract Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological state is quantized into a few discrete classes during recording and labeling. The discreteness introduces misalignment between the true value and its label, meaning that these labels are unfortunately imprecise and coarse-grained. Most previous work did not consider the inaccuracy and directly utilized the coarse labels to train the machine learning algorithms, whose predictions are also coarse-grained. In this work, we propose to learn a precise, fine-grained estimation of physiological states using these coarse-grained ground truths. Established on mathematical rigorous proof, we utilize imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation. We demonstrate the effectiveness of our approach in assessing the pathological tremor in Parkinson’s Disease and estimating the systolic blood pressure from bioelectrical signals.https://doi.org/10.1038/s41598-020-79007-5 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zengyi Qin Jiansheng Chen Zhenyu Jiang Xumin Yu Chunhua Hu Yu Ma Suhua Miao Rongsong Zhou |
spellingShingle |
Zengyi Qin Jiansheng Chen Zhenyu Jiang Xumin Yu Chunhua Hu Yu Ma Suhua Miao Rongsong Zhou Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration Scientific Reports |
author_facet |
Zengyi Qin Jiansheng Chen Zhenyu Jiang Xumin Yu Chunhua Hu Yu Ma Suhua Miao Rongsong Zhou |
author_sort |
Zengyi Qin |
title |
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
title_short |
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
title_full |
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
title_fullStr |
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
title_full_unstemmed |
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
title_sort |
learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2020-12-01 |
description |
Abstract Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological state is quantized into a few discrete classes during recording and labeling. The discreteness introduces misalignment between the true value and its label, meaning that these labels are unfortunately imprecise and coarse-grained. Most previous work did not consider the inaccuracy and directly utilized the coarse labels to train the machine learning algorithms, whose predictions are also coarse-grained. In this work, we propose to learn a precise, fine-grained estimation of physiological states using these coarse-grained ground truths. Established on mathematical rigorous proof, we utilize imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation. We demonstrate the effectiveness of our approach in assessing the pathological tremor in Parkinson’s Disease and estimating the systolic blood pressure from bioelectrical signals. |
url |
https://doi.org/10.1038/s41598-020-79007-5 |
work_keys_str_mv |
AT zengyiqin learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT jianshengchen learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT zhenyujiang learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT xuminyu learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT chunhuahu learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT yuma learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT suhuamiao learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration AT rongsongzhou learningfinegrainedestimationofphysiologicalstatesfromcoarsegrainedlabelsbydistributionrestoration |
_version_ |
1724376543349702656 |