Accounting for Label Uncertainty in Machine Learning for Detection of Acute Respiratory Distress Syndrome.
Saved in:
| Title: | Accounting for Label Uncertainty in Machine Learning for Detection of Acute Respiratory Distress Syndrome. |
|---|---|
| Authors: | Reamaroon, Narathip, Sjoding, Michael W., Lin, Kaiwen, Iwashyna, Theodore J., Najarian, Kayvan |
| Source: | IEEE Journal of Biomedical & Health Informatics. Jan2019, Vol. 23 Issue 1, p407-415. 9p. |
| Subjects: | Adult respiratory distress syndrome, Supervised learning, Support vector machines, Time series analysis, Electronic health records |
| Abstract: | When training a machine learning algorithm for a supervised-learning task in some clinical applications, uncertainty in the correct labels of some patients may adversely affect the performance of the algorithm. For example, even clinical experts may have less confidence when assigning a medical diagnosis to some patients because of ambiguity in the patient's case or imperfect reliability of the diagnostic criteria. As a result, some cases used in algorithm training may be mislabeled, adversely affecting the algorithm's performance. However, experts may also be able to quantify their diagnostic uncertainty in these cases. We present a robust method implemented with support vector machines (SVM) to account for such clinical diagnostic uncertainty when training an algorithm to detect patients who develop the acute respiratory distress syndrome (ARDS). ARDS is a syndrome of the critically ill that is diagnosed using clinical criteria known to be imperfect. We represent uncertainty in the diagnosis of ARDS as a graded weight of confidence associated with each training label. We also performed a novel time-series sampling method to address the problem of intercorrelation among the longitudinal clinical data from each patient used in model training to limit overfitting. Preliminary results show that we can achieve meaningful improvement in the performance of algorithm to detect patients with ARDS on a hold-out sample, when we compare our method that accounts for the uncertainty of training labels with a conventional SVM algorithm. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 134019875 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Accounting for Label Uncertainty in Machine Learning for Detection of Acute Respiratory Distress Syndrome. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Reamaroon%2C+Narathip%22">Reamaroon, Narathip</searchLink><br /><searchLink fieldCode="AR" term="%22Sjoding%2C+Michael+W%2E%22">Sjoding, Michael W.</searchLink><br /><searchLink fieldCode="AR" term="%22Lin%2C+Kaiwen%22">Lin, Kaiwen</searchLink><br /><searchLink fieldCode="AR" term="%22Iwashyna%2C+Theodore+J%2E%22">Iwashyna, Theodore J.</searchLink><br /><searchLink fieldCode="AR" term="%22Najarian%2C+Kayvan%22">Najarian, Kayvan</searchLink> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Journal+of+Biomedical+%26+Health+Informatics%22">IEEE Journal of Biomedical & Health Informatics</searchLink>. Jan2019, Vol. 23 Issue 1, p407-415. 9p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Adult+respiratory+distress+syndrome%22">Adult respiratory distress syndrome</searchLink><br /><searchLink fieldCode="DE" term="%22Supervised+learning%22">Supervised learning</searchLink><br /><searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink><br /><searchLink fieldCode="DE" term="%22Time+series+analysis%22">Time series analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+health+records%22">Electronic health records</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: When training a machine learning algorithm for a supervised-learning task in some clinical applications, uncertainty in the correct labels of some patients may adversely affect the performance of the algorithm. For example, even clinical experts may have less confidence when assigning a medical diagnosis to some patients because of ambiguity in the patient's case or imperfect reliability of the diagnostic criteria. As a result, some cases used in algorithm training may be mislabeled, adversely affecting the algorithm's performance. However, experts may also be able to quantify their diagnostic uncertainty in these cases. We present a robust method implemented with support vector machines (SVM) to account for such clinical diagnostic uncertainty when training an algorithm to detect patients who develop the acute respiratory distress syndrome (ARDS). ARDS is a syndrome of the critically ill that is diagnosed using clinical criteria known to be imperfect. We represent uncertainty in the diagnosis of ARDS as a graded weight of confidence associated with each training label. We also performed a novel time-series sampling method to address the problem of intercorrelation among the longitudinal clinical data from each patient used in model training to limit overfitting. Preliminary results show that we can achieve meaningful improvement in the performance of algorithm to detect patients with ARDS on a hold-out sample, when we compare our method that accounts for the uncertainty of training labels with a conventional SVM algorithm. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=134019875 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/JBHI.2018.2810820 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 9 StartPage: 407 Subjects: – SubjectFull: Adult respiratory distress syndrome Type: general – SubjectFull: Supervised learning Type: general – SubjectFull: Support vector machines Type: general – SubjectFull: Time series analysis Type: general – SubjectFull: Electronic health records Type: general Titles: – TitleFull: Accounting for Label Uncertainty in Machine Learning for Detection of Acute Respiratory Distress Syndrome. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Reamaroon, Narathip – PersonEntity: Name: NameFull: Sjoding, Michael W. – PersonEntity: Name: NameFull: Lin, Kaiwen – PersonEntity: Name: NameFull: Iwashyna, Theodore J. – PersonEntity: Name: NameFull: Najarian, Kayvan IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: Jan2019 Type: published Y: 2019 Identifiers: – Type: issn-print Value: 21682194 Numbering: – Type: volume Value: 23 – Type: issue Value: 1 Titles: – TitleFull: IEEE Journal of Biomedical & Health Informatics Type: main |
| ResultId | 1 |
