Continuous, Learned Imputation of Missing Values in Parkinson's Disease
Standard
Continuous, Learned Imputation of Missing Values in Parkinson's Disease. / Gundler, Christopher; Pötter-Nerger, Monika.
In: Stud Health Technol Inform, Vol. 316, 22.08.2024, p. 654-658.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Continuous, Learned Imputation of Missing Values in Parkinson's Disease
AU - Gundler, Christopher
AU - Pötter-Nerger, Monika
PY - 2024/8/22
Y1 - 2024/8/22
N2 - Parkinson's disease management requires accurate clinical scores but suffers from missing data. Leveraging self-supervised learning, we demonstrate superior generalization capabilities across populations compared to other well-established imputation techniques (MIWAE, MissForest, MICE). With the ability to employ the method already during the data collection and not afterward, the technology allows more robust data collection in clinical reality.
AB - Parkinson's disease management requires accurate clinical scores but suffers from missing data. Leveraging self-supervised learning, we demonstrate superior generalization capabilities across populations compared to other well-established imputation techniques (MIWAE, MissForest, MICE). With the ability to employ the method already during the data collection and not afterward, the technology allows more robust data collection in clinical reality.
KW - Parkinson Disease
KW - Humans
KW - Supervised Machine Learning
U2 - 10.3233/SHTI240499
DO - 10.3233/SHTI240499
M3 - SCORING: Journal article
C2 - 39176827
VL - 316
SP - 654
EP - 658
ER -