Format

Send to

Choose Destination
Stud Health Technol Inform. 2019 Aug 21;264:1596-1597. doi: 10.3233/SHTI190552.

Early Nephrosis Detection Based on Deep Learning with Clinical Time-Series Data.

Author information

1
Graduate School of Informatics Kyoto University, Kyoto-City, Kyoto, Japan.
2
Kyoto University Hospital, Kyoto-City, Kyoto, Japan.

Abstract

Nephrosis is disease characterized by abnormal protein loss from impaired kidney. We constructed early prediction model using machine learning from clinical time series data, that can predict onset of nephrosis for more than one month. Long short-term memory capable of recognizing temporal sequential data patterns, was adopted as early prediction model for nephrosis. We verified our proposed prediction model has higher accuracy compared with those of baseline classifiers by 5-fold cross validation.

KEYWORDS:

Decision support techniques; nephrosis; supervised machine learning

PMID:
31438249
DOI:
10.3233/SHTI190552
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IOS Press
Loading ...
Support Center