Prediction of chronic kidney disease progression using recurrent neural network and electronic health records
Yitan Zhu, Dehua Bi, Milda Saunders, Yuan Ji · 2023
Read Prediction of chronic kidney disease progression using recurrent neural network and electronic health records by Yitan Zhu, Dehua Bi, Milda Saunders, Yuan Ji (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10716428.txt.
Description
Chronic kidney disease slowly robs the kidneys of their filtering power, and catching fast decliners early can change their care. Yitan Zhu and three co-authors built a computer model in 2023 that reads a patient's record over time to predict who will slide from early to late stage disease. The model is a recurrent neural network, a design that learns from sequences rather than single snapshots.
Using only the history of one blood based kidney measure, the model scored 0.957 on a standard accuracy scale. Adding lab results, vital signs, and habits raised the score to 0.967. It beat older tools such as random forests and survival models. The authors say the record history alone carries strong warning value.
Catalog record
| CREATOR | Yitan Zhu, Dehua Bi, Milda Saunders, Yuan Ji |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |