Interpretable deep learning survival predictions in sporadic Creutzfeldt–Jakob disease
Johnny Tam, John Centola, Hatice Kurucu, Neil Watson, Janet MacKenzie, Alison Green, David Summers, Marcelo Barria, Sohan Seth, Colin Smith, Suvankar Pal · 2024
Read Interpretable deep learning survival predictions in sporadic Creutzfeldt–Jakob disease by Johnny Tam, John Centola, Hatice Kurucu, Neil Watson, Janet MacKenzie, Alison Green, David Summers, Marcelo Barria, Sohan Seth, Colin Smith, Suvankar Pal (2024) 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-11649833.txt.
Description
Johnny Tam and co-authors build a deep learning model to forecast survival in a fatal prion disease, in a 2024 study. Sporadic Creutzfeldt-Jakob disease advances fast and always ends in death. How long a patient lives varies a lot, which makes planning care hard. The team used national surveillance data from the United Kingdom.
More than six hundred confirmed cases supplied symptoms, spinal fluid tests, brain scans, and gene details. A neural network built for survival analysis produced the forecasts. Explanation tools then showed which inputs drove each result. The model edged past a classic survival method, though not by a clear margin. Two factors stood out in both: a gene variant and a spinal fluid protein.
Catalog record
| CREATOR | Johnny Tam, John Centola, Hatice Kurucu, Neil Watson, Janet MacKenzie, Alison Green, David Summers, Marcelo Barria, Sohan Seth, Colin Smith, Suvankar Pal |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |