Development and application of a multi-task fusion model using susceptibility-weighted imaging-based substantia nigra and adjacent structures for prognostic prediction of subthalamic nucleus deep brain stimulation in Parkinson’s disease
Chi Xiong, Kun Wang, Erkang Cheng, Zhiyong Sun, Bin Cai, Chaoshi Niu, Bo Song · 2026
Read Development and application of a multi-task fusion model using susceptibility-weighted imaging-based substantia nigra and adjacent structures for prognostic prediction of subthalamic nucleus deep brain stimulation in Parkinson’s disease by Chi Xiong, Kun Wang, Erkang Cheng, Zhiyong Sun, Bin Cai, Chaoshi Niu, Bo Song (2026) 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-13563298.txt.
Description
Chi Xiong and co-authors build a 2026 computer model to predict who gains most from deep brain stimulation for Parkinson disease. The treatment sends pulses to a small brain target, and results vary a lot by patient. Their model reads brain scans taken before surgery, focused on the substantia nigra and nearby areas.
The model joins two tasks at once, sorting patients by likely response and estimating the size of the gain. Good response meant at least half better on a standard movement score one year after surgery. In a first group of 36 patients the model beat simpler models, and in a wider group of 60 it reached 88.3 percent accuracy.
Catalog record
| CREATOR | Chi Xiong, Kun Wang, Erkang Cheng, Zhiyong Sun, Bin Cai, Chaoshi Niu, Bo Song |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |