Reinforcement learning-driven adaptive game therapy for cognitive impairment patients with improved vision transformer based detection model
Youseef Alotaibi, Surendran Rajendran · 2026
Read Reinforcement learning-driven adaptive game therapy for cognitive impairment patients with improved vision transformer based detection model by Youseef Alotaibi, Surendran Rajendran (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/PMC13555988.txt.
Description
Youseef Alotaibi and Surendran Rajendran presented in 2026 a system that pairs detection of cognitive impairment with adaptive game therapy. Their design reads brain scans and tries to catch decline early in conditions such as Alzheimer's disease. A game component then adjusts its difficulty to each patient, aiming to keep therapy matched to ability.
The detection side combines an improved vision transformer with a recurrent network, so spatial detail and change across scan slices both inform the result. A reinforcement learning method, driven by an iterative hiking search, tunes game difficulty as the patient plays. Reported test scores were very high across accuracy, recall, and related measures. The authors present the pairing as a way to join diagnosis with engaging, personalised treatment.
Catalog record
| CREATOR | Youseef Alotaibi, Surendran Rajendran |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 86104 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |