Dementia Language Models: a generalizable and controllable representation of cognitive impairment
Peled-Cohen, L.; Shmidov, A.; Rein, N.; Shapira, E.; Calderon, N.; Tikochinski, R.; Zeltzer, E.; Nathan, T.; Uliel, B.; Mueller, K. D.; Ganmore, I.; Reis, B.; Reichart, R.
Show abstract
We introduce Dementia Language Models (DLMs)--a generalizable and controllable representation of cognitive impairment through language--alongside an evaluation framework for establishing their validity and clinical grounding. DLMs created by large language models fine-tuned on a small clinical corpus successfully generated patient-like narratives across unseen tasks, received predicted MMSE scores in the impaired range, and produced narratives that neurologists identified with accuracy comparable to real transcripts. The models' internal representations themselves, as well as their non-linguistic decision-making, supported cognitive-state detection in unseen cohorts. The effect was controllable: moving from Healthy toward Dementia in weight space progressively worsened language and predicted MMSE scores while increasing dementia probability. DLMs could support clinician training, hypothesis generation, and scalable experimentation, reserving patient involvement for where it is truly needed.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Large language models improve transferability of electronic health record-based predictions across countries and coding systems 93%
- Interpretable Fine-tuned Large Language Models Facilitate Making Genetic Test Decisions for Rare Diseases 92%
- Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults 92%
Similar papers in this journal
Similar papers in this journal
- Stratification of Alzheimer's Disease Patients Using Knowledge-Guided Unsupervised Latent Factor Clustering with Electronic Health Record Data 91%
- Pretrained Patient Trajectories for Adverse Drug Event Prediction Using Common Data Model-based Electronic Health Records 91%
- Spatial Navigation as a Digital Marker for Clinically Differentiating Cognitive Impairment Severity 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.