Predicting explainable dementia types with LLM-aided feature engineering

Topic: Risk, prevention and care in population studies

MOTIVATION: The integration of Machine Learning and Artificial Intelligence (AI) into healthcare has immense potential due to the rapidly growing volume of clinical data. However, existing AI models, particularly Large Language Models (LLMs) like GPT-4, face significant challenges in terms of explainability and reliability, particularly in high-stakes domains like healthcare. RESULTS: This paper proposes a novel LLM-aided feature engineering approach that enhances interpretability by extracting clinically relevant features from the Oxford Textbook of Medicine. By converting clinical notes into concept vector representations and employing a linear classifier, our method achieved an accuracy of 0.72, outperforming a traditional n-gram Logistic Regression baseline (0.64) and the GPT-4 baseline (0.48), while focusing on high-level clinical features. We also explore using Text Embeddings to reduce the overall time and cost of our approach by 97%. AVAILABILITY AND IMPLEMENTATION: All code relevant to this paper is available at: https://github.com/AdityaKashyap423/Dementia_LLM_Feature_Engineering/tree/main.

Key findings

• However, existing AI models, particularly Large Language Models (LLMs) like GPT-4, face significant challenges in terms of explainability and reliability, particularly in high-stakes domains like healthcare.
• RESULTS: This paper proposes a novel LLM-aided feature engineering approach that enhances interpretability by extracting clinically relevant features from the Oxford Textbook of Medicine.
• We also explore using Text Embeddings to reduce the overall time and cost of our approach by 97%.

Why it matters

This paper proposes an LLM-aided feature engineering approach to make machine learning predictions of dementia types more explainable, achieving accuracy of 0.72. It is about improving the interpretability of diagnostic models, not about treating, curing, or preventing Alzheimer's disease.

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.1093/bioinformatics/btaf156
• PubMed: 40199828
• Original source →
• Free full text: Bioinformatics →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{kashyap2025-40199828,
  author  = {Kashyap, Aditya M and Rao, Delip and Boland, Mary Regina and Shen, Li and Callison-Burch, Chris},
  title   = {{Predicting explainable dementia types with LLM-aided feature engineering}},
  journal = {Bioinformatics},
  year    = {2025},
  doi     = {10.1093/bioinformatics/btaf156},
  pmid    = {40199828},
  url     = {https://doi.org/10.1093/bioinformatics/btaf156}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here.

• Alzheimer's Disease: Epidemiology and Clinical Progression Neurology and therapy · 2022-03-14 · usefulness score 55/100 · Getting a diagnosis
• The Alzheimer's Disease Clinical Spectrum: Diagnosis and Management The Medical clinics of North America · 2019-03-01 · usefulness score 54/100 · Getting a diagnosis
• Diversity and disparity in dementia: the impact of ethnoracial differences in Alzheimer disease Alzheimer disease and associated disorders · 2011-07-01 · usefulness score 47/100 · Getting a diagnosis

Later studies that cite this one

1 study in the alzhub library lists this one in its references.

• Integrative machine learning approach to risk prediction for dementia and Alzheimer’s disease GeroScience · 2025-08-27 · usefulness score 50/100 · Digital health tools

Related studies in Digital health tools

• Explainable machine learning for predicting longitudinal dementia status: Establishing a leakage-free benchmark PLOS Digital Health · 2026-05-18 · usefulness score 50/100
• nterpretable Alzheimer’s Disease Detection from CHAT Transcripts Using Criterion-Guided LLM Prompting and In-Context Learning Research Square · 2026-09-10 · usefulness score 16/100
• A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease Scientific reports · 2021-01-29 · usefulness score 76/100
• An explainable machine learning approach for Alzheimer's disease classification Scientific reports · 2024-02-01 · usefulness score 56/100
• Explainable machine learning models for identifying mild cognitive impairment in older patients with chronic pain BMC Nursing · 2025-01-21 · usefulness score 55/100
• Explainable AI-based Alzheimer's prediction and management using multimodal data PloS one · 2023-11-16 · usefulness score 53/100

Also tagged “prevalence”

1,224 studies in the library carry the topic tag “prevalence”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,224 tagged studies.

• Perspectives in dementia risk reduction – food for thought Neurodegenerative Disease Management · 2026-05-11 · usefulness score 33/100 · Prevention and risk
• Alzheimer's disease and dementia in Japan: Epidemiological trends, regional disparities, and future projections Alzheimer s & Dementia · 2025-07-01 · usefulness score 42/100 · Disparities
• Prevalence of dementia subtypes in United States Medicare fee-for-service beneficiaries, 2011-2013 Alzheimer's & dementia : the journal of the Alzheimer's Association · 2016-05-10 · usefulness score 59/100 · Getting a diagnosis

Similar studies

• Predicting dementia from spontaneous speech using large language models 2022 · Digital health tools
• MMSE-Based Dementia Prediction: Deep vs. Traditional Models 2025 · Cognitive tests and assessment
• Leveraging explainable artificial intelligence with ensemble of deep learning model for dementia prediction to enhance clinical decision support systems 2025 · Digital health tools
• Explainable Machine Learning-Based Classification of Clinical Dementia Ratings Using a Tablet-Based Cognitive Assessment 2025 · Getting a diagnosis
• Predicting Cognitive Impairment and Dementia: A Machine Learning Approach 2020 · Digital health tools
• Developing an explainable machine learning and fog computing-based visual rating scale for the prediction of dementia progression 2025 · Digital health tools

More on Digital health tools

• A review that covers this ground Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review Medical image analysis · 2020-10-06 · usefulness score 70/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →