{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:13:02Z","timestamp":1791915182300,"version":"4.3.4"},"reference-count":58,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01 AG066833"],"award-info":[{"award-number":["U01 AG066833"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 AG073105"],"award-info":[{"award-number":["P30 AG073105"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>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%.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All code relevant to this paper is available at: https:\/\/github.com\/AdityaKashyap423\/Dementia_LLM_Feature_Engineering\/tree\/main.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf156","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T03:02:58Z","timestamp":1744167778000},"source":"Crossref","is-referenced-by-count":15,"title":["Predicting explainable dementia types with LLM-aided feature engineering"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6104-3037","authenticated-orcid":false,"given":"Aditya M","family":"Kashyap","sequence":"first","affiliation":[{"name":"Department of Computer and Information Science, University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4534-9906","authenticated-orcid":false,"given":"Delip","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-6408","authenticated-orcid":false,"given":"Mary Regina","family":"Boland","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Data Science, Saint Vincent College , Latrobe, PA 15650,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5443-0503","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8196-1943","authenticated-orcid":false,"given":"Chris","family":"Callison-Burch","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"2025042501213135600_btaf156-B1","author":"Achiam","year":"2023"},{"key":"2025042501213135600_btaf156-B2","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"2025042501213135600_btaf156-B3","author":"Alsentzer","year":"2019"},{"key":"2025042501213135600_btaf156-B4","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.mcna.2018.10.009","article-title":"The Alzheimer\u2019s disease clinical spectrum: diagnosis and management","volume":"103","author":"Atri","year":"2019","journal-title":"Med Clin North Am"},{"key":"2025042501213135600_btaf156-B5","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.jalz.2018.09.009","article-title":"Perspectives on ethnic and racial disparities in Alzheimer\u2019s disease and related dementias: update and areas of immediate need","volume":"15","author":"Babulal","year":"2019","journal-title":"Alzheimers Dement"},{"key":"2025042501213135600_btaf156-B6","author":"Bahdanau","year":"2014"},{"key":"2025042501213135600_btaf156-B7","author":"Basaj","year":"2018"},{"key":"2025042501213135600_btaf156-B8","author":"Bastings","year":"2019"},{"key":"2025042501213135600_btaf156-B9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025042501213135600_btaf156-B10","first-page":"9539","article-title":"e-SNLI: natural language inference with natural language explanations","volume":"31","author":"Camburu","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025042501213135600_btaf156-B11","author":"Camburu","year":"2019"},{"key":"2025042501213135600_btaf156-B12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","article-title":"Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios","volume":"47","author":"Cascella","year":"2023","journal-title":"J Med Syst"},{"key":"2025042501213135600_btaf156-B13","first-page":"1","author":"Chakraborty","year":"2017"},{"key":"2025042501213135600_btaf156-B14","doi-asserted-by":"crossref","first-page":"e342","DOI":"10.1016\/j.wneu.2023.08.088","article-title":"Chat GPT as a neuro-score calculator: analysis of a large language model\u2019s performance on various neurological exam grading scales","volume":"179","author":"Chen","year":"2023","journal-title":"World Neurosurg"},{"key":"2025042501213135600_btaf156-B15","first-page":"6","author":"Chiang","year":"2023"},{"key":"2025042501213135600_btaf156-B16","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1097\/WAD.0b013e318211c6c9","article-title":"Diversity and disparity in dementia: the impact of ethnoracial differences in Alzheimer disease","volume":"25","author":"Chin","year":"2011","journal-title":"Alzheimer Dis Assoc Disord"},{"key":"2025042501213135600_btaf156-B17","author":"Devlin","year":"2018"},{"key":"2025042501213135600_btaf156-B18","author":"Hendricks","year":"2018"},{"key":"2025042501213135600_btaf156-B19","first-page":"175","article-title":"Big data in health care: applications and challenges","volume":"2","author":"Hong","year":"2018","journal-title":"Data Inf Manag"},{"key":"2025042501213135600_btaf156-B20","author":"Hu","year":"2021"},{"key":"2025042501213135600_btaf156-B21","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"2025042501213135600_btaf156-B22","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1586\/ern.11.155","article-title":"Distinguishing Alzheimer\u2019s disease from other major forms of dementia","volume":"11","author":"Karantzoulis","year":"2011","journal-title":"Expert Rev Neurother"},{"key":"2025042501213135600_btaf156-B23","first-page":"5338","author":"Koh","year":"2020"},{"key":"2025042501213135600_btaf156-B24","author":"Kumar","year":"2020"},{"key":"2025042501213135600_btaf156-B25","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2025042501213135600_btaf156-B26","first-page":"552","author":"Li","year":"2018"},{"key":"2025042501213135600_btaf156-B27","doi-asserted-by":"crossref","first-page":"e48568","DOI":"10.2196\/48568","article-title":"Utility of ChatGPT in clinical practice","volume":"25","author":"Liu","year":"2023","journal-title":"J Med Internet Res"},{"key":"2025042501213135600_btaf156-B28","first-page":"1","article-title":"Local interpretations for explainable natural language processing: a survey","volume":"56","author":"Luo","year":"2024","journal-title":"ACM Comput Surv"},{"key":"2025042501213135600_btaf156-B29","author":"Luong","year":"2015"},{"key":"2025042501213135600_btaf156-B30","author":"McCoy","year":"2019"},{"key":"2025042501213135600_btaf156-B31","author":"McInerney","year":"2023"},{"key":"2025042501213135600_btaf156-B32","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1159\/000470836","article-title":"Multi-infarct dementia: a historical perspective","volume":"7","author":"McKay","year":"2017","journal-title":"Dement Geriatr Cogn Dis Extra"},{"key":"2025042501213135600_btaf156-B33","first-page":"2024","author":"Mo","year":"2024"},{"key":"2025042501213135600_btaf156-B34","doi-asserted-by":"crossref","first-page":"9777","DOI":"10.3390\/ijms23179777","article-title":"Shared risk factors between dementia and atherosclerotic cardiovascular disease","volume":"23","author":"Nordestgaard","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2025042501213135600_btaf156-B35","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1093\/jamia\/ocaa053","article-title":"Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review","volume":"27","author":"Payrovnaziri","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2025042501213135600_btaf156-B36","author":"Qi","year":"2020"},{"key":"2025042501213135600_btaf156-B37","author":"Rajani","year":"2019"},{"key":"2025042501213135600_btaf156-B38","author":"Ribeiro","year":"2020"},{"key":"2025042501213135600_btaf156-B39","first-page":"457","article-title":"Please stop explaining black box models for high stakes decisions","volume":"1050","author":"Rudin","year":"2018","journal-title":"Statistics"},{"key":"2025042501213135600_btaf156-B40","doi-asserted-by":"crossref","first-page":"105111","DOI":"10.1016\/j.compbiomed.2021.105111","article-title":"Transparency of deep neural networks for medical image analysis: a review of interpretability methods","volume":"140","author":"Salahuddin","year":"2022","journal-title":"Comput Biol Med"},{"key":"2025042501213135600_btaf156-B41","doi-asserted-by":"crossref","first-page":"2050","DOI":"10.1038\/s41467-024-46411-8","article-title":"Systematic analysis of ChatGPT, google search and Llama 2 for clinical decision support tasks","volume":"15","author":"Sandmann","year":"2024","journal-title":"Nat Commun"},{"key":"2025042501213135600_btaf156-B42","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1093\/cid\/ciad633","article-title":"Black box warning: large language models and the future of infectious diseases consultation","volume":"78","author":"Schwartz","year":"2024","journal-title":"Clin Infect Dis"},{"key":"2025042501213135600_btaf156-B43","author":"Shen","year":"2023"},{"key":"2025042501213135600_btaf156-B44","author":"Su","year":"2022"},{"key":"2025042501213135600_btaf156-B45","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1007\/s40120-022-00338-8","article-title":"Alzheimer\u2019s disease: epidemiology and clinical progression","volume":"11","author":"Tahami Monfared","year":"2022","journal-title":"Neurol Ther"},{"key":"2025042501213135600_btaf156-B46","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1038\/s41467-022-28273-0","article-title":"Deep phenotyping of Alzheimer\u2019s disease leveraging electronic medical records identifies sex-specific clinical associations","volume":"13","author":"Tang","year":"2022","journal-title":"Nat Commun"},{"key":"2025042501213135600_btaf156-B47","doi-asserted-by":"crossref","first-page":"473","DOI":"10.21552\/edpl\/2017\/4\/9","article-title":"Algorithms and transparency in view of the new general data protection regulation","volume":"3","author":"Temme","year":"2017","journal-title":"Eur Data Prot L Rev"},{"key":"2025042501213135600_btaf156-B48","author":"Touvron","year":"2023"},{"key":"2025042501213135600_btaf156-B49","author":"Tutek","year":"2018"},{"key":"2025042501213135600_btaf156-B50","first-page":"4566","author":"Vedantam","year":"2015"},{"key":"2025042501213135600_btaf156-B51","doi-asserted-by":"crossref","first-page":"e43","DOI":"10.1002\/mef2.43","article-title":"Accelerating the integration of ChatGPT and other large-scale AI models into biomedical research and healthcare","volume":"2","author":"Wang","year":"2023","journal-title":"MedComm Fut Med"},{"key":"2025042501213135600_btaf156-B52","volume-title":"Oxford Textbook of Medicine","author":"Warrell","year":"2003"},{"key":"2025042501213135600_btaf156-B53","author":"Xu","year":"2023"},{"key":"2025042501213135600_btaf156-B54","doi-asserted-by":"crossref","first-page":"9919269","DOI":"10.1155\/2023\/9919269","article-title":"Interpretability of clinical decision support systems based on artificial intelligence from technological and medical perspective: a systematic review","volume":"2023","author":"Xu","year":"2023","journal-title":"J Healthc Eng"},{"key":"2025042501213135600_btaf156-B55","author":"Xu","year":"2024"},{"key":"2025042501213135600_btaf156-B56","author":"Yordanov","year":"2021"},{"key":"2025042501213135600_btaf156-B57","author":"Yu","year":"2013"},{"key":"2025042501213135600_btaf156-B58","first-page":"23634","article-title":"MERLOT: multimodal neural script knowledge models","volume":"34","author":"Zellers","year":"2021","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf156\/62892640\/btaf156.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf156\/62892640\/btaf156.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf156\/62892640\/btaf156.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T05:21:45Z","timestamp":1745558505000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf156\/8108827"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,29]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf156","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,3,29]]},"article-number":"btaf156"}}