{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:54Z","timestamp":1759708854486,"version":"build-2065373602"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"vor","delay-in-days":252,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study evaluates the value self-reported free-text symptom descriptions for supporting diagnostic decisions in osteoarthritis (OA), fibromyalgia (FM) and immune-mediated rheumatic diseases (imRD) using natural language processing (NLP) and machine learning (ML).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Free-text descriptions from 8454 patients were processed using a word-weighting method (TF-IDF vectorization) that reflects how relevant each word is across the dataset, and then classified with support vector machine (SVM) models. OA and FM models were optimized for specificity and the imRD model for sensitivity based on disease context and validated against an independent dataset. Model explainability was explored using SHapley Additive exPlanations (SHAP) values.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The SVM models demonstrated moderate diagnostic support potential with Area under the Receiver Operating Characteristic Curve (AUC-ROC) values of 0.68 for OA, 0.75 for FM and 0.69 for imRD. When optimized for clinical utility, the models achieved high specificity of 0.82 for OA and 0.92 for FM, effectively reducing unnecessary referrals with misdiagnosis rates of only 17% and 8%, respectively. For imRD, the model achieved a sensitivity of 0.92 and negative predictive value (NPV) of 0.77, ensuring minimal missed diagnoses of these potentially serious conditions. Decision curve analysis confirmed clinical utility across varying threshold preferences. SHAP analysis revealed that key linguistic patterns in patient descriptions aligned with clinical reasoning, enhancing the models\u2019 interpretability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Our results highlight the value of patient-reported data in augmenting rheumatology decision-making and sets the stage for further development in AI-assisted diagnostics. While not a standalone diagnostic tool, the integration of NLP-driven analysis of free-text symptom descriptions shows promise in reducing diagnostic ambiguity.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/rap\/rkaf103","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:28:48Z","timestamp":1757514528000},"source":"Crossref","is-referenced-by-count":0,"title":["Let\u2019s ask the patient: disease prediction based on patients\u2019 symptom descriptions in free text"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2098-4313","authenticated-orcid":false,"given":"In\u00e9s","family":"P\u00e9rez-Sancrist\u00f3bal","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Complutense University of Madrid , Madrid,","place":["Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Steinz","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Leiden University Medical Center , Leiden,","place":["The Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Leiden University Medical Center , Leiden,","place":["The Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tjardo","family":"Maarseveen","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Leiden University Medical Center , Leiden,","place":["The Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Floor","family":"Zegers","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Leiden University Medical Center , Leiden,","place":["The Netherlands"]},{"name":"Department of Biomedical Data Sciences, Leiden University Medical Center , Leiden,","place":["The Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Bislawska Axn\u00e4s","sequence":"additional","affiliation":[{"name":"Elsa Science , Stockholm,","place":["Sweden"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2869-7861","authenticated-orcid":false,"given":"Luis","family":"Rodr\u00edguez-Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Grupo de Patolog\u00eda Musculoesquel\u00e9tica, Hospital Clinico San Carlos, IdISSC , Madrid,","place":["Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachel","family":"Knevel","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Leiden University Medical Center , Leiden,","place":["The Netherlands"]},{"name":"Translational and Clinical Research Institute, Newcastle University , Newcastle Upon Tyne,","place":["UK"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"volume-title":"The musculoskeletal services framework\u2014a joint responsibility: doing it differently","year":"2006","author":"Department of Health","key":"2025100420070024800_rkaf103-B1"},{"key":"2025100420070024800_rkaf103-B2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/s0304-3959(02)00372-x","article-title":"Musculoskeletal pain in the Netherlands: prevalences, consequences and risk groups, the DMC3-study","volume":"102","author":"Picavet","year":"2003","journal-title":"Pain"},{"key":"2025100420070024800_rkaf103-B3","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1007\/s00393-018-0578-3","article-title":"Use of medical apps and online platforms among German rheumatologists: results of the 2016 and 2018 DGRh conference surveys and research conducted by rheumadocs","volume":"78","author":"Knitza","year":"2019","journal-title":"Z Rheumatol"},{"key":"2025100420070024800_rkaf103-B4","doi-asserted-by":"crossref","first-page":"e19661","DOI":"10.2196\/19661","article-title":"Mobile health usage, preferences, barriers, and eHealth literacy in rheumatology: patient survey study","volume":"8","author":"Knitza","year":"2020","journal-title":"JMIR Mhealth Uhealth"},{"key":"2025100420070024800_rkaf103-B5","doi-asserted-by":"crossref","first-page":"3519","DOI":"10.1002\/art.27691","article-title":"Delay in receiving rheumatology care leads to long-term harm","volume":"62","author":"Bykerk","year":"2010","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"2025100420070024800_rkaf103-B6","doi-asserted-by":"crossref","first-page":"3537","DOI":"10.1002\/art.27692","article-title":"Long-term impact of delay in assessment of patients with early arthritis","volume":"62","author":"Van der Linden","year":"2010","journal-title":"Arthritis Rheum"},{"key":"2025100420070024800_rkaf103-B7","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1136\/annrheumdis-2011-201063","article-title":"A systematic literature review of strategies promoting early referral and reducing delays in the diagnosis and management of inflammatory arthritis","volume":"72","author":"Villeneuve","year":"2013","journal-title":"Ann Rheum Dis"},{"key":"2025100420070024800_rkaf103-B8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.4137\/CMAMD.S40361","article-title":"Rate of proven rheumatic diseases in a large collective of referrals to an outpatient rheumatology clinic under routine conditions","volume":"9","author":"Feuchtenberger","year":"2016","journal-title":"Clin Med Insights Arthritis Musculoskelet Disord"},{"key":"2025100420070024800_rkaf103-B9","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1038\/s41746-022-00667-w","article-title":"The diagnostic and triage accuracy of digital and online symptom checker tools: a systematic review","volume":"5","author":"Wallace","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2025100420070024800_rkaf103-B10","first-page":"534","article-title":"A is for aphorism\u2014is it true that \u201ca careful history will lead to the diagnosis 80% of the time\u201d?","volume":"41","author":"Cooke","year":"2012","journal-title":"Aust Fam Physician"},{"key":"2025100420070024800_rkaf103-B11","first-page":"163","article-title":"Contributions of the history, physical examination, and laboratory investigation in making medical diagnoses","volume":"156","author":"Peterson","year":"1992","journal-title":"West J Med"},{"key":"2025100420070024800_rkaf103-B12","doi-asserted-by":"crossref","first-page":"774945","DOI":"10.3389\/fmed.2022.774945","article-title":"Rheumatic? \u2013 A digital diagnostic decision support tool for individuals suspecting rheumatic diseases: a multicenter pilot validation study","volume":"9","author":"Knevel","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"2025100420070024800_rkaf103-B13","doi-asserted-by":"crossref","first-page":"e002974","DOI":"10.1136\/rmdopen-2022-002974","article-title":"Population-based user-perceived experience of Rheumatic?: A novel digital symptom-checker in rheumatology","volume":"9","author":"Lundberg","year":"2023","journal-title":"RMD Open"},{"key":"2025100420070024800_rkaf103-B14","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1001\/jama.2023.8288","article-title":"Accuracy of a generative artificial intelligence model in a complex diagnostic challenge","volume":"330","author":"Kanjee","year":"2023","journal-title":"JAMA"},{"key":"2025100420070024800_rkaf103-B15","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N Engl J Med"},{"key":"2025100420070024800_rkaf103-B16","doi-asserted-by":"crossref","first-page":"e2336100","DOI":"10.1001\/jamanetworkopen.2023.36100","article-title":"Generative artificial intelligence for chest radiograph interpretation in the emergency department","volume":"6","author":"Huang","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2025100420070024800_rkaf103-B17","doi-asserted-by":"crossref","first-page":"100213","DOI":"10.1016\/j.jtauto.2023.100213","article-title":"Accuracy of generative artificial intelligence models in differential diagnoses of familial Mediterranean fever and deficiency of interleukin-1 receptor antagonist","volume":"7","author":"Pillai","year":"2023","journal-title":"J Transl Autoimmun"},{"key":"2025100420070024800_rkaf103-B18","doi-asserted-by":"crossref","first-page":"e242609","DOI":"10.1001\/jamanetworkopen.2024.2609","article-title":"Recognition of genetic conditions after learning with images created using generative artificial intelligence","volume":"7","author":"Waikel","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2025100420070024800_rkaf103-B19","doi-asserted-by":"crossref","first-page":"66","DOI":"10.3389\/fmed.2019.00066","article-title":"The revival of the notes field: leveraging the unstructured content in electronic health records","volume":"6","author":"Assale","year":"2019","journal-title":"Front Med (Lausanne)"},{"key":"2025100420070024800_rkaf103-B20","doi-asserted-by":"crossref","first-page":"e23930","DOI":"10.2196\/23930","article-title":"Machine learning electronic health record identification of patients with rheumatoid arthritis: algorithm pipeline development and validation study","volume":"8","author":"Maarseveen","year":"2020","journal-title":"JMIR Med Inform"},{"key":"2025100420070024800_rkaf103-B21","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2025100420070024800_rkaf103-B22","doi-asserted-by":"crossref","first-page":"i6","DOI":"10.1136\/bmj.i6","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"2025100420070024800_rkaf103-B23","first-page":"4766","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025100420070024800_rkaf103-B24","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2025100420070024800_rkaf103-B25","doi-asserted-by":"crossref","first-page":"30","DOI":"10.3390\/jfmk4020030","article-title":"An overview of the pathogenesis and treatment of elbow osteoarthritis","volume":"4","author":"Ravalli","year":"2019","journal-title":"J Funct Morphol Kinesiol"},{"key":"2025100420070024800_rkaf103-B26","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1016\/j.ajic.2024.03.016","article-title":"Utilizing natural language processing and large language models in the diagnosis and prediction of infectious diseases: a systematic review","volume":"52","author":"Omar","year":"2024","journal-title":"Am J Infect Control"},{"key":"2025100420070024800_rkaf103-B27","first-page":"1130","article-title":"Natural language processing and machine learning to enable clinical decision support for treatment of pediatric pneumonia","volume":"2020","author":"Smith","year":"2020","journal-title":"AMIA Annu Symp Proc"},{"key":"2025100420070024800_rkaf103-B28","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.thromres.2021.11.020","article-title":"Developing and validating natural language processing algorithms for radiology reports compared to ICD-10 codes for identifying venous thromboembolism in hospitalized medical patients","volume":"209","author":"Verma","year":"2022","journal-title":"Thromb Res"},{"key":"2025100420070024800_rkaf103-B29","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1007\/s11657-020-00859-5","article-title":"Natural language processing of radiology reports for the identification of patients with fracture","volume":"16","author":"Kolanu","year":"2021","journal-title":"Arch Osteoporos"},{"volume-title":"Sistema de Informaci\u00f3n DIRAYA","author":"Ministerio de Sanidad, Servicios Sociales e Igualdad","key":"2025100420070024800_rkaf103-B30"},{"key":"2025100420070024800_rkaf103-B31","first-page":"1","article-title":"2016\/679 of the European Parliament and of the Council. General Data Protection Regulation (GDPR)","volume":"L119","author":"Regulation (EU)","year":"2016","journal-title":"Off J Eur Union"},{"key":"2025100420070024800_rkaf103-B32","first-page":"5262","article-title":"Stratification of patients using advanced integrative modelling of data routinely acquired for diagnosing rheumatic complaints (SPIDeRR): a multicenter European consortium","volume":"82","author":"Desai","year":"2024","journal-title":"Ann Rheum Dis"}],"container-title":["Rheumatology Advances in Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/rheumap\/advance-article-pdf\/doi\/10.1093\/rap\/rkaf103\/64236238\/rkaf103.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/rheumap\/article-pdf\/9\/4\/rkaf103\/64236238\/rkaf103.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/rheumap\/article-pdf\/9\/4\/rkaf103\/64236238\/rkaf103.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:07:12Z","timestamp":1759622832000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/rheumap\/article\/doi\/10.1093\/rap\/rkaf103\/8250602"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,9,13]]}},"URL":"https:\/\/doi.org\/10.1093\/rap\/rkaf103","relation":{},"ISSN":["2514-1775"],"issn-type":[{"type":"electronic","value":"2514-1775"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"rkaf103"}}