Leveraging social media data to study disease and treatment characteristics of Hodgkin’s lymphoma Using Natural Language Processing methods DOI Creative Commons
Zasim Azhar Siddiqui, M. M. Pathan, Sabina O. Nduaguba

et al.

PLOS Digital Health, Journal Year: 2025, Volume and Issue: 4(3), P. e0000765 - e0000765

Published: March 19, 2025

Background The use of social media platforms in health research is increasing, yet their application studying rare diseases limited. Hodgkin’s lymphoma (HL) a malignancy with high incidence young adults. This study evaluates the feasibility using data to disease and treatment characteristics HL. Methods We utilized X (formerly Twitter) API v2 developer portal download posts tweets) from January 2010 October 2022. Annotation guidelines were developed literature manual review limited was performed identify class attributes (characteristics) HL discussed on X, create gold standard dataset. dataset subsequently employed train, test, validate Named Entity Recognition (NER) Natural Language Processing (NLP) application. Results After preparation, 80,811 collected: 500 for annotation guideline development, 2,000 NLP remaining 78,311 deploying identified nine classes related HL, such as classification, etiopathology, stages progression, treatment. progression most frequently discussed, 20,013 (25.56%) mentioning HL’s treatments 17,177 (21.93%) progression. model exhibited robust performance, achieving 86% accuracy an 87% F1 score. etiopathology demonstrated excellent 93% 95% Discussion displayed efficacy extracting characterizing HL-related information posts, evidenced by Nonetheless, presented limitations distinguishing between patients, providers, caregivers establishing temporal relationships attributes. Further necessary bridge these gaps. Conclusion Our potential valuable preliminary source understanding Lymphoma.

Language: Английский

Applications of Natural Language Processing in Otolaryngology: A Scoping Review DOI Creative Commons
Norbert Banyi, Biao Ma, Ameen Amanian

et al.

The Laryngoscope, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

To review the current literature on applications of natural language processing (NLP) within field otolaryngology. MEDLINE, EMBASE, SCOPUS, Cochrane Library, Web Science, and CINAHL. The preferred reporting Items for systematic reviews meta-analyzes extension scoping checklist was followed. Databases were searched from date inception up to Dec 26, 2023. Original articles application language-based models otolaryngology patient care research, regardless publication date, included. studies classified under 2011 Oxford CEBM levels evidence. One-hundred sixty-six papers with a median year 2024 (range 1982, 2024) Sixty-one percent (102/166) used ChatGPT published in 2023 or 2024. Sixty NLP clinical education decision support, 42 education, 14 electronic medical record improvement, 5 triaging, 4 trainee monitoring, 3 telemedicine, 1 translation. For 37 extraction, classification, analysis data, 17 thematic analysis, evaluating scientific reporting, manuscript preparation. role is evolving, passing OHNS board simulations, though its requires improvement. shows potential post-treatment monitoring. effective at extracting data unstructured large sets. There limited research administrative tasks. Guidelines use are critical.

Language: Английский

Citations

0
Leveraging social media data to study disease and treatment characteristics of Hodgkin’s lymphoma Using Natural Language Processing methods DOI Creative Commons
Zasim Azhar Siddiqui, M. M. Pathan, Sabina O. Nduaguba

et al.

PLOS Digital Health, Journal Year: 2025, Volume and Issue: 4(3), P. e0000765 - e0000765

Published: March 19, 2025

Background The use of social media platforms in health research is increasing, yet their application studying rare diseases limited. Hodgkin’s lymphoma (HL) a malignancy with high incidence young adults. This study evaluates the feasibility using data to disease and treatment characteristics HL. Methods We utilized X (formerly Twitter) API v2 developer portal download posts tweets) from January 2010 October 2022. Annotation guidelines were developed literature manual review limited was performed identify class attributes (characteristics) HL discussed on X, create gold standard dataset. dataset subsequently employed train, test, validate Named Entity Recognition (NER) Natural Language Processing (NLP) application. Results After preparation, 80,811 collected: 500 for annotation guideline development, 2,000 NLP remaining 78,311 deploying identified nine classes related HL, such as classification, etiopathology, stages progression, treatment. progression most frequently discussed, 20,013 (25.56%) mentioning HL’s treatments 17,177 (21.93%) progression. model exhibited robust performance, achieving 86% accuracy an 87% F1 score. etiopathology demonstrated excellent 93% 95% Discussion displayed efficacy extracting characterizing HL-related information posts, evidenced by Nonetheless, presented limitations distinguishing between patients, providers, caregivers establishing temporal relationships attributes. Further necessary bridge these gaps. Conclusion Our potential valuable preliminary source understanding Lymphoma.

Language: Английский

Citations

0