2026-10-12T18:13:25Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33903060 2026-09-17T17:21:29Z category_146 category_21 category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>Statistics of the schizophrenia QA dataset.</p> Zhipeng Yin (7209527) Zichong Wang (21395057) Min Chen (147733) Ian Stockwell (13917356) Xin Ning (1619131) Jun Liu (42548) Wenbin Zhang (1840726) Space Science Biotechnology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy retriever &# 8211 guided semantic modeling experimental results demonstrate offering accurate patient manual dataset annotation automated topic identification specific qa dataset conscious qa dataset significant privacy concerns reliable information gathering unbiased medical datasets targeted annotation reliable health relevant patient related information medical domain employs topic xlink "> tuning state systematically build study propose study introduce replicable framework reader architecture rapidly advanced obtaining large inefficiencies due generated content enabling efficient derived insights constructed domain based models assisting patients art transformer <div><p>The application of question-answering (QA) systems in the medical domain has rapidly advanced, significantly improving patients’ access to reliable health-related information. However, current approaches face notable challenges, including the difficulty in obtaining large-scale and unbiased medical datasets, significant privacy concerns, and inefficiencies due to manual dataset annotation. To address these issues, This study introduce a novel methodology leveraging publicly accessible online health forums to systematically build an unbiased, privacy-conscious QA dataset, and it employs Topic-guided Semantic Modeling (TGSM) for automated topic identification, enabling efficient and targeted annotation of relevant patient-generated content. Subsequently, this study propose a two-stage QA pipeline based on a Retriever–Reader architecture, which is further enhanced through fine-tuning state-of-the-art transformer-based models on the constructed domain-specific QA dataset. Experimental results demonstrate that our fine-tuned BioBERT significantly outperforms existing benchmarks, offering accurate patient-derived insights and providing a replicable framework for building efficient medical QA systems.</p></div> 2026-09-17T17:21:24Z Dataset Dataset 10.1371/journal.pdig.0001634.t002 https://figshare.com/articles/dataset/_p_Statistics_of_the_schizophrenia_QA_dataset_p_/33903060 CC BY 4.0