English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic diagnosis (AD), a critical application of AI in healthcare, employsmachine learning techniques to assist doctors in gathering patient symptominformation for precise disease diagnosis. The Transformer-based methodutilizes an input symptom sequence, predicts itself through auto-regression,and employs the hidden state of the final symptom to determine the disease.Despite its simplicity and superior performance demonstrated, a decline indisease diagnosis accuracy is observed caused by 1) a mismatch between symptomsobserved during training and generation, and 2) the effect of different symptomorders on disease prediction. To address the above obstacles, we introduce theCoAD, a novel disease and symptom collaborative generation framework, whichincorporates several key innovations to improve AD: 1) aligning sentence-leveldisease labels with multiple possible symptom inquiry steps to bridge the gapbetween training and generation; 2) expanding symptom labels for eachsub-sequence of symptoms to enhance annotation and eliminate the effect ofsymptom order; 3) developing a repeated symptom input schema to effectively andefficiently learn the expanded disease and symptom labels. We evaluate the CoADframework using four datasets, including three public and one private, anddemonstrate that it achieves an average 2.3% improvement over previousstate-of-the-art results in automatic disease diagnosis. For reproducibility,we release the code and data at https://github.com/KwanWaiChung/coad.

CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation