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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Effective communication about breast and cervical cancers remains apersistent health challenge, with significant gaps in public understanding ofcancer prevention, screening, and treatment, potentially leading to delayeddiagnoses and inadequate treatments. This study evaluates the capabilities andlimitations of Large Language Models (LLMs) in generating accurate, safe, andaccessible cancer-related information to support patient understanding. Weevaluated five general-purpose and three medical LLMs using a mixed-methodsevaluation framework across linguistic quality, safety and trustworthiness, andcommunication accessibility and affectiveness. Our approach utilizedquantitative metrics, qualitative expert ratings, and statistical analysisusing Welch's ANOVA, Games-Howell, and Hedges' g. Our results show thatgeneral-purpose LLMs produced outputs of higher linguistic quality andaffectiveness, while medical LLMs demonstrate greater communicationaccessibility. However, medical LLMs tend to exhibit higher levels of potentialharm, toxicity, and bias, reducing their performance in safety andtrustworthiness. Our findings indicate a duality between domain-specificknowledge and safety in health communications. The results highlight the needfor intentional model design with targeted improvements, particularly inmitigating harm and bias, and improving safety and affectiveness. This studyprovides a comprehensive evaluation of LLMs for cancer communication, offeringcritical insights for improving AI-generated health content and informingfuture development of accurate, safe, and accessible digital health tools.

Large Language Models for Cancer Communication: Evaluating Linguistic Quality, Safety, and Accessibility in Generative AI