“Now you’re talking my language” - Improving health literacy and patient-directed knowledge of scientific abstracts through plain language summaries created by artificial intelligence - A cross sectional infodemiology study

Q: Why do patients struggle with scientific abstracts from medical journals?

The study notes that abstracts are difficult-to-read for the lay community because they are not written specifically for non-expert audiences, even though they are widely accessible online.

Q: How was readability measured for both scientific abstracts and AI-generated summaries?

Readability was calculated using Readable software with metrics including Flesch Reading Ease, Flesch-Kincaid Grade Level, Gunning Fog Index, SMOG Index, and basic text metrics such as word and sentence counts.

Q: Did AI-generated plain language summaries improve readability compared with the original abstracts?

Yes. AI-created plain language summaries showed improved readability scores, and summaries produced with extensive prompts reached reference readability targets for 46 of 48 abstracts.

Sep 29, 2026

Uploaded by dabgoudw

Across 2020–2024, patients increasingly rely on freely available scientific abstracts in medical journals and search engines, yet these abstracts are often difficult for lay readers to understand. This cross-sectional infodemiology study calculated readability of 48 Ulster Medical Journal scientific abstracts using multiple indices, then generated AI plain-language summaries with minimal vs extensive prompts and re-measured readability. AI-supported summaries improved readability toward target levels, supporting use of plain-language summaries to strengthen health literacy.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Background

Methods

Results

Conclusions

Plain Language Summary (AI-Generated)

Ulster Med J 2025;94(3):126-135 Clinical Paper “Now you’re talking my language” - Improving health literacy and patient-directed knowledge of scientific abstracts through provision of plain language summaries created by artificial intelligence: A cross sectional infodemiology study John E. Moore* and Beverley C. Millar SCIENTIFIC ABSTRACT (Author Written) Background Due to free and digital availability of scientific abstractsin medical journals, as well as search engines including PubMed, many patients are increasingly looking to these as reliable and trusted sources of information, amidst an information ecosystem of potential mis-and disinformation. However, such scientific abstracts are difficult-to-read by the lay community, as they are not written purposefully for a lay audience. The Plain Language Summary now offers such readers a new medium to engage with, thereby helping with their health literacy and understanding of the research findings being described. The aims and objectives of the present study were to: calculate the readability of all scientific abstracts published in the Ulster Medical Journal over the five year period 2020 – 2024 (n=48), (ii) using artificial intelligence, prepare a plain language summary of each scientific abstract (n=48) with (a) minimal prompts and (b) with extensive prompts and (iii) calculate the readability of AI-generated plain language summaries. Methods Readability was calculated using Readable software, defined by the (i) Flesch Reading Ease (FRE),(ii) Flesch-Kincaid Grade Level (FKGL), (iii) Gunning Fog Index and (iv) SMOG Index and four text metrics [word count, sentence count, words/sentence, syllables/word] on abstracts from all original clinical papers (n=48) published in the Ulster Medical Journal in the last five years (2020-2024) . Plain language summaries were created from the existing scientific abstract using artificial intelligence with (a) minimal promptsand (b) extensive prompts. The readability of all AI-created plain language summaries was further determined. Results Scientific abstracts had a mean FRE and FKGL score of 24.2±14.1 (standard deviation) and 14.4±2.8, respectively (Reference target values of ≥60 and ≤8, respectively) . AI created plain language summaries with improved readability scores of 59.8±7.4 and 8.9±1.6, respectively for summaries with minimal prompts, thereby almost meeting reference readability targets. AI-created summaries with extensive prompts had mean readability scores of 71.3±6.1 and 6.3±0.9, respectively, with 46/48 (96%) of scientific abstractsnow reaching reference readability target values. Scientific abstracts and Plain Language Summaries were statistically different (p<0.0001) in terms of both FRE and FKGL scores. Inputting the necessary and appropriate prompts to the AItool is critical to attaining the desired readability values. Conclusions Medical journals may reach out to lay readers, including service users, patients, family and friends, through new innovation with the inclusion of a Plain Language Summary. Scientific abstracts are written at a level which is beyond the average reading age of 11 years old in the UK. Computational creativity through the employment of AI platforms can successfully generate narrative text for specific reading ages, with optimal readability. Effective communication of medical research findings from medical and scientific papers is vital for service users to enhance their health literacy, thereby helping promote better clinical outcomes, as well as promoting inclusivity for lay readers. With thorough checks and controls by the authors of clinical papers, AI-created plain language summaries may provide School of Biomedical Sciences, Ulster University, Cromore Road, Coleraine, BT52 1SA, Northern Ireland, UK, School of Medicine, Dentistry and Biomedical Sciences, The Wellcome-Wolfson Institute for Experimental Medicine, Queen’s University, 97 Lisburn Road, Belfast BT9 7

FAQs

Why do patients struggle with scientific abstracts from medical journals?

The study notes that abstracts are difficult-to-read for the lay community because they are not written specifically for non-expert audiences, even though they are widely accessible online.

How was readability measured for both scientific abstracts and AI-generated summaries?

Readability was calculated using Readable software with metrics including Flesch Reading Ease, Flesch-Kincaid Grade Level, Gunning Fog Index, SMOG Index, and basic text metrics such as word and sentence counts.

Did AI-generated plain language summaries improve readability compared with the original abstracts?

Yes. AI-created plain language summaries showed improved readability scores, and summaries produced with extensive prompts reached reference readability targets for 46 of 48 abstracts.

Sep 29, 2026

Uploaded by dabgoudw