The use of large language models like ChatGPT on delivering patient information relating to surgery.

not applicable.

Assessing the quality and readability of online patient information: ENT UK patient information e-leaflets vs responses by a Generative Artificial Intelligence.

BACKGROUND: The evolution of artificial intelligence has introduced new ways to disseminate health information, including natural language processing models like ChatGPT. However, the quality and readability of such digitally-generated information remains understudied. This study is the first to compare the quality and readability of digitally-generated health information against leaflets produced by professionals. METHODOLOGY: Patient information leaflets for five ENT UK leaflets and their corresponding ChatGPT responses were extracted from the Internet. Assessors with various degree of medical knowledge evaluated the content using the Ensuring Quality Information for Patients (EQIP) tool and readability tools including the Flesch-Kincaid Grade Level (FKGL). Statistical analysis was performed to identify differences between leaflets, assessors, and sources of information. RESULTS: ENT UK leaflets were of moderate quality, scoring a median EQIP of 23. Statistically significant differences in overall EQIP score were identified between ENT UK leaflets but ChatGPT responses were of uniform quality. Non-specialist doctors rated the highest EQIP scores while medical students scored the lowest. The mean readability of ENT UK leaflets was higher than ChatGPT responses. The information metrics of ENT UK leaflets were moderate and varied between topics. Equivalent ChatGPT information provided comparable content quality, but with reduced readability. CONCLUSIONS: ChatGPT patient information and professionally-produced leaflets had comparable content, but LLM content were required a higher reading age. With the increasing use of online health resources, this study highlights the need for a balanced approach that considers optimises both the quality and readability of patient education materials.

Systematic approach needed to establish cause of vertigo.

Vertigo can be defined as an illusion or hallucination of movement. The control of balance is complicated. Vertigo can be caused by many different pathologies, some of which are potentially life threatening. An important differentiation is whether the symptoms of vertigo originate from a central or peripheral origin. Clues to a central origin are other brainstem symptoms or signs of acute onset such as headache, deafness and other neurological findings. These patients warrant urgent referral and investigation. Red flags in patients with vertigo include: headache; neurological symptoms; and neurological signs. It is useful to categorise vertigo into acute and chronic. The former usually has a single mechanism whereas chronic dizziness is often multifactorial. History is usually the most important part of the assessment. Key questions should be asked and it is vital to establish if the patient is suffering from vertigo or some other complaint such as anxiety or syncope. A neurological and otological examination should be performed, appropriate to the history. Assessment of gait and posture is crucial. If the patient has positional vertigo then a Hallpike test should be performed. Visual acuity should be checked as vision is a vital part of the balance system. The cranial nerves should be tested in particular eye movements for any ophthalmoplegia pointing to focal cranial nerve pathology and for nystagmus. The rest of the neurological examination should exclude evidence of central disease, in particular cerebellar disease, and neuropathy. If syncope is suspected it is wise to perform an extensive systemic examination in particular lying and standing BP, and cardiovascular and respiratory system assessments.