Comparison of ChatGPT and Traditional Patient Education Materials for Men's Health.

INTRODUCTION: ChatGPT is an artificial intelligence platform available to patients seeking medical advice. Traditionally, urology patients consulted official provider-created materials, particularly the Urology Care Foundation™ (UCF). Today, men increasingly go online due to the rising costs of health care and the stigma surrounding sexual health. Online health information is largely inaccessible to laypersons as it exceeds the recommended American sixth to eighth grade reading level. We conducted a comparative assessment of patient education materials generated by ChatGPT vs UCF regarding men's health conditions. METHODS: All 6 UCF men's health resources were identified. ChatGPT responses were generated using patient questions obtained from UCF. Adjusted ChatGPT responses were generated by prompting, "Explain it to me like I am in sixth grade." Textual analysis was performed using sentence, word, syllable, and complex word count. Six validated formulae were used for readability analysis. Two physicians independently scored responses for accuracy, comprehensiveness, and understandability. Statistical analysis involved Wilcoxon matched-pairs test. RESULTS: ChatGPT responses were longer and more complex. Both UCF and ChatGPT failed official readability standards, although ChatGPT performed significantly worse across all 6 topics (all P < .001). Conversely, adjusted ChatGPT readability typically surpassed UCF, even meeting the recommended level for 2 topics. Qualitatively, UCF and ChatGPT had comparable accuracy, although ChatGPT had better comprehensiveness and worse understandability. CONCLUSIONS: When comparing readability, ChatGPT-generated education is less accessible than provider-written content, although neither meets the recommended level. Our analysis indicates that specific artificial intelligence prompts can simplify educational materials to meet national standards and accommodate individual literacy.

Cerebral perfusion imaging.

Recent advances are allowing computed tomography (CT) and magnetic resonance imaging (MRI) to add diagnostic information derived from microscopic-scale brain structure, pathology, and physiology to the gross pathologic information that has been the core of brain imaging diagnosis since the 1980s. Physiologic imaging with MR perfusion weighted imaging has joined MR diffusion imaging as an essential components of stroke and brain tumor MRI. At the same time, the volume scanning revolution in CT technology has dramatically decreased the radiation doses required for CT perfusion imaging by allowing routine simultaneous CT perfusion and noninvasive dynamic bone subtracted CT angiography (CTA) without a significant increase in radiation dose over conventional head CT-CTA alone. Although ongoing research and clinical trials is needed to define more precisely how these techniques can best be exploited to improve clinical care and patient outcomes, in the acute stroke and subarachnoid hemorrhage populations the radiation risk associated with CT perfusion imaging is negligible and the physiologic information promises significant patient safety benefits.

Accuracy of on-call resident interpretation of CT angiography for intracranial aneurysm in subarachnoid hemorrhage.

OBJECTIVE: The purpose of this article is to evaluate the accuracy of preliminary on-call radiology resident interpretation of CT angiography (CTA) compared with digital subtraction angiography (DSA) in detecting cerebral aneurysms in subarachnoid hemorrhage (SAH). MATERIALS AND METHODS: A retrospective review compared resident interpretations of head CTA performed after hours for SAH to the results of DSA. The sensitivity and specificity of resident interpretations were classified on a per-patient and per-aneurysm basis. The accuracy of resident interpretations was also determined according to aneurysm location and number. RESULTS: Between January 2007 and December 2009, 83 patients with SAH underwent both CTA and DSA. DSA documented an aneurysm in 53 of 83 patients. Per patient, residents identified at least one aneurysm in 46 of 53 patients (87%). Per aneurysm, resident sensitivity and specificity for detecting aneurysms of any size were 62% and 91%, respectively, which improved for aneurysms 3 mm or larger to 73% and 97%, respectively. The posterior communicating and intracranial internal carotid arteries were resident "blind spots," with aneurysms 3 mm or larger detected with sensitivities of 33% and 50%, respectively. In contrast, anterior communicating artery aneurysms were correctly identified 95% of the time. In only 35% of cases with multiple aneurysms did residents correctly identify more than one aneurysm. CONCLUSION: The sensitivity of on-call resident interpretation of CTA for aneurysms in SAH is lower than expected, with a potential for delay in diagnosis and management in a small number of patients. Focused training to carefully review apparent blind spots and the frequency of multiple aneurysms may reduce inaccuracies.

Evaluation of blunt abdominal trauma using PACS-based 2D and 3D MDCT reformations of the lumbar spine and pelvis.

OBJECTIVE: The purpose of this study was to show the value of 2D and 3D reformations of CT data from abdominal and pelvic CT performed immediately at the workstation using a PACS-based software program to evaluate the lumbar spine and pelvis in patients with blunt abdominal trauma. MATERIALS AND METHODS: We reviewed the abdominopelvic CT scans and conventional radiographs of the lumbar spine or pelvis of 156 consecutive patients with blunt abdominal trauma. The CT data were compared with the radiographic findings and also with the findings of dedicated repeat CT of the spine or pelvis, when performed. RESULTS: CT depicted 80 fractures of the lumbar spine and 178 pelvic fractures. Radiography showed 40 fractures of the lumbar spine and 138 pelvic fractures. No additional fractures were identified on dedicated repeat CT. CONCLUSION: Conventional radiographs to clear the lumbar spine are no longer required when abdominopelvic CT data are available. CT and reformatted CT data show more fractures than radiography and miss no fractures compared with dedicated CT of the lumbar spine or pelvis. Having these images immediately available through the PACS workstation saves time for the trauma team in the management of critically ill patients.