Using artificial intelligence to generate medical literature for urology patients: a comparison of three different large language models.

PURPOSE: Large language models (LLMs) are a form of artificial intelligence (AI) that uses deep learning techniques to understand, summarize and generate content. The potential benefits of LLMs in healthcare is predicted to be immense. The objective of this study was to examine the quality of patient information leaflets (PILs) produced by 3 LLMs on urological topics. METHODS: Prompts were created to generate PILs from 3 LLMs: ChatGPT-4, PaLM 2 (Google Bard) and Llama 2 (Meta) across four urology topics (circumcision, nephrectomy, overactive bladder syndrome, and transurethral resection of the prostate). PILs were evaluated using a quality assessment checklist. PIL readability was assessed by the Average Reading Level Consensus Calculator. RESULTS: PILs generated by PaLM 2 had the highest overall average quality score (3.58), followed by Llama 2 (3.34) and ChatGPT-4 (3.08). PaLM 2 generated PILs were of the highest quality in all topics except TURP and was the only LLM to include images. Medical inaccuracies were present in all generated content including instances of significant error. Readability analysis identified PaLM 2 generated PILs as the simplest (age 14-15 average reading level). Llama 2 PILs were the most difficult (age 16-17 average). CONCLUSION: While LLMs can generate PILs that may help reduce healthcare professional workload, generated content requires clinician input for accuracy and inclusion of health literacy aids, such as images. LLM-generated PILs were above the average reading level for adults, necessitating improvement in LLM algorithms and/or prompt design. How satisfied patients are to LLM-generated PILs remains to be evaluated.

SCO-Spondin Defects and Neuroinflammation Are Conserved Mechanisms Driving Spinal Deformity across Genetic Models of Idiopathic Scoliosis.

Adolescent idiopathic scoliosis (AIS) affects 3% to 4% of children between the ages of 11 and 18 [1, 2]. This disorder, characterized by abnormal three-dimensional spinal curvatures that typically develop during periods of rapid growth, occurs in the absence of congenital vertebral malformations or neuromuscular defects [1]. Genetic heterogeneity [3] and a historical lack of appropriate animal models [4] have confounded basic understanding of AIS biology; thus, treatment options remain limited [5, 6]. Recently, genetic studies using zebrafish have linked idiopathic-like scoliosis to irregularities in motile cilia-mediated cerebrospinal fluid flow [7-9]. However, because loss of cilia motility in human primary ciliary dyskinesia patients is not fully associated with scoliosis [10, 11], other pathogenic mechanisms remain to be determined. Here, we demonstrate that zebrafish scospondin (sspo) mutants develop late-onset idiopathic-like spinal curvatures in the absence of obvious cilia motility defects. Sspo is a large secreted glycoprotein functionally associated with the subcommissural organ and Reissner's fiber [12]-ancient and enigmatic organs of the brain ventricular system reported to govern cerebrospinal fluid homeostasis [13, 14], neurogenesis [12, 15-18], and embryonic morphogenesis [19]. We demonstrate that irregular deposition of Sspo within brain ventricles is associated with idiopathic-like scoliosis across diverse genetic models. Furthermore, Sspo defects are sufficient to induce oxidative stress and neuroinflammatory responses implicated in AIS pathogenesis [9]. Through screening for chemical suppressors of sspo mutant phenotypes, we also identify potent agents capable of blocking severe juvenile spine deformity. Our work thus defines a new preclinical model of AIS and provides tools to realize novel therapeutic strategies.