Objective: This study evaluated the practical utility of Microsoft Copilot PRO®, a GPT-4-based generative AI tool, in addressing diverse medication inquiries at a hospital's drug information center.Design: We conducted an observational study in which three experienced drug information pharmacists independently evaluated the AI-generated responses and rated their overall utility using a three-point scale.Methods: A total of 330 inquiries drawn from 11 predefined categories (e.g., dose conversion, pharmacokinetics, and administration during pregnancy) were selected from five years of archived queries. Each question was entered verbatim into Copilot's "GPT-4 Strict" mode to generate one response per query. The raters classified the answers as "useful," "not useful," or "uncertain".Results: A total of 44.9% of the 330 answers were deemed "useful." Among the 11 categories, the highest proportion of "useful" responses was observed for pregnancy-related inquiries (58. 9%), while the lowest occurred for questions on admixture stability (15.6%).Conclusion: Although Microsoft Copilot PRO® achieved a 44.9% "useful" rating overall, its performance varied across inquiry categories, with particularly low usefulness for admixture-related questions. Despite presenting reference links that allow pharmacists to scrutinize supporting evidence, concerns remain regarding the limited agreement among evaluators, especially for "uncertain" cases. Further refinement of AI tools and increased availability of high-quality online drug information may enhance the reliability of the copilot. Future studies should examine the reproducibility, explore optimal prompt designs, and involve larger multicenter samples. Although Copilot shows promise, it cannot replace critical human judgment in drug information services, underscoring the need for ongoing evaluation.

STUDY DESIGN: Retrospective study. PURPOSE: We experienced the situation wherein some patients had new-onset pain or dysesthesia around the ring and little fingers (C8 symptom) or ulnar aspect of the forearm (T1 symptom) after cervical laminoplasty (LP). We investigated the incidence and the cause of new C8 or T1 symptoms and the clinical outcomes after C3–C6 LP or C3–C7 LP. OVERVIEW OF LITERATURE: There were some reports regarding complications after cervical LP. However, there was no report regarding C8 or T1 symptoms after cervical LP. METHODS: Among the 33 patients enrolled in this study, 11 and 22 patients were treated with C3–C6 LP and C3–C7 LP, respectively. We prospectively evaluated C8 or T1 symptoms daily postoperatively for 1 week. The distance of the posterior spinal cord shifting and posterior subarachnoid space from C2 to T1 was measured by T2-weighted midsagittal magnetic resonance imaging (MRI). We evaluated pre- and postoperative axial neck pain, Japanese Orthopaedic Association (JOA) score, and JOA score improvement rate. RESULTS: C8 or T1 symptoms occurred in five and three patients with C3–C6 LP (45.5%) and C3–C7 LP (13.6%), respectively. The distance of the posterior subarachnoid space in C3–C6 LP at C7 was significantly shorter than that in C3–C7 LP at T1 on MRI 24 hours postoperatively (p=0.0448). Postoperative axial neck pain, pre- and postoperative JOA scores, and JOA score improvement rate were not significantly different. CONCLUSIONS: The incidence of C8 or T1 symptoms in C3–C6 LP was higher than that in C3–C7 LP. C8 or T1 symptoms would be caused by the posterior fila radicularia and spinal cord impingement on the intact lower end of the lamina.
Asian Continental Ancestry Group ; Fingers ; Forearm ; Humans ; Incidence ; Laminoplasty ; Magnetic Resonance Imaging ; Neck Pain ; Paresthesia ; Prospective Studies ; Retrospective Studies ; Spinal Cord ; Subarachnoid Space