Objectives: Assessing medical disputes requires both medical and legal expertise, presenting challenges for patients seeking clarity regarding potential malpractice claims. This study aimed to develop and evaluate a chatbot based on a chain-of-thought pipeline using a large language model (LLM) for providing medical dispute counseling and compare its performance with responses from human experts. Methods: Retrospective counseling cases (n = 279) were collected from the Korea Medical Dispute Mediation and Arbitration Agency’s website, from which 50 cases were randomly selected as a validation dataset. The Claude 3.5 Sonnet model processed each counseling request through a five-step chain-of-thought pipeline. Thirty-eight experts evaluated the chatbot’s responses against the original human expert responses, rating them across four dimensions on a 5-point Likert scale. Statistical analyses were conducted using Wilcoxon signed-rank tests. Results: The chatbot significantly outperformed human experts in quality of information (p < 0.001), understanding and reasoning (p < 0.001), and overall satisfaction (p < 0.001). It also demonstrated a stronger tendency to produce opinion-driven content (p < 0.001). Despite generally high scores, evaluators noted specific instances where the chatbot encountered difficulties. Conclusions A chain-of-thought–based LLM chatbot shows promise for enhancing the quality of medical dispute counseling, outperforming human experts across key evaluation metrics. Future research should address inaccuracies resulting from legal and contextual variability, investigate patient acceptance, and further refine the chatbot’s performance in domain-specific applications.

Purpose: To compare the clinical outcomes of XEN45 gel stent implantation surgery (ab externo, open conjunctiva) with those of trabeculectomy. Methods: We retrospectively reviewed electronic medical record of 57 patients (62 eyes) treated with XEN implantation surgery (ab externo, open conjunctival approach) between April 1, 2021, and July 31, 2023, by the same surgeon. Preoperative clinical data including intraocular pressure (IOP), the number of glaucoma medications, and visual acuity were collected from 1 day to 12 months postoperatively. These data were compared and analyzed with those of 67 patients (78 eyes) received trabeculectomy between February 1, 2017, and April 30, 2022, by the same surgeon. Statistical analyses were performed with p < 0.05 as significant. Results: Complete surgical success rate was 33.9% and 57.7% of the XEN and trabeculectomy groups, respectively (p = 0.005). The qualified success rate was 79.0% and 93.6%, respectively (p = 0.011). Postoperatively, the XEN group used more glaucoma medications than the trabeculectomy group (1.21 ± 1.05 vs. 0.69 ± 0.90, p = 0.003 at postoperative month 12). After postoperative month 1, the XEN group had a higher IOP (15.77 ± 5.07 mmHg vs. 13.17 ± 3.81 mmHg; at postoperative month 12, p = 0.001) and lower corneal astigmatism than the trabeculectomy group (1.32 ± 0.79 diopters vs. 1.88 ± 1.45 diopters, p = 0.020 at postoperative month 6). There was no significant difference in preoperative and postoperative best-corrected visual acuity (logMAR) between the groups at any of the follow-up period (favorable visual acuity subgroup; logMAR < 0.7). Postoperative complications were 0 cases of XEN group and 13 cases of trabeculectomy group (0% vs. 16.7%, p = 0.001). Also, XEN surgery (24 minutes 40 seconds ± 6 minutes 26 seconds) had a shorter operation time than the trabeculectomy (40 minutes 18 seconds ± 8 minutes 27 seconds, p < 0.001). Conclusions Compared to trabeculectomy, XEN surgery (ab externo, open conjunctiva) showed relatively lower effectiveness (surgical success rate, IOP reduction). However, it demonstrated advantages as a minimally invasive glaucoma surgery, including a surgical success rate approaching about 80%, stability in inducing corneal astigmatism, fewer postoperative complications, and shorter operation times.

Purpose: To compare the clinical outcomes of XEN45 gel stent implantation surgery (ab externo, open conjunctiva) with those of trabeculectomy. Methods: We retrospectively reviewed electronic medical record of 57 patients (62 eyes) treated with XEN implantation surgery (ab externo, open conjunctival approach) between April 1, 2021, and July 31, 2023, by the same surgeon. Preoperative clinical data including intraocular pressure (IOP), the number of glaucoma medications, and visual acuity were collected from 1 day to 12 months postoperatively. These data were compared and analyzed with those of 67 patients (78 eyes) received trabeculectomy between February 1, 2017, and April 30, 2022, by the same surgeon. Statistical analyses were performed with p < 0.05 as significant. Results: Complete surgical success rate was 33.9% and 57.7% of the XEN and trabeculectomy groups, respectively (p = 0.005). The qualified success rate was 79.0% and 93.6%, respectively (p = 0.011). Postoperatively, the XEN group used more glaucoma medications than the trabeculectomy group (1.21 ± 1.05 vs. 0.69 ± 0.90, p = 0.003 at postoperative month 12). After postoperative month 1, the XEN group had a higher IOP (15.77 ± 5.07 mmHg vs. 13.17 ± 3.81 mmHg; at postoperative month 12, p = 0.001) and lower corneal astigmatism than the trabeculectomy group (1.32 ± 0.79 diopters vs. 1.88 ± 1.45 diopters, p = 0.020 at postoperative month 6). There was no significant difference in preoperative and postoperative best-corrected visual acuity (logMAR) between the groups at any of the follow-up period (favorable visual acuity subgroup; logMAR < 0.7). Postoperative complications were 0 cases of XEN group and 13 cases of trabeculectomy group (0% vs. 16.7%, p = 0.001). Also, XEN surgery (24 minutes 40 seconds ± 6 minutes 26 seconds) had a shorter operation time than the trabeculectomy (40 minutes 18 seconds ± 8 minutes 27 seconds, p < 0.001). Conclusions Compared to trabeculectomy, XEN surgery (ab externo, open conjunctiva) showed relatively lower effectiveness (surgical success rate, IOP reduction). However, it demonstrated advantages as a minimally invasive glaucoma surgery, including a surgical success rate approaching about 80%, stability in inducing corneal astigmatism, fewer postoperative complications, and shorter operation times.

Purpose: To compare the clinical outcomes of XEN45 gel stent implantation surgery (ab externo, open conjunctiva) with those of trabeculectomy. Methods: We retrospectively reviewed electronic medical record of 57 patients (62 eyes) treated with XEN implantation surgery (ab externo, open conjunctival approach) between April 1, 2021, and July 31, 2023, by the same surgeon. Preoperative clinical data including intraocular pressure (IOP), the number of glaucoma medications, and visual acuity were collected from 1 day to 12 months postoperatively. These data were compared and analyzed with those of 67 patients (78 eyes) received trabeculectomy between February 1, 2017, and April 30, 2022, by the same surgeon. Statistical analyses were performed with p < 0.05 as significant. Results: Complete surgical success rate was 33.9% and 57.7% of the XEN and trabeculectomy groups, respectively (p = 0.005). The qualified success rate was 79.0% and 93.6%, respectively (p = 0.011). Postoperatively, the XEN group used more glaucoma medications than the trabeculectomy group (1.21 ± 1.05 vs. 0.69 ± 0.90, p = 0.003 at postoperative month 12). After postoperative month 1, the XEN group had a higher IOP (15.77 ± 5.07 mmHg vs. 13.17 ± 3.81 mmHg; at postoperative month 12, p = 0.001) and lower corneal astigmatism than the trabeculectomy group (1.32 ± 0.79 diopters vs. 1.88 ± 1.45 diopters, p = 0.020 at postoperative month 6). There was no significant difference in preoperative and postoperative best-corrected visual acuity (logMAR) between the groups at any of the follow-up period (favorable visual acuity subgroup; logMAR < 0.7). Postoperative complications were 0 cases of XEN group and 13 cases of trabeculectomy group (0% vs. 16.7%, p = 0.001). Also, XEN surgery (24 minutes 40 seconds ± 6 minutes 26 seconds) had a shorter operation time than the trabeculectomy (40 minutes 18 seconds ± 8 minutes 27 seconds, p < 0.001). Conclusions Compared to trabeculectomy, XEN surgery (ab externo, open conjunctiva) showed relatively lower effectiveness (surgical success rate, IOP reduction). However, it demonstrated advantages as a minimally invasive glaucoma surgery, including a surgical success rate approaching about 80%, stability in inducing corneal astigmatism, fewer postoperative complications, and shorter operation times.

Purpose: To compare the clinical outcomes of XEN45 gel stent implantation surgery (ab externo, open conjunctiva) with those of trabeculectomy. Methods: We retrospectively reviewed electronic medical record of 57 patients (62 eyes) treated with XEN implantation surgery (ab externo, open conjunctival approach) between April 1, 2021, and July 31, 2023, by the same surgeon. Preoperative clinical data including intraocular pressure (IOP), the number of glaucoma medications, and visual acuity were collected from 1 day to 12 months postoperatively. These data were compared and analyzed with those of 67 patients (78 eyes) received trabeculectomy between February 1, 2017, and April 30, 2022, by the same surgeon. Statistical analyses were performed with p < 0.05 as significant. Results: Complete surgical success rate was 33.9% and 57.7% of the XEN and trabeculectomy groups, respectively (p = 0.005). The qualified success rate was 79.0% and 93.6%, respectively (p = 0.011). Postoperatively, the XEN group used more glaucoma medications than the trabeculectomy group (1.21 ± 1.05 vs. 0.69 ± 0.90, p = 0.003 at postoperative month 12). After postoperative month 1, the XEN group had a higher IOP (15.77 ± 5.07 mmHg vs. 13.17 ± 3.81 mmHg; at postoperative month 12, p = 0.001) and lower corneal astigmatism than the trabeculectomy group (1.32 ± 0.79 diopters vs. 1.88 ± 1.45 diopters, p = 0.020 at postoperative month 6). There was no significant difference in preoperative and postoperative best-corrected visual acuity (logMAR) between the groups at any of the follow-up period (favorable visual acuity subgroup; logMAR < 0.7). Postoperative complications were 0 cases of XEN group and 13 cases of trabeculectomy group (0% vs. 16.7%, p = 0.001). Also, XEN surgery (24 minutes 40 seconds ± 6 minutes 26 seconds) had a shorter operation time than the trabeculectomy (40 minutes 18 seconds ± 8 minutes 27 seconds, p < 0.001). Conclusions Compared to trabeculectomy, XEN surgery (ab externo, open conjunctiva) showed relatively lower effectiveness (surgical success rate, IOP reduction). However, it demonstrated advantages as a minimally invasive glaucoma surgery, including a surgical success rate approaching about 80%, stability in inducing corneal astigmatism, fewer postoperative complications, and shorter operation times.

Purpose: To compare the clinical outcomes of XEN45 gel stent implantation surgery (ab externo, open conjunctiva) with those of trabeculectomy. Methods: We retrospectively reviewed electronic medical record of 57 patients (62 eyes) treated with XEN implantation surgery (ab externo, open conjunctival approach) between April 1, 2021, and July 31, 2023, by the same surgeon. Preoperative clinical data including intraocular pressure (IOP), the number of glaucoma medications, and visual acuity were collected from 1 day to 12 months postoperatively. These data were compared and analyzed with those of 67 patients (78 eyes) received trabeculectomy between February 1, 2017, and April 30, 2022, by the same surgeon. Statistical analyses were performed with p < 0.05 as significant. Results: Complete surgical success rate was 33.9% and 57.7% of the XEN and trabeculectomy groups, respectively (p = 0.005). The qualified success rate was 79.0% and 93.6%, respectively (p = 0.011). Postoperatively, the XEN group used more glaucoma medications than the trabeculectomy group (1.21 ± 1.05 vs. 0.69 ± 0.90, p = 0.003 at postoperative month 12). After postoperative month 1, the XEN group had a higher IOP (15.77 ± 5.07 mmHg vs. 13.17 ± 3.81 mmHg; at postoperative month 12, p = 0.001) and lower corneal astigmatism than the trabeculectomy group (1.32 ± 0.79 diopters vs. 1.88 ± 1.45 diopters, p = 0.020 at postoperative month 6). There was no significant difference in preoperative and postoperative best-corrected visual acuity (logMAR) between the groups at any of the follow-up period (favorable visual acuity subgroup; logMAR < 0.7). Postoperative complications were 0 cases of XEN group and 13 cases of trabeculectomy group (0% vs. 16.7%, p = 0.001). Also, XEN surgery (24 minutes 40 seconds ± 6 minutes 26 seconds) had a shorter operation time than the trabeculectomy (40 minutes 18 seconds ± 8 minutes 27 seconds, p < 0.001). Conclusions Compared to trabeculectomy, XEN surgery (ab externo, open conjunctiva) showed relatively lower effectiveness (surgical success rate, IOP reduction). However, it demonstrated advantages as a minimally invasive glaucoma surgery, including a surgical success rate approaching about 80%, stability in inducing corneal astigmatism, fewer postoperative complications, and shorter operation times.

Objectives: Assessing medical disputes requires both medical and legal expertise, presenting challenges for patients seeking clarity regarding potential malpractice claims. This study aimed to develop and evaluate a chatbot based on a chain-of-thought pipeline using a large language model (LLM) for providing medical dispute counseling and compare its performance with responses from human experts. Methods: Retrospective counseling cases (n = 279) were collected from the Korea Medical Dispute Mediation and Arbitration Agency’s website, from which 50 cases were randomly selected as a validation dataset. The Claude 3.5 Sonnet model processed each counseling request through a five-step chain-of-thought pipeline. Thirty-eight experts evaluated the chatbot’s responses against the original human expert responses, rating them across four dimensions on a 5-point Likert scale. Statistical analyses were conducted using Wilcoxon signed-rank tests. Results: The chatbot significantly outperformed human experts in quality of information (p < 0.001), understanding and reasoning (p < 0.001), and overall satisfaction (p < 0.001). It also demonstrated a stronger tendency to produce opinion-driven content (p < 0.001). Despite generally high scores, evaluators noted specific instances where the chatbot encountered difficulties. Conclusions A chain-of-thought–based LLM chatbot shows promise for enhancing the quality of medical dispute counseling, outperforming human experts across key evaluation metrics. Future research should address inaccuracies resulting from legal and contextual variability, investigate patient acceptance, and further refine the chatbot’s performance in domain-specific applications.

Objectives: Assessing medical disputes requires both medical and legal expertise, presenting challenges for patients seeking clarity regarding potential malpractice claims. This study aimed to develop and evaluate a chatbot based on a chain-of-thought pipeline using a large language model (LLM) for providing medical dispute counseling and compare its performance with responses from human experts. Methods: Retrospective counseling cases (n = 279) were collected from the Korea Medical Dispute Mediation and Arbitration Agency’s website, from which 50 cases were randomly selected as a validation dataset. The Claude 3.5 Sonnet model processed each counseling request through a five-step chain-of-thought pipeline. Thirty-eight experts evaluated the chatbot’s responses against the original human expert responses, rating them across four dimensions on a 5-point Likert scale. Statistical analyses were conducted using Wilcoxon signed-rank tests. Results: The chatbot significantly outperformed human experts in quality of information (p < 0.001), understanding and reasoning (p < 0.001), and overall satisfaction (p < 0.001). It also demonstrated a stronger tendency to produce opinion-driven content (p < 0.001). Despite generally high scores, evaluators noted specific instances where the chatbot encountered difficulties. Conclusions A chain-of-thought–based LLM chatbot shows promise for enhancing the quality of medical dispute counseling, outperforming human experts across key evaluation metrics. Future research should address inaccuracies resulting from legal and contextual variability, investigate patient acceptance, and further refine the chatbot’s performance in domain-specific applications.

Purpose: To describe the features of the peripheral necrotic retinal lesions in a patient with acute retinal necrosis (ARN) using ultrawide-field optical coherence tomography (UWF OCT).Case summary: A 35-year-old male patient diagnosed with uveitis was referred to our clinic with decreased vision in the right eye.While the patient's progress was followed, peripheral whitish lesions increased in size in the right eye, and necrotic change with retinal hemorrhage was noted in his left eye. Viral polymerase chain reaction was performed with an aqueous humor sample, and Varicella-Zoster virus was detected, resulting in a diagnostic change to ARN. After antiviral treatment, the peripheral retinal necrotic lesions had recovered in both eyes, and the recovered areas were followed using UWF OCT in both eyes. Complete loss of the sensory retina with very gentle sloping at the borders of necrosis was noted. Three months later, near total loss of the sensory retina in the right eye progressed to retinal detachment. Pars plana vitrectomy, silicone oil injection, and barrier laser photocoagulation were performed, although no definite retinal tear was detected during retinal reattachment surgery. Conclusions This case illustrates the progression to retinal detachment in ARN in the absence of a definite retinal break, with almost complete loss of the sensory neuroretinal layer. UWF OCT may be a valuable tool in predicting progression to retinal detachment in ARN.