This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

Purpose: Although partial mesorectal excision (PME) and total mesorectal excision (TME) is primarily indicated for the upper and lower rectal cancer, respectively, few studies have evaluated whether PME or TME is more optimal for middle rectal cancer. Methods: This study included 671 patients with middle and upper rectal cancer who underwent robot-assisted PME or TME. The 2 groups were optimized by propensity score matching of sex, age, clinical stage, tumor location, and neoadjuvant treatment. Results: Complete mesorectal excision was achieved in 617 of 671 patients (92.0%), without showing a difference between the PME and TME groups. Local recurrence rate (5.3% vs. 4.3%, P>0.999) and systemic recurrence rate (8.5% vs. 16.0%, P=0.181) also did not differ between the 2 groups, in patients with middle and upper rectal cancer. The 5-year disease-free survival (81.4% vs. 74.0%, P=0.537) and overall survival (88.0% vs. 81.1%, P=0.847) also did not differ between the PME and TME groups, confined to middle rectal cancer. Moreover, 5-year recurrence and survival rates were not affected by distal resection margins of 2 cm (P=0.112) to 4 cm (P>0.999), regardless of pathological stages. Postoperative complication rate was higher in the TME than in the PME group (21.4% vs. 14.5%, P=0.027). Incontinence was independently associated with TME (odds ratio [OR], 2.009; 95% confidence interval, 1.015–3.975; P=0.045), along with older age (OR, 4.366, P<0.001) and prolonged operation time (OR, 2.196; P=0.500). Conclusion PME can be primarily recommended for patients with middle rectal cancer with lower margin of >5 cm from the anal verge.

Purpose: This study was designed to determine the feasibility of preoperative chemoradiotherapy (PCRT) in patients with clinical T2N0 distal rectal cancer. Methods: Patients who underwent surgery for clinical T2N0 distal rectal cancer between January 2008 and December 2016 were included. Patients were divided into PCRT and non-PCRT groups. Non-PCRT patients underwent radical resection or local excision (LE) according to the surgeon’s decision, and PCRT patients underwent surgery according to the response to PCRT. Patients received 50.0 to 50.4 gray of preoperative radiotherapy with concurrent chemotherapy. Results: Of 127 patients enrolled, 46 underwent PCRT and 81 did not. The mean distance of lesions from the anal verge was lower in the PCRT group (P=0.004). The most frequent operation was transanal excision and ultralow anterior resection in the PCRT and non-PCRT groups, respectively. Of the 46 patients who underwent PCRT, 21 (45.7%) achieved pathologic complete response, including 15 of the 24 (62.5%) who underwent LE. Rectal sparing rate was significantly higher in the PCRT group (11.1% vs. 52.2%, P<0.001). There were no significant differences in 3- and 5-year overall survival and recurrence-free survival regardless of PCRT or surgical procedures. Conclusion PCRT in clinical T2N0 distal rectal cancer patients increased the rectal sparing rate via LE and showed acceptable oncologic outcomes. PCRT may be a feasible therapeutic option to avoid abdominoperineal resection in clinical T2N0 distal rectal cancer.

Objective: Dysphagia is a common clinical condition characterized by difficulty in swallowing. It is sub-classified into oropharyngeal dysphagia, which refers to problems in the mouth and pharynx, and esophageal dysphagia, which refers to problems in the esophageal body and esophagogastric junction. Dysphagia can have a significant negative impact one’s physical health and quality of life as its severity increases. Therefore, proper assessment and management of dysphagia are critical for improving swallowing function and preventing complications. Thus a guideline was developed to provide evidence-based recommendations for assessment and management in patients with dysphagia. Methods: Nineteen key questions on dysphagia were developed. These questions dealt with various aspects of problems related to dysphagia, including assessment, management, and complications. A literature search for relevant articles was conducted using Pubmed, Embase, the Cochrane Library, and one domestic database of KoreaMed, until April 2021. The level of evidence and recommendation grade were established according to the Grading of Recommendation Assessment, Development and Evaluation methodology. Results: Early screening and assessment of videofluoroscopic swallowing were recommended for assessing the presence of dysphagia. Therapeutic methods, such as tongue and pharyngeal muscle strengthening exercises and neuromuscular electrical stimulation with swallowing therapy, were effective in improving swallowing function and quality of life in patients with dysphagia. Nutritional intervention and an oral care program were also recommended. Conclusion This guideline presents recommendations for the assessment and management of patients with oropharyngeal dysphagia, including rehabilitative strategies.

Primary aldosteronism (PA) is a common, yet underdiagnosed cause of secondary hypertension. It is characterized by an overproduction of aldosterone, leading to hypertension and/or hypokalemia. Despite affecting between 5.9% and 34% of patients with hypertension, PA is frequently missed due to a lack of clinical awareness and systematic screening, which can result in significant cardiovascular complications. To address this, medical societies have developed clinical practice guidelines to improve the management of hypertension and PA. The Korean Endocrine Society, drawing on a wealth of research, has formulated new guidelines for PA. A task force has been established to prepare PA guidelines, which encompass epidemiology, pathophysiology, clinical presentation, diagnosis, treatment, and follow-up care. The Korean clinical guidelines for PA aim to deliver an evidence-based protocol for PA diagnosis, treatment, and patient monitoring. These guidelines are anticipated to ease the burden of this potentially curable condition.

Purpose: To derive the optimized intraocular lens (IOL) constants from automated and manifest refraction after cataract surgery in Korean patients, and to evaluate whether there is a difference in optimized IOL constants according to the refraction method. Methods: This retrospective multicenter cohort study enrolled 4,103 eyes of 4,103 patients who underwent phacoemulsification and in-the-bag IOL implantation at 18 institutes. Optimized IOL constants for the SRK/T, Holladay, Hoffer Q, and Haigis formulas were calculated via autorefraction or manifest refraction of samples using the same biometry and IOL. The IOL constants derived from autorefraction and manifest refraction were compared. Results: Of the 4,103 eyes, the majority (62.9%) were measured with an IOLMaster 500 followed by an IOLMaster 700 (15.2%). A total of 33 types of IOLs were used, and the Tecnis ZCB00 was the most frequently used (53.0%). There was no statistically significant difference in IOL constants derived from autorefraction and manifest refraction when IOL constants were optimized with a large number of study subjects. On the other hand, optimized IOL constants derived from autorefraction were significantly smaller than those from manifest refraction when the number of subjects was small. Conclusions It became possible to use the IOL constants optimized from Koreans to calculate the IOL power. However, if the IOL constant is optimized using autorefraction in a small sample group, the IOL constant tends to be small, which may lead to refractive error after surgery.