Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: The risk of device thrombosis and device-oriented clinical outcomes with bioresorbable vascular scaffold (BVS) was reported to be significantly higher than with contemporary drug-eluting stents (DESs). However, optimal device implantation may improve clinical outcomes in patients receiving BVS. The current study evaluated mid-term safety and efficacy of Absorb BVS with meticulous device optimization under intravascular imaging guidance. Methods: The SMART-REWARD and PERSPECTIVE-PCI registries in Korea prospectively enrolled 390 patients with BVS and 675 patients with DES, respectively. The primary endpoint was target vessel failure (TVF) at 2 years and the secondary major endpoint was patientoriented composite outcome (POCO) at 2 years. Results: Patient-level pooled analysis evaluated 1,003 patients (377 patients with BVS and 626 patients with DES). Mean scaffold diameter per lesion was 3.24 ± 0.30 mm in BVS group.Most BVSs were implanted with pre-dilatation (90.9%), intravascular imaging guidance (74.9%), and post-dilatation (73.1%) at proximal to mid segment (81.9%) in target vessel.Patients treated with BVS showed comparable risks of 2-year TVF (2.9% vs. 3.7%, adjusted hazard ratio [HR], 1.283, 95% confidence interval [CI], 0.487–3.378, P = 0.615) and 2-year POCO (4.5% vs. 5.9%, adjusted HR, 1.413, 95% CI, 0.663–3.012,P = 0.370) than those with DES. The rate of 2-year definite or probable device thrombosis (0.3% vs. 0.5%, P = 0.424) was also similar. The sensitivity analyses consistently showed comparable risk of TVF and POCO between the 2 groups. Conclusion With meticulous device optimization under imaging guidance and avoidance of implantation in small vessels, BVS showed comparable risks of 2-year TVF and device thrombosis with DES.

Purpose: Renal tumors account for approximately 7% of all childhood cancers. These include Wilms tumor (WT), clear cell sarcoma of the kidney (CCSK), malignant rhabdoid tumor of the kidney (MRTK), renal cell carcinoma (RCC), congenital mesoblastic nephroma (CMN) and other rare tumors. We investigated the epidemiology of pediatric renal tumors in Korea. Materials and Methods: From January 2001 to December 2015, data of pediatric patients (0–18 years) newly-diagnosed with renal tumors at 26 hospitals were retrospectively analyzed. Results: Among 439 patients (male, 240), the most common tumor was WT (n=342, 77.9%), followed by RCC (n=36, 8.2%), CCSK (n=24, 5.5%), MRTK (n=16, 3.6%), CMN (n=12, 2.7%), and others (n=9, 2.1%). Median age at diagnosis was 27.1 months (range 0-225.5) and median follow-up duration was 88.5 months (range 0-211.6). Overall, 32 patients died, of whom 17, 11, 1, and 3 died of relapse, progressive disease, second malignant neoplasm, and treatment-related mortality. Five-year overall survival and event free survival were 97.2% and 84.8% in WT, 90.6% and 82.1% in RCC, 81.1% and 63.6% in CCSK, 60.3% and 56.2% in MRTK, and 100% and 91.7% in CMN, respectively (p < 0.001). Conclusion The pediatric renal tumor types in Korea are similar to those previously reported in other countries. WT accounted for a large proportion and survival was excellent. Non-Wilms renal tumors included a variety of tumors and showed inferior outcome, especially MRTK. Further efforts are necessary to optimize the treatment and analyze the genetic characteristics of pediatric renal tumors in Korea.

Objective: Anxious depression is associated with greater chronicity, higher severity of symptoms, more severe functional impairment, and poor response to drug treatment. However, evidence for first-choice antidepressants in patients with anxious depression is limited. This study aimed to compare the efficacy and safety of escitalopram, desvenlafaxine, and vortioxetine in the acute treatment of anxious depression. Methods: Patients (n = 124) with major depressive disorder and high levels of anxiety were randomly assigned to an escitalopram treatment group (n = 42), desvenlafaxine treatment group (n = 40), or vortioxetine treatment group (n = 42) in a 6-week randomized rater-blinded head-to-head comparative trial. Changes in overall depressive and anxiety symptoms were assessed using the 17-item Hamilton Depression Rating Scale (HAMD) and Hamilton Anxiety Rating Scale (HAMA), respectively. Results: Patients demonstrated similar baseline-to-endpoint improvement in scores and similar response and remission rates for HAMD and HAMA. Analysis of the individual HAMD items revealed that desvenlafaxine significantly reduced anxiety somatic scores (p= 0.013) and hypochondriasis scores (p = 0.014) compared to escitalopram. With respect to the individual HAMA items, desvenlafaxine treatment showed significantly lower scores for respiratory symptoms (p = 0.013) than escitalopram treatment and cardiovascular symptoms (p = 0.005) than vortioxetine treatment. The treatments were well tolerated, with no significant differences. Conclusion Our results indicated no significant differences in the efficacy and tolerability of escitalopram, desvenlafaxine, and vortioxetine in this subtype of patients with anxious depression during the acute phase of treatment.

Background: AML is a heterogeneous disease, and despite intensive therapy, recurrence is still high in AML patients who achieve the criterion for cytomorphologic remission (residual tumor burden [measurable residual disease, MRD]<5%). This study aimed to develop a targeted next-generation sequencing (NGS) panel to detect MRD in AML patients and validate its performance. Methods: We designed an error-corrected, targeted MRD-NGS panel without using physical molecular barcodes, including 24 genes. Fifty-four bone marrow and peripheral blood samples from 23 AML patients were sequenced using the panel. The panel design was validated using reference material, and accuracy was assessed using droplet digital PCR. Results: Dilution tests showed excellent linearity and a strong correlation between expected and observed clonal frequencies (R>0.99). The test reproducibly detected MRD in three dilution series samples, with a sensitivity of 0.25% for single-nucleotide variants. More than half of samples from patients with morphologic remission after one month of chemotherapy had detectable mutations. NGS-MRD positivity for samples collected after one month of chemotherapy tended to be associated with poor overall survival and progression-free survival. Conclusions Our highly sensitive and accurate NGS-MRD panel can be readily used to monitor most AML patients in clinical practice, including patients without gene rearrangement. In addition, this NGS-MRD panel may allow the detection of newly emerging clones during clinical relapse, leading to more reliable prognoses of AML.

Purpose: Acute promyelocytic leukemia (APL) is a rare disease in children and there are some different characteristics between children and adult. We aimed to evaluate incidence, clinical characteristics and treatment outcomes of pediatric APL in Korea. Materials and Methods: Seventy-nine pediatric APL patients diagnosed from January 2009 to December 2016 in 16 tertiary medical centers in Korea were reviewed retrospectively. Results: Of 801 acute myeloid leukemia children, 79 (9.9%) were diagnosed with APL. The median age at diagnosis was 10.6 years (range, 1.3 to 18.0). Male and female ratio was 1:0.93. Thirty patients (38.0%) had white blood cell (WBC) count greater than 10×109/L at diagnosis. All patients received induction therapy consisting of all-trans retinoic acid and chemotherapy. Five patients (6.6%) died during induction chemotherapy and 66 patients (86.8%) achieved complete remission (CR) after induction chemotherapy. The causes of death were three intracranial hemorrhage, one cerebral infarction, and one sepsis. Five patients (7.1%) suffered a relapse during or after maintenance chemotherapy. The estimated 4-year event-free survival and overall survival (OS) rates were 82.1%±4.4%, 89.7%±5.1%, respectively. The 4-year OS was significantly higher in patients with initial WBC < 10×109/L than in those with initial WBC ≥ 10×109/L (p=0.020). Conclusion This study showed that the CR rates and survival outcomes in Korean pediatric APL patients were relatively good. The initial WBC count was the most important prognostic factor and most causes of death were related to serious bleeding in the early stage of treatment.

Background/Aims: Hypoxemia in chronic obstructive pulmonary disease (COPD) leads to reduced ability to exercise, decreased quality of life, and, eventually, increased mortality. Home oxygen therapy in patients with severe COPD reduces distress symptoms and mortality rates. However, there have been few studies on physicians’ prescription behavior toward home oxygen therapy. Therefore, we investigated the respiratory specialists’ perspective on home oxygen therapy. Methods: In this cross-sectional, study, a questionnaire was completed by 30 pulmonary specialists who worked in tertiary hospitals and prescribed home oxygen therapy. The questionnaire consisted of 28 items, including 15 items on oxygen prescription for outpatients, four for inpatients, and nine on service improvement. Results: All physicians were prescribing less than 2 L/min of oxygen for either 24 (n = 10, 33.3%) or 15 hours (n = 9, 30.3%). All (n = 30) used pulse oximetry, 26 (86.7%) analyzed arterial blood gas. Thirteen physicians had imposed restrictions and recommended oxygen use only during exercise or sleep. Sixteen (53.3%) physicians were educating their patients about home oxygen therapy. Furthermore, physicians prescribed home oxygen to patients that did not fit the typical criteria for longterm oxygen therapy, with 30 prescribing it for acute relief and 17 for patients with borderline hypoxemia. Conclusions This study identified the prescription pattern of home oxygen therapy in Korea. Respiratory physicians prescribe home oxygen therapy to hypoxemic COPD patients for at least 15 hours/day, and at a rate of less than 2 L/min. More research is needed to provide evidence for establishing policies on oxygen therapy in COPD patients.