ECEun Chang Choi

Eun Chang Choi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Eun Chang Choi has a total of 111 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning-Based Predictor for Treatment Outcomes of Patients With Salivary Gland Cancer After Operation

    by Min Cheol Jeong, Yoon Woo Koh, Eun Chang Choi, Jae-Yol Lim, Se-Heon Kim, Young Min Park

    Background and Objectives The purpose of this study was to analyze the survival data of salivary gland cancer (SGCs) patients to construct machine learning and deep learning models that can predict survival and use them to stratify SGC patients according to risk estimate.Subjects and Method We retrospectively analyzed the clinicopathologic data from 460 patients with SGCs from 2006 to 2018.Results In Cox proportional hazard (CPH) model, pM, stage, lymphovascular invasion, lymph node ratio, and age exhibited significant correlation with patient’s survival. In the CPH model, the c-index value for the training set was 0.85, and that for the test set was 0.81. In the Random Survival Forest model, the c-index value for the training set was 0.86, and that for the test set was 0.82. Stage and age exhibited high importance in both the Random Survival Forest and CPH models. In the deep learning-based model, the c-index value was 0.72 for the training set and 0.72 for the test set. Among the three models mentioned above, the Random Survival Forest model exhibited the highest performance in predicting the survival of SGC patients.Conclusion A survival prediction model using machine learning techniques showed acceptable performance in predicting the survival of SGC patients. Although large-scale clinical and multicenter studies should be conducted to establish more powerful predictive model, we expect that individualized treatment can be realized according to risk stratification made by the machine learning model.

  • Open Access

    Robot-Assisted Total Thyroidectomy with or without Robot-Assisted Neck Dissection in Pediatric Patients with Differentiated Thyroid Cancer

    by Dahee Kim, Nam Suk Sim, Dachan Kim, Eun Chang Choi, Jae Won Chang, Yoon Woo Koh

    Pediatric thyroid cancer more frequently develops cervical node metastasis than adult thyroid cancer, even in differentiated thyroid carcinoma (DTC). Thus, cervical neck dissection often needs to be performed simultaneously with thyroidectomy in pediatric patients. Herein, we describe our experience with robot-assisted total thyroidectomy with/without robot-assisted neck dissection in pediatric patients compared with the conventional operated group. A total of 30 pediatric patients who underwent thyroidectomy for DTC between July 2011 and December 2019 were retrospectively reviewed. Among them, 22 underwent robot-assisted operation, whereas 8 underwent conventional operation. There was no statistical difference in the mean operation times, blood loss, drainage amounts, and hospital stay length between the robot-assisted and conventional operation groups; however, the operation time was less in the retroauricular approach subgroup (robot-assisted operation group) with better satisfaction on cosmesis. No postoperative complications, such as seromas, hemorrhages, or hematomas were observed. Our experience suggested that robot-assisted thyroidectomy with or without neck dissection through the retroauricular approach is a feasible and safe alternative treatment, producing outstanding esthetic results compared to the conventional approach, especially in pediatric patients with DTC.


  • Open Access

    Externally Monitored Versus Conventional Buried Flaps in Laryngopharyngeal Reconstruction

    by Myung Jin Ban, Gina Na, Sungchul Ko, Joohyun Kim, Nam Hun Heo, Eun Chang Choi, Jae Hong Park, Won Shik Kim

    Objectives. To compare the surgical outcomes of externally monitored and conventional buried flaps with the goal of determining the usefulness of external monitoring of buried flaps.Methods. In this case-control study with propensity score matching, 30 patients were evenly divided into externally monitored buried flap and conventional buried flap groups. The total operative time for free flap reconstruction, the flap survival rate, the length of hospital stay, the initial time of a reliable visual assessment, complications, the final diet achieved, and the duration until diet initiation were compared between the groups.Results. The mean operative time for reconstruction was 115 minutes (interquartile range, 85–150 minutes) and 142 minutes (interquartile range, 95–180 minutes) in the externally monitored and conventional groups, respectively (P= 0.245). The median length of hospital stay was 24 days (interquartile range, 18–30 days) and 27 days (interquartile range, 20–41 days) in the externally monitored and conventional groups, respectively (P=0.298). The median duration until diet initiation was 15 days (interquartile range, 15–21 days) and 18 days (interquartile range, 15–34 days) in the externally monitored and conventional groups, respectively (P=0.466). The final diet, initial time of a reliable visual assessment, and complications were comparable between the groups, but the external skin paddle provided an excellent visual assessment immediately postoperatively in all cases.Conclusion. The outcomes were comparable between the groups, indicating that externalization of the cutaneous component of a buried flap may be a straightforward and useful technique for monitoring a buried anterolateral thigh free flap in laryngopharyngeal reconstructions. The salvage and false-positive rates of compromised flaps should be compared in large subject groups in future studies to prove that the use of an external skin paddle improves flap monitoring.


  • Open Access

    Comprehensive Analysis of Clinicopathologic Factors Predictive of an Unfavorable Prognosis in Patients With Acinic Cell Carcinoma of the Parotid Gland

    by Young Min Park, Sun Och Yoon, Joo Hyun Kim, Min Seok Kang, Da Hee Kim, Yoon Woo Koh, Se-Heon Kim, Jae-Yol Lim, Eun Chang Choi

    Objectives. In subset of patients, acinic cell carcinoma (AcCC) exhibits aggressive features such as recurrence, distant metastasis, and mortality. This study aimed to investigate clinicopathologic factors influencing patients’ prognosis and to identify adverse features predictive of an unfavorable prognosis.Methods. Between January 2000 and December 2016, 59 patients with AcCC were enrolled in this study.Results. The patients’ 5-year overall survival rate was 93.3%, and their 5-year recurrence-free survival rate was 80.5%. During the study period, recurrence occurred in 10 patients. The mean time to recurrence after surgery was 26 months (range, 5–60 months). During the study period, three patients died from the disease. Univariate analysis showed that sex, surgical extent, extranodal extension, T classification, and TNM stage were significantly associated with disease recurrence. Multivariate analysis showed that, among the clinicopathologic factors included in the analysis, only TNM stage displayed a statistically significant correlation with disease recurrence.Conclusion. Surgical treatment alone yielded good results for AcCC, and additional treatment did not affect the recurrence-free survival rate or the overall survival rate, even when the resection margin was less than 1 mm. Other pathologic factors did not show prognostic significance for disease recurrence or death.


  • Clinical-pathological prognostic factors and treatment failure patterns in T1-2 high-grade parotid gland cancer

    by Young Min Park, Sun Och Yoon, Yoon Woo Koh, Se-Heon Kim, Jae-Yol Lim, Eun Chang Choi


  • Surgical extent and role of adjuvant radiotherapy of surgically resectable, low-grade parotid cancer

    by Young Min Park, Min Seok Kang, Da Hee Kim, Yoon Woo Koh, Se-Heon Kim, Jae-Yol Lim, Eun Chang Choi


  • Prognostic Significance of Lymph Node Status in p16+ Oropharyngeal Cancer After Surgical Treatment

    by Young Min Park, Tae Seong Eo, Yoon Woo Koh, Se‐Heon Kim, Eun Chang Choi

    Objectives/Hypothesis: In this study, we retrospectively reviewed medical records of patients who underwent surgery for p16+ oropharyngeal cancer and analyzed the prognostic implications of pathologic lymph node (LN) status, including number of metastatic LNs, LN ratio, and location of metastatic LNs.Study Design: Retrospective case series.Methods: We retrospectively reviewed data on patients diagnosed with p16+ oropharyngeal cancer.Results: The study population consisted of 159 males and 29 females with a mean age of 57.2 years. The primary tumor sites were tonsils (n = 160), base of the tongue (n = 24), and soft palate (n = 4). Only recurrence‐free survival (RFS) showed a significant correlation with contralateral LN metastasis on multivariate analysis. On Kaplan‐Meier analysis, 5‐year RFS was 92.4% in patients without contralateral LN metastasis and 68.8% in patients with contralateral LN metastasis.Conclusions: Among pathologic LN status in p16+ oropharyngeal cancer, only contralateral LN metastasis showed prognostic significance in disease recurrence of p16+ oropharyngeal squamous cell carcinoma patients.Level of Evidence: 4 Laryngoscope, 130: 1973–1979, 2020


  • ICG‐Guided Sentinel Lymph Node Sampling during Robotic Retroauricular Neck Dissection in cN0 Oral Cancer

    by Ji Hoon Kim, Hyung Kwon Byeon, Da Hee Kim, Se‐Heon Kim, Eun Chang Choi, Yoon Woo Koh

    In this study, we sought to evaluate the clinical feasibility of indocyanine green (ICG)–guided sentinel lymph node (SLN) sampling during robotic retroauricular neck dissection (RAND) in patients with cN0 oral cancer. Nine adult patients diagnosed with T1 to T2 oral squamous cell carcinoma were consecutively recruited. All of them underwent transoral partial glossectomy and robotic RAND (levels I‐III) simultaneously. Twelve hours prior to surgery, ICG was injected into the 4 quadrants around primary tongue tumors. During robotic RAND, intraoperative and ex vivo ICG‐stained LNs were identified using the Firefly system and examined for the presence of fluorescence. ICG‐stained LNs were identified in all patients. Thirty‐one ICG‐stained LNs were detected in 313 retrieved LNs (9.9%). Occult metastases were detected among the ICG‐stained LNs in 2 patients (22.2%). There was no metastasis identified in the ICG‐unstained LNs. Upstaging rates, sensitivity, specificity, and negative predictive value of ICG‐guided SLN sampling were 22.2%, 100%, 91.5%, and 100%, respectively.