Jun S. Kim

Jun S. Kim

Auto-generated profile, based on publicly available information

Jun S. Kim

Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 August 2018 in Nature Medicine
Verified
Journal Article
Closed access
PDF file
JTJoseph J. Titano
Joseph J. Titano
MBMarcus Badgeley
Marcus Badgeley
JSJavin Schefflein
Javin Schefflein
MPMargaret Pain
Margaret Pain
ASAndres Su
Andres Su
EOEric K. Oermann
Eric K. Oermann

13 February 2019 in PLOS ONE
Verified
Journal Article
Open access
PDF file
DKDeepak A. Kaji
Deepak A. Kaji
JZJohn R. Zech
John R. Zech
JKJun S. Kim
Jun S. Kim
SCSamuel K. Cho
Samuel K. Cho
NDNeha S. Dangayach
Neha S. Dangayach
EOEric K. Oermann
Eric K. Oermann
This study trained long short-term memory (LSTM) recurrent neural networks (RNNs) incorporating an attention mechanism to predict daily sepsis, myocardial infarction (MI), and vancomycin antibiotic administration over two week patient ICU courses in the MIMIC-III dataset. These models achieved next-day predictive AUC of 0.876 for sepsis, 0.823 for MI, and 0.833 for vancomycin administration. Attention maps built from these models highlighted those times when input variables most influenced predictions and could provide a degree of interpretability to clinicians. These models appeared to attend to variables that were proxies for clinician decision-making, demonstrating a challenge of using flexible deep learning approaches trained with EHR data to build clinical decision support. While continued development and refinement is needed, we believe that such models could one day prove useful in reducing information overload for ICU physicians by providing needed clinical decision support for a variety of clinically important tasks.

15 June 2018 in Spine
Verified
Journal Article
Closed access
JKJun S. Kim
Jun S. Kim
RMRobert K. Bs Merrill
Robert K. Bs Merrill
VAVarun Bs Arvind
Varun Bs Arvind
DKDeepak Ba Kaji
Deepak Ba Kaji
SPSara D. Ba Pasik
Sara D. Ba Pasik
SCSamuel K. Cho
Samuel K. Cho
Study Design.: A cross-sectional database study. Objective.: The aim of this study was to train and validate machine learning models to identify risk factors for complications following posterior lumbar spine fusion. Summary of Background Data.: Machine learning models such as artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex datasets. ANNs have yet to be used for risk factor analysis in orthopedic surgery. Methods.: The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent posterior lumbar spine fusion. This query returned 22,629 patients, 70% of whom were used to train our models, and 30% were used to evaluate the models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society for Anesthesiology (ASA) class ≥3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating curves (AUC) was used to determine the accuracy of our machine learning models. Results.: On the basis of AUC values, ANN and LR both outperformed ASA class for predicting all four types of complications. ANN was the most accurate for predicting cardiac complications, and LR was most accurate for predicting wound complications, VTE, and mortality, though ANN and LR had comparable AUC values for predicting all types of complications. ANN had greater sensitivity than LR for detecting wound complications and mortality. Conclusion.: Machine learning in the form of logistic regression and ANNs were more accurate than benchmark ASA scores for identifying risk factors of developing complications following posterior lumbar spine fusion, suggesting they are potentially great tools for risk factor analysis in spine surgery. Level of Evidence: 3

1 February 2016 in Journal of Shoulder and Elbow Surgery
Verified
Journal Article
Closed access
DSDave R. Shukla
Dave R. Shukla
SMSteven McAnany
Steven McAnany
JKJun Kim
Jun Kim
SOSam Overley
Sam Overley
BPBradford O. Parsons
Bradford O. Parsons

13 December 2018 in Global Spine Journal
Verified
Journal Article
Open access
PDF file
JDJames Dowdell
James Dowdell
RBRobert Brochin
Robert Brochin
JKJun Kim
Jun Kim
SOSamuel Overley
Samuel Overley
JOJonathan Oren
Jonathan Oren
SCSamuel Cho
Samuel Cho
Study Design: Review article. Objectives: A review of the literature on postoperative spinal infections, their diagnosis, and management. Methods: A systematic computerized Medline literature search was performed using PubMed, Cochrane Database of Systematic Reviews, and EMBASE. The electronic databases were searched for publication dates from the last 10 years. The searches were performed from Medical Subject Headings (MeSH) used by the National Library of Medicine. Specifically, MeSH terms “spine,” “infections,” “management,” and “diagnosis” were used. Results: Currently, the gold standard for diagnosis of postoperative spine infection is positive deep wound culture. Many of the current radiologic and laboratory tests can assist with the initial diagnosis and monitoring treatment response. Currently erythrocyte sedimentation rate, C-reactive protein, computed tomography scan, and magnetic resonance imaging with and without contrast are used in combination to establish diagnosis. Management of postoperative spine infection involves thorough surgical debridement and targeted antibiotic therapy. Conclusions: Postoperative spine infection is a not uncommon complication following surgery that may have devastating consequences for a patient’s short- and long-term health. A high index of suspicion is needed to make an early diagnosis.

31 May 2017 in Global Spine Journal
Verified
Journal Article
Open access
KPKevin Phan
Kevin Phan
JKJun S. Kim
Jun S. Kim
JKJoung Heon Kim
Joung Heon Kim
SSSulaiman Somani
Sulaiman Somani
JDJohn Di’capua
John Di’capua
SCSamuel K. Cho
Samuel K. Cho
Retrospective study. To determine the presence of any potential associations between anesthesia time with postoperative outcome and complications following elective anterior cervical discectomy and fusion (ACDF). Patients who underwent elective ACDF were identified in the American College of Surgeons National Quality Improvement Program database. Patient demographics, medical comorbidities, and perioperative and postoperative complications up to 30 days were analyzed by univariate and multivariate analysis. A total of 3801 patients undergoing elective ACDF were identified. Patients were subdivided into quintiles of anesthesia time: Group 1, 48 to 129 minutes (n = 761, 20%); Group 2, 129 to 156 minutes (n = 760, 20%); Group 3, 156 to 190 minutes (n = 760, 20%); Group 4, 190 to 245 minutes (n = 760, 20%); and Group 5, 245 to 1025 minutes (n = 760, 20%). Univariate analysis showed significantly higher rates of any complication (P < .0001), pulmonary complication (P < .0001), intra-/postoperative blood transfusions (P < .0001), sepsis (P = .017), wound complications (P = .002), total length of stay >5 days (P < .0001), and return to operating room (P = .006) in the highest quintile compared to those of other groups. Multivariate regression analysis revealed that prolonged anesthesia was an independent factor for increased odds of overall complications (odds ratio [OR] = 2.71, P = .012), venous thromboembolism (OR = 2.69, P = .011), and return to the operating room (OR = 2.92, P = .004). The 2 groups with the longest anesthesia durations (quintiles 4 and 5) had increased total length of stay more than 5 days (for quintile 4, OR = 3.10, P = .0004; for quintile 5, OR = 3.61, P < .0001). Prolonged anesthesia duration is associated with increased odds of complication, venous thromboembolism, increased length of stay, and return to the operating room.