Sang Hyun Kim

Dr. Sang Hyun Kim


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
31 March 2023 in Neurospine
Verified
Journal Article
Open access
PDF file
SKSang Hyun Kim
Sang Hyun Kim
HLHye Sun Lee
Hye Sun Lee
GPGo Eun Park
Go Eun Park
YHYoon Ha
Yoon Ha
JPJeong Yoon Park
Jeong Yoon Park
KKKyung-Hyun Kim
Kyung-Hyun Kim
Objective: This study aimed to create an ideal machine learning model to predict mechanical complications in adult spinal deformity (ASD) surgery based on GAPB (modified global alignment and proportion scoring with body mass index and bone mineral density) factors.Methods: Between January 2009 and December 2018, 238 consecutive patients with ASD, who received at least 4-level fusions and were followed-up for ≥ 2 years, were included in the study. The data were stratified into training (n = 167, 70%) and test (n = 71, 30%) sets and input to machine learning algorithms, including logistic regression, random forest gradient boosting system, and deep neural network.Results: Body mass index, bone mineral density, the relative pelvic version score, the relative lumbar lordosis score, and the relative sagittal alignment score of the global alignment and proportion score were significantly different in the training and test sets (p < 0.05) between the complication and no complication groups. In the training set, the area under receiver operating characteristics (AUROCs) for logistic regression, gradient boosting, random forest, and deep neural network were 0.871 (0.817–0.925), 0.942 (0.911–0.974), 1.000 (1.000–1.000), and 0.947 (0.915–0.980), respectively, and the accuracies were 0.784 (0.722–0.847), 0.868 (0.817–0.920), 1.000 (1.000–1.000), and 0.856 (0.803–0.909), respectively. In the test set, the AUROCs were 0.785 (0.678–0.893), 0.808 (0.702–0.914), 0.810 (0.710–0.910), and 0.730 (0.610–0.850), respectively, and the accuracies were 0.732 (0.629–0.835), 0.718 (0.614–0.823), 0.732 (0.629–0.835), and 0.620 (0.507–0.733), respectively. The random forest achieved the best predictive performance on the training and test dataset.Conclusion: This study created a comprehensive model to predict mechanical complications after ASD surgery. The best prediction accuracy was 73.2% for predicting mechanical complications after ASD surgery.

17 March 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SNSung Hyun Noh
Sung Hyun Noh
PCPyung Goo Cho
Pyung Goo Cho
KKKeung Nyun Kim
Keung Nyun Kim
BLBoeun Lee
Boeun Lee
JLJae Kwang Lee
Jae Kwang Lee
SKSang Hyun Kim
Sang Hyun Kim
Degenerative lumbar spine disease is becoming increasingly prevalent in the aging population. Surgical treatment is the standard treatment modality for intractable cases, but the reoperation rate remains high. We conducted this study to longitudinally evaluate the impact of health risk factors on the risk of lumbar spine reoperation in Koreans aged over 40 years. Subjects aged > 40 years who underwent their first lumbar spinal surgery between January 2005 and December 2008 were selected and followed up until 2015. A total of 6300 people were included. The reoperation rate during the 10-year follow-up period was 13.2% (831/6300 patients). The reoperation rate was the highest in patients in their 60 s (15.4%, P < 0.05). The reoperation rates were also significantly higher in men (vs. women: 14.7% vs. 11.7%, P < 0.05), smokers (vs. non-smokers: 15.2% vs. 12.7%, P < 0.05), alcohol drinkers (vs. non-drinkers: 14.7% vs. 12.4%, P < 0.05), and those with a higher Charlson Comorbidity Index (CCI) score (CCI 0, 11.6%; 1–2, 13.2%; and ≥ 3, 15%; P < 0.05). Among patients undergoing lumbar spine surgery, reoperation is performed in 13.2% of patients within 10 years. Male sex, age in the 60 s, alcohol use, smoking, higher Hgb and a high CCI score increased the risk of reoperation after lumbar spine operation.

1 March 2023 in Journal of Korean Neurosurgical Society
Verified
Journal Article
Open access
PDF file
SKSang Hyun Kim
Sang Hyun Kim
PCPyunggoo Cho
Pyunggoo Cho
KKKeung Nyun Kim
Keung Nyun Kim
SKSang Hyun Kim
Sang Hyun Kim
Dong  Ah ShinDong Ah Shin
Dong Ah Shin
Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient’s prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient’s care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.

25 June 2022 in ACS Applied Materials & Interfaces
Verified
Journal Article
Closed access
SKSang Hyun Kim
Sang Hyun Kim
HLHakbong Lee
Hakbong Lee
KLKyong Sub Lee
Kyong Sub Lee
HLHyeonhoo Lee
Hyeonhoo Lee
Tae Hee HanTae Hee Han
Tae Hee Han

9 April 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SNSung Hyun Noh
Sung Hyun Noh
ELEunyoung Lee
Eunyoung Lee
KKKyoung-Tae Kim
Kyoung-Tae Kim
SKSang Hyun Kim
Sang Hyun Kim
PCPyung Goo Cho
Pyung Goo Cho
Traumatic spinal cord injury (TSCI) has significant physical, psychological, and socioeconomic impacts. However, the epidemiological characteristics and treatment patterns of TSCI in South Korea remain unclear. This study aimed to investigate TSCI incidence and treatment behaviors in South Korea from 2008 to 2020. We included data from 30,979 newly diagnosed TSCI patients obtained from the Health Insurance Review and Assessment Service (HIRA). Treatment trends, location of surgery, surgical method, comorbidities, factors affecting hospital stay, and risk factors affecting readmission were analyzed. Patients were divided into the surgery group [n = 7719; (25%)] and the non-surgery group [n = 23,260; (75%)]. Surgical cases involved cervical (64%), thoracic (17%), and lumbar/sacral (19%) lesions. Anterior fusion (38%), posterior fusion (54%), and corpectomy (8%) were the surgical methods. Surgical treatments increased annually. Factors influencing hospital stay included male sex, older age, and higher Charlson comorbidity index (CCI). Female sex and higher CCI scores were associated with readmission. In conclusion, a quarter of all TSCI patients underwent surgery, with an upward trend. Risk factors for longer hospital stays were thoracic spine injury, older age, higher CCI, and male sex. Risk factors for readmission included age range of 40–59 years, lumbar/sacral spine injuries, CCI score of 2, and female sex.

31 October 2020 in The Nerve
Verified
Journal Article
Open access
PDF file
SKSeung Hyun Kim
Seung Hyun Kim
PCPyung Goo Cho
Pyung Goo Cho
KKKyu-Sung Kwack
Kyu-Sung Kwack
Objective: This was a prospective study to compare anterior cervical discectomy and fusion (ACDF) using a synthetic bioactive glass-ceramic spacer (NOVOMAX ®) and allograft spacer by evaluating the clinical and radiologic results. Methods: In total, 51 patients were prospectively enrolled with cervical degenerative disc disease who requiring ACDF. Seventeen patients were enrolled who underwent ACDF with NOVOMAX ® spacer (Group 2) study group, and 34 patients were enrolled who underwent ACDF with allograft spacer (Group 1). Both groups were fixed with a cervical locking plate. Plain X-ray and computed tomographic scans were performed 12 and 24 months later after surgery to evaluate the status of bone fusion. Clinical outcome was assessed using the neck disability index (NDI) and the Visual analogue scale (VAS). Results: The 32 levels (100%) in Group 2 and 46 levels (97.8%) in Group 1 were confirmed as fused at 24 months. There was no significant difference between the fusion rates observed in both groups (p=0.82). In Group 1, allograft spacer related complications occurred in 34 cases (74%), whereas in 6 cases in Group 2 (19%). There was no significant difference in NDI, or VAS scores at 24 months follow-up. Conclusion: ACDF using NOVOMAX ® spacer well maintains the height of the intervertebral space of the operative segment as well as the decompression of neural structure and is recommended as surgical treatment of safe and efficient degenerative cervical disc disease which can expect stable radiological results.