Medical degree, Seoul National University, Korea (1996)
PhD degree, Seoul National University, Korea (2006)
Assistant Professor, University of Ulsan College of Medicine, Asan Medical Center (2006-2010)
Associate Professor, University of Ulsan College of Medicine, Asan Medical Center (2011-2016)
Professor, University of Ulsan College of Medicine, Asan Medical Center (2017-Present)
Imaging of bowel diseases, Clinical Epidemiology, Biostatistics
Honors & Awards
Award for highest impact research of the year, Korean Radiological Society (2017)
Taejoon Radiology Award, Korean Radiological Society (2015)
1. Park HJ, Jang JK, Park SH (corresponding), Park IJ, Kim JH, Baek S, Hong YS. Restaging Abdominopelvic Computed Tomography Before Surgery After Preoperative Chemoradiotherapy in Patients With Locally Advanced Rectal Cancer. JAMA Oncol 2018;4(2):259-262.
2. Park SH (corresponding), Lee JH, Lee SS, Kim JC, Yu CS, Kim HC, Ye BD, Kim MJ, Kim AY, Ha HK. CT Colonography for Detection and Characterisation of Synchronous Proximal Colonic Lesions in Patients with Stenosing Colorectal Cancer. Gut 2012;61(12):1716-22.
3. Lee SS, Park SH (corresponding), Kim HJ, Kim SY, Kim MY, Kim DY, Suh DJ, Kim KM, Bae MH, Lee JY, Lee SG, Yu ES. Non-invasive Assessment of Hepatic Steatosis: Prospective Comparison of the Accuracy of Imaging Examinations. J Hepatol 2010;52(4):579-85.
Methodology for Proper Clinical Validation of Artificial Intelligence Technology for Medical Diagnosis and Prediction
Artificial intelligence (AI) is projected to substantially influence clinical practice in the foreseeable future, especially in areas of diagnosis, risk assessment, and prognostication through predictive algorithms. However, despite the excitement around the technologies, it is yet rare to see examples of robust clinical validation of these clinical applications and, as a result, very few are currently in clinical use. Thorough, systematic validation of AI technologies using adequately designed clinical research studies before their integration into clinical practice is critical to ensure patient benefit and safety while avoiding any inadvertent harms. The use of external data unused for algorithm development, collected in a manner that minimizes spectrum bias ideally from multiple institutions, is crucial for proper validation of the clinical performance of an AI algorithm for medical diagnosis and prediction. The ultimate clinical validation requires a demonstration of the value of an AI system through positive impact on patient outcomes, beyond performance metrics.