Publications by authors named "Yechan Seo"
Machine-learning-based models for the optimization of post-cervical spinal laminoplasty outpatient follow-up schedules.
BMC Med Inform Decis Mak
September 2024
Article Synopsis
- Patients after cervical laminoplasty may not need regular follow-ups if their symptoms improve significantly; this study aimed to use machine learning to predict long-term outcomes at the 2-year mark based on initial postoperative results.
- A total of 80 patients’ progress was tracked using Japanese Orthopedic Association (JOA) scores over the first year, and eight machine learning algorithms were developed, with the LSTM algorithm showing the highest accuracy in predicting which patients would achieve a satisfactory symptom state (PASS) by 24 months.
- Despite a small patient sample, the findings suggest that past outcomes can inform future predictions, potentially helping optimize follow-up schedules and allocate medical resources more efficiently.