RESUMO
From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components. However, both data-driven and exploration-based machine learning strategies have limitations in their effectiveness for nanophotonic inverse design. Supervised machine learning approaches require large quantities of training data to produce high-performance models and have difficulty generalizing beyond training data given the complexity of the design space. Unsupervised and reinforcement learning-based approaches on the other hand can have very lengthy training or optimization times associated with them. Here we demonstrate a hybrid supervised learning and reinforcement learning approach to the inverse design of nanophotonic structures and show this approach can reduce training data dependence, improve the generalizability of model predictions, and significantly shorten exploratory training times. The presented strategy thus addresses several contemporary deep learning-based challenges, while opening the door for new design methodologies that leverage multiple classes of machine learning algorithms to produce more effective and practical solutions for photonic design.
RESUMO
BACKGROUND: With the growing prevalence of lumbar spinal stenosis, endoscopic surgery, which incorporates techniques such as transforaminal, interlaminar, and unilateral biportal (UBE) endoscopy, is increasingly considered. However, the patient selection criteria are debated among spine surgeons. OBJECTIVE: This study used a polytomous Rasch analysis to evaluate the factors influencing surgeon decision-making in selecting patients for endoscopic surgical treatment of lumbar spinal stenosis. METHODS: A comprehensive survey was distributed to a representative sample of 296 spine surgeons. Questions encompassed various patient-related and clinical factors, and responses were captured on a logit scale graphically displaying person-item maps and category probability curves for each test item. Using a Rasch analysis, the data were subsequently analyzed to determine the latent traits influencing decision-making. RESULTS: The Rasch analysis revealed that surgeons' preferences for transforaminal, interlaminar, and UBE techniques were easily influenced by comfort level and experience with the endoscopic procedure and patient-related factors. Harder-to-agree items included technological aspects, favorable clinical outcomes, and postoperative functional recovery and rehabilitation. Descriptive statistics suggested interlaminar as the best endoscopic spinal stenosis decompression technique. However, logit person-item analysis integral to the Rasch methodology showed highest intensity for transforaminal followed by interlaminar endoscopic lumbar stenosis decompression. The UBE technique was the hardest to agree on with a disordered person-item analysis and thresholds in category probability curve plots. CONCLUSION: Surgeon decision-making in selecting patients for endoscopic surgery for lumbar spinal stenosis is multifaceted. While the framework of clinical guidelines remains paramount, on-the-ground experience-based factors significantly influence surgeons' selection of patients for endoscopic lumbar spinal stenosis surgeries. The Rasch methodology allows for a more granular psychometric evaluation of surgeon decision-making and accounts better for years-long experience that may be lost in standardized clinical guideline development. This new approach to assessing spine surgeons' thought processes may improve the implementation of evidence-based protocol change dictated by technological advances was endorsed by the Interamerican Society for Minimally Invasive Spine Surgery (SICCMI), the International Society for Minimal Intervention in Spinal Surgery (ISMISS), the Mexican Spine Society (AMCICO), the Brazilian Spine Society (SBC), the Society for Minimally Invasive Spine Surgery (SMISS), the Korean Minimally Invasive Spine Society (KOMISS), and the International Society for the Advancement of Spine Surgery (ISASS).
RESUMO
BACKGROUND: Effective 1 January 2017, single-level endoscopic lumbar discectomy received a Category I Current Procedural Terminology (CPT) code 62380. However, no work relative value units (RVUs) are currently assigned to the procedure. An international team of endoscopic spine surgeons conducted a study, endorsed by several spine societies, analyzing the learning curve, difficulty, psychological intensity, and estimated work RVUs of endoscopic lumbar spinal decompression compared with other common lumbar spine surgeries. METHODS: A survey comparing CPT 62380 to 10 other comparator CPT codes reflective of common spine surgeries was developed to assess the work RVUs in terms of learning curve, difficulty, psychological intensity, and work effort using a paired Rasch method. RESULTS: The survey was sent to 542 spine specialists. Of 322 respondents, 150 completed the survey for a 43.1% completion rate. Rasch analysis of the submitted responses statistically corroborated common knowledge that the learning curve with lumbar endoscopic spinal surgery is steeper and more complex than with traditional translaminar lumbar decompression surgeries. It also showed that the psychological stress and mental and work effort with the lumbar endoscopic decompression surgery were perceived to be higher by responding spine surgeons compared with posterior comparator decompression and fusion surgeries and even posterior interbody and posterolateral fusion surgeries. The regression analysis of work effort vs procedural difficulty showed the real-world evaluation of the lumbar endoscopic decompression surgery described in CPT code 62380 with a calculated work RVU of 18.2464. CONCLUSION: The Rasch analysis suggested the valuation for the endoscopic lumbar decompression surgery should be higher than for standard lumbar surgeries: 111.1% of the laminectomy with exploration and/or decompression of spinal cord and/or cauda equina (CPT 63005), 118.71% of the laminectomy code (CPT 63047), which includes foraminotomy and facetectomy, 152.1% of the hemilaminectomy code (CPT 63030), and 259.55% of the interlaminar or interspinous process stabilization/distraction without decompression code (CPT 22869). This research methodology was endorsed by the Interamerican Society for Minimally Invasive Spine Surgery (SICCMI), the Mexican Society of Spinal Surgeons (AMCICO), the International Society For Minimally Invasive Spine Surgery (ISMISS), the Brazilian Spine Society (SBC), the Society for Minimally Invasive Spine Surgery (SMISS), the Korean Minimally Invasive Spine Surgery (KOMISS), and the International Society for the Advancement of Spine Surgery (ISASS). CLINICAL RELEVANCE: This study provides an updated reimbursement recommendation for endoscopic spine surgery. LEVEL OF EVIDENCE: Level 3.