Nathan John Lee

Dr. Nathan John Lee

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
20 November 2024 in Journal of Bone and Joint Surgery
Verified
Journal Article
Closed access
NLNathan John Lee
Nathan John Lee
LLLawrence G. Lenke
Lawrence G. Lenke
VAVarun Arvind
Varun Arvind
TSTed Shi
Ted Shi
ADAlexandra C. Dionne
Alexandra C. Dionne
FHFthimnir M Hassan
Fthimnir M Hassan
Background: An accurate knowledge of a patient’s risk of cord-level intraoperative neuromonitoring (IONM) data loss is important for an informed decision-making process prior to deformity correction, but no prediction tool currently exists. Methods: A total of 1,106 patients with spinal deformity and 205 perioperative variables were included. A stepwise machine-learning (ML) approach using random forest (RF) analysis and multivariable logistic regression was performed. Patients were randomly allocated to training (75% of patients) and testing (25% of patients) groups. Feature score weights were derived by rounding up the regression coefficients from the multivariable logistic regression model. Variables in the final scoring calculator were automatically selected through the ML process to optimize predictive performance. Results: Eight features were included in the scoring system: sagittal deformity angular ratio (sDAR) of ≥15 (score = 2), type-3 spinal cord shape (score = 2), conus level below L2 (score = 2), cervical upper instrumented vertebra (score = 2), preoperative upright largest thoracic Cobb angle of ≥75° (score = 2), preoperative lower-extremity motor deficit (score = 2), preoperative upright largest thoracic kyphosis of ≥80° (score = 1), and total deformity angular ratio (tDAR) of ≥25 (score = 1). Higher cumulative scores were associated with increased rates of cord-level IONM data loss: patients with a cumulative score of ≤2 had a cord-level IONM data loss rate of 0.9%, whereas those with a score of ≥7 had a loss rate of 86%. When evaluated in the testing group, the scoring system achieved an accuracy of 93%, a sensitivity of 75%, a specificity of 94%, and an AUC (area under the receiver operating characteristic curve) of 0.898. Conclusions: This is the first study to provide an ML-derived preoperative scoring system that predicts cord-level IONM data loss during pediatric and adult spinal deformity surgery with >90% accuracy. Level of Evidence: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

11 September 2024 in Journal of the American Academy of Orthopaedic Surgeons
Verified
Journal Article
Closed access
NLNathan John Lee
Nathan John Lee
JLJoseph M. Lombardi
Joseph M. Lombardi
SQSheeraz Qureshi
Sheeraz Qureshi
RLRonald A. Lehman
Ronald A. Lehman
Robot-assisted spine surgery has gained notable popularity among surgeons because of recent advancements in technology. These innovations provide several key benefits, including high screw accuracy rates, reduced radiation exposure, customized preoperative and intraoperative planning options, and improved ergonomics for surgeons. Despite the promising outcomes reported in literature, potential technical challenges remain across various robotic platforms. It is crucial for surgeons to remember that robotic platforms are shared-control systems, requiring the surgeon to maintain primary control throughout the procedure. To ensure patient safety, surgeons should be well versed in common technical pitfalls and strategies to mitigate these limitations.

Verified
Journal Article
Open access
PDF file
NKNora Chung Kim
Nora Chung Kim
EJEli Johnson
Eli Johnson
CDChristopher DeWald
Christopher DeWald
NLNathan John Lee
Nathan John Lee
TWTimothy Wang
Timothy Wang
The management of adult spinal deformity (ASD) has evolved dramatically over the past century, transitioning from external bracing and in situ fusion to complex, technology-driven surgical interventions. This review traces the historical development of spinal deformity correction and highlights contemporary enabling technologies that are redefining the surgical landscape. Advances in stereoradiographic imaging now allow for precise, low-dose three-dimensional assessment of spinopelvic parameters and segmental bone density, facilitating individualized surgical planning. Robotic assistance and intraoperative navigation improve the accuracy and safety of instrumentation, while patient-specific rods and interbody implants enhance biomechanical conformity and alignment precision. Machine learning and predictive modeling tools have emerged as valuable adjuncts for risk stratification, surgical planning, and outcome forecasting. Minimally invasive deformity correction strategies, including anterior column realignment and circumferential minimally invasive surgery (cMIS), have demonstrated equivalent clinical and radiographic outcomes to traditional open surgery with reduced perioperative morbidity in select patients. Despite these advancements, complications such as proximal junctional kyphosis and failure remain prevalent. Adjunctive strategies—including ligamentous tethering, modified proximal fixation, and vertebral cement augmentation—offer promising preventive potential. Collectively, these innovations signal a paradigm shift toward precision spine surgery, characterized by data-informed decision-making, individualized construct design, and improved patient-centered outcomes in spinal deformity care.

19 August 2026 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
RPRohan A. Phadke
Rohan A. Phadke
SSSamer G. Salman
Samer G. Salman
ZSZane G Salman
Zane G Salman
AMAkhil Marupudi
Akhil Marupudi
KPKirtan Patel
Kirtan Patel
NLNathan John Lee
Nathan John Lee
Lumbar foraminal stenosis grading contributes to surgical-level selection, but automated four-grade classification remains challenging. Published pipelines for this dataset reach approximately 65% four-class accuracy, and deep classifiers offer no anatomical rationale. We investigated whether interpretable, millimeter-scale morphometry from segmentation masks improves grading beyond a deep image model. We analyzed the LSS-MRI-AISSLab sagittal T2-weighted dataset (469 patients, 2979 expert-graded foramina spanning L1-L2 through L5-S1 bilaterally on a four-grade scale). Ten morphometric descriptors were computed from mid-sagittal polygon segmentations and scaled to millimeters using each patient’s recorded pixel spacing. A dual-branch network combined a fine-tuned ResNet-18 embedding of each foraminal region of interest with the morphometric vector through an ordinal regression head. Foraminal regions were supplied from expert bounding-box annotations; automated localization within the full sagittal examination was not evaluated. Four configurations (nominal softmax, appearance-only, anatomy-only, and fusion) were compared on a locked patient-level test set of 94 patients after five-fold cross-validation, with quadratic weighted kappa (QWK) as the primary endpoint and patient-clustered bootstrap inference. Feature-grade correlations were reported pooled and adjusted for lumbar level. Fusion achieved QWK 0.813 (95% confidence interval [CI] 0.769–0.847) and 75.3% four-class accuracy. Appearance-only was statistically indistinguishable (QWK 0.806; delta QWK +0.006, 95% CI −0.023 to 0.036, p = 0.68), whereas anatomy-only reached 0.444, and a level-and-side-only reference reached 0.314. Boundary discrimination was strong (area under the curve 0.92–0.99), 98.3% of predictions fell within one grade, and performance was consistent across scanner vendors. Morphometric associations were confounded by level: the apparent spondylolisthesis effect (rho −0.349) disappeared after adjustment (rho −0.000), while disc height, null when pooled (rho +0.021), emerged as a genuine within-level effect (rho −0.108). A fine-tuned ordinal image classifier achieved strong agreement for four-grade lumbar foraminal stenosis classification. The evaluated segmentation-derived morphometric features did not improve performance beyond imaging alone, and several apparent anatomic associations reflected confounding by lumbar level. External and prospective validation in complete clinical MRI workflows are needed before implementation.

13 February 2026 in European Spine Journal
Verified
Journal Article
Open access
PDF file
JSJoshua Samaniego
Joshua Samaniego
Arnold Y.L. WongArnold Y.L. Wong
Arnold Y.L. Wong
Karin Wuertz-KozakKarin Wuertz-Kozak
Karin Wuertz-Kozak
HWHans-Joachim Wilke
Hans-Joachim Wilke
NLNathan John Lee
Nathan John Lee
DSDino Samartzis
Dino Samartzis
Z intervertebral discs, implicating hematogenous deposition within musculoskeletal tissues [3, 4]. MPs/NPs are known to trigger oxidative stress, mitochondrial dysfunction and TLR/NF-κB-mediated inflammatory signaling-pathways central to intervertebral disc degeneration, inflammation, apoptosis and extracellular matrix breakdown [1, 5]. These findings raise an urgent question: could MPs/NPs act as the impetus or accelerants of spinal aging, pain development and intensity, degeneration or even deformity? If so, this would redefine our understanding of spine pathology, highlighting an underappreciated environmental and implant-derived dimension to conditions long attributed to mechanical or genetic factors. Studying this relationship could also reveal new therapeutic targets focused on mitigating environmentally and implant-induced spine pathology. In lieu of the aforementioned, we propose the existence of the "Plastic Spine Phenotype," a distinct biological and clinical expression of spine disease/disorder shaped by MP/NP exposure.

22 October 2026 in European Spine Journal
Verified
Journal Article
Open access
PDF file
RPRohan A. Phadke
Rohan A. Phadke
SSSamer G. Salman
Samer G. Salman
BMBrandon Matthews
Brandon Matthews
Rahul KumarRahul Kumar
Rahul Kumar
AMArbaz Momin
Arbaz Momin
NLNathan John Lee
Nathan John Lee
Introduction Artificial intelligence (AI) is increasingly transforming spine care by enabling analysis of imaging, clinical, and textual data to support diagnosis, risk stratification, and treatment planning. Techniques including deep learning–based image analysis, radiomics, and natural language processing (NLP) offer opportunities to standardize interpretation and derive quantitative biomarkers beyond human visual assessment. This narrative review examines recent innovations in spine-focused biomedical informatics and evaluates their clinical relevance and translational challenges. Methods A narrative review was conducted, focusing on AI in spine care across imaging, radiomics, NLP of electronic health records, and clinical decision support. Literature was selected via targeted PubMed searches; studies describing technical development, validation, and clinical implementation were synthesized, addressing explainability, uncertainty, workflow, and regulation. Results Convolutional neural networks enable vertebral and disc segmentation, detection of degenerative and traumatic pathology, and quantitative assessment of paraspinal musculature. Radiomics approaches extract high-dimensional imaging features that improve the prediction of osteoporosis, fracture risk, tumor characterization, and surgical outcomes. NLP techniques, including emerging large language models, unlock clinically relevant information from unstructured text, enhancing outcome prediction and population-level analyses. Multimodal clinical decision support systems integrating imaging, EHR data, and NLP-derived features demonstrate promise for personalized risk assessment and treatment guidance. Challenges remain regarding data heterogeneity, generalizability, privacy, and prospective validation. Conclusion AI-driven biomedical informatics holds substantial promise to enhance diagnostic accuracy, prognostication, and personalized decision-making in spine care. Successful clinical translation will require robust validation, explainable, uncertainty-aware models, regulatory alignment, and integration into clinical workflows to ensure safe, trustworthy, and patient-centered adoption.