Stanford Neurosurgical
Artificial Intelligence and Machine Learning Laboratory

Abstract

INTRODUCTION: Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art of revision prediction of cervical spine surgery using laboratory and operative variables.METHODS: Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016-2022 were identified (N=3151) and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and timeframe. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables.RESULTS: Red blood cell count, Hemoglobin, Hematocrit, Mean Corpuscular Hemoglobin Concentration, Red Blood Cell Distribution Width, Platelet Count, CO2, Anion Gap, and Calcium were all significantly associated with one or more revision cohorts. For the prediction of 3-month revision, the deep neural network achieved AUC of 0.833. The model demonstrated increased performance for anterior than posterior and arthrodesis than decompression procedures.CONCLUSIONS: Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables, in a cervical spine surgery cohort. This work introduces standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of "one-size-fits-all" risk scores for spine procedures.

View details for DOI 10.1016/j.wneu.2024.02.112

View details for PubMedID 38408699

Abstract

Endovenous stents for deep venous thrombosis treatment can be unintentionally placed in the spinal canal, resulting in neurological deficit.The authors report the case of a patient presenting to our institution with intraspinal misplacement of an endovenous stent, resulting in cauda equina syndrome. The authors also performed a systematic literature review, evaluating the few previously reported cases. This review was performed according to the updated Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. In four of five cases describing stent misplacement into the spinal canal, the authors report that only anteroposterior monoplanar imaging modalities were utilized for venous localization and stent deployment. The anteroposterior plane cannot assess the relative depth of structures, nor can it distinguish between superimposed structures well. Therefore, the use of biplanar imaging should at least be considered before stent deployment, as intraspinal stent placement can lead to disastrous consequences.This report should serve as an impetus for the use of biplanar or three-dimensional imaging modalities for iliac venous stent placement. Additionally, this work should increase spine surgeons' awareness about management and operative techniques when faced with this complication.

View details for DOI 10.3171/CASE23482

View details for PubMedID 38346298

Abstract

Background: Adult spinal deformities (ASD) are varied spinal abnormalities, often necessitating surgical intervention when associated with pain, worsening deformity, or worsening function. Predicting post-operative complications and revision surgery is critical for surgical planning and patient counseling. Due to the relatively small number of cases of ASD surgery, machine learning applications have been limited to traditional models (e.g., logistic regression or standard neural networks) and coarse clinical variables. We present the novel application of advanced models (CNN, LLM, GWAS) using complex data types (radiographs, clinical notes, genomics) for ASD outcome prediction. Methods: We developed a CNN trained on 209 ASD patients (1549 radiographs) from the Stanford Research Repository, a CNN pre-trained on VinDr-SpineXR (10,468 spine radiographs), and an LLM using free-text clinical notes from the same 209 patients, trained via Gatortron. Additionally, we conducted a GWAS using the UK Biobank, contrasting 540 surgical ASD patients with 7355 non-surgical ASD patients. Results: The LLM notably outperformed the CNN in predicting pulmonary complications (F1: 0.545 vs. 0.2881), neurological complications (F1: 0.250 vs. 0.224), and sepsis (F1: 0.382 vs. 0.132). The pre-trained CNN showed improved sepsis prediction (AUC: 0.638 vs. 0.534) but reduced performance for neurological complication prediction (AUC: 0.545 vs. 0.619). The LLM demonstrated high specificity (0.946) and positive predictive value (0.467) for neurological complications. The GWAS identified 21 significant (p < 10-5) SNPs associated with ASD surgery risk (OR: mean: 3.17, SD: 1.92, median: 2.78), with the highest odds ratio (8.06) for the LDB2 gene, which is implicated in ectoderm differentiation. Conclusions: This study exemplifies the innovative application of cutting-edge models to forecast outcomes in ASD, underscoring the utility of complex data in outcome prediction for neurosurgical conditions. It demonstrates the promise of genetic models when identifying surgical risks and supports the integration of complex machine learning tools for informed surgical decision-making in ASD.

View details for DOI 10.3390/jcm13030656

View details for PubMedID 38337352

Abstract

Physical therapy (PT) is an important component of low back pain (LBP) management. Despite established guidelines, heterogeneity in medical management remains common.We sought to understand how copayments impact timing and utilization of PT in newly diagnosed LBP.The IBM Watson Health MarketScan claims database was utilized in a longitudinal setting.Adult patients with LBP.The primary outcomes-of-interest were timing and overall utilization of PT services. Additional outcomes-of-interest included timing of opioid prescribing.Actual and inferred copayments based on non-PCP visit claims were used to evaluate the relationship between PT copayment and incidence of PT initiation. Multivariable regression models were used to evaluate factors influencing PT usage.Overall, 2,467,389 patients were included. PT initiation, among those with at ≥1 PT service during the year after LBP diagnosis (30.6%), occurred at a median of 8 days post-diagnosis (IQR 1-55). Among those with at least one PT encounter, incidence of subsequent PT visits was significantly lower for those with high initial PT copayments. High initial PT copayments, while inversely correlated with PT utilization, were directly correlated with subsequent opioid use (0.77 prescriptions/patient [

View details for DOI 10.7759/cureus.51963

View details for Web of Science ID 001153117000002