Publications by authors named "GuanRui Ren"
Article Synopsis
- The objective of the study was to create and validate AI models using natural language processing to diagnose lumbar disc herniation (LDH) with L5 and S1 radiculopathy, based on electronic health records (EHRs).
- The research involved analyzing EHRs from patients who underwent specific surgeries between 2013 and 2021, focusing on nurse documentation related to nerve root compression to train machine learning models.
- Results showed that the long short-term memory model achieved the highest performance metrics in identifying L5 and S1 radiculopathy, suggesting that AI analysis of EHRs could significantly improve diagnostic processes for lumbar diseases.
Study Design: Retrospective study.
Objectives: Our objective is to create comprehensible machine learning (ML) models that can forecast bone cement leakage in percutaneous vertebral augmentation (PVA) for individuals with osteoporotic vertebral compression fracture (OVCF) while also identifying the associated risk factors.
Methods: We incorporated data from patients (n = 425) which underwent PVA.
Objective: The purpose of the present study was to compare the clinical outcomes and complications between the mini-open Wiltse approach with pedicle screw fixation (MWPSF) and percutaneous pedicle screw fixation (PPSF) in treating neurologically intact thoracolumbar fractures.
Methods: We comprehensively searched PubMed, Web of Science, Embase, and the Cochrane Library and performed a systematic review and meta-analysis of all randomized controlled trials and retrospective comparative studies assessing these important indexes of the 2 methods using Review Manager, version 5.4.
Article Synopsis
- The study is a retrospective analysis involving 1159 patients who underwent percutaneous endoscopic lumbar discectomy (PELD) for lumbar disc herniation (LDH) between July 2014 and December 2019, aiming to predict recurrent lumbar disc herniation (rLDH) using machine learning models.
- Significant factors influencing rLDH included body mass index (BMI), facet orientation, herniation type, Modic changes, and disc calcification, with various machine learning models, such as Extreme Gradient Boost (XGBoost) and Random Forest, showing strong predictive performance.
- The findings suggest that using these machine learning models could improve decision-making and potentially reduce rLDH rates after PELD
Article Synopsis
- - The study aimed to create machine learning algorithms using natural language processing (NLP) to automatically distinguish between lumbar disc herniation (LDH) and lumbar spinal stenosis (LSS) from admission notes that describe symptoms.
- - Data from 1921 patients was analyzed using two models: Long Short-Term Memory (LSTM) and extreme gradient boosting (XGBoost), with performance measured using various metrics.
- - Results showed that the LSTM model outperformed the XGBoost model in accuracy and recall, indicating that NLP-based algorithms could effectively aid in diagnosing spine diseases, particularly in differentiating between LDH and LSS.
Study Design: Narrative review.
Objectives: This review aims to present current applications of machine learning (ML) in spine domain to clinicians.
Methods: We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine.
Objective: To investigate whether lumbosacral transitional vertebrae (LSTV) affects the clinical outcomes of percutaneous endoscopic lumbar discectomy (PELD) in adolescent patients with lumbar disc herniation (LDH).
Methods: This was a retrospective study with two groups. Group A was made up of 22 adolescent LDH patients with LSTV (18 males and 4 females).