Differentiation of lumbar disc herniation and lumbar spinal stenosis using natural language processing-based machine learning based on positive symptoms.

OBJECTIVE: The purpose of this study was to develop natural language processing (NLP)-based machine learning algorithms to automatically differentiate lumbar disc herniation (LDH) and lumbar spinal stenosis (LSS) based on positive symptoms in free-text admission notes. The secondary purpose was to compare the performance of the deep learning algorithm with the ensemble model on the current task. METHODS: In total, 1921 patients whose principal diagnosis was LDH or LSS between June 2013 and June 2020 at Zhongda Hospital, affiliated with Southeast University, were retrospectively analyzed. The data set was randomly divided into a training set and testing set at a 7:3 ratio. Long Short-Term Memory (LSTM) and extreme gradient boosting (XGBoost) models were developed in this study. NLP algorithms were assessed on the testing set by the following metrics: receiver operating characteristic (ROC) curve, area under the curve (AUC), accuracy score, recall score, F1 score, and precision score. RESULTS: In the testing set, the LSTM model achieved an AUC of 0.8487, accuracy score of 0.7818, recall score of 0.9045, F1 score of 0.8108, and precision score of 0.7347. In comparison, the XGBoost model achieved an AUC of 0.7565, accuracy score of 0.6961, recall score of 0.7387, F1 score of 0.7153, and precision score of 0.6934. CONCLUSIONS: NLP-based machine learning algorithms were a promising auxiliary to the electronic health record in spine disease diagnosis. LSTM, the deep learning model, showed better capacity compared with the widely used ensemble model, XGBoost, in differentiation of LDH and LSS using positive symptoms. This study presents a proof of concept for the application of NLP in prediagnosis of spine disease.

Pharmacodynamics of Five Anthraquinones (Aloe-emodin, Emodin, Rhein, Chysophanol, and Physcion) and Reciprocal Pharmacokinetic Interaction in Rats with Cerebral Ischemia.

(1) Background: Rhubarb anthraquinones-a class of components with neuroprotective function-can be used to alleviate cerebral ischemia reperfusion injury. (2) Methods: The three pharmacodynamic indicators are neurological function score, brain water content, and cerebral infarction area; UPLC-MS/MS was used in pharmacokinetic studies to detect plasma concentrations at different time points, and DAS software was used to calculate pharmacokinetic parameters in a noncompartmental model. (3) Results: The results showed that the pharmacodynamics and pharmacokinetics of one of the five anthraquinone aglycones could be modified by the other four anthraquinones, and the degree of interaction between different anthraquinones was different. The chrysophanol group showed the greatest reduction in pharmacodynamic indicators comparing with other four groups where the rats were administered one of the five anthraquinones, and there was no significant difference between the nimodipine group. While the Aloe-emodin + Physcion group showed the most obvious anti-ischemic effect among the groups where the subjects were administered two of the five anthraquinones simultaneously. Emodin, rhein, chrysophanol, and physcion all increase plasma exposure levels of aloe-emodin, while aloe-emodin lower their plasma exposure levels. (4) Conclusions: This experiment provides a certain preclinical basis for the study of anthraquinone aglycones against cerebral ischemia and a theoretical basis for the study of the mechanism of interaction between anthraquinones.

Interpretable Machine Learning Models Based on SHapley Additive exPlanations for Predicting the Risk of Cerebrospinal Fluid Leakage in Lumbar Fusion Surgery.

STUDY DESIGN: Retrospective study. OBJECTIVES: The objective of this investigation was to formulate and internally verify a customized machine learning (ML) framework for forecasting cerebrospinal fluid leakage (CSFL) in lumbar fusion surgery. This was accomplished by integrating imaging parameters and employing the SHapley Additive exPlanation (SHAP) technique to elucidate the interpretability of the model. SUMMARY OF BACKGROUND DATA: Given the increasing incidence and surgical volume of spinal degeneration worldwide, accurate predictions of postoperative complications are urgently needed. SHAP-based interpretable ML models have not been used for CSFL risk factor analysis in lumbar fusion surgery. METHODS: Clinical and imaging data were retrospectively collected from 3505 patients who underwent lumbar fusion surgery. Six distinct machine learning models were formulated: extreme gradient boosting (XGBoost), decision tree (DT), random forest (RF), support vector machine (SVM), Gaussian naive Bayes (GaussianNB), and K-nearest neighbors (KNN) models. Evaluation of model performance on the test dataset was performed using performance metrics, and the analysis was executed through the SHAP framework. RESULTS: CSFL was detected in 95 out of 3505 patients (2.71%). Notably, the XGBoost model exhibited outstanding accuracy in forecasting CSFLs, with high precision (0.9815), recall (0.6667), accuracy (0.8182), F1 score (0.7347), and AUC (0.7343). Additionally, through SHAP analysis, significant predictors of CSFL were identified, including ligamentum flavum thickness, zygapophysial joint degeneration grade, central spinal stenosis grade, decompression segment count, decompression mode, intervertebral height difference, Cobb angle, intervertebral height index difference, operation mode, lumbar segment lordosis angle difference, Meyerding grade of lumbar spondylolisthesis, and revision surgery. CONCLUSION: The combination of the XGBoost model with the SHAP is an effective tool for predicting the risk of CSFL during lumbar fusion surgery. Its implementation could aid clinicians in making informed decisions, potentially enhancing patient outcomes and lowering healthcare expenses. This study advocates for the adoption of this approach in clinical settings to enhance the evaluation of CSFL risk among patients undergoing lumbar fusion.

Natural Language Processing-Driven Artificial Intelligence Models for the Diagnosis of Lumbar Disc Herniation with L5 and S1 Radiculopathy: A Preliminary Evaluation.

OBJECTIVE: To develop and validate natural language processing-driven artificial intelligence (AI) models for the diagnosis of lumbar disc herniation (LDH) with L5 and S1 radiculopathy using electronic health records (EHRs). METHODS: EHRs of patients undergoing single-level percutaneous endoscopic lumbar discectomy for the treatment of LDH at the L4/5 or L5/S1 level between June 1, 2013, and December 31, 2021, were collected. The primary outcome was LDH with L5 and S1 radiculopathy, which was defined as nerve root compression recorded in the operative notes. Datasets were created using the history of present illness text and positive symptom text with radiculopathy (L5 or S1), respectively. The datasets were randomly split into a training set and a testing set in a 7:3 ratio. Two machine learning models, the long short-term memory network and Extreme Gradient Boosting, were developed using the training set. Performance evaluation of the models on the testing set was done using measures such as the receiver operating characteristic curve, area under the curve, accuracy, recall, F1-score, and precision. RESULTS: The study included a total of 1681 patients, with 590 patients having L5 radiculopathy and 1091 patients having S1 radiculopathy. Among the 4 models developed, the long short-term memory model based on positive symptom text showed the best discrimination in the testing set, with precision (0.9054), recall (0.9405), accuracy (0.8950), F1-score (0.9226), and area under the curve (0.9485). CONCLUSIONS: This study provides preliminary validation of the concept that natural language processing-driven AI models can be used for the diagnosis of lumbar disease using EHRs. This study could pave the way for future research that may develop more comprehensive and clinically impactful AI-driven diagnostic systems.

Identification of lncRNA-based regulatory mechanisms of Takifugu rubripes growth traits in fast and slow-growing family lines.

Family selection is an important method in fish aquaculture because growth is the most important economic trait. Fast-and slow-growing families of tiger puffer fish (Takifugu rubripes) have been established through family selection. The development of teleost fish is primarily controlled by the growth hormone (GH)-insulin-like growth factor 1 (IGF-1) axis that includes the hypothalamus-pituitary-liver. In this study, the molecular mechanisms underlying T. rubripes growth were analyzed by comparing transcriptomes from fast- and slow-growing families. The expressions of 214 lncRNAs were upregulated, and those of 226 were downregulated in the brain tissues of the fast-growing T. rubripes family compared to those of the slow-growing family. Differentially expressed lncRNAs centrally regulate mitogen-activated protein kinase (MAPK) and forkhead box O (FoxO) signaling pathways. Based on the results of lncRNA-gene network construction, we found that lncRNA3133.13, lncRNA23169.1, lncRNA23145.1, and lncRNA23141.3 regulated all four genes (igf1, mdm2, flt3, and cwf19l1). In addition, lncRNA7184.10 may be a negative regulator of rasgrp2 and a positive regulator of gadd45ga, foxo3b, and dusp5. These target genes are associated with the growth and development of organisms through the PI3K/AKT and MAPK/ERK pathways. Overall, transcriptomic analyses of fast- and slow-growing families of T. rubripes provided insights into the molecular mechanisms of teleost fish growth rates. Further, these analyses provide evidence for key genes related to growth regulation and the lncRNA expression regulatory network that will provide a framework for improving puffer fish germplasm resources.

Interpretable Machine Learning Model to Predict Bone Cement Leakage in Percutaneous Vertebral Augmentation for Osteoporotic Vertebral Compression Fracture Based on SHapley Additive exPlanations.

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. To predict cement leakage, we devised six models based on a variety of parameters. Evaluate and juxtapose the predictive performances relied on measures of discrimination, calibration, and clinical utility. SHapley Additive exPlanations (SHAP) methodology was used to interpret model and evaluate the risk factors associated with cement leakage. RESULTS: The occurrence rate of cement leakage was established at 50.4%. A binary logistic regression analysis identified cortical disruption (OR 6.880, 95% CI 4.209-11.246), the basivertebral foramen sign (OR 2.142, 95% CI 1.303-3.521), the fracture type (OR 1.683, 95% CI 1.083-2.617), and the volume of bone cement (OR 1.198, 95% CI 1.070-1.341) as independent predictors of cement leakage. The XGBoost model outperformed all others in predicting cement leakage in the testing set, with AUC of .8819, accuracy of .8025, recall score of .7872, F1 score of .8315, and a precision score of .881. Several important factors related to cement leakage were drawn based on the analysis of SHAP values and their clinical significance. CONCLUSION: The ML based predictive model demonstrated significant accuracy in forecasting bone cement leakage for patients with OVCF undergoing PVA. When combined with SHAP, ML facilitated a personalized prediction and offered a visual interpretation of feature importance.

Current Applications of Machine Learning in Spine: From Clinical View.

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. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text. RESULTS: Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost. CONCLUSIONS: ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

[Study of modified subcutaneous lumbar spine index as a predictor for short-term effectiveness in transforaminal lumbar interbody fusion].

OBJECTIVE: To explore the value of modified subcutaneous lumbar spine index (MSLSI) as a predictor for short-term effectiveness of transforaminal lumbar interbody fusion (TLIF) in treatment of lumbar degenerative disease (LDD). METHODS: Between February 2014 and October 2019, 450 patients who were diagnosed as LDD and received single-segment TLIF were included in the study. Based on the MSLSI measured by preoperative lumbar MRI, the patients were sorted from small to large and divided into three groups ( n=150). The MSLSI of group A was 0.11-0.49, group B was 0.49-0.73, and group C was 0.73-1.88. There was no significance in gender, age, disease duration, diagnosis, surgical segment, and improved Charlson comorbidity index between groups ( P>0.05). There were significant differences in the subcutaneous adipose depth of the L 4 vertebral body and body mass index (BMI) between groups ( P<0.05). The operation time, intra-operative blood loss, length of incision, drainage tube placement time, drainage volume on the 1st day after operation, drainage volume on the 2nd day after operation, total drainage volume, antibiotic use time after operation, walking exercise time after operation, hospital stay, the incidences of surgical or non-surgical complications in the three groups were compared. Pearson correlation analysis was used to analyze the correlation between MSLSI and BMI, and partial correlation analysis was used to study the relationship between MSLSI, BMI, improved Charlson comorbidity index, subcutaneous adipose depth of the L 4 vertebral body and complications. The Receiver Operating Characteristic (ROC) curve was used to evaluate the value of SLSI and MSLSI in predicting the occurrence of complications after TLIF in treatment of LDD. RESULTS: There was no significant difference in operation time, length of incision, antibiotic use time after operation, walking exercise time after operation, drainage tube placement time, drainage volume on the 1st day after operation, drainage volume on the 2nd day after operation, and total drainage volume between groups ( P>0.05). The amount of intra-operative blood loss in group C was higher than that in groups A and B, and the hospital stay was longer than that in group B, with significant differences ( P<0.05). Surgical complications occurred in 22 cases (14.7%), 25 cases (16.7%), and 39 cases (26.0%) of groups A, B, and C, respectively. There was no significant difference in the incidence between groups ( χ 2=0.826, P=0.662). The incidences of nerve root injury and wound aseptic complications in group C were higher than those in groups A and B, and the incidence of nerve root injury in group B was higher than that in group A, with significant differences ( P<0.05). There were 13 cases (8.7%), 7 cases (4.7%), and 11 cases (7.3%) of non-surgical complications in groups A, B, and C, respectively, with no significant difference ( χ 2=2.128, P=0.345). There was no significant difference in the incidences of cardiovascular complications, urinary system complications, central system complications, and respiratory system complications between groups ( P>0.05). There was a correlation between MSLSI and BMI in 450 patients ( r=0.619, P=0.047). Partial correlation analysis showed that MSLSI was related to wound aseptic complications ( r=0.172, P=0.032), but not related to other surgical and non-surgical complications ( P>0.05). There was no correlation between BMI, improved Charlson comorbidity index, subcutaneous adipose depth of the L 4 vertebral body and surgical and non-surgical complications ( P>0.05). ROC curve analysis showed that the area under ROC curve (AUC) of MSLSI was 0.673 (95%CI 0.546-0.761, P=0.025), and the AUC of SLSI was 0.582 (95%CI 0.472-0.693, P=0.191). CONCLUSION: MSLSI can predict the short-term effectiveness of TLIF in treatment of LDD. Patients with high MSLSI suffer more intra-operative blood loss, longer hospital stay, and higher incidence of nerve root injury and postoperative incision complications.

Impact evaluation of a sexually transmitted disease preventive intervention among female sex workers in Hohhot, China.

OBJECTIVES: The aim of this study was to evaluate the impact of HIV and sexually transmitted disease (STD) prevention interventions among female sex workers (FSWs) in the city of Hohhot in northern China. METHODS: Three serial cross-sectional surveys were conducted in 2006, 2007, and 2008 among FSWs. A questionnaire was administered to the FSWs, and HIV and syphilis tests were performed for all participants. Intervention activities including condom promotion and provision, increased condom availability and accessibility, and voluntary HIV counseling and testing (VCT) were carried out among FSWs. RESULTS: There were 624 participants in the 2006 survey, 444 in the 2007 survey, and 451 in the 2008 survey. The United Nations General Assembly Special Session (UNGASS) indicators for FSWs increased from 13.9% in 2006 to 37.7% in 2008 (p<0.001). The average rate of consistent condom use with commercial clients in the month preceding the interview increased significantly from 39.8% in 2006 to 59.6% in 2008 (p<0.001). Not a single HIV-positive case was found among the FSWs over these 3 years, and the prevalence of syphilis decreased remarkably from 9.5% in 2006 to 1.3% in 2008. Logistic regression analysis showed that sauna or hair salon work venues, receiving services from intervention programs, and accepting HIV tests were factors associated with consistent condom use. CONCLUSIONS: The findings suggest that consistent condom use and awareness of HIV/AIDS prevention-related knowledge among FSWs have been improved by the intervention. Further prioritized and combined prevention programs aimed at FSWs are needed in order to prevent the HIV/AIDS epidemic spreading in the general population in China.