机器学习算法在肝细胞癌微血管侵犯术前预测中的应用价值

目的探讨机器学习算法在肝细胞癌微血管侵犯(MVI)术前预测中的应用价值。方法采用回顾性描述性研究方法。收集2015年5月至2018年12月福建医科大学孟超肝胆医院收治的277例肝细胞癌患者的临床病理资料;男235例,女42例;年龄为(56±10)岁,年龄范围为33~80岁。患者术前均行磁共振成像检查。227例肝细胞癌患者通过计算机产生随机数方法以7∶3比例分为训练集193例和验证集84例。应用逻辑回归列线图,支持向量机(SVM)、随机森林(RF)、人工神经网络(ANN)和轻量级梯度提升机(LightGBM)机器学习算法构建MVI术前预测模型。观察指标:(1)训练集及验证集患者临床病理资料分析。(2)影响训练集患者肿瘤MVI危险因素分析。(3)机器学习算法预测模型构建及其术前预测肿瘤MVI准确性比较。正态分布的计量资料以±s表示,组间比较采用配对t检验。计数资料以绝对数表示,组间比较采用χ2检验。单因素和多因素分析采用Logistic回归模型。结果(1)训练集及验证集患者临床病理资料分析:训练集和验证集患者性别(男,女)分别为157、36例和78、6例,两组比较,差异有统计学意义(χ2=6.028,P<0.05)。(2)影响训练集患者肿瘤MVI危险因素分析:训练集193例患者中,MVI阳性108例,MVI阴性85例。单因素分析结果显示:年龄、肿瘤数目、肿瘤直径、卫星病灶、肿瘤边界、甲胎蛋白(AFP)、碱性磷酸酶(ALP)和纤维蛋白原水平是影响肿瘤MVI的相关因素(比值比=0.971,2.449,1.368,4.050,2.956,4.083,2.532,1.996,95%可信区间为0.943~1.000,1.169~5.130,1.180~1.585,1.316~12.465,1.310~6.670,2.214~7.532,1.016~6.311,1.323~3.012,P<0.05)。多因素分析结果显示:AFP>20μg/L、肿瘤多发、肿瘤直径越大、肿瘤边界不光滑是影响肿瘤MVI的独立危险因素(比值比=3.680,3.100,1.438,3.628,95%可信区间为1.842~7.351,1.334~7.203,1.201~1.721,1.438~9.150,P<0.05),而年龄越大,MVI发生风险越低(比值比=0.958,95%可信区间为0.923~0.994,P<0.05)。(3)机器学习算法预测模型构建及其术前预测肿瘤MVI准确性比较:①应用多因素分析结果筛选指标,包括年龄、AFP、肿瘤数目、肿瘤直径、肿瘤边界,构建逻辑回归列线图,SVM、RF、ANN及LightGBM机器学习算法预测模型,一致性分析结果显示逻辑回归列线图预测模型稳定性较好。逻辑回归列线图、SVM、RF、ANN、LightGBM机器学习算法预测模型训练集和验证集曲线下面积(AUC)分别为0.812、0.794、0.807、0.814、0.810和0.784、0.793、0.783、0.803、0.815,SVM、RF、ANN、LightGBM机器学习算法AUC分别与逻辑回归列线图AUC比较,差异均无统计学意义[(95%可信区间为0.731~0.849,0.744~0.860,0.752~0.867,0.747~0.862,Z=0.995,0.245,0.130,0.102,P>0.05)和(95%可信区间为0.690~0.873,0.679~0.865,0.702~0.882,0.715~0.891,Z=0.325,0.026,0.744,0.803,P>0.05)]。②应用RF、LightGBM机器学习算法自行筛选临床病理因素指标构建预测模型。根据指标对预测模型重要度排序,选择重要度>0.01的指标,包括年龄、肿瘤直径、AFP、白细胞(WBC)、血小板、总胆红素、天冬氨酸氨基转移酶、γ-谷氨酰转移酶、ALP和纤维蛋白原,构建RF机器学习算法预测模型;挑选重要度>5.0的指标,包括年龄、肿瘤直径、AFP、WBC、ALP和纤维蛋白原,构建LightGBM机器学习算法预测模型;由于ANN及SVM机器学习算法不具备筛选指标能力,应用单因素分析结果筛选指标,包括年龄、肿瘤数目、肿瘤直径、卫星病灶、肿瘤边界、AFP、ALP和纤维蛋白原水平,构建SVM、ANN机器学习算法预测模型。SVM、RF、ANN、LightGBM机器学习算法预测模型训练集和验证集AUC分别为0.803、0.838、0.793、0.847和0.810、0.802、0.802、0.836,分别与逻辑回归列线图AUC比较,差异均无统计学意义[(95%可信区间为0.740~0.857,0.779~0.887,0.729~0.848,0.789~0.895,Z=0.421,0.119,0.689,1.517,P>0.05)和(95%可信区间为0.710~0.888,0.700~0.881,0.701~0.881,0.740~0.908,Z=0.856,0.458,0.532,1.306,P>0.05)]。结论机器学习算法可用于术前预测肝细胞癌MVI,但其应用价值尚需多中心大样本数据进一步验证。     

Fostering reproducibility and generalizability in machine learning for clinical prediction modeling in spine surgery

As the use of machine learning algorithms in the development of clinical prediction models has increased, researchers are becoming more aware of the deleterious effects that stem from the lack of reporting standards. One of the most obvious consequences is the insufficient reproducibility found in current prediction models. In an attempt to characterize methods to improve reproducibility and to allow for better clinical performance, we utilize a previously proposed taxonomy that separates reproducibility into 3 components: technical, statistical, and conceptual reproducibility. By following this framework, we discuss common errors that lead to poor reproducibility, highlight the importance of generalizability when evaluating a ML model's performance, and provide suggestions to optimize generalizability to ensure adequate performance. These efforts are a necessity before such models are applied to patient care.     

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: “artificial intelligence” OR “machine learning” AND “neurosurgery” AND “spine.” Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

     

Robotic-assisted spine surgery: Application of preoperative and intraoperative imaging

Technological advancements in spine surgery have paved the way for improved patient outcomes, and robotic-assistance has become a frontrunner in spine research and development. However, its use and understanding is yet to be fully determined. The purpose of this chapter is to highlight the applications of current robotic systems in spine surgery. The chapter focuses on current imaging modalities and their uses, as well as future imaging techniques that may broaden the indications for robotic use, while maintaining optimal outcomes.     

Development and validation of machine learning models for the prediction of blunt cerebrovascular injury in children

BackgroundBlunt cerebrovascular injury (BCVI) is a rare finding in trauma patients. The previously validated BCVI (Denver and Memphis) prediction model in adult patients was shown to be inadequate as a screening option in injured children. We sought to improve the detection of BCVI by developing a prediction model specific to the pediatric population.MethodsThe National Trauma Databank (NTDB) was queried from 2007 to 2015. Test and training datasets of the total number of patients (885,100) with complete ICD data were used to build a random forest model predicting BCVI. All ICD features not used to define BCVI (2268) were included within the random forest model, a machine learning method. A random forest model of 1000 decision trees trying 7 variables at each node was applied to training data (50% of the dataset, 442,600 patients) and validated with test data in the remaining 50% of the dataset. In addition, Denver and Memphis model variables were re-validated and compared to our new model.ResultsA total of 885,100 pediatric patients were identified in the NTDB to have experienced blunt pediatric trauma, with 1,998 (0.2%) having a diagnosis of BCVI. Skull fractures (OR 1.004, 95% CI 1.003–1.004), extremity fractures (OR 1.001, 95% 1.0006–1.002), and vertebral injuries (OR 1.004, 95% CI 1.003–1.004) were associated with increased risk for BCVI. The BCVI prediction model identified 94.4% of BCVI patients and 76.1% of non-BCVI patients within the NTDB. This study identified ICD9/ICD10 codes with strong association to BCVI. The Denver and Memphis criteria were re-applied to NTDB data to compare validity and only correctly identified 13.4% of total BCVI patients and 99.1% of non BCVI patients.ConclusionThe prediction model developed in this study is able to better identify pediatric patients who should be screened with further imaging to identify BCVI.Level of evidenceRetrospective diagnostic study–level III evidence.     

多模式神经电生理监测在颈椎前路手术中的预警意义

目的:探讨多模式神经电生理监测在颈椎前路手术中的预警意义。方法:2014年9月~2015年4月对53例行颈椎前路手术的颈椎病患者术中进行多模式神经电生理监测(A组),选取60例年龄、性别、病变节段和手术方式匹配但未进行神经电生理监测的颈椎前路手术患者作为对照(B组)。比较两组患者手术时间、术中出血量、神经根型颈椎病患者手术前后颈痛及上肢疼痛视觉模拟评分法(visual analogue scales,VAS)评分、颈部功能障碍指数(neck disability index,NDI)、脊髓型颈椎病患者术后JOA评分改善率和并发症的发生情况,分析A组病例中术中预警的类型和原因,以及与术前诊断、手术方式和手术节段之间的关系。结果:A组患者的手术时间为1.3±0.5h(0.8~2.1h),术中出血量为390±236ml(120~600ml),B组患者的手术时间为1.2±0.7h(0.6~2.4h),术中出血量为346±293ml(105~610ml),两组比较均无统计学差异(P0.05)。A、B两组神经根型颈椎病患者术前、术后的颈部和上肢VAS评分均无显著性差异(6.5±1.6 vs.6.8±1.4,7.6±2.4 vs.7.4±2.7,3.8±1.2vs.3.6±1.6,3.3±1.4 vs.3.9±1.8,P0.05),A组神经根型颈椎病患者术后NDI和脊髓型颈椎病患者JOA评分改善率明显优于B组[(19.2±7.1 vs 22.1±5.6,(84.1±10.3)%vs(73.3±9.2)%;P0.05]。在A组病例中,颈椎前路椎体次全切椎间融合手术较颈前路椎间盘切除椎间融合术的术中监测"严重预警"发生率更高(P0.05),但两种手术方式的"次要预警"发生率无显著性差异(P0.05);脊髓型颈椎病与神经根型颈椎病之间、单节段手术与双节段手术之间的术中监测"严重预警"和"次要预警"发生率均无统计学差异(P0.05)。结论:多模式神经电生理监测在颈椎前路手术中能及时预警神经损伤,可有效提高手术的安全性和临床疗效。     

腰椎毗邻血管的应用解剖及血管损伤并发症

下腰椎前入路手术,在治疗腰椎疾病方面扮演着非常重要的角色,其手术区域相关的临床解剖学研究也日益深入。腰椎局部区域的血管、神经对于术中的显露有着直接影响,熟悉这些结构不仅能减少术中创伤和术后并发症,也能为新的手术入路和技术的发展提供新思路。该文对腰椎前方血管的特点和减少血管并发症的研究现状进行综述。     

Updated external validation of the SORG machine learning algorithms for prediction of ninety-day and one-year mortality after surgery for spinal metastasis

BACKGROUND CONTEXTSurgical decompression and stabilization in the setting of spinal metastasis is performed to relieve pain and preserve functional status. These potential benefits must be weighed against the risks of perioperative morbidity and mortality. Accurate prediction of a patient's postoperative survival is a crucial component of patient counseling.PURPOSETo externally validate the SORG machine learning algorithms for prediction of 90-day and 1-year mortality after surgery for spinal metastasis.STUDY DESIGN/SETTINGRetrospective, cohort studyPATIENT SAMPLEPatients 18 years or older at a tertiary care medical center treated surgically for spinal metastasisOUTCOME MEASURESMortality within 90 days of surgery, mortality within 1 year of surgeryMETHODSThis is a retrospective cohort study of 298 adult patients at a tertiary care medical center treated surgically for spinal metastasis between 2004 and 2020. Baseline characteristics of the validation cohort were compared to the derivation cohort for the SORG algorithms. The following metrics were used to assess the performance of the algorithms: discrimination, calibration, overall model performance, and decision curve analysis.RESULTSSixty-one patients died within 90 days of surgery and 133 died within 1 year of surgery. The validation cohort differed significantly from the derivation cohort. The SORG algorithms for 90-day mortality and 1-year mortality performed excellently with respect to discrimination; the algorithm for 1-year mortality was well-calibrated. At both postoperative time points, the SORG algorithms showed greater net benefit than the default strategies of changing management for no patients or for all patients.CONCLUSIONSWith an independent, contemporary, and geographically distinct population, we report successful external validation of SORG algorithms for preoperative risk prediction of 90-day and 1-year mortality after surgery for spinal metastasis. By providing accurate prediction of intermediate and long-term mortality risk, these externally validated algorithms may inform shared decision-making with patients in determining management of spinal metastatic disease.     

基于H2O自动化机器学习的肝硬化患者死亡预测模型的建立

背景与目的 晚期肝硬化患者往往出现一系列并发症,死亡风险增加。因此,尽早识别肝硬化死亡高风险具有重要的临床意义。本研究利用H2O平台自动化机器学习（AutoML）框架,建立预测肝硬化患者入院30 d死亡模型,以期为改善肝硬化患者预后以及肝硬化临床管理提供新的方法。方法 收集江苏大学附属金坛医院及湖南省人民医院肝硬化住院患者入院时一般资料及实验室检查数据。利用H2O AutoML框架建立针对死亡结局的多种机器学习算法模型,绘制受试者工作特征（ROC）曲线并建立混淆矩阵来评价模型效力,同时对重要变量进行可视化呈现。结果 最佳模型为梯度提升机（GBM）,Gini值0.994,R²为0.775,LogLoss为0.120。模型中重要变量包括凝血酶原时间、肌酐、白细胞及年龄。变量SHAP特征图及部分依赖图呈现了重要变量与模型整体预测的相关性。局部可解析性算法（LIME）可视化显示变量在个体预测的作用。最佳模型GBM在验证集中特异度为0.950,敏感度0.676,ROC曲线下面积（AUC）为0.793,优于基于极致梯度提升（XGBoost）、Logistic回归、随机森林和深度学习四个算法模型,以及终末期肝病模型（MELD）及白蛋白-胆红素（ALBI）评分。结论 所建立的预测短期死亡机器学习模型对肝硬化患者的短期死亡风险筛查提供了有效的工具,但其可靠性仍需多中心的外部验证进一步评估。     

Natural language processing and entrustable professional activity text feedback in surgery: A machine learning model of resident autonomy

BackgroundEntrustable Professional Activities (EPAs) contain narrative ‘entrustment roadmaps’ designed to describe specific behaviors associated with different entrustment levels. However, these roadmaps were created using expert committee consensus, with little data available for guidance. Analysis of actual EPA assessment narrative comments using natural language processing may enhance our understanding of resident entrustment in actual practice.MethodsAll text comments associated with EPA microassessments at a single institution were combined. EPA—entrustment level pairs (e.g. Gallbladder Disease—Level 1) were identified as documents. Latent Dirichlet Allocation (LDA), a common machine learning algorithm, was used to identify latent topics in the documents associated with a single EPA. These topics were then reviewed for interpretability by human raters.ResultsOver 18 months, 1015 faculty EPA microassessments were collected from 64 faculty for 80 residents. LDA analysis identified topics that mapped 1:1 to EPA entrustment levels (Gammas >0.99). These LDA topics appeared to trend coherently with entrustment levels (words demonstrating high entrustment were consistently found in high entrustment topics, word demonstrating low entrustment were found in low entrustment topics).ConclusionsLDA is capable of identifying topics relevant to progressive surgical entrustment and autonomy in EPA comments. These topics provide insight into key behaviors that drive different level of resident autonomy and may allow for data-driven revision of EPA entrustment maps.     

Facial nerve preservation with preoperative identification and intraoperative monitoring in large vestibular schwannoma surgery

Background

Microsurgery is an option of choice for large vestibular schwannomas (VSs). Anatomical and functional preservation of facial nerve (FN) is still a challenge in these surgeries. FNs are often displaced and morphologically changed by large VSs. Preoperative identification of FN with magnetic resonance (MR) diffusion tensor tracking (DTT) and intraoperative identification with facial electromyography (EMG) may be desirable for improving functional results of FN.

Method

In this retrospective study, eight consecutive cases with large VS (≥30 mm in maximal extrameatal diameter) were retrospectively studied. FN DTT was performed in each case preoperatively. All the cases underwent microsurgical resection of the tumor with intraoperative FN EMG monitoring. Correctness of prediction for FN location by DTT was verified by the surgeon’s inspection. Postoperative FN function of each patient was followed up.

Results

Preoperative identification of FN was possible in 7 of 8 (87.5 %) cases. FN location predicted by preoperative DTT agreed to surgical finding in all the 7 cases. FN EMG was helpful to locate and protect the FN. Total resection was achieved in 7 of 8 (87.5 %). All FNs were anatomically preserved. All cases had excellent facial nerve function (House–Brackmann Grade I–II).

Conclusions

FN DTT is a powerful technique in preoperatively identification of FN in large VS cases. Continuous intraoperative FN EMG monitoring is contributive to locating and protecting FNs. Radical resection of large VSs as well as favorable postoperative FN outcome is available with application of these techniques.     

Development and validation of a risk-based algorithm for preoperative type and screen testing in spine surgery

BACKGROUND CONTEXTWith improvements in surgical techniques and perioperative management, transfusion rates after spine surgery have decreased over time. Given this trend, routine preoperative ABO/Rh type and antibody screen (T&S) laboratory testing may not be warranted in all patients undergoing spine surgery.PURPOSEThe aim of the current study is to evaluate risk factors for intra/postoperative transfusion in patients undergoing a variety of spine procedures and to develop an algorithm for selectively ordering preoperative T&S testing in appropriate patients.STUDY DESIGN/SETTINGThis is a single institution, retrospective observational study of patients undergoing emergent or elective spine surgery. External validation of the algorithm was performed on a national sample of patients undergoing spine surgery from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) national database.PATIENT SAMPLEA total of 5,947 surgeries from January 1, 2016 to December 31, 2019 at a single institution, and 166,113 surgeries from the 2016 to 2018 ACS-NSQIP database.OUTCOME MEASURESThe primary outcome measure was performance of intraoperative or postoperative transfusion.METHODSUsing the institutional sample, univariate statistics (chi-square tests, fisher's exact test, 2-sided independent sample tests) were performed to compare demographics, comorbidities, and surgical details (case type, number of levels treated, etc.) between patients who did and did not require intra- or postoperative transfusion. Transfusion rates were calculated and compared across procedure types. Multivariate logistic regression was performed to identify independent predictors of transfusion and the model's accuracy was evaluated using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. A risk-based algorithm suggesting no preoperative T&S in low transfusion risk procedures, routine preoperative T&S in high-risk procedures, and further assessment in medium risk thoracolumbar fusion procedures was created. The algorithm's sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were evaluated when it was applied to both the institutional and national samples. Potential cost savings from reducing T&S orders were calculated.RESULTSIn the institutional sample, 120 patients (2.0%) required intraoperative or postoperative transfusion. The highest rates of transfusion were found in corpectomy (10.5%) and anterior/posterior cervical fusion (6.9%) procedures. In the multivariate logistic regression model, the presence of a preoperative coagulation defect or hemorrhagic condition (OR: 7.149, p<.001) and 6+ level surgery (OR: 7.511, p<.001) were the strongest predictors of transfusion. Overall, the model generated an AUC of 0.882, indicating excellent predictive accuracy. When applied to the institutional cohort, the risk-based algorithm had a sensitivity of 78.3%, specificity of 80.5%, PPV of 7.6%, and NPV of 99.4% for evaluating likelihood of transfusion. Using the algorithm 4,717 T&S tests would have been eliminated (79.3%), resulting in a cost savings of $179,246. Application of the model to the ACS-NSQIP cohort resulted in a sensitivity of 61.9%, specificity of 84.6%, PPV of 15.6%, and NPV of 98.0%.CONCLUSIONSThe routine use of preoperative ABO/Rh type and antibody screen testing does not appear to be warranted in patients undergoing spine surgery. A risk-based approach to preoperative type and screen testing may eliminate unnecessary tests and generate significant cost savings with minimal disruption to clinical care.     

Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy

BACKGROUNDDegenerative cervical myelopathy (DCM) is the most common cause of spinal cord dysfunction worldwide. Current guidelines recommend management based on the severity of myelopathy, measured by the modified Japanese Orthopedic Association (mJOA) score. Patients with moderate to severe myelopathy, defined by an mJOA below 15, are recommended to undergo surgery. However, the management for mild myelopathy (mJOA between 15 and 17) is controversial since the response to surgery is more heterogeneous.PURPOSETo develop machine learning algorithms predicting phenotypes of mild myelopathy patients that would benefit most from surgery.STUDY DESIGNRetrospective subgroup analysis of prospectively collected data.PATIENT SAMPLESData were obtained from 193 mild DCM patients who underwent surgical decompression and were enrolled in the multicenter AOSpine CSM clinical trials.OUTCOME MEASURESThe mJOA score, an assessment of functional status, was used to isolate patients with mild DCM. The primary outcome measures were change from baseline for the Short Form-36 (SF-36) mental component summary (MCS) and physical component summary (PCS) at 1-year postsurgery. These changes were dichotomized according to whether they exceeded the minimal clinically important difference.METHODSThe data were split into training (75%) and testing (25%) sets. Model predictors included baseline demographic variables and clinical presentation. Seven machine learning algorithms and a logistic regression model were trained and optimized using the training set, and their performances were evaluated using the testing set. For each outcome (improvement in MCS or PCS), the machine learning algorithm with the greatest area under the curve (AUC) on the training set was selected for further analysis.RESULTSThe generalized boosted model (GBM) and earth models performed well in the prediction of significant improvement in MCS and PCS respectively, with AUCs of 0.72 to 0.78 on the training set. This performance was replicated on the testing set, in which the GBM and earth models showed AUCs of 0.77 and 0.78, respectively, as well as fair to good calibration across the predicted range of probabilities. Female patients with a low initial MCS were less likely to experience significant improvement in MCS than males. The presence of certain signs and symptoms (eg, lower limb spasticity, clumsy hands) were also predictive of worse outcome.CONCLUSIONSMachine learning models showed good predictive power and provided information about the phenotypes of mild DCM patients most likely to benefit from surgical intervention. Overall, machine learning may be a useful tool for management of mild DCM, though external validation and prospective analysis should be performed to better solidify its role.     

胸腔镜辅助下胸椎、上腰椎前路手术的体会

目的 探讨胸腔镜技术在胸、腰椎前路手术的适应证、操作要点以及单肺或双肺通气麻醉的选择。方法 对5例结核病人行胸腔镜下结核病灶清除术，其中2例同时行自体髂骨植骨术，1例以自固化磷酸钙人工骨(CPC)植入；对3例爆裂性骨折截瘫及1例L1陈旧性爆裂骨折并马尾综合征病人进行脊髓减压、自体髂骨植骨、钢板螺丝钉内固定术。结果 全部病例都得到随访，术后切口一期愈合，X光、CT检查也都显示病灶清除彻底，脊髓减压充分，复位满意，内固定可靠，位置良好。结论 胸椎、上腰椎结核或骨折，不论是否并发脊髓、马尾神经压迫的病例，均适宜在胸腔镜辅助下进行病灶清除、脊髓减压、脊柱前路内固定术。