Establishment of a Nomogram for Predicting Lumbar Drainage-Related Meningitis: A Simple Tool to Estimate the Infection Risk

Wang, Peng; Song, Weizheng; Cheng, Shuwen; Shuai, Yongxiao; Yang, Jing; Luo, Shuang

doi:10.1007/s12028-020-01076-1

Cited by 5 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, scholars have an increasing enthusiasm for utilizing supervised ML to predict the occurrence of infection, including iatrogenic and non-iatrogenic (21,(25)(26)(27)(28)(29)(30)(31)(32)(33). Nonetheless, the study that forecasts the risk of LDRM in an early stage before the clinical diagnosis is limited, although we have proposed a prediction model using the traditional logistic regression algorithm (19). To search for potential ML models and improve the prediction accuracy, we used three prevalent ML algorithms to establish the LDRM prediction models in this research.…”

Section: Discussionmentioning

confidence: 99%

“…We used a cohort of 273 eligible cases, as described in our previous report ( 19 ). All the enrolled patients received LD treatment during a research period from January 2012 to December 2018 in the Chengdu Fifth People's Hospital (Chengdu, China).…”

Section: Methodsmentioning

confidence: 99%

“…These factors include duration days, drain opening, site leakage, admission to intensive care unit (ICU), diabetes, and accompanied craniotomy (15-18). In our earlier study, we proposed a prediction model by screening the risk factors of LDRM and established a nomogram as a simple tool to estimate the infection risk (19). However, this model was built based on a traditional logistic regression method, which is challenging to fit Abbreviations: LD, Lumbar drainage; CSF, Cerebrospinal fluid; LDRM, Lumbar drainage-related meningitis; ICU, Intensive care unit; ML, Machine learning; SVM, Support vector machine; RF, Random forest; ANN, Artificial neural network; SICU, Surgery intensive care unit; ROC, Receiver operating characteristic curve; PRC, Precision-recall curve; AUROC, Area under receiver operating characteristic curve; AUPRC, Area under precision-recall curve; TPR, True positive ratio; TNR, True negative ratio.…”

Section: Introductionmentioning

confidence: 99%

“…These factors include duration days, drain opening, site leakage, admission to intensive care unit (ICU), diabetes, and accompanied craniotomy ( 15 – 18 ). In our earlier study, we proposed a prediction model by screening the risk factors of LDRM and established a nomogram as a simple tool to estimate the infection risk ( 19 ). However, this model was built based on a traditional logistic regression method, which is challenging to fit the actual distribution of data and deal with the problem of collinearity.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Wang

Cheng

et al. 2022

Front. Public Health

Self Cite

View full text Add to dashboard Cite

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Wang

Cheng

et al. 2022

Front. Public Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nomograms are helpful and readily available models that can be scored by integrating significant risk factors, which is convenient for clinicians to predict prognosis and individual treatment plans in numerous diseases [ 13 , 14 ]. Some studies have used nomograms to predict the incidence and mortality of meningitis [ 15 , 16 ]. However, to our knowledge, no studies use nomograms to predict the occurrence of paradoxical CM-IRIS in HIV-infected patients.…”

Section: Introductionmentioning

confidence: 99%

A nomogram for predicting paradoxical immune reconstitution inflammatory syndrome associated with cryptococcal meningitis among HIV-infected individuals in China

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Cryptococcal meningitis (CM) associated immune reconstitution inflammatory syndrome (CM-IRIS) is the second most common complication in HIV-infected individuals with cryptococcal meningitis, with a reported mortality rate ranging from 8 to 30%. Given the devastating consequences of CM-IRIS related intracranial neuroinflammation and its challenging in diagnosis, we conducted a study to explore the risk factors and the occurrence of paradoxical CM-IRIS in HIV-infected patients, which is of great value for prevention and clinical management. Methods We conducted a retrospective cohort study to identify the indicators associated with paradoxical CM-IRIS among 86 HIV-infected patients with CM using univariate and multivariate cox analysis. A nomogram was constructed using selected variables to evaluate the occurrence of paradoxical CM-IRIS at 6 months and 12 months after ART initiation. The discrimination and calibration of the nomogram were assessed by concordance index (C-index) and calibration plots. Decision curves analysis (DCA) were used to evaluate clinical effectiveness of the nomogram. Subsequently, to help clinicians recognize patients at high risk faster, patients were divided into high-risk and low-risk groups according to the best cutoff point identified by X-tile. Results Of 86 AIDS patients with CM, 22.1% experienced paradoxical CM-IRIS at a median of 32 days after antiretroviral therapy (ART) initiation. The occurrence of paradoxical CM-IRIS was associated with age, ART initiation within 4 weeks of antifungal treatment, a four-fold increase in CD4 T cell counts, C-reactive protein levels, and hemoglobin levels independently. These five variables were further used to construct a predictive nomogram. The C-index (0.876) showed the favorable discriminative ability of the nomogram. The calibration plot revealed a high consistency between the predicted and actual observations. DCA showed that the nomogram was clinically useful. Risk stratification based on the total score of the nomogram showed well-differentiated in the high-risk and low-risk groups. Clinicians should pay attention to patients with total points high than 273. Conclusions We identified the predictive factors of paradoxical CM-IRIS and constructed a nomogram to evaluate the occurrence of paradoxical CM-IRIS in 6 months and 12 months. The nomogram represents satisfactory performance and might be applied clinically to the screening and management of high-risk patients.

show abstract

Construction and validation of infection risk model for patients with external ventricular drainage: a multicenter retrospective study

Wang,

Luo,

Cheng

et al. 2023

Acta Neurochir

View full text Add to dashboard Cite

Establishment of a Nomogram for Predicting Lumbar Drainage-Related Meningitis: A Simple Tool to Estimate the Infection Risk

Cited by 5 publications

References 31 publications

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

A nomogram for predicting paradoxical immune reconstitution inflammatory syndrome associated with cryptococcal meningitis among HIV-infected individuals in China

Construction and validation of infection risk model for patients with external ventricular drainage: a multicenter retrospective study

Contact Info

Product

Resources

About