Machine Learning-based Prediction of Prolonged Intensive Care Unit Stay for Critical Patients with Spinal Cord Injury

Fan, Guoxin; Yang, Sheng; Liu, Huaqing; Xu, Ningze; Chen, Yuyong; He, Jie; Su, Xiuyun; Pang, Mao; Liu, Bin; Han, Lanqing; Rong, Limin

doi:10.1097/brs.0000000000004267

Cited by 15 publications

(13 citation statements)

References 57 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prognostication and anticipated survival are important for clinical practice and can contribute to decision-making while also aiding communication with patients and their families. 17 Nomogram transforms traditional statistical prediction into visual probability estimates customized for each patient and is suitable for cancer prognosis research. [18][19][20] In terms of the calibration curves, IBS, c-indices, and ROC curves, the established nomograms showed excellent performance and potential as accurate prognostic tools for predicting OS and CSS in SPS patients.…”

Section: Discussionmentioning

confidence: 99%

Novel Nomograms and Web-Based Tools Predicting Overall Survival and Cancer-specific Survival of Solitary Plasmacytoma of the Spine

Yang

Fan

Feng

et al. 2023

Spine

Self Cite

View full text Add to dashboard Cite

Study Design. Retrospective analysis. Objective. This study aimed to establish nomograms for predicting overall survival (OS) and cancer-specific survival (CSS) in patients with solitary plasmacytoma of the spine (SPS). Summary of Background Data. SPS is a rare type of malignant spinal tumor. A systematic study of prognostic factors associated with survival can provide guidance to clinicians and patients. Consideration of other causes of death (OCOD) in CSS will improve clinical practicability. Methods. A total of 1078 patients extracted from the SEER database between 2000 and 2018 were analyzed. Patients were grouped into training and testing data sets (7:3). Factors associated with OS and CSS were identified by Cox regression and competing risk regression, respectively, for the establishment of nomograms on a training data set. The testing data set was used for the external validation of the performance of the nomograms using calibration curves, Brier’s scores, C-indexes, time-dependent receiver operating characteristic curves, and decision curve analysis (DCA). Results. Age and grade were identified as factors associated with both OS and CSS, along with marital status, radiation for OS, and chemotherapy for CSS. Heart disease, cerebrovascular disease, and diabetes mellitus were found to be the 3 most common causes of OCOD. The nomograms showed satisfactory agreement on calibration plots for both training and testing data sets. Integrated Brier score, C-index, and overall area under the curve on the testing data set were 0.162/0.717/0.789 and 0.173/0.709/0.756 for OS and CSS, respectively. DCA curves showed a good clinical net benefit. Nomogram-based web tools were developed for clinical application. Conclusion. This study provides evidence for risk factors and prognostication of survival in SPS patients. The novel nomograms and web-based tools we developed demonstrated good performance and might serve as accessory tools for clinical decision-making and SPS management. Level of Evidence. 3

show abstract

Section: Discussionmentioning

confidence: 99%

Novel Nomograms and Web-Based Tools Predicting Overall Survival and Cancer-specific Survival of Solitary Plasmacytoma of the Spine

Yang

Fan

Feng

et al. 2023

Spine

Self Cite

View full text Add to dashboard Cite

show abstract

“…We excluded patients who met the following criteria: (1) AIS grade E at initial examination, (2) underwent conservative treatment, (3) follow-up period < 6 months, (4) underwent surgery at another hospital, (5) underwent surgery after 24 hours from injury, (6) neurological status not evaluable because of disturbed consciousness, such as brain injury or severe mental disorder.…”

Section: Patient Populationmentioning

confidence: 99%

“…Previous studies reported that ML models were useful for predicting the outcomes of orthopedic conditions, such as hip fracture, 1 carpal tunnel syndrome, 2 ossi cation of the posterior longitudinal ligament (OPLL), 3 and degenerative cervical myelopathy. 4 ML can predict intensive care unit (ICU) stay 5 and 1-year mortality 6 in patients with spinal cord injuries. A previous study reported that ML models were useful for predicting neurological improvements in patients with CSCI.…”

Section: Introductionmentioning

confidence: 99%

Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery

Shimizu

Suda

Maki

et al. 2022

Preprint

View full text Add to dashboard Cite

Prediction of the neurological prognosis of cervical spinal cord injury (CSCI) is useful for setting treatment goals. This study aimed to develop a machine learning (ML) model for predicting neurological outcomes of CSCI. We retrospectively analyzed 135 patients with CSCI who underwent surgery within 24 hours after injury. American Spinal Injury Association impairment scales (AIS; grades A to E) were analyzed 6 months after injury as primary outcome measures. A total of 33 features extracted from demographic variables, surgical factors, laboratory variables, neurological status, and radiological findings were analyzed. The multiclass ML model was created using Light GBM, XGBoost, and CatBoost. The accuracy, recall, precision, and F1 score were calculated for each classification model. We evaluated Shapley Additive Explanations (SHAP) values to determine the variables that contributed the most to the prediction models. Of the ML models used, CatBoost had the highest accuracy (0.807), recall (0.574), precision (0.808), and F1 score (0.622). AIS grade at admission, intramedullary hemorrhage, longitudinal extent of intramedullary T2 hyperintensity, total motor index score of the lower extremity, and HbA1c were identified as important features for the prediction model. The ML models successfully predicted neurological outcomes for five grades of AIS 6 months after injury.

show abstract

“…In recent years, many studies have shown that stacked ensemble algorithms have greater predictive advantages in clinical decision support. Fan et al used a stacked ensemble algorithm to classify normal and delayed hospitalizations in 1599 critically ill patients with spinal cord injuries [ 20 ]. Fan et al selected three classifiers with the best performance from 91 base classifiers, and subsequently further superimposed the three classifiers into an stacked ensemble model using logistic regression classification.…”

Section: Introductionmentioning

confidence: 99%

“…The results demonstrated that the EDRnet provided 100% sensitivity, 91% specificity, and 92% accuracy [ 21 ]. The stacked ensemble algorithms [ 20 , 21 ] achieved a high prediction performance and generalization ability because it fully utilized base classifiers, such as XGBoost and lightGBM, which were excellent for large sample sizes with multiple features, and the Bayesian neural network algorithm, which was suitable for small sample sets and effectively prevented overfitting. By integrating different classifiers, the disadvantages could be avoided, and the generality of the stacked ensemble algorithm could be considerably improved [ 22 – 24 ].…”

Section: Introductionmentioning

confidence: 99%

Early prediction of MODS interventions in the intensive care unit using machine learning

et al. 2023

View full text Add to dashboard Cite

Background Multiple organ dysfunction syndrome (MODS) is one of the leading causes of death in critically ill patients. MODS is the result of a dysregulated inflammatory response that can be triggered by various causes. Owing to the lack of an effective treatment for patients with MODS, early identification and intervention are the most effective strategies. Therefore, we have developed a variety of early warning models whose prediction results can be interpreted by Kernel SHapley Additive exPlanations (Kernel-SHAP) and reversed by diverse counterfactual explanations (DiCE). So we can predict the probability of MODS 12 h in advance, quantify the risk factors, and automatically recommend relevant interventions. Methods We used various machine learning algorithms to complete the early risk assessment of MODS, and used a stacked ensemble to improve the prediction performance. The kernel-SHAP algorithm was used to quantify the positive and minus factors corresponding to the individual prediction results, and finally, the DiCE method was used to automatically recommend interventions. We completed the model training and testing based on the MIMIC-III and MIMIC-IV databases, in which the sample features in the model training included the patients’ vital signs, laboratory test results, test reports, and data related to the use of ventilators. Results The customizable model called SuperLearner, which integrated multiple machine learning algorithms, had the highest authenticity of screening, and its Yordon index (YI), sensitivity, accuracy, and utility_score on the MIMIC-IV test set were 0.813, 0.884, 0.893, and 0.763, respectively, which were all maximum values of eleven models. The area under the curve of the deep–wide neural network (DWNN) model on the MIMIC-IV test set was 0.960, and the specificity was 0.935, which were both the maximum values of all these models. The Kernel-SHAP algorithm combined with SuperLearner was used to determine the minimum value of glasgow coma scale (GCS) in the current hour (OR = 0.609, 95% CI 0.606–0.612), maximum value of MODS score corresponding to GCS in the past 24 h (OR = 2.632, 95% CI 2.588–2.676), and maximum score of MODS corresponding to creatinine in the past 24 h (OR = 3.281, 95% CI 3.267–3.295) were generally the most influential factors. Conclusion The MODS early warning model based on machine learning algorithms has considerable application value, and the prediction efficiency of SuperLearner is superior to those of SubSuperLearner, DWNN, and other eight common machine learning models. Considering that the attribution analysis of Kernel-SHAP is a static analysis of the prediction results, we introduce the DiCE algorithm to automatically recommend counterfactuals to reverse the prediction results, which will be an important step towards the practical application of automatic MODS early intervention.

show abstract

Machine Learning-based Prediction of Prolonged Intensive Care Unit Stay for Critical Patients with Spinal Cord Injury

Cited by 15 publications

References 57 publications

Novel Nomograms and Web-Based Tools Predicting Overall Survival and Cancer-specific Survival of Solitary Plasmacytoma of the Spine

Novel Nomograms and Web-Based Tools Predicting Overall Survival and Cancer-specific Survival of Solitary Plasmacytoma of the Spine

Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery

Early prediction of MODS interventions in the intensive care unit using machine learning

Contact Info

Product

Resources

About