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

Machine-learning-based prediction by stacking ensemble strategy for surgical outcomes in patients with degenerative cervical myelopathy

BACKGROUND

Machine learning (ML) is extensively employed for forecasting the outcome of various illnesses. The objective of the study was to develop ML based classifiers using a stacking ensemble strategy to predict the Japanese Orthopedic Association (JOA) recovery rate for patients with degenerative cervical myelopathy (DCM).

METHODS

A total of 672 patients with DCM were included in the study and labeled with JOA recovery rate by 1-year follow-up. All data were collected during 2012-2023 and were randomly divided into training and testing (8:2) sub-datasets. A total of 91 initial ML classifiers were developed, and the top 3 initial classifiers with the best performance were further stacked into an ensemble classifier with a supported vector machine (SVM) classifier. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicted outcome was the JOA recovery rate.

RESULTS

By applying an ensemble learning strategy (e.g., stacking), the accuracy of the ML classifier improved following combining three widely used ML models (e.g., RFE-SVM, EmbeddingLR-LR, and RFE-AdaBoost). Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top 3 initial classifiers varied a lot in predicting JOA recovery rate in DCM patients.

CONCLUSIONS

The ensemble classifiers successfully predict the JOA recovery rate in DCM patients, which showed a high potential for assisting physicians in managing DCM patients and making full use of medical resources.

Predicting the Outcome and Survival of Patients with Spinal Cord Injury Using Machine Learning Algorithms: A Systematic Review

BACKGROUND

Spinal cord injury (SCI) is a significant public health issue, leading to physical, psychological, and social complications. Machine learning (ML) algorithms have shown potential in diagnosing and predicting the functional and neurologic outcomes of subjects with SCI. ML algorithms can predict scores for SCI classification systems and accurately predict outcomes by analyzing large amounts of data. This systematic review aimed to examine the performance of ML algorithms for diagnosing and predicting the outcomes of subjects with SCI.

METHODS

The literature was comprehensively searched for the pertinent studies from inception to May 25, 2023. Therefore, electronic databases of PubMed, Embase, Scopus, and Web of Science were systematically searched with individual search syntax.

RESULTS

A total of 9424 individuals diagnosed with SCI across multiple studies were analyzed. Among the 21 studies included, 5 specifically aimed to evaluate diagnostic accuracy, while the remaining 16 focused on exploring prognostic factors or management strategies.

CONCLUSIONS

ML and deep learning (DL) have shown great potential in various aspects of SCI. ML and DL algorithms have been employed multiple times in predicting and diagnosing patients with SCI. While there are studies on diagnosing acute SCI using DL algorithms, further research is required in this area.

Prediction of gait recovery using machine learning algorithms in patients with spinal cord injury

With advances in artificial intelligence, machine learning (ML) has been widely applied to predict functional outcomes in clinical medicine. However, there has been no attempt to predict walking ability after spinal cord injury (SCI) based on ML. In this situation, the main purpose of this study was to predict gait recovery after SCI at discharge from an acute rehabilitation facility using various ML algorithms. In addition, we explored important variables that were related to the prognosis. Finally, we attempted to suggest an ML-based decision support system (DSS) for predicting gait recovery after SCI. Data were collected retrospectively from patients with SCI admitted to an acute rehabilitation facility between June 2008 to December 2021. Linear regression analysis and ML algorithms (random forest [RF], decision tree [DT], and support vector machine) were used to predict the functional ambulation category at the time of discharge (FAC_DC) in patients with traumatic or non-traumatic SCI (n = 353). The independent variables were age, sex, duration of acute care and rehabilitation, comorbidities, neurological information entered into the International Standards for Neurological Classification of SCI worksheet, and somatosensory-evoked potentials at the time of admission to the acute rehabilitation facility. In addition, the importance of variables and DT-based DSS for FAC_DC was analyzed. As a result, RF and DT accurately predicted the FAC_DC measured by the root mean squared error. The root mean squared error of RF and the DT were 1.09 and 1.24 for all participants, 1.20 and 1.06 for those with trauma, and 1.12 and 1.03 for those with non-trauma, respectively. In the analysis of important variables, the initial FAC was found to be the most influential factor in all groups. In addition, we could provide a simple DSS based on strong predictors such as the initial FAC, American Spinal Injury Association Impairment Scale grades, and neurological level of injury. In conclusion, we provide that ML can accurately predict gait recovery after SCI for the first time. By focusing on important variables and DSS, we can guide early prognosis and establish personalized rehabilitation strategies in acute rehabilitation hospitals.

Early Prognostication of Critical Patients With Spinal Cord Injury: A Machine Learning Study With 1485 Cases

STUDY DESIGN

A retrospective case-series.

OBJECTIVE

The study aims to use machine learning to predict the discharge destination of spinal cord injury (SCI) patients in the intensive care unit.

SUMMARY OF BACKGROUND DATA

Prognostication following SCI is vital, especially for critical patients who need intensive care.

PATIENTS AND METHODS

Clinical data of patients diagnosed with SCI were extracted from a publicly available intensive care unit database. The first recorded data of the included patients were used to develop a total of 98 machine learning classifiers, seeking to predict discharge destination (eg, death, further medical care, home, etc.). The microaverage area under the curve (AUC) was the main indicator to assess discrimination. The best average-AUC classifier and the best death-sensitivity classifier were integrated into an ensemble classifier. The discrimination of the ensemble classifier was compared with top death-sensitivity classifiers and top average-AUC classifiers. In addition, prediction consistency and clinical utility were also assessed.

RESULTS

A total of 1485 SCI patients were included. The ensemble classifier had a microaverage AUC of 0.851, which was only slightly inferior to the best average-AUC classifier ( P =0.10). The best average-AUC classifier death sensitivity was much lower than that of the ensemble classifier. The ensemble classifier had a death sensitivity of 0.452, which was inferior to the top 8 death-sensitivity classifiers, whose microaverage AUC were inferior to the ensemble classifier ( P <0.05). In addition, the ensemble classifier demonstrated a comparable Brier score and superior net benefit in the DCA when compared with the performance of the origin classifiers.

CONCLUSIONS

The ensemble classifier shows an overall superior performance in predicting discharge destination, considering discrimination ability, prediction consistency, and clinical utility. This classifier system may aid in the clinical management of critical SCI patients in the early phase following injury.

LEVEL OF EVIDENCE

Level 3.

The Predictive Abilities of Machine Learning Algorithms in Patients with Thoracolumbar Spinal Cord Injuries

OBJECTIVES

The goal of this study is to implement machine learning (ML) algorithms to predict mortality, non-home discharge, prolonged length of stay (LOS), prolonged length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with thoracolumbar spinal cord injury, while creating a publicly accessible online tool.

METHODS

The American College of Surgeons Trauma Quality Program database was used to identify patients with thoracolumbar spinal cord injury. Feature selection was performed with the Least Absolute Shrinkage and Selection Operator algorithm. Five ML algorithms, including TabPFN, TabNet, XGBoost, LightGBM, and Random Forest, were used along with the Optuna optimization library for hyperparameter tuning.

RESULTS

A total of 147,819 patients were included in the analysis. For each outcome, we determined the best model for deployment in our web application based on the area under the receiver operating characteristic (AUROC) values. The top performing algorithms were as follows: LightGBM for mortality with an AUROC of 0.885, TabPFN for non-home discharge with an AUROC of 0.801, LightGBM for prolonged LOS with an AUROC of 0.673, Random Forest for prolonged ICU-LOS with an AUROC of 0.664, and LightGBM for major complications with an AUROC of 0.73.

CONCLUSIONS

ML models demonstrate good predictive ability for in-hospital mortality and non-home discharge, fair predictive ability for major complications and prolonged ICU-LOS, but poor predictive ability for prolonged LOS. We have developed a web application that allows these models to be accessed.

Studying missingness in spinal cord injury data: challenges and impact of data imputation

BACKGROUND

In the last decades, medical research fields studying rare conditions such as spinal cord injury (SCI) have made extensive efforts to collect large-scale data. However, most analysis methods rely on complete data. This is particularly troublesome when studying clinical data as they are prone to missingness. Often, researchers mitigate this problem by removing patients with missing data from the analyses. Less commonly, imputation methods to infer likely values are applied.

OBJECTIVE

Our objective was to study how handling missing data influences the results reported, taking the example of SCI registries. We aimed to raise awareness on the effects of missing data and provide guidelines to be applied for future research projects, in SCI research and beyond.

METHODS

Using the Sygen clinical trial data (n = 797), we analyzed the impact of the type of variable in which data is missing, the pattern according to which data is missing, and the imputation strategy (e.g. mean imputation, last observation carried forward, multiple imputation).

RESULTS

Our simulations show that mean imputation may lead to results strongly deviating from the underlying expected results. For repeated measures missing at late stages (> = 6 months after injury in this simulation study), carrying the last observation forward seems the preferable option for the imputation. This simulation study could show that a one-size-fit-all imputation strategy falls short in SCI data sets.

CONCLUSIONS

Data-tailored imputation strategies are required (e.g., characterisation of the missingness pattern, last observation carried forward for repeated measures evolving to a plateau over time). Therefore, systematically reporting the extent, kind and decisions made regarding missing data will be essential to improve the interpretation, transparency, and reproducibility of the research presented.

Precision medicine for traumatic cervical spinal cord injuries: accessible and interpretable machine learning models to predict individualized in-hospital outcomes

BACKGROUND CONTEXT

A traumatic spinal cord injury (SCI) can cause temporary or permanent motor and sensory impairment, leading to serious short and long-term consequences that can result in significant morbidity and mortality. The cervical spine is the most commonly affected area, accounting for about 60% of all traumatic SCI cases.

PURPOSE

This study aims to employ machine learning (ML) algorithms to predict various outcomes, such as in-hospital mortality, nonhome discharges, extended length of stay (LOS), extended length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with cervical SCI (cSCI).

STUDY DESIGN

Our study was a retrospective machine learning classification study aiming to predict the outcomes of interest, which were binary categorical variables, in patients diagnosed with cSCI.

PATIENT SAMPLE

The data for this study were obtained from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database, which was queried to identify patients who suffered from cSCI between 2019 and 2021.

OUTCOME MEASURES

The outcomes of interest of our study were in-hospital mortality, nonhome discharges, prolonged LOS, prolonged ICU-LOS, and major complications. The study evaluated the models' performance using both graphical and numerical methods. The receiver operating characteristic (ROC) and precision-recall curves (PRC) were used to assess model performance graphically. Numerical evaluation metrics included AUROC, balanced accuracy, weighted area under PRC (AUPRC), weighted precision, and weighted recall.

METHODS

The study employed data from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database to identify patients with cSCI. Four ML algorithms, namely XGBoost, LightGBM, CatBoost, and Random Forest, were utilized to develop predictive models. The most effective models were then incorporated into a publicly available web application designed to forecast the outcomes of interest.

RESULTS

There were 71,661 patients included in the analysis for the outcome mortality, 67,331 for the outcome nonhome discharges, 76,782 for the outcome prolonged LOS, 26,615 for the outcome prolonged ICU-LOS, and 72,132 for the outcome major complications. The algorithms exhibited an AUROC value range of 0.78 to 0.839 for in-hospital mortality, 0.806 to 0.815 for nonhome discharges, 0.679 to 0.742 for prolonged LOS, 0.666 to 0.682 for prolonged ICU-LOS, and 0.637 to 0.704 for major complications. An open access web application was developed as part of the study, which can generate predictions for individual patients based on their characteristics.

CONCLUSIONS

Our study suggests that ML models can be valuable in assessing risk for patients with cervical cSCI and may have considerable potential for predicting outcomes during hospitalization. ML models demonstrated good predictive ability for in-hospital mortality and nonhome discharges, fair predictive ability for prolonged LOS, but poor predictive ability for prolonged ICU-LOS and major complications. Along with these promising results, the development of a user-friendly web application that facilitates the integration of these models into clinical practice is a significant contribution of this study. The product of this study may have significant implications in clinical settings to personalize care, anticipate outcomes, facilitate shared decision making and informed consent processes for cSCI patients.

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

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.

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

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.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00719-2.

Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery within 24 h after injury

We aimed to develop a machine learning (ML) model for predicting the neurological outcomes of cervical spinal cord injury (CSCI). We retrospectively analyzed 135 patients with CSCI who underwent surgery within 24 h after injury. Patients were assessed with the American Spinal Injury Association Impairment Scale (AIS; grades A to E) 6 months after injury. A total of 34 features extracted from demographic variables, surgical factors, laboratory variables, neurological status, and radiological findings were analyzed. The ML model was created using Light GBM, XGBoost, and CatBoost. We evaluated Shapley Additive Explanations (SHAP) values to determine the variables that contributed most to the prediction models. We constructed multiclass prediction models for the five AIS grades and binary classification models to predict more than one-grade improvement in AIS 6 months after injury. Of the ML models used, CatBoost showed the highest accuracy (0.800) for the prediction of AIS grade and the highest AUC (0.90) for predicting improvement in AIS. AIS grade at admission, intramedullary hemorrhage, longitudinal extent of intramedullary T2 hyperintensity, and HbA1c were identified as important features for these prediction models. The ML models successfully predicted neurological outcomes 6 months after injury following urgent surgery in patients with CSCI.

Inhibition of IL1R1 or CASP4 attenuates spinal cord injury through ameliorating NLRP3 inflammasome-induced pyroptosis

Spinal cord injury (SCI) is a devastating trauma characterized by serious neuroinflammation and permanent neurological dysfunction. However, the molecular mechanism of SCI remains unclear, and few effective medical therapies are available at present. In this study, multiple bioinformatics methods were used to screen out novel targets for SCI, and the mechanism of these candidates during the progression of neuroinflammation as well as the therapeutic effects were both verified in a rat model of traumatic SCI. As a result, CASP4, IGSF6 and IL1R1 were identified as the potential diagnostic and therapeutic targets for SCI by computational analysis, which were enriched in NF-κB and IL6-JAK-STATA3 signaling pathways. In the injured spinal cord, these three signatures were up-regulated and closely correlated with NLRP3 inflammasome formation and gasdermin D (GSDMD) -induced pyroptosis. Intrathecal injection of inhibitors of IL1R1 or CASP4 improved the functional recovery of SCI rats and decreased the expression of these targets and inflammasome component proteins, such as NLRP3 and GSDMD. This treatment also inhibited the pp65 activation into the nucleus and apoptosis progression. In conclusion, our findings of the three targets shed new light on the pathogenesis of SCI, and the use of immunosuppressive agents targeting these proteins exerted anti-inflammatory effects against spinal cord inflammation by inhibiting NF-kB and NLRP3 inflammasome activation, thus blocking GSDMD -induced pyroptosis and immune activation.