Machine-Learning-Based Rehabilitation Prognosis Prediction in Patients with Ischemic Stroke Using Brainstem Auditory Evoked Potential

Assessment of the Negative Impact of Urban Air Pollution on Population Health Using Machine Learning Method

This study focuses on assessing the level of morbidity among the population of Almaty, Kazakhstan, and investigating its connection with atmospheric air pollution using machine learning algorithms. The use of these algorithms is aimed at analyzing the relationship between air pollution levels and the state of public health, as well as the correlations between COVID-19 infection and the development of respiratory diseases. This study analyzes the respiratory diseases of the population of Almaty and the level of air pollution as a result of suspended particles for the period of 2017-2022. The study includes recommendations to reduce harmful emissions into the atmosphere using machine learning methods. The results of the study show that air pollution is a critical factor affecting the increase in the number of diseases of the respiratory system. The study recommends taking measures to reduce air pollution and improve air quality in order to prevent the development of chronic respiratory diseases. The study offers recommendations to industrial enterprises, traffic management organizations, thermal power plants, the Department of Environmental Protection, and local executive bodies in order to reduce respiratory diseases among the population.

A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke

Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of Ft-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics

Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.

Novel Survival Features Generated by Clinical Text Information and Radiomics Features May Improve the Prediction of Ischemic Stroke Outcome

Background: Accurate outcome prediction is of great clinical significance in customizing personalized treatment plans, reducing the situation of poor recovery, and objectively and accurately evaluating the treatment effect. This study intended to evaluate the performance of clinical text information (CTI), radiomics features, and survival features (SurvF) for predicting functional outcomes of patients with ischemic stroke. Methods: SurvF was constructed based on CTI and mRS radiomics features (mRSRF) to improve the prediction of the functional outcome in 3 months (90-day mRS). Ten machine learning models predicted functional outcomes in three situations (2-category, 4-category, and 7-category) using seven feature groups constructed by CTI, mRSRF, and SurvF. Results: For 2-category, ALL (CTI + mRSRF+ SurvF) performed best, with an mAUC of 0.884, mAcc of 0.864, mPre of 0.877, mF1 of 0.86, and mRecall of 0.864. For 4-category, ALL also achieved the best mAuc of 0.787, while CTI + SurvF achieved the best score with mAcc = 0.611, mPre = 0.622, mF1 = 0.595, and mRe-call = 0.611. For 7-category, CTI + SurvF performed best, with an mAuc of 0.788, mPre of 0.519, mAcc of 0.529, mF1 of 0.495, and mRecall of 0.47. Conclusions: The above results indicate that mRSRF + CTI can accurately predict functional outcomes in ischemic stroke patients with proper machine learning models. Moreover, combining SurvF will improve the prediction effect compared with the original features. However, limited by the small sample size, further validation on larger and more varied datasets is necessary.

Machine Learning Models for Predicting the Occurrence of Respiratory Diseases Using Climatic and Air-Pollution Factors

Objectives

Because climatic and air-pollution factors are known to influence the occurrence of respiratory diseases, we used these factors to develop machine learning models for predicting the occurrence of respiratory diseases.

Methods

We obtained the daily number of respiratory disease patients in Seoul. We used climatic and air-pollution factors to predict the daily number of patients treated for respiratory diseases per 10,000 inhabitants. We applied the relief-based feature selection algorithm to evaluate the importance of feature selection. We used the gradient boosting and Gaussian process regression (GPR) methods, respectively, to develop two different prediction models. We also employed the holdout cross-validation method, in which 75% of the data was used to train the model, and the remaining 25% was used to test the trained model. We determined the estimated number of respiratory disease patients by applying the developed prediction models to the test set. To evaluate the performance of each model, we calculated the coefficient of determination (R²) and the root mean square error (RMSE) between the original and estimated numbers of respiratory disease patients. We used the Shapley Additive exPlanations (SHAP) approach to interpret the estimated output of each machine learning model.

Results

Features with negative weights in the relief-based algorithm were excluded. When applying gradient boosting to unseen test data, R² and RMSE were 0.68 and 13.8, respectively. For GPR, the R² and RMSE were 0.67 and 13.9, respectively. SHAP analysis showed that reductions in average temperature, daylight duration, average humidity, sulfur dioxide (SO₂), total solar insolation amount, and temperature difference increased the number of respiratory disease patients, whereas increases in atmospheric pressure, carbon monoxide (CO), and particulate matter ≤2.5 μm in aerodynamic diameter (PM_2.5) increased the number of respiratory disease patients.

Conclusion

We successfully developed models for predicting the occurrence of respiratory diseases using climatic and air-pollution factors. These models could evolve into public warning systems.

Clinical evaluation of acute necrotizing encephalopathy in children

OBJECTIVE

Acute necrotizing encephalopathy (ANE) is a rare but severe encephalopathy and is associated with a high morbidity and mortality. We aimed to analyze and compare the clinical features and predictive indicators of pediatric ANE.

MATERIALS AND METHODS

This retrospective study included children with ANE diagnosed at Guangzhou Women and Children's Medical Center between November 2018 and January 2020. Pediatric patients' information, including clinical characteristics, laboratory tests, neuroelectrophysiology and brain magnetic resonance imaging (MRI) findings, MRI score, brainstem auditory evoked potential (BAEP) grades, ANE severity scores (ANE-SS), and modified Rankin scale (mRS), were collected.

RESULTS

Twelve ANE patients were included. Among them, one patient (8.3%) died from brainstem dysfunction, one (8.3%) recovered and 10 (83.3%) experienced neurological sequelae. All patients had an initial viral infection and neurological symptoms such as acute disturbance of consciousness (ADOC) or seizure, and the interval from onset of the disease to neurological manifestations was 3 (1.25-3) days. MRI score-I ranged from 1 to 3 (1.8 ± 0.7), MRI score-II ranged from 1 to 4 (2.5 ± 1.1). ANE-SS varied from 1 to 6 (3.9 ± 1.3). The scores of mRS were from 0 to 6 (2.9 ± 1.7). Higher MRI score were associated with worse outcomes, while the BAEP grade and ANE-SS score were not significantly associated with mRS.

CONCLUSION

ANE is a severe encephalopathy syndrome with rapid progression, resulting in serious neurological sequelae. Compared with BAEP grade and ANE-SS, brain MRI shows more comprehensive advantages in predicting the prognosis of ANE patients. More in-depth research and better indicators are still needed to support the evaluation and treatment of ANE.

Prognostic Factors in Neurorehabilitation of Stroke: A Comparison among Regression, Neural Network, and Cluster Analyses

There is a large body of literature reporting the prognostic factors for a positive outcome of neurorehabilitation performed in the subacute phase of stroke. Despite the recent development of algorithms based on neural networks or cluster analysis for the identification of these prognostic factors, the literature lacks a rigorous comparison among classical regression, neural network, and cluster analysis. Moreover, the three methods have rarely been tested on a sample independent from that in which prognostic factors have been identified. This study aims at providing this comparison on a wide sample of data (1522 patients) and testing the results on an independent sample (1000 patients) using 30 variables. The accuracy was similar among regression, neural network, and cluster analyses on the analyzed sample (76.6%, 74%, and 76.1%, respectively), but on the test sample, the accuracy of neural network decreased (70.1%). The three models agreed in identifying older age, severe impairment, unilateral spatial neglect, and total anterior circulation infarcts as important prognostic factors. The binary regression analysis also provided solid results in the test sample, especially in terms of specificity (81.8%). Cluster analysis also showed a high sensitivity in the test sample (82.6%) and allowed a meaningful easy-to-use classification tree to be obtained.