Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke

Background. Accurate prediction of clinical impairment in upper-extremity motor function following therapy in chronic stroke patients is a difficult task for clinicians but is key in prescribing appropriate therapeutic strategies. Machine learning is a highly promising avenue with which to improve prediction accuracy in clinical practice. Objectives. The objective was to evaluate the performance of 5 machine learning methods in predicting postintervention upper-extremity motor impairment in chronic stroke patients using demographic, clinical, neurophysiological, and imaging input variables. Methods. A total of 102 patients (female: 31%, age 61 ± 11 years) were included. The upper-extremity Fugl-Meyer Assessment (UE-FMA) was used to assess motor impairment of the upper limb before and after intervention. Elastic net (EN), support vector machines, artificial neural networks, classification and regression trees, and random forest were used to predict postintervention UE-FMA. The performances of methods were compared using cross-validated R². Results. EN performed significantly better than other methods in predicting postintervention UE-FMA using demographic and baseline clinical data (median REN2=0.91,RRF2=0.88,RANN2=0.83,RSVM2=0.79,RCART2=0.70; P < .05). Preintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors. The difference in MT had greater importance than the absence or presence of a motor-evoked potential (MEP) in the affected hemisphere. Conclusion. Machine learning methods may enable clinicians to accurately predict a chronic stroke patient's postintervention UE-FMA. Interhemispheric difference in the MT is an important predictor of chronic stroke patients' response to therapy and, therefore, could be included in prospective studies.

Predicting likelihood of psychological disorders in PlayerUnknown's Battlegrounds (PUBG) players from Asian countries using supervised machine learning

Multiplayer Online Battle Arena (MOBA) has become one of the most popular genre of online video games played by gamers worldwide. Previous studies have exhibited that excessive engagement in games can lead to Internet Gaming Disorder (IGD). Internet Gaming Disorder has been associated with psychological disorders like impulsivity, anxiety and Attention Deficit Hyperactivity Disorder (ADHD). In this study, we propose an approach to use the game and player statistics along with self-esteem measure of a PlayerUnknown's Battlegrounds (PUBG, a MOBA game) player to predict whether he/she suffers from IGD and psychological disorders namely ADHD and Generalized Anxiety Disorder (GAD). We extract the game and player statistics of PUBG players from Asian countries and then run several state of the art supervised machine learning models to predict the occurrence of IGD, ADHD, and GAD. Initial experiments and results show that we are able to predict IGD, ADHD, and GAD with an accuracy of 93.18%, 81.81% and 84.9% respectively. Game statistics of PUBG players show strong positive correlation with IGD and ADHD indicating detrimental effects of MOBA games.

On the Performance of Oversampling Techniques for Class Imbalance Problems

Although over 90 oversampling approaches have been developed in the imbalance learning domain, most of the empirical study and application work are still based on the “classical” resampling techniques. In this paper, several experiments on 19 benchmark datasets are set up to study the efficiency of six powerful oversampling approaches, including both “classical” and new ones. According to our experimental results, oversampling techniques that consider the minority class distribution (new ones) perform better in most cases and RACOG gives the best performance among the six reviewed approaches. We further validate our conclusion on our real-world inspired vehicle datasets and also find applying oversampling techniques can improve the performance by around 10%. In addition, seven data complexity measures are considered for the initial purpose of investigating the relationship between data complexity measures and the choice of resampling techniques. Although no obvious relationship can be abstracted in our experiments, we find F1v value, a measure for evaluating the overlap which most researchers ignore, has a strong negative correlation with the potential AUC value (after resampling).

Development of a Novel Prognostic Model to Predict 6-Month Swallowing Recovery After Ischemic Stroke

Background and Purpose- The aim of this study was to explore clinical and radiological prognostic factors for long-term swallowing recovery in patients with poststroke dysphagia and to develop and validate a prognostic model using a machine learning algorithm. Methods- Consecutive patients (N=137) with acute ischemic stroke referred for swallowing examinations were retrospectively reviewed. Dysphagia was monitored in the 6 months poststroke period and then analyzed using the Kaplan-Meier method and Cox regression model for clinical and radiological factors. Bayesian network models were developed using potential prognostic factors to classify patients into those with good (no need for tube feeding or diet modification for 6 months) and poor (tube feeding or diet modification for 6 months) recovery of swallowing function. Results- Twenty-four (17.5%) patients showed persistent dysphagia for the first 6 months with a mean duration of 65.6 days. The time duration of poststroke dysphagia significantly differed by tube feeding status, clinical dysphagia scale, sex, severe white matter hyperintensities, and bilateral lesions at the corona radiata, basal ganglia, or internal capsule (CR/BG/IC). Among these factors, tube feeding status (P<0.001), bilateral lesions at CR/BG/IC (P=0.001), and clinical dysphagia scale (P=0.042) were significant prognostic factors in a multivariate analysis using Cox regression models. The tree-augmented network classifier, based on 10 factors (sex, lesions at CR, BG/IC, and insula, laterality, anterolateral territory of the brain stem, bilateral lesions at CR/BG/IC, severe white matter hyperintensities, clinical dysphagia scale, and tube feeding status), performed better than other benchmarking classifiers developed in this study. Conclusions- Initial dysphagia severity and bilateral lesions at CR/BG/IC are revealed to be significant prognostic factors for 6-month swallowing recovery. The prediction of 6-month swallowing recovery was feasible based on clinical and radiological factors using the Bayesian network model. We emphasize the importance of bilateral subcortical lesions as prognostic factors that can be utilized to develop prediction models for long-term swallowing recovery.

Predicting High-Risk Prostate Cancer Using Machine Learning Methods

Prostate cancer can be low- or high-risk to the patient’s health. Current screening on the basis of prostate-specific antigen (PSA) levels has a tendency towards both false positives and false negatives, both of which have negative consequences. We obtained a dataset of 35,875 patients from the screening arm of the National Cancer Institute’s Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial. We segmented the data into instances without prostate cancer, instances with low-risk prostate cancer, and instances with high-risk prostate cancer. We developed a pipeline to deal with imbalanced data and proposed algorithms to perform preprocessing on such datasets. We evaluated the accuracy of various machine learning algorithms in predicting high-risk prostate cancer. An accuracy of 91.5% can be achieved by the proposed pipeline, using standard scaling, SVMSMOTE sampling method, and AdaBoost for machine learning. We then evaluated the contribution of rate of change of PSA, age, BMI, and filtration by race to this model’s accuracy. We identified that including the rate of change of PSA and age in our model increased the area under the curve (AUC) of the model by 6.8%, whereas BMI and race had a minimal effect.

Evaluation of performance of drought prediction in Indonesia based on TRMM and MERRA-2 using machine learning methods

East Nusa Tenggara Province is one of the most vulnerable regions in Indonesia to drought. Drought prediction is definitely needed as a mitigation action to minimize the risk of drought. However, a sparse dataset has led to difficulties in accurately predicting future droughts in areas without meteorological stations, and hence a dataset with a finer resolution is required. This research investigates the performance of a 3-month Standardized Precipitation Index (SPI) derived from the Tropical Rainfall Measuring Mission (TRMM) and Modern-Era Retrospective analysis for Research and Applications (MERRA-2) to predict drought. CART and Random Forest are applied as the classification methods. Using several predictors, the analysis finds that CART has lower predictability than Random Forest. The average accuracy of the prediction using Random Forest reaches 100% with an average Area Under Curve (AUC) of about 0.8. The analysis also shows that predictions using the MERRA-2 dataset lead to higher accuracy and AUC than those using the TRMM. Therefore, using the MERRA-2 dataset predicted by Random Forest can be an optimal way to predict drought in East Nusa Tenggara. The methods confirmed that average soil surface temperature (day and night), Multivariate ENSO Index (MEI), Arctic Oscillation Index (AOI) and Normalized Difference Vegetation Index (NDVI) are strong predictors of drought. The performance of CART and Random Forest is improved with the Synthetic Minority Over-Sampling Technique (SMOTE).

The techniques described:

•

translate drought information and predictors of drought into a base classifier that optimizes the AUC;

•

allow drought to be predicted for many grid points efficiently and with high accuracy; and

•

are computationally efficient and easy to implement.