Tai Chi has been proven effective in preventing falls in older adults, improving the joint function of knee osteoarthritis patients, and improving the balance of stroke survivors. However, the effect of Tai Chi on human gait dynamics is still less understood. Studies conducted in this domain only relied on statistical and clinical measurements on the time-series gait data. In recent years machine learning has proven its ability in recognizing complex patterns from time-series data. In this research work, we have evaluated the performance of several machine learning algorithms in classifying the walking gait of Tai Chi masters (people expert on Tai Chi) from the normal subjects. The study is designed in a longitudinal manner where the Tai Chi naive subjects received 6 months of Tai Chi training and the data was recorded during the initial and follow-up sessions. A total of 57 subjects participated in the experiment among which 27 were Tai Chi masters. We have introduced a gender, BMI-based scaling of the features to mitigate their effects from the gait parameters. A hybrid feature ranking technique has also been proposed for selecting the best features for classification. The research reports 88.17% accuracy and 93.10% ROC AUC values from subject-wise 5-fold cross-validation for the Tai Chi masters' vs normal subjects' walking gait classification for the "Single-task" walking scenarios. We have also got fairly good accuracy for the "Dual-task" walking scenarios (82.62% accuracy and 84.11% ROC AUC values). The results indicate that Tai Chi clearly has an effect on the walking gait dynamics. The findings and methodology of this study could provide preliminary guidance for applying machine learning-based approaches to similar gait kinematics analyses.
The reverse transcription-polymerase chain reaction (RT-PCR) test is considered the current gold standard for the detection of coronavirus disease (COVID-19), although it suffers from some shortcomings, namely comparatively longer turnaround time, higher false-negative rates around 20-25%, and higher cost equipment. Therefore, finding an efficient, robust, accurate, and widely available, and accessible alternative to RT-PCR for COVID-19 diagnosis is a matter of utmost importance. This study proposes a complete blood count (CBC) biomarkers-based COVID-19 detection system using a stacking machine learning (SML) model, which could be a fast and less expensive alternative. This study used seven different publicly available datasets, where the largest one consisting of fifteen CBC biomarkers collected from 1624 patients (52% COVID-19 positive) admitted at San Raphael Hospital, Italy from February to May 2020 was used to train and validate the proposed model. White blood cell count, monocytes (%), lymphocyte (%), and age parameters collected from the patients during hospital admission were found to be important biomarkers for COVID-19 disease prediction using five different feature selection techniques. Our stacking model produced the best performance with weighted precision, sensitivity, specificity, overall accuracy, and F1-score of 91.44%, 91.44%, 91.44%, 91.45%, and 91.45%, respectively. The stacking machine learning model improved the performance in comparison to other state-of-the-art machine learning classifiers. Finally, a nomogram-based scoring system (QCovSML) was constructed using this stacking approach to predict the COVID-19 patients. The cut-off value of the QCovSML system for classifying COVID-19 and Non-COVID patients was 4.8. Six datasets from three different countries were used to externally validate the proposed model to evaluate its generalizability and robustness. The nomogram demonstrated good calibration and discrimination with the area under the curve (AUC) of 0.961 for the internal cohort and average AUC of 0.967 for all external validation cohort, respectively. The external validation shows an average weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 92.02%, 95.59%, 93.73%, 90.54%, and 93.34%, respectively.