METHODS: After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann-Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot.

RESULTS: A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve).

OBJECTIVES: To describe the effects of electrical stimulation (ES) therapy in the 4-week management of two sub-acute spinal cord-injured (SCI) individuals (C7 American Spinal Injury Association Impairment Scale (AIS) B and T9 AIS (B)).

SETTING: University Malaya Medical Centre, Kuala Lumpur, Malaysia.

METHODS: A diagnostic tilt-table test was conducted to confirm the presence of orthostatic hypotension (OH) based on the current clinical definitions. Following initial assessment, subjects underwent 4 weeks of ES therapy 4 times weekly for 1 h per day. Post-tests tilt table challenge, both with and without ES on their rectus abdominis, quadriceps, hamstrings and gastrocnemius muscles, was conducted at the end of the study (week 5). Subjects' blood pressures (BP) and heart rates (HR) were recorded every minute during pre-test and post-tests. Orthostatic symptoms, as well as the maximum tolerance time that the subjects could withstand head up tilt at 60°, were recorded.

RESULTS: Subject A improved his orthostatic symptoms, but did not recover from clinically defined OH based on the 20-min duration requirement. With concurrent ES therapy, 60° head up tilt BP was 89/62 mm Hg compared with baseline BP of 115/71 mm Hg. Subject B fully recovered from OH demonstrated by BP of 105/71 mm Hg during the 60° head up tilt compared with baseline BP of 124/77 mm Hg. Both patients demonstrated longer tolerance time during head up tilt with concomitant ES (subject A: pre-test 4 min, post-test without ES 6 min, post-test with ES 12 min; subject B: pre-test 4 min, post-test without ES 28 min, post-test with ES 60 min).