Classification of vasovagal syncope from physiological signals on tilt table testing.

BACKGROUND: The diagnostic test for vasovagal syncope (VVS), the most common cause of syncope is head-up tilt test (HUTT) assessment. During the test, subjects experienced clinical symptoms such as nausea, sweating, pallor, the feeling of palpitations, being on the verge of passing out, and fainting. The study's goal is to develop an algorithm to classify VVS patients based on physiological signals blood pressure (BP) and electrocardiography (ECG) obtained from the HUTT. 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). CONCLUSIONS: The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.

Potentially inappropriate prescribing in a falls clinic using the STOPP and START criteria.

Background Potentially inappropriate prescribing is increasingly common in older patients with falls. However, published indicators to assess inappropriate prescribing remains unestablished in many countries. Objective This study determined the burden and profile of potentially inappropriate prescribing among patients attending a falls clinic using the STOPP/START criteria and evaluated the factors for falls potentially associated to inappropriate prescribing. Setting University of Malaya Medical Centre Falls Clinic. Method Data of individuals aged ≥ 65 years referred to the falls and syncope clinic were extracted from the falls registry. Potentially inappropriate prescribing was determined with the STOPP/START version 2 criteria. The relationship between potentially inappropriate prescribing with polypharmacy (≥ 5 medications), comorbidities and clinical variables were determined using Pearson's chi-square and potential confounders adjusted for with multivariate regression. Main outcome measure Potentially inappropriate medicines and/or omitted medicines using STOPP/START criteria. Results Data from 421 individuals, aged 77.8 ± 6.7 years and 53.4% women, were included. Potentially inappropriate prescribing was present in 311 (73.9%). Potentially inappropriate medicines use accounted for 84.6% of the 325 prescriptions. 361/659 instances (54.8%) were falls-risk-increasing drugs, with vasodilators (49.3%) being the main potentially inappropriate medicine identified. Of the 177/421 with polypharmacy, 169/177 (95.5%) were exposed to ≥ one potentially inappropriate medicine. 129 instances of potentially omitted medicines were observed in 109 prescriptions (25.9%). Conclusion STOPP/START criteria are useful to identify potentially inappropriate prescribing at the falls and syncope clinic. This finding has important implications for medication review strategies at falls clinic. Future research should determine whether identifying potentially inappropriate prescribing may reduce adverse falls outcomes among patients in this setting.