Objective: Syncope is defined as a sudden loss of consciousness due to cerebral hypoperfusion, with vasovagal syncope (VVS) being the most common form. The Head-Upright Tilt Test (HUTT) is the primary diagnostic tool but is time-consuming and has a suboptimal diagnostic yield. Machine Learning (ML) may improve early syncope prediction, thereby increasing diagnostic efficiency and reducing the burden on patients and healthcare professionals. Methods: We searched PubMed for studies using ML on HUTT data for syncope testing. Extracted data included ML models, input features, performance metrics, preprocessing, and evaluation methods. Study quality was assessed using the STAR-ML checklist. Results: Thirteen studies were included. Commonly used ML algorithms were support vector machines (SVM), neural networks, decision trees, k-nearest neighbor, and logistic regression. Features were derived from Electrocardiogram (ECG), continuous blood pressure (CBP), and transthoracic impedance (TIM). The highest-performing model used an SVM with features from ECG, CBP, and TIM. Conclusions: ML integrated with HUTT signal analysis shows promise for improving diagnostic accuracy and efficiency. SVM models using multimodal features were particularly effective. Significance: This review supports further development of ML-based tools to enhance diagnostic workflows in syncope care, especially for early VVS prediction.

Objective: Myasthenia gravis (MG) is an autoimmune disease leading to fatigable muscle weakness. Extra-ocular and bulbar muscles are most commonly affected. We aimed to investigate whether facial weakness can be quantified automatically and used for diagnosis and disease monitoring. Methods: In this cross-sectional study, we analyzed video recordings of 70 MG patients and 69 healthy controls (HC) with two different methods. Facial weakness was first quantified with facial expression recognition software. Subsequently, a deep learning (DL) computer model was trained for the classification of diagnosis and disease severity using multiple cross-validations on videos of 50 patients and 50 controls. Results were validated using unseen videos of 20 MG patients and 19 HC. Results: Expression of anger (p = 0.026), fear (p = 0.003), and happiness (p < 0.001) was significantly decreased in MG compared to HC. Specific patterns of decreased facial movement were detectable in each emotion. Results of the DL model for diagnosis were as follows: area under the curve (AUC) of the receiver operator curve 0.75 (95% CI 0.65–0.85), sensitivity 0.76, specificity 0.76, and accuracy 76%. For disease severity: AUC 0.75 (95% CI 0.60–0.90), sensitivity 0.93, specificity 0.63, and accuracy 80%. Results of validation, diagnosis: AUC 0.82 (95% CI: 0.67–0.97), sensitivity 1.0, specificity 0.74, and accuracy 87%. For disease severity: AUC 0.88 (95% CI: 0.67–1.0), sensitivity 1.0, specificity 0.86, and accuracy 94%. Interpretation: Patterns of facial weakness can be detected with facial recognition software. Second, this study delivers a ‘proof of concept’ for a DL model that can distinguish MG from HC and classifies disease severity.