Daniel C. Pichler

Background and Clinical Significance: When diverse clinical presentations coincide with complex laboratory findings, particularly in older adults, the diagnostic process can be especially challenging. Case Presentation: We report the case of a geriatric patient who was hospitalized with initial gastrointestinal and respiratory symptoms, followed by progressive chest pain and profound weakness, accompanied by elevated transaminases, troponin elevation, and hyponatremia, initially suggesting multiple competing diagnostic entities. During the clinical course, the patient developed neurological symptoms. Ultimately, careful history-taking, including detailed exposure assessment, raised suspicion for tick-borne encephalitis, which was subsequently confirmed by serological testing. Conclusions: This case highlights the diagnostic complexity of tick-borne encephalitis in older adults, where atypical and multisystem presentations may obscure the underlying etiology and delay recognition of a neuroinfectious disease.

Patients with advanced Parkinson’s disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.