Exploring novel algorithms for atrial fibrillation detection by driving graduate level education in medical machine learning.

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

YouTube Videos on Parkinson's Disease are a Relevant Source of Patient Information.

BACKGROUND: Parkinson's disease (PD) is the most frequent movement disorder. Patients access YouTube, one of the largest video databases in the world, to retrieve health-related information increasingly often. OBJECTIVE: We aimed to identify high-quality publishers, so-called "channels" that can be recommended to patients. We hypothesized that the number of views and the number of uploaded videos were indicators for the quality of the information given by a video on PD. METHODS: YouTube was searched for 8 combinations of search terms that included "Parkinson" in German. For each term, the first 100 search results were analyzed for source, date of upload, number of views, numbers of likes and dislikes, and comments. The view ratio (views / day) and the likes ratio (likes * 100 / [likes + dislikes]) were determined to calculate the video popularity index (VPI). The global quality score (GQS) and title - content consistency index (TCCI) were assessed in a subset of videos. RESULTS: Of 800 search results, 251 videos met the inclusion criteria. The number of views or the publisher category were not indicative of higher quality video content. The number of videos uploaded by a channel was the best indicator for the quality of video content. CONCLUSION: The quality of YouTube videos relevant for PD patients is increased in channels with a high number of videos on the topic. We identified three German channels that can be recommended to PD patients who prefer video over written content.

A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients.

Infrared thermography for camera-based skin temperature measurement is increasingly used in medical practice, e.g., to detect fevers and infections, such as recently in the COVID-19 pandemic. This contactless method is a promising technology to continuously monitor the vital signs of patients in clinical environments. In this study, we investigated both skin temperature trend measurement and the extraction of respiration-related chest movements to determine the respiratory rate using low-cost hardware in combination with advanced algorithms. In addition, the frequency of medical examinations or visits to the patients was extracted. We implemented a deep learning-based algorithm for real-time vital sign extraction from thermography images. A clinical trial was conducted to record data from patients on an intensive care unit. The YOLOv4-Tiny object detector was applied to extract image regions containing vital signs (head and chest). The infrared frames were manually labeled for evaluation. Validation was performed on a hold-out test dataset of 6 patients and revealed good detector performance (0.75 intersection over union, 0.94 mean average precision). An optical flow algorithm was used to extract the respiratory rate from the chest region. The results show a mean absolute error of 2.69 bpm. We observed a computational performance of 47 fps on an NVIDIA Jetson Xavier NX module for YOLOv4-Tiny, which proves real-time capability on an embedded GPU system. In conclusion, the proposed method can perform real-time vital sign extraction on a low-cost system-on-module and may thus be a useful method for future contactless vital sign measurements.