TY - JOUR A1 - Rigamonti, Lia A1 - Estel, Katharina A1 - Gehlen, Tobias A1 - Wolfarth, Bernd A1 - Lawrence, James B. A1 - Back, David A. T1 - Use of artificial intelligence in sports medicine BT - a report of 5 fictional cases JF - BMC Sports Science, Medicine & Rehabilitation N2 - Background Artificial intelligence (AI) is one of the most promising areas in medicine with many possibilities for improving health and wellness. Already today, diagnostic decision support systems may help patients to estimate the severity of their complaints. This fictional case study aimed to test the diagnostic potential of an AI algorithm for common sports injuries and pathologies. Methods Based on a literature review and clinical expert experience, five fictional “common” cases of acute, and subacute injuries or chronic sport-related pathologies were created: Concussion, ankle sprain, muscle pain, chronic knee instability (after ACL rupture) and tennis elbow. The symptoms of these cases were entered into a freely available chatbot-guided AI app and its diagnoses were compared to the pre-defined injuries and pathologies. Results A mean of 25–36 questions were asked by the app per patient, with optional explanations of certain questions or illustrative photos on demand. It was stressed, that the symptom analysis would not replace a doctor’s consultation. A 23-yr-old male patient case with a mild concussion was correctly diagnosed. An ankle sprain of a 27-yr-old female without ligament or bony lesions was also detected and an ER visit was suggested. Muscle pain in the thigh of a 19-yr-old male was correctly diagnosed. In the case of a 26-yr-old male with chronic ACL instability, the algorithm did not sufficiently cover the chronic aspect of the pathology, but the given recommendation of seeing a doctor would have helped the patient. Finally, the condition of the chronic epicondylitis in a 41-yr-old male was correctly detected. Conclusions All chosen injuries and pathologies were either correctly diagnosed or at least tagged with the right advice of when it is urgent for seeking a medical specialist. However, the quality of AI-based results could presumably depend on the data-driven experience of these programs as well as on the understanding of their users. Further studies should compare existing AI programs and their diagnostic accuracy for medical injuries and pathologies. KW - Artificial intelligence KW - App KW - Sport medicine KW - Orthopedics KW - Pathologies Y1 - 2020 U6 - https://doi.org/10.1186/s13102-021-00243-x SN - 2052-1847 VL - 13 PB - BioMed Central CY - London ER - TY - GEN A1 - Rigamonti, Lia A1 - Estel, Katharina A1 - Gehlen, Tobias A1 - Wolfarth, Bernd A1 - Lawrence, James B. A1 - Back, David A. T1 - Use of artificial intelligence in sports medicine BT - a report of 5 fictional cases T2 - Postprints der Universität Potsdam : Humanwissenschaftliche Reihe N2 - Background Artificial intelligence (AI) is one of the most promising areas in medicine with many possibilities for improving health and wellness. Already today, diagnostic decision support systems may help patients to estimate the severity of their complaints. This fictional case study aimed to test the diagnostic potential of an AI algorithm for common sports injuries and pathologies. Methods Based on a literature review and clinical expert experience, five fictional “common” cases of acute, and subacute injuries or chronic sport-related pathologies were created: Concussion, ankle sprain, muscle pain, chronic knee instability (after ACL rupture) and tennis elbow. The symptoms of these cases were entered into a freely available chatbot-guided AI app and its diagnoses were compared to the pre-defined injuries and pathologies. Results A mean of 25–36 questions were asked by the app per patient, with optional explanations of certain questions or illustrative photos on demand. It was stressed, that the symptom analysis would not replace a doctor’s consultation. A 23-yr-old male patient case with a mild concussion was correctly diagnosed. An ankle sprain of a 27-yr-old female without ligament or bony lesions was also detected and an ER visit was suggested. Muscle pain in the thigh of a 19-yr-old male was correctly diagnosed. In the case of a 26-yr-old male with chronic ACL instability, the algorithm did not sufficiently cover the chronic aspect of the pathology, but the given recommendation of seeing a doctor would have helped the patient. Finally, the condition of the chronic epicondylitis in a 41-yr-old male was correctly detected. Conclusions All chosen injuries and pathologies were either correctly diagnosed or at least tagged with the right advice of when it is urgent for seeking a medical specialist. However, the quality of AI-based results could presumably depend on the data-driven experience of these programs as well as on the understanding of their users. Further studies should compare existing AI programs and their diagnostic accuracy for medical injuries and pathologies. T3 - Zweitveröffentlichungen der Universität Potsdam : Humanwissenschaftliche Reihe - 711 KW - Artificial intelligence KW - App KW - Sport medicine KW - Orthopedics KW - Pathologies Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-515528 SN - 1866-8364 ER - TY - THES A1 - Rigamonti, Lia T1 - Use of digital media for remote instruction in exercise sciences education and research N2 - To grant high-quality evidence-based research in the field of exercise sciences, it is often necessary for various institutions to collaborate over longer distances and internationally. Here, not only with regard to the recent COVID-19-pandemic, digital means provide new options for remote scientific exchanges. This thesis is meant to analyse and test digital opportunities to support the dissemination of knowledge and instruction of investigators about defined examination protocols in an international multi-center context. The project consisted of three studies. The first study, a questionnaire-based survey, aimed at learning about the opinions and preferences of digital learning or social media among students of sport science faculties in two universities each in Germany, the UK and Italy. Based on these findings, in a second study, an examination video of an ultrasound determination of the intima-media-thickness and diameter of an artery was distributed by a messenger app to doctors and nursing personnel as simulated investigators and efficacy of the test setting was analysed. Finally, a third study integrated the use of an augmented reality device for direct remote supervision of the same ultrasound examinations in a long-distance international setting with international experts from the fields of engineering and sports science and later remote supervision of augmented reality equipped physicians performing a given task. The first study with 229 participating students revealed a high preference for YouTube to receive video-based knowledge as well as a preference for using WhatsApp and Facebook for peer-to-peer contacts for learning purposes and to exchange and discuss knowledge. In the second study, video-based instructions send by WhatsApp messenger showed high approval of the setup in both study groups, one with doctors familiar with the use of ultrasound technology as well as one with nursing staff who were not familiar with the device, with similar results in overall time of performance and the measurements of the femoral arteries. In the third and final study, experts from different continents were connected remotely to the examination site via an augmented reality device with good transmission quality. The remote supervision to doctors ́ examination produced a good interrater correlation. Experiences with the augmented reality-based setting were rated as highly positive by the participants. Potential benefits of this technique were seen in the fields of education, movement analysis, and supervision. Concluding, the findings of this thesis were able to suggest modern and addressee- centred digital solutions to enhance the understanding of given examinations techniques of potential investigators in exercise science research projects. Head-mounted augmented reality devices have a special value and may be recommended for collaborative research projects with physical examination–based research questions. While the established setting should be further investigated in prospective clinical studies, digital competencies of future researchers should already be enhanced during the early stages of their education. N2 - Um qualitativ hochwertige, evidenzbasierte Forschung im Bereich der Bewegungswissenschaften zu gewährleisten, ist es oft notwendig, dass verschiedene Einrichtungen über größere Entfernungen und international zusammenarbeiten. Hier bieten digitale Mittel, nicht nur im Hinblick auf die aktuelle COVID-19-Pandemie, neue Möglichkeiten des wissenschaftlichen Austauschs aus der Ferne. In dieser Arbeit sollen digitale Möglichkeiten zur Unterstützung der Wissensverbreitung und der Instruktion von Untersuchern über definierte Untersuchungsprotokolle in einem internationalen multizentrischen Kontext analysiert und getestet werden. Das Projekt bestand aus drei Studien. Die erste Studie, eine fragebogenbasierte Umfrage, zielte darauf ab, die Meinungen und Präferenzen von Studierenden sportwissenschaftlicher Fakultäten an je zwei Universitäten in Deutschland, Großbritannien und Italien in Bezug auf digitales Lernen oder soziale Medien zu erfahren. Darauf aufbauend wurde in einer zweiten Studie ein Untersuchungsvideo einer Ultraschallbestimmung der Intima-Media-Dicke und des Durchmessers einer Arterie mittels einer Messenger-App an Ärzt*innen und Pflegepersonal als simulierte Untersucher verteilt und die Wirksamkeit des Testsettings analysiert. Schließlich wurde in einer dritten Studie die Verwendung eines Augmented-Reality-Geräts zur direkten Fernüberwachung derselben Ultraschalluntersuchungen in einem internationalen Umfeld mit internationalen Experten aus den Bereichen Ingenieurwesen und Sportwissenschaft und später zur Fernüberwachung von mit Augmented Reality ausgestatteten Ärzt*innen bei der Durchführung einer bestimmten Aufgabe integriert. Die erste Studie mit 229 teilnehmenden Studierenden ergab eine hohe Präferenz für YouTube, um videobasiertes Wissen zu erhalten, sowie eine Präferenz für die Nutzung von WhatsApp und Facebook für Peer-to-Peer-Kontakte zu Lernzwecken und zum Austausch und zur Diskussion von Wissen. In der zweiten Studie zeigten videobasierte Anleitungen, die per WhatsApp-Messenger versandt wurden, eine hohe Akzeptanz in beiden Studiengruppen, sowohl bei Ärzt*innen, die mit der Anwendung der Ultraschalltechnologie vertraut waren, als auch bei dem Pflegepersonal, das mit dem Gerät nicht vertraut war, mit ähnlichen Ergebnissen bei der Gesamtdurchführungszeit und den Messungen der Oberschenkelarterien. In der dritten und letzten Studie wurden Experten aus verschiedenen Kontinenten über ein Augmented-Reality-Gerät mit guter Übertragungsqualität aus der Ferne mit dem Untersuchungsort verbunden. Die Fernüberwachung der ärztlichen Untersuchung ergab eine gute Interrater-Korrelation. Die Erfahrungen mit dem Augmented-Reality-basierten Setting wurden von den Teilnehmenden als sehr positiv bewertet. Potenzielle Vorteile dieser Technik wurden in den Bereichen Ausbildung, Bewegungsanalyse und Supervision gesehen. Zusammenfassend lässt sich sagen, dass die Ergebnisse dieser Arbeit moderne und adressatenorientierte digitale Lösungen vorschlagen können, um das Verständnis für bestimmte Untersuchungstechniken bei potenziellen Untersuchenden in bewegungswissenschaftlichen Forschungsprojekten zu verbessern. Kopfgetragene Augmented-Reality-Geräte haben einen besonderen Wert und können für kollaborative Forschungsprojekte mit untersuchungsbasierten Forschungsfragen empfohlen werden. Während das etablierte Setting in prospektiven klinischen Studien weiter untersucht werden sollte, sollten die digitalen Kompetenzen zukünftiger Forschenden bereits in den frühen Phasen ihrer Ausbildung verbessert werden. KW - digital media KW - remote instruction KW - exercise science KW - digitale Medien KW - Bewegungswissenschaft KW - Fernausbildung Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-583642 ER -