Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice’s quality, and judge their own confidence. We manipulated whether the advice came with or without a visual annotation on the X-rays, and whether it was labeled as coming from an AI or a human radiologist. Overall, receiving annotated advice from an AI resulted in the highest diagnostic accuracy. Physicians rated the quality of AI advice higher than human advice. We did not find a strong effect of either manipulation on participants’ confidence. The magnitude of the effects varied between task experts and non-task experts, with the latter benefiting considerably from correct explainable AI advice. These findings raise important considerations for the deployment of diagnostic advice in healthcare.
Text is one of the most prevalent types of digital data that people create as they go about their lives. Digital footprints of people's language usage in social media posts were found to allow for inferences of their age and gender. However, the even more prevalent and potentially more sensitive text from instant messaging services has remained largely uninvestigated. We analyze language variations in instant messages with regard to individual differences in age and gender by replicating and extending the methods used in prior research on social media posts. Using a dataset of 309,229 WhatsApp messages from 226 volunteers, we identify unique age-and gender-linked language variations. We use cross-validated machine learning algorithms to predict volunteers' age (MAEMd = 3.95, rMd = 0.81, R 2 Md = 0.49) and gender (AccuracyMd = 85.7%, F1Md = 0.67, AUCMd = .82) significantly above baseline-levels and identify the most predictive language features. We discuss implications for psycholinguistic theory, present opportunities for application in author profiling, and suggest methodological approaches for making predictions from small text data sets. Given the recent trend towards the dominant use of private messaging and increasingly weaker user data protection, we highlight rising threats to individual privacy rights in instant messaging.
Supplementary materials for this manuscript, including code, figures, and results, are available in the project's repository on the Open Science Framework (OSF): https://osf.io/ugt2v/ Acknowledgments: We thank Carina Kemmer and Susanne Grundler for their substantial support in the early stage of this project, particularly in conceptualization and data collection. We thank Regina Rockinger for her support with literature research. We thank David Goretzko and Florian Pargent for their statistical advice.
Zusammenfassung Hintergrund Die Gabe von Opioiden zur Schmerzunterdrückung spielt eine zentrale Rolle in der modernen Anästhesiologie. Messungen von Hypnosetiefe und Muskelrelaxierung sind im Gegensatz zur Schmerzmessung seit Jahren etabliert. Seit Kurzem ist das PMD200 („Pain Monitoring System“; Fa. Medasense Biometrics™ Ltd., Ramat-Gan, Israel) verfügbar. Dieser Schmerzmonitor misst nichtinvasiv und errechnet einen dimensionslosen Schmerzindex („nociceptor level“, NoL). Die Validität und Zuverlässigkeit des Verfahrens sind Gegenstand von klinischen Studien. Fragestellung Reduziert die Verwendung des PMD200 die Gabe von Analgetika während einer Da-Vinci-Prostatektomie? Material und Methoden In die Studie wurden 50 Patienten aufgenommen. Nach gewichtsadaptierter Sufentanilgabe zur Narkoseinduktion und einem 10 µg Bolus vor Hautschnitt erfolgte die intraoperative Analgesie durch subjektive Entscheidung (CONT) oder aufgrund eines erhöhten NoL-Index (INT). Die statistische Auswertung erfolgte durch Mann-Whitney-U-, Kolmogorow-Smirnow-Test und Levene-Statistik. Ergebnisse In der INT-Gruppe war die Anzahl der Sufentanilboli/h nicht signifikant geringer als in der CONT-Gruppe (p = 0,065). Die Varianz der Sufentanilgaben unterschied sich signifikant (p = 0,033). In der CONT-Gruppe war die Applikation normal verteilt (p = 0,2), in der INT-Gruppe hingegen nicht (p = 0,003). Diskussion Eine mögliche Interpretation der Daten ist, dass die Schmerzmittelgabe in der INT-Gruppe individualisierter erfolgte, d. h., es wurden nichterforderliche Schmerzmittelgaben vermieden, und gleichzeitig detektierte das NoL-Monitoring einzelne Patienten mit deutlich erhöhtem Schmerzmittelbedarf. Diese Schlussfolgerung ist nur unter der Voraussetzung zulässig, dass das PMD200 auch tatsächlich die Entität Schmerz misst.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.