How does an AI diagnose dyspnoea in ED triage without human guidance?

Summary, in English

• We aimed to capture possible insights from an AI diagnosing without human guidance.
• We believe the result mainly aligns with previous knowledge. Though, vital signs and sex did not aid the AI diagnostics.

• Author: Ellen Tolestam Heyman; Awais Ashfaq; Ulf Ekelund; Mattias Ohlsson; Jonas Björk; Ardavan M. Khoshnood; Markus Lingman
• Department/s: Emergency medicine; Medicine, Lund; EpiHealth: Epidemiology for Health; LU Profile Area: Natural and Artificial Cognition; Centre for Environmental and Climate Science (CEC); eSSENCE: The e-Science Collaboration; Artificial Intelligence in CardioThoracic Sciences (AICTS); LU Profile Area: Nature-based future solutions; EPI@LUND; Surgery and public health; Centre for Economic Demography; Division of Occupational and Environmental Medicine, Lund University; Cardiovascular Research - Hypertension
• Publishing year: 2024-03-20
• Language: English
• Full text: - 1 MB; Download statistics
• Document type: Poster
• Topic: Cardiac and Cardiovascular Systems; Respiratory Medicine and Allergy; Computer Science
• Keywords: artificial intelligence; AI; Dyspnea; emergency medicine; artificiell intelligens; AI; Dyspne; akutsjukvård
• Conference name: Swedish Emergency Medicine Talks - SWEETS24
• Conference date: 2024-03-20 - 2024-03-22
• Conference place: Göteborg, Sweden
• Status: Published
• Project: Resource Management in the Emergency Department by using Machine Learning
• Research group: Emergency medicine; Artificial Intelligence in CardioThoracic Sciences (AICTS); EPI@LUND; Surgery and public health; Cardiovascular Research - Hypertension