Välkommen att delta vid Stefan Candefjords publika föreläsning i samband med hans befordran till oavlönad docent. Föreläsningen kommer att hållas online.
Beskrivning av föredraget
For several of our most serious public health problems, minimizing time to adequate care and treatment is essential to limit mortality and improve patient outcomes. This applies to e.g., trauma, stroke, sepsis and acute myocardial infarction, which together cause over 100,000 cases and over 20,000 deaths per year in Sweden. However, insufficient information about the state, circumstances and history of the patient can lead to delays in providing adequate treatment or the patient receiving suboptimal treatment at a hospital with inadequate resources. The key to improve these scenarios is to enrich information about the patient’s condition, incident circumstances and previous history in an early phase, e.g., in prehospital settings with ambulance transportations, and enhance the precision in decisions about what treatment and in turn what transport destination is most suitable for the patient.
Digital health and precision healthcare, i.e., an individually tailored care, powered by artificial intelligence can be leveraged to create new systems for improved diagnostics and decision support, which can contribute to providing equal care to all citizens regardless of demographic factors. In this lecture several such systems being developed at Chalmers University of Technology together with clinical collaborators will be presented. A future outlook to how the tools could be used in combination to achieve sophisticated systems promoting individual health and bringing clinical benefits to patients will also be provided.
The presentation will cover four related tracks of research and utilization that together highlight challenges in care chains and how to develop solutions to address them. The focus of the presentation lies on the first two tracks, whereas the last two tracks form a future outlook and point out directions ahead.
- Evaluations of prehospital patient flows and patient outcomes
- Develop new tools for diagnostics and decision support based on portable medical devices and retrospective data collections, signal processing and mathematical models
- Performing prospective clinical trials to assess real performance compared to the clinical state-of-the-practice
- Iterative improvements of the systems and feedback to data scientists and clinicians
The presentation will provide insights into our work on microwave diagnostics for trauma and stroke, developing a smartphone platform and algorithms for detecting motorcycle crashes, assessing driver sleepiness based on physiological measurements, and predicting severe injury for trauma patients based on variables that can be assessed on the scene of a motor vehicle crash.