1 |
Saving Lives More Efficiently: A First Step in Designing a Visual Language : Creating and evaluating a visual language aimed at the medical field / Rädda liv på ett mer effektivt sätt : Skapande och evaluerande av ett visuellt språk inom vårdenJahic, Jasmina January 2017 (has links)
The aim of this study is to create and evaluate a grammar for a visual language, which is to be used in the medical domain. The grammar was created with gestalt laws in mind. The grammar must also fit, in part, with the ontology of the clinical terminology SNOMED CT. Evaluation was conducted with think aloud tests and with complementary semi-structured interviews. The participants overall believed that a complementary visual language for patient journals would be useful, and the majority understood the logic behind the grammar. Most complaints were about some of the pictograms in the icons of the grammar, which were unclear, and some requested a clear time axis to be included. Another suggestionwas to add pop-up boxes with more detailed information. This is only the first step in a big project and there is potential for many improvements - future development of this visual language should be done in iterations by teams of complementing competencies.
|
2 |
Pulse Oximetry : Signal Processing in real time on Raspberry Pi / Pulsoximetri : Signalbehandling i realtid på Raspberry PiThunholm, Malin January 2017 (has links)
This thesis introduces the reader into RespiHeart, which is a product under development. RespiHeart is an complement/alternative to the regular Pulse Oximeter and is intended to be used within the health care sector for combined measurements and communication on open inexpensive platforms. This thesis evaluates interaction between RespiHeart and a Raspberry Pi 3 Model B to evaluate if the computer is capable of handling the data from RespiHeart and make signal processing. Python is used throughout the whole project and is a suitable language for interaction and signal processing in real time. / Detta examensarbete introducerar läsaren till RespiHeart, en ny trådlös produkt som är under utveckling. RespiHeart är ett komplement/alternativ till den nuvarande Pulsoximetern och är tänkt att användas inom sjukvården för analys, kommuniakation och kombinerade mätningar på öppna billiga plattformar. Detta project utvärderar interaktionen mellan RespiHeart och en Raspberry Pi 3 Model B för att undersöka om datorn är kapabel till att hantera datan från RespiHeart samt göra signal processing i real tid. Programmeringsspråket Python användes under hela projektet och är ett lämpligt språk att använda för interation och signal processing i real tid.
|
3 |
Discovering Implant Terms in Medical RecordsJerdhaf, Oskar January 2021 (has links)
Implant terms are terms like "pacemaker" which indicate the presence of artifacts in the body of a human. These implant terms are key to determining if a patient can safely undergo Magnetic Resonance Imaging (MRI). However, to identify these terms in medical records is time-consuming, laborious and expensive, but necessary for taking the correct precautions before an MRI scan. Automating this process is of great interest to radiologists as it ideally saves time, prevents mistakes and as a result saves lives. The electronic medical records (EMR) contain the documented medical history of a patient, including any implants or objects that an individual would have inside their body. Information about such objects and implants are of great interest when determining if and how a patient can be scanned using MRI. This information is unfortunately not easily extracted through automatic means. Due to their sparse presence and the unusual structure of medical records compared to most written text, makes it very difficult to automate using simple means. By leveraging the recent advancements in Artificial Intelligence (AI), this thesis explores the ability to identify and extract such terms automatically in Swedish EMRs. For the task of identifying implant terms in medical records a generally trained Swedish Bidirectional Encoder Representations from Transformers (BERT) model is used, which is then fine-tuned on Swedish medical records. Using this model a variety of approaches are explored two of which will be covered in this thesis. Using this model a variety of approaches are explored, namely BERT-KDTree, BERT-BallTree, Cosine Brute Force and unsupervised NER. The results show that BERT-KDTree and BERT-BallTree are the most rewarding methods. Results from both methods have been evaluated by domain experts and appear promising for such an early stage, given the difficulty of the task. The evaluation of BERT-BallTree shows that multiple methods of extraction may be preferable as they provide different but still useful terms. Cosine brute force is deemed to be an unrealistic approach due to computational and memory requirements. The NER approach was deemed too impractical and laborious to justify for this study, yet is potentially useful if not more suitable given a different set of conditions and goals. While there is much to be explored and improved, these experiments are a clear indication that automatic identification of implant terms is possible, as a large number of implant terms were successfully discovered using automated means.
|
Page generated in 0.0791 seconds