Väitös (tieto- ja viestintätekniikka): MSc Saeed Mehrang
Aika
12.12.2023 klo 12.00 - 16.00
M.Sc. Saeed Mehrang esittää väitöskirjansa ”Machine Learning for The Classification of Atrial Fibrillation Utilizing Seismo- and Gyrocardiogram” julkisesti tarkastettavaksi Turun yliopistossa tiistaina 12.12.2023 klo 12.00 (Turun yliopisto, Natura, X-luentosali, Turku).
Vastaväittäjänä toimii apulaisprofessori Samuel Emil Schmidt (Aalborg University, Tanska) ja kustoksena professori Pasi Liljeberg (Turun yliopisto). Tilaisuus on englanninkielinen. Väitöksen alana on tieto- ja viestintätekniikka.
Väitöskirja yliopiston julkaisuarkistossa: https://www.utupub.fi/handle/10024/175993
***
Tiivistelmä väitöstutkimuksesta:
Cardiovascular diseases (CVDs) are responsible for a significant number of deaths worldwide. In 2019, CVDs accounted for approximately one-third of the total mortality, with an estimated 18 million deaths. Technological advancements, particularly wearable devices for remote patient monitoring, have significantly improved the diagnosis, treatment, and monitoring of CVDs. Atrial fibrillation (AFib) is a type of arrhythmia that can lead to severe complications and potential fatality. It requires prolonged monitoring of heart activity for accurate diagnosis and severity assessment. Seismo- and gyrocardiogram signals (SCG and GCG) provide information about the hearts mechanical function, enabling AFib monitoring within or outside clinical settings. SCG and GCG signals can be conveniently recorded using smartphones, which are affordable and ubiquitous in most countries.
This doctoral research explores the potential of using smartphones to detect atrial fibrillation (AFib) through short recordings of heart signals (SCG and GCG). The overarching goal was to assess and enhance the capability of machine learning techniques for the effective detection of atrial fibrillation, considering measurements taken by both healthcare professionals and patients themselves.
Results indicate successful AFib detection using joint SCG and GCG recordings, regardless of the operator. This suggests the potential for remote AFib monitoring outside hospitals, using smartphones as a solution for suspected AFib cases. Notably, short recordings of 10 to 60 seconds produced clinically relevant results.
It is important to note that SCG and GCG are not, however, meant to replace clinical grade and Holter ECG. But, rather as a complementary technology that comes to the rescue when ECG is unavailable.
Vastaväittäjänä toimii apulaisprofessori Samuel Emil Schmidt (Aalborg University, Tanska) ja kustoksena professori Pasi Liljeberg (Turun yliopisto). Tilaisuus on englanninkielinen. Väitöksen alana on tieto- ja viestintätekniikka.
Väitöskirja yliopiston julkaisuarkistossa: https://www.utupub.fi/handle/10024/175993
***
Tiivistelmä väitöstutkimuksesta:
Cardiovascular diseases (CVDs) are responsible for a significant number of deaths worldwide. In 2019, CVDs accounted for approximately one-third of the total mortality, with an estimated 18 million deaths. Technological advancements, particularly wearable devices for remote patient monitoring, have significantly improved the diagnosis, treatment, and monitoring of CVDs. Atrial fibrillation (AFib) is a type of arrhythmia that can lead to severe complications and potential fatality. It requires prolonged monitoring of heart activity for accurate diagnosis and severity assessment. Seismo- and gyrocardiogram signals (SCG and GCG) provide information about the hearts mechanical function, enabling AFib monitoring within or outside clinical settings. SCG and GCG signals can be conveniently recorded using smartphones, which are affordable and ubiquitous in most countries.
This doctoral research explores the potential of using smartphones to detect atrial fibrillation (AFib) through short recordings of heart signals (SCG and GCG). The overarching goal was to assess and enhance the capability of machine learning techniques for the effective detection of atrial fibrillation, considering measurements taken by both healthcare professionals and patients themselves.
Results indicate successful AFib detection using joint SCG and GCG recordings, regardless of the operator. This suggests the potential for remote AFib monitoring outside hospitals, using smartphones as a solution for suspected AFib cases. Notably, short recordings of 10 to 60 seconds produced clinically relevant results.
It is important to note that SCG and GCG are not, however, meant to replace clinical grade and Holter ECG. But, rather as a complementary technology that comes to the rescue when ECG is unavailable.
Viestintä