EVALUATION COMMITTEE

The Faculty Council has appointed the following adjudication committee to evaluate the thesis and the associated lecture: 

• Prof. Abdollah Vahabpour‐Roudsari, School of Health Information Science, Canada
• Prof. Mariann Fossum, Institutt for helse‐ og sykepleievitenskap, Universitetet i Agder, Norge
• Dr. Lasse Riis Østergaard, HST, Aalborg University, Denmark (Chairman).

Moderator: Dr. Thomas Kronborg, Health Science and Technology, Aalborg University

ABSTRACT

Chronic heart failure is a serious condition with a high and increasing prevalence, particularly in the western world. To combat the rising healthcare costs associated with the syndrome, different avenues for improving the management of the disease are being investigated. One treatment technology has recently been recommended by guidelines, telemonitoring. Telemonitoring of chronic patients has gained increased traction in recent years, especially in the wake of the Covid-19 Pandemic.

This paper-based PhD thesis delves into some of the unknown potentials of telemonitoring for chronic heart failure patients. The thesis consists of a background section which introduces CHF, including its causes and prevalence, and discusses the utilization of telehealth technologies for managing CHF.

The first paper, titled "Geographical Impact on Supplementary Telemedicine for CHF Patients," examines existing healthcare access disparities and demonstrates how supplementary telemedicine can help mitigate these disparities by overcoming geographical barriers.

The second paper, "Weekly Measurements for Predicting Deterioration in Telemonitored CHF Patients," investigates whether regularly measuring biometric data (such as blood pressure, weight, and pulse) can help differentiate stable periods from those leading to hospitalization in CHF patients. It concludes that features based on changes in periodic trends of biometric values enhance prediction.

The third paper, "Predicting 14-Day Hospitalization Risk in CHF Patients," builds upon the findings of the second study. It employs machine learning algorithms to develop predictive models that estimate the risk of non-elective hospitalizations within a 14-day timeframe. These models are designed for interpretability to aid carers in monitoring CHF patients.

While the predictive models exhibit modest performance, the thesis contributes to a contemporary field of research and suggests new avenues for further investigation. In addition, the findings of the first paper shows the potential of telemedicine in combating rising equity concerns in healthcare.