Detecting impending malnutrition of elderly people in domestic smart home environments
This addresses the challenge of continuous, reliable monitoring of malnutrition risk for elderly individuals in smart home environments, offering a practical alternative to professional or self-monitoring.
The paper tackled the problem of detecting impending malnutrition in elderly people by proposing a method that uses ambient sensors to monitor meal preparation time as an indicator of BMI trends, achieving a very strong correlation between the two measures in a 10-month study with 20 participants aged about 85 years.
Proper nutrition is very important for the well-being and independence of elderly people. A significant loss of body weight or a decrease of the Body Mass Index respectively is an indicator for malnutrition. A continuous monitoring of the BMI enables doctors and nutritionists to intervene on impending malnutrition. However, continuous monitoring of the BMI by professionals is not applicable and self-monitoring not reliable. In this article a method for monitoring the trend of the BMI based on ambient sensors is introduced. The ambient sensors are used to measure the time a person spends for preparing meals at home. When the trend of the average time for 4 weeks changes, so does the trend of the BMI for those 4 weeks. Both values show a very strong correlation. Thus, the average time for preparing a meal is a suitable indicator for doctors and nutritionists to examine the patient further, become aware of an impending malnutrition, and intervene at an early stage of malnutrition. The method has been tested on a real-world dataset collected during a 10-month field study with 20 participants of an age of about 85 years.