Rates of overweight and obesity are increasing globally. The World Health Organization estimated that there were approximately 1.6 billion overweight and at least 400 million obese adults worldwide in 2005. Overweight and obesity increase the risk of developing chronic diseases such as type 2 diabetes, cardiovascular disease and cancer. Overweight and obesity result from an imbalance between energy intake and energy expenditure but the etiology of that imbalance and the underlying mechanisms are still incompletely understood. The devices for monitoring of energy expenditure are well developed and accurate and have been successfully employed in intervention studies. In contrast, methods for monitoring energy intake are inaccurate, tedious, and cumbersome. For example, dietary self-report has been used intensively for the measurement of food intake, but there are numerous shortcomings, particularly in regards to long-term use. Using cameras to assess food intake appears to be comparable to diet but even when multimedia diet records that include tape recorders and cameras are used, it appears that people still underreport their food intake. There is an urgent need for innovative strategies for accurately assessing free-living energy and food intake in humans. The goal of this study is to develop an accurate and objective methodology of assessing free- living ingestive behavior and energy intake. The results of our previous study show that metrics derived from measured chewing and swallowing events can be used to reliably (>95% accuracy) identify each occurrence of food ingestion with fine time granularity of 30s;differentiate between ingestion of solids and liquids (>90% accuracy) and predict the mass of ingested solids and liquids (>90% solids, >80% liquids). We also showed that swallowing instances can be automatically identified by a computer algorithm from the data captured by a miniature microphone. The overall goal of this R21 proposal is to make the next step in methodology development for monitoring of energy intake in free living conditions. Specifically, we will develop methods such that chews and swallowing events can provide additional information about a meal: predict number of distinct foods consumed in the course of meal;estimate mass for each distinct food;predict caloric content of the food based on automatically obtained mass estimates and user - entered food type. This study is expected to validate the methodology under conditions maximally close to unrestricted food intake in free living conditions. The proposed technology is inexpensive and provides unique information about eating patterns which enable research, clinical and consumer applications for diagnostic of ingestive behaviors leading to weight gain (excessive snacking, night eating, evening and weekend overeating) and accurate estimation of daily caloric intake.
The combination of the proposed methods in a miniature wearable device can enable objective diagnostics and monitoring of ingestive behavior and caloric intake in free living population, and can be used by researchers, nutritionists and general population. Applications of the proposed device include 1) study of patterns of food consumption that are indicative of obesity (for use by researchers);2) a diagnostic tool (for use by a nutritionist/heath adviser) and a behavioral modification tool for correcting known behaviors leading to weight gain (snacking, night eating, weekend or evening overeating);3) a diagnostic and monitoring tool for caloric intake. The main advantage over existing methods is objective estimation of food intake occurrence and food intake mass (reduction or elimination of underreporting). The sensors can be easily worn by individuals of all sizes, and thus can be used in a wide range of populations (e.g., children, elderly, normal weight individuals, obese individuals, and persons with anorexia). We envision that these sensors will improve our assessment of energy intake in free-living individuals and be useful as a therapeutic tool for behavioral modification of energy intake.
| Farooq, Muhammad; Sazonov, Edward (2016) Detection of chewing from piezoelectric film sensor signals using ensemble classifiers. Conf Proc IEEE Eng Med Biol Soc 2016:4929-4932 |
| Farooq, Muhammad; Sazonov, Edward (2016) Automatic Measurement of Chew Count and Chewing Rate during Food Intake. Electronics (Basel) 5: |
| Fontana, Juan M; Higgins, Janine A; Schuckers, Stephanie C et al. (2015) Energy intake estimation from counts of chews and swallows. Appetite 85:14-21 |
| Fontana, Juan M; Farooq, Muhammad; Sazonov, Edward (2014) Automatic ingestion monitor: a novel wearable device for monitoring of ingestive behavior. IEEE Trans Biomed Eng 61:1772-9 |
| Farooq, Muhammad; Fontana, Juan M; Sazonov, Edward (2014) A novel approach for food intake detection using electroglottography. Physiol Meas 35:739-51 |
| Fontana, Juan M; Sazonov, Edward S (2013) Evaluation of Chewing and Swallowing Sensors for Monitoring Ingestive Behavior. Sens Lett 11:560-565 |
| Fontana, Juan M; Farooq, Muhammad; Sazonov, Edward (2013) Estimation of feature importance for food intake detection based on Random Forests classification. Conf Proc IEEE Eng Med Biol Soc 2013:6756-9 |
| Fontana, Juan M; Sazonov, Edward S (2012) A robust classification scheme for detection of food intake through non-invasive monitoring of chewing. Conf Proc IEEE Eng Med Biol Soc 2012:4891-4 |
| Sazonov, Edward S; Fontana, Juan M (2012) A Sensor System for Automatic Detection of Food Intake Through Non-Invasive Monitoring of Chewing. IEEE Sens J 12:1340-1348 |
| Makeyev, Oleksandr; Lopez-Meyer, Paulo; Schuckers, Stephanie et al. (2012) Automatic food intake detection based on swallowing sounds. Biomed Signal Process Control 7:649-656 |
Showing the most recent 10 out of 13 publications
