VioWell: An Automated Guidance Tool for Medical Encounters Addressing Therapeutic Lifestyle Changes
|
If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL). |
Abstract
Dietary and physical activity patterns are poised to become leading contributors to premature death in the US. Most primary healthcare practitioners recognize the important relationship among nutrition, physical activity and health. Few incorporate either dietary or physical activity counseling into routine practice.
VioWell is an interactive digital platform focused on promoting sustainable behavior change. It integrates all components of a wellness program (expert support delivery mechanism, social networking, rewards and information content management system) accessible from a user dashboard. VioWell supports healthcare organizations that wish to identify and help patients develop healthier lifestyles but who cannot commit adequate resources and time to this activity.
The system uses technology to automate the administration, collection, and analysis of dietary and physical activity assessments; and guide counseling and resources tailored to the patient’s unique needs. The patient responds to questionnaire prompts on a tablet computer in the physician’s office or from a home computer.
The innovative dietary assessment used within VioWell, VioScreen, uses a graphical method for dietary data collection that reliably assess dietary intake making it suitable for clinical counseling and research. VioScreen’s web-based self-administered dietary habits questionnaire provides an efficient and thorough assessment of dietary intake data. VioScreen is the only web-based, dietary assessment tool that includes 1,200 food images and portion size options. Results are immediately available to the clinician and patient and includes a food pattern analysis and a list of foods and nutrients consumed. VioScreen was evaluated and determined very accurate through a study with 74 subjects conducted at The Ohio State University. All subjects rated VioScreen as easy to use and 99% would complete the questionnaire if asked by a doctor. The system classifies the responses into behavior models and generates a personalized plan tailored to the needs of the patient.
Web and mobile-based food tracking tools support the patient’s plan for dietary change. Refinements under development will allow a patient to uses the mobile food tracker app to take a short video from a phone camera to automatically and accurately record their intake. The mobile phone transmits the video to a server where image definition, color analysis and texture classification facilitate the food identification process. The system uses automated volume determination. Most people can readily state what they are eating, but estimating portion size is more difficult. The portion estimation uses computer vision techniques to identify both the type and amount of foods consumed.
The mobile tool utilizes texture, color, and shape to segment the 3D image according to local-area similarities and define individual foods. The 3D model of food items are measured against a known fiducial marker to determine a volume for each food which can then be converted to a weight. Currently, the mobile tool is trained to recognize 146 different food types, tested with 322 plates and achieved as little as 5% error in volume estimation in internal lab tests.
VioWell enables the delivery of individually tailored diet and physical activity counseling in the context of standard primary care.
VioWell is an interactive digital platform focused on promoting sustainable behavior change. It integrates all components of a wellness program (expert support delivery mechanism, social networking, rewards and information content management system) accessible from a user dashboard. VioWell supports healthcare organizations that wish to identify and help patients develop healthier lifestyles but who cannot commit adequate resources and time to this activity.
The system uses technology to automate the administration, collection, and analysis of dietary and physical activity assessments; and guide counseling and resources tailored to the patient’s unique needs. The patient responds to questionnaire prompts on a tablet computer in the physician’s office or from a home computer.
The innovative dietary assessment used within VioWell, VioScreen, uses a graphical method for dietary data collection that reliably assess dietary intake making it suitable for clinical counseling and research. VioScreen’s web-based self-administered dietary habits questionnaire provides an efficient and thorough assessment of dietary intake data. VioScreen is the only web-based, dietary assessment tool that includes 1,200 food images and portion size options. Results are immediately available to the clinician and patient and includes a food pattern analysis and a list of foods and nutrients consumed. VioScreen was evaluated and determined very accurate through a study with 74 subjects conducted at The Ohio State University. All subjects rated VioScreen as easy to use and 99% would complete the questionnaire if asked by a doctor. The system classifies the responses into behavior models and generates a personalized plan tailored to the needs of the patient.
Web and mobile-based food tracking tools support the patient’s plan for dietary change. Refinements under development will allow a patient to uses the mobile food tracker app to take a short video from a phone camera to automatically and accurately record their intake. The mobile phone transmits the video to a server where image definition, color analysis and texture classification facilitate the food identification process. The system uses automated volume determination. Most people can readily state what they are eating, but estimating portion size is more difficult. The portion estimation uses computer vision techniques to identify both the type and amount of foods consumed.
The mobile tool utilizes texture, color, and shape to segment the 3D image according to local-area similarities and define individual foods. The 3D model of food items are measured against a known fiducial marker to determine a volume for each food which can then be converted to a weight. Currently, the mobile tool is trained to recognize 146 different food types, tested with 322 plates and achieved as little as 5% error in volume estimation in internal lab tests.
VioWell enables the delivery of individually tailored diet and physical activity counseling in the context of standard primary care.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.

This work is licensed under a Creative Commons Attribution 3.0 License.