An interactive healthcare system with personalized diet and exercise guideline recommendation

Abstract

Recently people pay more and more attention on how to effectively and efficiently analyze the result of regular physical examinations to provide the most helpful information for individual health management. In this paper, we design and develop an interactive system of virtual healthcare assistant to help people, especially for those who suffer from chronic diseases (e.g., metabolic syndrome) to easily understand their health conditions and then well manage it. This system analyzes the result of regular physical examination to evaluate the health risk and provide personalized healthcare services for users in terms of diet and exercise guideline recommendations. We developed some interactive ways for users to easily feedback their vital signs to the system and quickly get the suggestions for health management from the system. Besides the browser-based system, we also developed a mobile App that can regularly remind users to carry out the recommendations, which are provided by the system. To prove the system is feasible in the real-world clinical environment, we also applied the Institutional Review Board (IRB) for a human subject research to validate this system. Other than the functional features, there are also several important non-functional features of the extensibility and the convenience for use. First, we use the physical examination result as the raw data to be analyzed. It's very convenient for users with very low cost. Second, the system design is extendable, so it can be easily adjusted to work for any chronic ills, even other kinds of diseases. Moreover, it can be extended to provide other kinds of healthcare guideline recommendations as well. These features constitute the main contributions of this work.

User Models for Personalized Physical Activity Interventions: Scoping Review

“…The last study aimed at rehabilitation provided real-time as well as weekly adaptation of exercises for the patients [52]. For the 8 studies on healthy lifestyle, their objectives included wellness services [32], exercise and diet recommendation [6,7,47,76-78], and a personalized coaching system [54], which was illustrated through 3 use cases, that is, neck coach, activity coach, and stress coach.…”

“…Data were collected for the intervention (for monitoring users and generating user models) in various ways, for example, through questionnaires [3,21,80], mobile phone sensors [9,32,45,85], specific activity monitors [41,64,66,81], or fitness trackers [2,3,86]. The target population of the studies varied from specific to general users, that is, people with chronic disease [76], elderly adults [79,80], diabetes patients [9,87], cancer patients [78,82,84], people with CVD or at risk of CVD or heart failure [7,21], osteoarthritis patients [48], young adults [3,72,88], and general users [2,32,45,86].…”

“…In the study by Tseng et al [76], automated activity and goal recommendations were provided, which could be modified by a medical expert. Similarly, for the case of SmartLoss [2], the system required a goal to be set in consultation with the nurse, but the platform also automatically provided a set of “SmartTips” in case the user was predicted to be deviating from the weight loss program.…”

“…The specification of the goals differed across the systems and apps. The goals could be specified in terms of game level [80], training zone and HR [52,75,81], activity duration [3,43,76,81,82,89], step data [2,54,60,93,95], or activity level prescription by an expert [23]. These goals were adapted according to the person’s status and did not follow standardized fixed goals (such as “30 minutes of MVPA”).…”

On How Chronic Conditions Affect the Patient-AI Interaction: A Literature Review

“…These metrics are usually represented by a question with a binary answer (e.g., Did the participant adopt the system past the experiment phase or not?). This is observed in the four studies that measure the adoption of the system post the experiment phase [ 22 , 32 , 36 , 48 ]. At the opposite end of the spectrum, the majority of the studies that do not specify the measured outcome metrics, as illustrated by the studies that measure the effectiveness of the system (refer to the full list of the 17 studies that fall under this category in Table 3 ), find the task of providing a trenchant decision with regards to the outcome of the study difficult.…”