Xi Wang

Ms. Xi Wang

School of Social Work, Boston College, Boston, Massachusetts, USA
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 June 2025 in Healthcare
Verified
Journal Article
Open access
PDF file
Xi WangXi Wang
Xi Wang
ZSZhiyuan Sun
Zhiyuan Sun
HXHong Xue
Hong Xue
RARuopeng An
Ruopeng An
Background/Objectives: Personalized dietary recommendations are essential for managing chronic conditions such as diabetes and irritable bowel syndrome (IBS). However, traditional approaches often fall short in accounting for individual metabolic variability. This systematic review evaluates the effectiveness of artificial intelligence (AI)-generated dietary interventions in improving clinical outcomes among adults. Methods: Following PRISMA guidelines, we searched six electronic databases for peer-reviewed studies published between 19 November 2015 to 6 September 2024. Eligible studies included adults aged 18 to 91 who received AI-generated dietary recommendations based on biomarkers such as blood glucose, gut microbiome composition, and self-reported data. Study designs included randomized controlled trials (RCTs), pre-post studies, and cross-sectional analyses. The GRADE system was used to assess the quality of evidence. Results: Eleven studies met inclusion criteria (five RCTs, five pre-post designs, one cross-sectional). Most AI methods used in the included studies were based on machine learning (ML), including conventional ML algorithms, deep learning (DL), and hybrid approaches integrating ML with IoT-based systems. Interventions led to improved glycemic control, metabolic health, and psychological well-being. Notable outcomes included a 39% reduction in IBS symptom severity and a 72.7% diabetes remission rate. Among nine studies with comparison groups, six reported statistically significant improvements in AI groups, two found comparable or better outcomes, and one found no difference. Mild side effects such as fatigue and constipation were observed. Conclusions: AI-generated dietary interventions show promise in surpassing traditional approaches by providing personalized, data-driven recommendations. Further research is needed to validate long-term effects, refine intervention protocols, and enhance user adherence in both clinical and public health settings.

13 November 2023 in Journal of Medical Internet Research
Verified
Journal Article
Open access
HLHaiyan Liang
Haiyan Liang
Xi WangXi Wang
Xi Wang
RARuopeng An
Ruopeng An
Background: Pokémon GO, an augmented reality game with widespread popularity, can potentially influence players’ physical activity (PA) levels and psychosocial well-being. Objective: This review aims to systematically examine the scientific evidence regarding the impact of Pokémon GO on PA and psychosocial well-being in children and adolescents. Methods: Using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and the GRADE (Grading of Recommendations, Assessment, Development, and Evaluations) framework, we conducted keyword and reference searches in the PubMed, CINAHL, Web of Science, and Scopus databases. We performed title and abstract screening, full-text review, evidence synthesis, and identified research gaps. Results: Our review included 10 studies that explored the effect of Pokémon GO on PA or psychosocial well-being among children and adolescents. These studies used diverse designs across multiple countries and regions. Pokémon GO use measures encompassed frequency, experience, adherence, and motivation. PA assessment methods ranged from self-reported questionnaires to technology-based evaluations and qualitative approaches. Psychosocial well-being measures included emotional intelligence, personal well-being, self-control, emotionality, and sociability. In general, the estimated impact of Pokémon GO on PA was positive, with gaming elements and engagement correlating with increased PA levels. However, the effect on psychosocial well-being presented mixed results, with positive associations for sociability but a complex relationship involving well-being and internet gaming disorder. The limitations of these studies comprised the absence of randomized controlled trials, heterogeneity in study designs and outcome measures, and potential confounding bias. Conclusions: Overall, Pokémon GO tends to positively affect PA levels, while the impact on psychosocial well-being remains complex and requires further investigation. Future research should investigate the mechanisms connecting Pokémon GO use with PA and psychosocial well-being and the potential risks of excessive gameplay. These findings can help inform public health interventions to harness gaming technologies for promoting PA and enhancing well-being among the younger generation. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD42023412032; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=412032

9 September 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YSYafei Si
Yafei Si
YYYuyi Yang
Yuyi Yang
Xi WangXi Wang
Xi Wang
JZJiaqi Zu
Jiaqi Zu
XCXi Chen
Xi Chen
SGSen Gong
Sen Gong
Using simulated patients to mimic 9 established noncommunicable and infectious diseases, we assessed ChatGPT’s performance in treatment recommendations for common diseases in low- and middle-income countries. ChatGPT had a high level of accuracy in both correct diagnoses (20/27, 74%) and medication prescriptions (22/27, 82%) but a concerning level of unnecessary or harmful medications (23/27, 85%) even with correct diagnoses. ChatGPT performed better in managing noncommunicable diseases than infectious ones. These results highlight the need for cautious AI integration in health care systems to ensure quality and safety.

26 April 2024 in Nutrients
Verified
Journal Article
Open access
PDF file
RARuopeng An
Ruopeng An
JPJoshua Perez-Cruet
Joshua Perez-Cruet
Xi WangXi Wang
Xi Wang
YYYuyi Yang
Yuyi Yang
Nuts are nutrient-dense foods and can be incorporated into a healthy diet. Artificial intelligence-powered diet-tracking apps may promote nut consumption by providing real-time, accurate nutrition information but depend on data and model availability. Our team developed a dataset comprising 1380 photographs, each in RGB color format and with a resolution of 4032 × 3024 pixels. These images feature 11 types of nuts that are commonly consumed. Each photo includes three nut types; each type consists of 2–4 nuts, so 6–9 nuts are in each image. Rectangular bounding boxes were drawn using a visual geometry group (VGG) image annotator to facilitate the identification of each nut, delineating their locations within the images. This approach renders the dataset an excellent resource for training models capable of multi-label classification and object detection, as it was meticulously divided into training, validation, and test subsets. Utilizing transfer learning in Python with the IceVision framework, deep neural network models were adeptly trained to recognize and pinpoint the nuts depicted in the photographs. The ultimate model exhibited a mean average precision of 0.7596 in identifying various nut types within the validation subset and demonstrated a 97.9% accuracy rate in determining the number and kinds of nuts present in the test subset. By integrating specific nutritional data for each type of nut, the model can precisely (with error margins ranging from 0.8 to 2.6%) calculate the combined nutritional content—encompassing total energy, proteins, carbohydrates, fats (total and saturated), fiber, vitamin E, and essential minerals like magnesium, phosphorus, copper, manganese, and selenium—of the nuts shown in a photograph. Both the dataset and the model have been made publicly available to foster data exchange and the spread of knowledge. Our research underscores the potential of leveraging photographs for automated nut calorie and nutritional content estimation, paving the way for the creation of dietary tracking applications that offer real-time, precise nutritional insights to encourage nut consumption.

12 May 2024 in Nutrients
Verified
Journal Article
Open access
PDF file
CACharles Alba
Charles Alba
Xi WangXi Wang
Xi Wang
RARuopeng An
Ruopeng An
The participants in the Supplemental Nutrition Assistance Program (SNAP) consume greater amounts of sugar and sweetened beverages (SSBs) compared to non-eligible individuals, which could result in potential negative health outcomes. This can be attributed to the lack of restrictions on SSB purchases with SNAP benefits. In view of the increasing calls from advocates and policymakers to restrict the purchase of SSBs with SNAP benefits, we performed a systematic review to assess its impact towards SSB purchases and consumption. We searched articles from five databases—Cochrane, EBSCO, SCOPUS, Web of Science, and PubMed—and selected seven studies, four of which were randomized controlled trials (RCTs) and three were simulation modeling studies. All three simulation studies and one RCT reported outcomes in terms of consumption, while the other three RCTs reported outcomes in terms of purchases. All seven studies found that an SSB restriction led to a decrease in SSB consumption or purchases, with six studies reporting significant results. Nonetheless, limitations exist. These include limited studies on this subject, potential workarounds circumventing SSB restrictions, like making purchases using personal cash, potentially differed estimated effects when combined with incentives or other initiatives, and the limited geographical scope among the selected RCTs.

18 February 2025
Verified
Conference Paper
Open access
CACharles Alba
Charles Alba
Xi WangXi Wang
Xi Wang
CWChenyu Wang
Chenyu Wang
RARuopeng An
Ruopeng An
The release of popular generative artificial intelligence (AI) tools like ChatGPT have prompted universities to introduce new policies or update existing ones. Currently, most institutions adapt their policies reactively as challenges arise, often without adopting a systematic framework, with minimal guidance and limited knowledge of the approaches taken by other institutions across the United States (U.S.). This study aims to bridge this gap by identifying core themes surrounding AI policies and guidelines across the top 50 U.S. universities. Given the labor- and time-intensive nature required to manually synthesize multiple policy documents across many institutions, we leverage large language models (LLMs) to identify common and prevalent themes. Our framework first summarizes AI policies at the institutional level, followed by the generation of multiple sets of themes through an iterative process of prompt chaining and self-refinement. Finally, the common themes from these distinct sets were consolidated. This framework is designed to address potential flaws in pre-trained LLMs, such as hallucinations. Seven distinct themes are uncovered: (1) academic integrity and responsible AI use, (2) communication of AI policies, (3) data privacy and security concerns, (4) ethical considerations in AI use, (5) continuous adaptation and policy evolution, (6) documentation and transparency in AI usage, and (7) instructor discretion in AI integration. Our work lays the foundation for future analyses or recommendations in developing comprehensive and equitable AI policies. Furthermore, leveraging LLMs allows us to respond swiftly to developments surrounding AI policies across universities.