Partial Membership Latent Dirichlet Allocation for Soft Image Segmentation

Nguyen

Pham

et al. 2020

IJERPH

Improving the quality of life (QOL) of people living with diabetes is the ultimate goal of diabetes care. This study provides a quantitative overview of global research on interventions aiming to improve QOL among people with diabetes. A total of 700 English peer-reviewed papers published during 1990–2018 were collected and extracted from the Web of Science databases. Latent Dirichlet Allocation (LDA) analysis was undertaken to categorize papers by topic or theme. Results showed an increase in interventions to improve the QOL of patients with diabetes across the time period, with major contributions from high-income countries. Community- and family-based interventions, including those focused on lifestyle and utilizing digital technologies, were common approaches. Interventions that addressed comorbidities in people with diabetes also increased. Our findings emphasize the necessity of translating the evidence from clinical interventions to community interventions. In addition, they underline the importance of developing collaborative research between developed and developing countries.

Section: Discussionmentioning

confidence: 99%

Global Mapping of Interventions to Improve Quality of Life of People with Diabetes in 1990–2018

Nguyen

Pham

et al. 2020

IJERPH

“…Jaccard's similarity index. Latent Dirichlet Allocation (LDA) was used for classifying papers into corresponding topics [8][9][10][11][12]. Principal component analysis (PCA) was used to create the keyword map as the technique is able to reduce the number of variables, and thus, cluster them into more manageable groups [13].…”

Section: Discussionmentioning

confidence: 99%

Modeling the Research Landscapes of Artificial Intelligence Applications in Diabetes (GAPRESEARCH)

McIntyre

et al. 2020

IJERPH

The rising prevalence and global burden of diabetes fortify the need for more comprehensive and effective management to prevent, monitor, and treat diabetes and its complications. Applying artificial intelligence in complimenting the diagnosis, management, and prediction of the diabetes trajectory has been increasingly common over the years. This study aims to illustrate an inclusive landscape of application of artificial intelligence in diabetes through a bibliographic analysis and offers future direction for research. Bibliometrics analysis was combined with exploratory factor analysis and latent Dirichlet allocation to uncover emergent research domains and topics related to artificial intelligence and diabetes. Data were extracted from the Web of Science Core Collection database. The results showed a rising trend in the number of papers and citations concerning AI applications in diabetes, especially since 2010. The nucleus driving the research and development of AI in diabetes is centered around developed countries, mainly consisting of the United States, which contributed 44.1% of the publications. Our analyses uncovered the top five emerging research domains to be: (i) use of artificial intelligence in diagnosis of diabetes, (ii) risk assessment of diabetes and its complications, (iii) role of artificial intelligence in novel treatments and monitoring in diabetes, (iv) application of telehealth and wearable technology in the daily management of diabetes, and (v) robotic surgical outcomes with diabetes as a comorbid. Despite the benefits of artificial intelligence, challenges with system accuracy, validity, and confidentiality breach will need to be tackled before being widely applied for patients’ benefits.

“…A network graph showing the cooccurrence of authors' keywords was generated by the VOSviewer software tool (https://www.vosviewer.com/ ). The Latent Dirichlet Allocation (LDA), a generative statistical model, was used for classifying publications into topics [26][27][28][29][30]. The LDA approach was selected because of its ability to group and explain trends and patterns in text content.…”

Section: Discussionmentioning

confidence: 99%

Global mapping of interventions to improve the quality of life of patients with cardiovascular diseases during 1990–2018

Health Qual Life Outcomes

Nghiem

Afoakwah

et al. 2020

Background: Cardiovascular diseases (CVDs) have been the global health problems that cause a substantial burden for the patients and the society. Assessing the Quality of Life (QOL) of CVD patients is critical in the effectiveness evaluation of CVD treatments as well as in determining potential areas for enhancing health outcomes. Through the adoption of a combination of bibliometric approach and content analysis, publications trend and the common topics regarding interventions to improve QOL of CVD patients were searched and characterized to inform priority setting and policy development. Methods: Bibliographic data of publications published from 1990 to 2018 on interventions to improve QOL of CVD patients were retrieved from Web of Science. Network graphs illustrating the terms co-occurrence clusters were created by VOSviewer software. Latent Dirichlet Allocation approach was adopted to classify papers into major research topics. Results: A total of 6457 papers was analyzed. We found a substantial increase in the number of publications, citations, and the number of download times of papers in the last 5 years. There has been a rise in the number of papers related to intervention to increase quality of life among patients with CVD during 1990-2018. Conventional therapies (surgery and medication), and psychological, behavioral interventions were common research topics. Meanwhile, the number of papers evaluating economic effectiveness has not been as high as that of other topics. Conclusions: The research areas among the scientific studies emphasized the importance of interdisciplinary and intersectoral approaches in both evaluation and intervention. Future research should be a focus on economic evaluation of intervention as well as interventions to reduce mental issues among people with CVD.