Sign in Subscribe
Diseases

Big Data-Driven Health Portraits for Personalized Management in Noncommunicable Diseases: A Comprehensive Review

Strategic Insights

— 2 min read

A comprehensive review of big data-driven health portraits for personalized management of noncommunicable diseases (NCDs) was conducted by researchers from Zhejiang University. The study aimed to integrate diverse health-related data into actionable insights, facilitating precise risk prediction and personalized management of NCDs. Despite the promise of health portraits, their adoption and application remain fragmented due to the lack of a standardized conceptual and methodological framework. The researchers identified a total of 8707 records and included 89 studies for full-text analysis, categorizing them into four types of health portraits: diagnostic, prognostic, monitoring, and recommender. The evaluation based on the 3V framework showed that only 17.78% of studies met all three criteria, highlighting the need for more robust data integration strategies and artificial intelligence-enabled approaches.

Key Takeaways:

  • The study emphasizes the importance of integrating diverse health-related data into actionable insights for precise risk prediction and personalized management of NCDs.
  • The researchers identified four types of health portraits: diagnostic, prognostic, monitoring, and recommender, with only 17.78% of studies meeting all three criteria based on the 3V framework.
  • The study highlights the need for more robust data integration strategies and artificial intelligence-enabled approaches to advance the implementation of personalized health management solutions.
  • Enhancing external validation and addressing ethical and privacy considerations are critical for advancing the implementation of personalized health management solutions.
  • The study provides a standardized lens for evaluating the development and application of health portraits in NCD management.
  • The researchers emphasize the importance of incorporating all three data attributes (natural, domain, and specific attributes) to achieve comprehensive data integration.

Statistics:

  • 8707 records were identified in the study, with 89 studies included for full-text analysis.
  • Only 17.78% of studies met all three criteria based on the 3V framework.
  • 64.29%-100% of studies used structured data, while 19.05%-93.33% used unstructured data.
  • Monitoring and recommender portraits showed high reliance on digital interactive data (over 85%).
  • Only 31.11% of studies incorporated all three data attributes (natural, domain, and specific attributes).
  • Only 30% of studies reported external validation, with only 10% meeting both external validation and 3V criteria.
  • Recommender portraits outperformed other types in terms of external validation and 3V criteria.

Sources:

  • NewsRx. Zhejiang University Reports Findings in Personalized Medicine (Big Data-Driven Health Portraits for Personalized Management in Noncommunicable Diseases: Scoping Review). Information Technology Newsweekly. June 17, 2025; p 963.
  • Journal of Medical Internet Research. Big Data-Driven Health Portraits for Personalized Management in Noncommunicable Diseases: Scoping Review. 2025;27.
  • Zhejiang University, School of Nursing and Institute of Nursing Research, School of Medicine.
  • Jianing Yu, Haoyang Du, Dandan Chen, Jingjie Wu, Erxu Xue, Yufeng Zhou, Xiaohua Pan, Jing Shao, and Zhihong Ye.

Read more