Preprint Review Version 1 Preserved in Portico This version is not peer-reviewed

Opportunities and Challenges in Data-Driven Healthcare Research

Version 1 : Received: 8 June 2018 / Approved: 8 June 2018 / Online: 8 June 2018 (13:22:08 CEST)

How to cite: Chen, Y. Opportunities and Challenges in Data-Driven Healthcare Research. Preprints 2018, 2018060137. https://doi.org/10.20944/preprints201806.0137.v1 Chen, Y. Opportunities and Challenges in Data-Driven Healthcare Research. Preprints 2018, 2018060137. https://doi.org/10.20944/preprints201806.0137.v1

Abstract

Health information technology has been widely used in healthcare, which has contributed a huge amount of data. Health data has four characteristics: high volume; high velocity; high variety and high value. Thus, they can be leveraged to i) discover associations between genes, diseases and drugs to implement precision medicine; ii) predict diseases and identify their corresponding causal factors to prevent or control the diseases at an earlier time; iii) learn risk factors related to clinical outcomes (e.g., patients’ unplanned readmission), to improve care quality and reduce healthcare expenditure; and iv) discover care coordination patterns representing good practice in the implementation of collaborative patient-centered care. At the same time, there are major challenges existing in data-driven healthcare research, which include: i) inefficient health data exchanges across different sources; ii) learned knowledge is biased to specific institution; iii) inefficient strategies to evaluate plausibility of the learned patterns and v) incorrect interpretation and translation of the learned patterns. In this paper, we review various types of health data, discuss opportunities and challenges existing in the data-driven healthcare research, provide solutions to solve the challenges, and state the important role of the data-driven healthcare research in the establishment of smart healthcare system.

Keywords

opportunity; challenge; perspective; health data; disease prediction; clinical outcome prediction; healthcare process; data quality; quantity and quality analysis; artificial intelligence

Subject

Medicine and Pharmacology, Other

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.