Promises and Challenges of Big Data Computing in Health Sciences

An impressive study concerning Big Data and how to transfer the concept to the Health Science: The concept of Big Data is causing a world-wide buzz. Its successful applications in business, sciences and healthcare have radically changed their traditional practices. The demand for Big Data analysis is increasing day by day. More than 200 colleges provide degrees with Data Science

Type of content: Assets
Type of asset:
Model
Big data potential
No
Policy domains: Health
Phase in the policy cycle:
Policy Design and Analysis
Open license availability
No
Ease of use
High
Tags: Big data Data management
Addresses:
SWOT Analysis for
Promises and Challenges of Big Data Computing in Health Sciences
Helpful Harmful
Internal
Strengths• Making fundamental changes in care delivery and discovery of treatments such
• Reducing health care costs,
• Reducing number of hospital re-admissions,
• Targeted interventions for reducing emergency department (ED) visits,
• Triage of patients in ED,
• Preventing adverse drug effects
Weaknesses• More data needed: Identifying a cohort in the MIMIC (Medical Information Mart for Intensive Care) for answering a specific clinical question, it often results in a very small set of cases (small cohort) that makes it almost impossible to answer the question with a strong statistical confidence.
• Data do not fully capture temporal and process information: In most cases, clinical data are captured in various systems, even within an organisation, each with a somewhat different intent and often not well integrated.
External
Opportunities• The volume of data being captured from biological experiments and routine health care procedures is growing at an unprecedented pace. This data trove has brought new promises for discovery in health care research and breakthrough treatments as well as new challenges in technology, management, and dissemination of knowledge
• Building specific systems in addressing the need for analysis of different types of data, e.g., integrated electronic health record (EHR), genomics-EHR, genomics-connectomes, insurance claims data, etc.
Threats• Data ownership, Access, Shareability, Proprietary rights: Accessibility to patient data for scientific research and sharing of the scientific work as digital objects for validation and reproducibility is another challenging domain due to patient privacy concerns, technological issues such as interoperability, and data ownership confusion.
• Translation: Many machine learning algorithms work as a “black box” with no provision of good interpretations and clinical context of the outcomes, even though they often perform with reasonable accuracy.
• Incentive: the lack of incentive for organisations to take initiative to address the technological challenges

Open data - Download the Knowledge base

You are free to download the data of this Knowledge base.

To do this you must be an authenticated user: log in or sign in now.

All the data are licensed as Creative Common CC-BY 4.0.