What is it about?

The application of data mining (DM) in healthcare is increasing. Healthcare organizations generate and collect large voluminous and heterogeneous information daily and DM helps to uncover some interesting patterns, which leads to the manual tasks elimination, easy data extraction directly from records, to save lives, to reduce the cost of medical services and to enable early detection of diseases. These patterns can help healthcare specialists to make forecasts, put diagnoses, and set treatments for patients in health facilities. This work overviews DM methods and main issues. Three case studies illustrate DM in healthcare applications: (i) In-Vitro Fertilization; (ii) Content-Based Image Retrieval (CBIR); and (iii) Organ transplantation.

Featured Image

Why is it important?

The application of data mining (DM) in healthcare is increasing. Healthcare organizations generate and collect large voluminous and heterogeneous information daily and DM helps to uncover some interesting patterns, which leads to the manual tasks elimination, easy data extraction directly from records, to save lives, to reduce the cost of medical services and to enable early detection of diseases. These patterns can help healthcare specialists to make forecasts, put diagnoses, and set treatments for patients in health facilities. Data Mining; Healthcare Automation; Pattern Recognition; Computer Vision; Feature Extraction; Similarity Comparison

Perspectives

This paper explains DM and overviews its basic methods. Health care applications were described to give an idea about DM uses with the data side in mind. Data such as images, video or audio involve more complex data structures. Misused DM can produce results which appear to be significant; but which do not predict future behavior and cannot be replicated on a new sample of data and bear little use. Frequently this happens when investigating too many hypotheses and not doing appropriate statistical hypothesis testing. In machine learning, this is known as overfitting. The same problem can happen at different process phases and thus a train/test split (when applicable) may not be sufficient to prevent this from occurring.

Dr Vania V. Estrela
Universidade Federal Fluminense

Read the Original

This page is a summary of: An Introduction to Data Mining Applied to Health-Oriented Databases, Oriental journal of computer science and technology, December 2016, Oriental Scientific Publishing Company,
DOI: 10.13005/ojcst/09.03.03.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page