Database of Scriptum

Health care nowadays collects data in gigabytes per hour volume. Data mining can help with data reduction, exploration, and hypothesis formulation to find new patterns and information in health care data that surpass human information processing limitations. There is a spread of reports and articles that apply data mining to a wide variety of health care problems and clinical domains and includes diverse projects related to cardiology, cancer, diabetes, finding medication errors, and many others.

Methods in data mining use powerful computer software tools and large clinical databases, sometimes in the form of data repositories and data warehouses, to detect patterns in data. Within data mining methodologies, one may select from an extensive array of techniques that include classification, clustering, and association rules.

Classification

Classification in data mining maps data into predefined groups or classes. Also it is often referred to as supervised learning because the groups or classes are determined before examining the data. Classification algorithms require that the groups or classes be defined based on data attribute values. They often describe these classes by looking at the characteristics of data already known to belong to the classes. Pattern recognition is a type of classification where an input pattern is classified into one of several classes based on its similarity to these predefined classes. One of the applications of classification in health care is the automatic categorization of medical images.

Clustering
Clustering is similar to classification except that the groups are not predefined, but rather defined by the data alone. Clustering is alternatively referred to as unsupervised learning or segmentation. It can be thought of as partitioning or segmenting the data into groups that might or might not be disjointed. The clustering is usually accomplished by determining the similarity among the data on predefined attributes. The most similar data are grouped into clusters.

Clustering can be used in designing a triage system. Triage helps to classify patients at emergency units to make the most effective use of resources distributed. The more important is that accuracy in carrying out triage matters greatly in terms of medical quality, patient satisfaction and life security.

Association rules

Determining association rules is refers to the data mining task of uncovering relationships among data. An association rule is a model that identifies specific types of data associations. These associations are often used in the retail sales community to identify items that are frequently purchased together.

The discovery of new knowledge by mining medical databases is crucial in order to make an effective use of stored data, enhancing patient management tasks. One of the main objectives of data mining methods is to provide a clear and understandable description of patterns held in data. One of the best studied models for pattern discovery in the field of data mining is that of association rules. The accuracy and importance of association rules are usually estimated by means of two probability measures called confidence and support respectively. Discovery of association rules is one of the main techniques that can be used both by physicians and managers to obtain knowledge from large medical databases.

At a hospital we find daily activity correspond to medical treatment and other health care business. For example some patients come to internist get some medicine or just routine health check up, some physician get busy treating emergency patient at emergency room, at another place the patient's family go to cashier for paying the bill, etc. It is critical to understand the benefits and limitations of using these large-scale administrative databases. From an evidence-based medicine perspective, these data are important for generating hypotheses but not cause and effect relationships. In other words, the data itself are not specifically collected to address a clinical question, but rather represent a quality assurance process.

The phrase, ‘hospital information system’, is frequently used in discussions about the flow of information throughout a hospital with the assumption that everybody has the same concept in mind. Closer examination shows that this is not necessarily the case. 

Many organizations including modern hospitals are capable of generating and collecting a huge amount of data. This explosive growth of data requires an automated way to extract useful knowledge. Thus, medical domain is a major area for applying data mining. Through data mining, we can extract interesting knowledge and regularities. The discovered knowledge can then be applied in the corresponding field to increase the working efficiency and improve the quality of decision making.

Nowadays, data stored in medical databases are growing in an increasingly rapid way. Analyzing that data is crucial for medical decision making and management. It has been widely recognized that medical data analysis can lead to an enhancement of health care by improving the performance of patient management tasks. There are two main aspects that define the need for medical data analysis.

1. Support of specific knowledge-based problem solving activities through the analysis of patients’ raw data collected in monitoring.
2. Discovery of new knowledge that can be extracted through the analysis of representative collections of example cases, described by symbolic or numeric descriptors.