Data mining in health and medical information

Developing a Health Risk Evaluation Method for Triple H

The development of a health evaluation system from human-related data is an important issue in preventive medicine. Previously, most studies have focused on disease assessment and prevention in patients. However, even if certain risk factors are all within normal ranges, individuals may not necessarily be completely healthy. This study focused on healthy individuals to develop a new index to assess health risks; this index can be used for the prevention of multiple diseases in healthy people. The kernel density technique was proposed to estimate the distribution of common risk factors and to develop a health risk index. A dataset of hypertension, hyperlipidemia, and hyperglycemia (Triple H) data from the National Health Insurance Research Database in Taiwan was used to demonstrate the proposed analytical process. The results of risk factor changes after six weeks of exercise were used to calculate the health risk index. The results showed that the subjects experienced a 7.29% reduction in their health risk index after the exercise intervention. This finding demonstrates the potential impact of an important reference index on quantifying the effect of maintenance in healthy people.

Mining the electronic health record for disease knowledge

The growing amount and availability of electronic health record (EHR) data present enhanced opportunities for discovering new knowledge about diseases. In the past decade, there has been an increasing number of data and text mining studies focused on the identification of disease associations (e.g., disease-disease, disease-drug, and disease-gene) in structured and unstructured EHR data. This chapter presents a knowledge discovery framework for mining the EHR for disease knowledge and describes each step for data selection, preprocessing, transformation, data mining, and interpretation/validation. Topics including natural language processing, standards, and data privacy and security are also discussed in the context of this framework.

New developments in the spatial scan statistic

The quantity and variety of spatial data have increased over recent years, and the variety and sophistication of tools for analysing this type of data have also increased. One such tool is the spatial scan statistic, which is freely available ( www.satscan.org ) and has been the subject of much scholarly research since its introduction in 1995 owing to its numerous applications in epidemiology, criminology and other fields. This paper provides readers with a non-technical introduction to the spatial scan statistic, together with an overview of associated research, which focuses particularly on work conducted at the University of Sheffield’s Information School, in collaboration with the School of Health and Related Research. This work falls into three main areas. First, we provide an examination of the probability of obtaining false alerts when using the statistic, and ways in which this can be managed. Second, we describe the development of a definitive way of measuring the spatial accuracy of the statistic. Third, and potentially the most important in terms of impact, we discuss a means of substantially increasing the detection capability of the statistic by placing a realistic constraint on the strength of any cluster that is likely to be present in the data. The paper also provides a discussion of potential future research directions.

The development of dentist practice profiles and management

RATIONALE AND OBJECTIVES

With the current large computerized payment systems and increase in the number of claims, unusual dental practice patterns to cover up fraud are becoming widespread and sophisticated. Clustering the characteristic of dental practice patterns is an essential task for improving the quality of care and cost containment. This study aims at providing an easy, efficient and practical alternative approach to developing patterns of dental practice profiles. This will help the third-party payer to recognize and describe novel or unusual patterns of dental practice and thus adopt various strategies in order to prevent fraudulent claims and overcharges.

METHODOLOGY

Knowledge discovery (or data mining) was used to cluster the dentists' profiles by carrying out clustering techniques based on the features of service rates. It is a hybrid of the knowledge discovery, statistical and artificial neural network methodologies that extracts knowledge from the dental claim database.

RESULTS

The results of clustering highlight characteristics related to dentists' practice patterns, and the detailed managerial guidance is illustrated to support the third-party payer in the management of various patterns of dentist practice.

CONCLUSION

This study integrates the development of dentists' practice patterns with the knowledge discovery process. These findings will help the third-party payer to discriminate the patterns of practice, and also shed more light on the suspicious claims and practice patterns among dentists.

Health informatics: current issues and challenges

Health informatics concerns the use of information and information and communication technologies within healthcare. Health informatics and information science need to take account of the unique aspects of health and medicine. The development of information systems and electronic records within health needs to consider the information needs and behaviour of all users. The sensitivity of personal health data raises ethical concerns for developing electronic records. E-health initiatives must actively involve users in the design, development, implementation and evaluation, and information science can contribute to understanding the needs and behaviour of user groups. Health informatics could make an important contribution to the ageing society and to reducing the digital divide and health divides within society. There is a need for an appropriate evidence base within health informatics to support future developments, and to ensure health informatics reaches its potential to improve the health and well-being of patients and the public.

Knowledge discovery in traditional Chinese medicine: State of the art and perspectives

OBJECTIVE

As a complementary medical system to Western medicine, traditional Chinese medicine (TCM) provides a unique theoretical and practical approach to the treatment of diseases over thousands of years. Confronted with the increasing popularity of TCM and the huge volume of TCM data, historically accumulated and recently obtained, there is an urgent need to explore these resources effectively by the techniques of knowledge discovery in database (KDD). This paper aims at providing an overview of recent KDD studies in TCM field.

METHODS

A literature search was conducted in both English and Chinese publications, and major studies of knowledge discovery in TCM (KDTCM) reported in these materials were identified. Based on an introduction to the state of the art of TCM data resources, a review of four subfields of KDTCM research was presented, including KDD for the research of Chinese medical formula, KDD for the research of Chinese herbal medicine, KDD for TCM syndrome research, and KDD for TCM clinical diagnosis. Furthermore, the current state and main problems in each subfield were summarized based on a discussion of existing studies, and future directions for each subfield were also proposed accordingly.

RESULTS

A series of KDD methods are used in existing KDTCM researches, ranging from conventional frequent itemset mining to state of the art latent structure model. Considerable interesting discoveries are obtained by these methods, such as novel TCM paired drugs discovered by frequent itemset analysis, functional community of related genes discovered under syndrome perspective by text mining, the high proportion of toxic plants in the botanical family Ranunculaceae disclosed by statistical analysis, the association between M-cholinoceptor blocking drug and Solanaceae revealed by association rule mining, etc. It is particularly inspiring to see some studies connecting TCM with biomedicine, which provide a novel top-down view for functional genomics research. However, further developments of KDD methods are still expected to better adapt to the features of TCM.

CONCLUSIONS

Existing studies demonstrate that KDTCM is effective in obtaining medical discoveries. However, much more work needs to be done in order to discover real diamonds from TCM domain. The usage and development of KDTCM in the future will substantially contribute to the TCM community, as well as modern life science.

Identification of Risk Factors for 15-Year Mortality Among Community-Dwelling Older People Using Cox Regression and a Genetic Algorithm

BACKGROUND

Previous research has identified various risk factors for mortality in older people, but has considered a limited number of the variables available for analysis. The aim of this study was to use a genetic algorithm combined with Cox regression (CoRGA) to examine all the variables to identify risk factors for 15-year mortality.

METHODS

Data were obtained from a nationally representative sample of 1,042 community-dwelling people aged 65+. Data on cognitive impairment, physical health, physical activity, psychological well-being, social engagement, and physical capability resulted in 460 independent variables for analysis. Outcome was time from 1985 interview to death or censorship on February 29, 2000. CoRGA was used to selected combinations of 1, 2, 4, 8, 12, and 16 variables as potential risk factors for 15-year mortality.

RESULTS

CoRGA selected age in all six models; variables relating to handgrip strength were selected in five models; variables relating to reported chest pain were selected in four models; and pain in joints causing difficulty in carrying bags and self-rated activity compared to peers were both selected in three models. Other variables selected by CoRGA included time since last visited the dentist and optician, use of hypnotic drugs, and number of prescribed drugs being taken.

CONCLUSIONS

CoRGA confirmed current risk factors for long-term mortality among older people and identified new risk factors. Age was confirmed as the most important predictor of mortality in older people. Handgrip strength is an important marker of frailty in predicting mortality. Self-rated activity is an important predictor of long-term mortality.