Biomedical subjects

I-Nong Lee

Publications and source records attributed to I-Nong Lee.

5 recordsLinked to original sources

PubMed2006

Discovering meaningful information from large amounts of environment and health data to reduce uncertainties in formulating environmental policies.

This study uses knowledge discovery concepts to analyze large amounts of data step by step for the purpose of assisting in the formulation of environmental policy. We performed data cleansing and extracting from existing nation-wide databases, and used regression and classification techniques to analyze the data. The current water hardness in Kaohsiung, Taiwan contributes to the prevention of cardiovascular disease (CVD) but exacerbates the development of renal stones (RS). However, to focus on water hardness alone to control RS would not be cost effective at all, because the existing database parameters do not adequately allow for a clear understanding of RS. Analysis of huge amounts of data can most often turn up the most reliable and convincing results and the use of existing databases can be cost-effective.

Data Interpretation, Statistical↗

PubMed2004

Developing a safety and health training model for petrochemical workers.

The production processes of the petrochemical industry expose workers to high potential hazards. Our previous study showed that hazard recognition was closely related to worker safety and health training activities. The purpose of this study was to establish and validate a safety and health training model. It is expected that the training model will help workers to recognize hazards, thereby lowering their operating risks. The training model, which included a complete training course and follow-up scoring using a questionnaire, was applied to three groups of subjects for comparison. Group A had joined our study previously and took the training course again at this time. Group B had also joined our previous study but did not take this training course. Group C was new to our study and took this training course for the first time. Groups A and C (who took the training course) had higher cognition and attitude scores than group B (who did not take the training course). The training course was a significant factor that positively influenced both cognition and attitude scores among managers and workers. The training course was more significant for managers while the duration of education was more significant for workers.

Adult↗

PubMed2003

Building collapse and human deaths resulting from the Chi-Chi Earthquake in Taiwan, September 1999.

In this study, the authors attempted to determine factors associated with earthquake deaths in the great Chi-Chi Earthquake that occurred on September 21, 1999, in Taiwan. An isoseismal map was used to identify life-threatening hazards. The vertical peak ground acceleration of ground motion intensity was deemed the most appropriate index for the evaluation of building collapse and mortality. Mortality increased with the increase in earthquake intensity, and building collapse, approaching the epicenter. The greatest number of collapsed buildings and human deaths occurred between the Chelungpu Fault and the Shuantun Fault. Individuals 65 yr of age and older were the most vulnerable to the impact. The authors' findings suggest that improvements in earthquake-resistant building design and construction, as well as improved medical rescue for the elderly, could reduce the level of exposure to earthquake hazards.

Adolescent↗

PubMed2002

Appropriate medical data categorization for data mining classification techniques.

Some data mining (DM) methods, or software tools, require normalized data, others rely on categorized data, and some can accommodate multiple data scales. Each DM technique has a specific background theory; therefore, different results are expected when applying multiple methods. The purpose of this study is to find the data format appropriate for each DM classification technique for wider applications, and efficiently to obtain trustworthy results. Considering the nature of medical data, categorical variables are sometimes useful for making decisions and can make it easier to extrapolate knowledge. In this study, three mathematical data categorization methods (Fusinter, minimum description length principle [MDLPC] and Chi-merge) were applied to accommodate five data mining classification techniques (statistics discriminant analysis, supervised classification with Neural Networks, Decision trees, Genetic supervised clustering and Bayesian classification [probability neural networks; PNN]) using a heart disease database with four types of data (continuous data, binary data, nominal data, and ordinal data). Compared with original or normalized data, data categorized by the MDLPC categorization method was found to perform better in most of the DM classification techniques used in this study. Categorical data is good for most DM classification techniques (e.g. classification of disease and non-disease groups) and is relatively easy to use for extracting medical knowledge.

Bayes Theorem↗

PubMed2002

Important variable selection techniques with multiple solutions for medical information applications.

The purpose of this study is to utilize the strategy of multiple solutions with easily operated tools to make compatible and affordable trustworthy results. This strategy can satisfy general users in extracting specific knowledge (e.g. diagnosis, treatment, health education, hospital administration, etc.). Wide application is one of the key promoters of a successful medical information system. Risk factors of heart disease can be identified by important variable selection techniques. Four techniques, Chi-square test, correlation analysis, stepwise discriminant analysis, and decision trees, were used in this study. One must compile the results of the different methods to deal with specific research questions in a logical way. It is expected that this approach may reduce the uncertainties obtained from a single method. When applying the important index derived from the four different method results to several applications, all results have been confirmed by current medical knowledge or otherwise provide meaningful information. The prime purpose of this study is not disease diagnosis, but to enable the general health practitioner (medical doctor, hospital administrator, etc.) to formulate their hypothesis.

Case-Control Studies↗