Feature selection and classification model construction on type 2 diabetic patients' data.

Feature selection and classification model construction on type 2 diabetic patients' data. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Feature selection and classification model construction on type 2 diabetic patients' data. Abstract Text:

Yue Huang,Paul McCullagh,Norman Black,Roy Harper,Yue Huang,Paul McCullagh,Norman Black,Roy Harper,Yue Huang,Paul McCullagh,Norman Black,Roy Harper,

OBJECTIVE: Diabetes affects between 2% and 4% of the global population (up to 10% in the over 65 age group), and its avoidance and effective treatment are undoubtedly crucial public health and health economics issues in the 21st century. The aim of this research was to identify significant factors influencing diabetes control, by applying feature selection to a working patient management system to assist with ranking, classification and knowledge discovery. The classification models can be used to determine individuals in the population with poor diabetes control status based on physiological and examination factors. METHODS: The diabetic patients' information was collected by Ulster Community and Hospitals Trust (UCHT) from year 2000 to 2004 as part of clinical management. In order to discover key predictors and latent knowledge, data mining techniques were applied. To improve computational efficiency, a feature selection technique, feature selection via supervised model construction (FSSMC), an optimisation of ReliefF, was used to rank the important attributes affecting diabetic control. After selecting suitable features, three complementary classification techniques (Naïve Bayes, IB1 and C4.5) were applied to the data to predict how well the patients' condition was controlled. RESULTS: FSSMC identified patients' 'age', 'diagnosis duration', the need for 'insulin treatment', 'random blood glucose' measurement and 'diet treatment' as the most important factors influencing blood glucose control. Using the reduced features, a best predictive accuracy of 95% and sensitivity of 98% was achieved. The influence of factors, such as 'type of care' delivered, the use of 'home monitoring', and the importance of 'smoking' on outcome can contribute to domain knowledge in diabetes control. CONCLUSION: In the care of patients with diabetes, the more important factors identified: patients' 'age', 'diagnosis duration' and 'family history', are beyond the control of physicians. Treatment methods such as 'insulin', 'diet' and 'tablets' (a variety of oral medicines) may be controlled. However lifestyle indicators such as 'body mass index' and 'smoking status' are also important and may be controlled by the patient. This further underlines the need for public health education to aid awareness and prevention. More subtle data interactions need to be better understood and data mining can contribute to the clinical evidence base. The research confirms and to a lesser extent challenges current thinking. Whilst fully appreciating the requirement for clinical verification and interpretation, this work supports the use of data mining as an exploratory tool, particularly as the domain is suffering from a data explosion due to enhanced monitoring and the (potential) storage of this data in the electronic health record. FSSMC has proved a useful feature estimator for large data sets, where processing efficiency is an important factor.

Feature selection and classification model construction on type 2 diabetic patients' data. Publishing Authors By Initials

Y Huang,P McCullagh,N Black,R Harper,Y Huang,P McCullagh,N Black,R Harper,Y Huang,P McCullagh,N Black,R Harper,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

Feature selection and classification model construction on type 2 diabetic patients' data. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: Artificial intelligence in medicine

VOLUME: 41

Page Numbers: 251-62

Journal Abbreviation:

ISSN: 0933-3657

DAY: 17

MONTH: 08

YEAR: 2007

Feature selection and classification model construction on type 2 diabetic patients' data. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 8915031

Feature selection and classification model construction on type 2 diabetic patients' data. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: Feature selection and classification model construction on type 2 diabetic patients' data. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Feature selection and classification model construction on type 2 diabetic patients' data.

AFFILIATION: Department of Computing, Faculty of Engineering, Imperial College London, South Kensington, London SW7 2AZ, UK.

Country: Netherlands

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: Artif Intell Med

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Feature selection and classification model construction on type 2 diabetic patients' data Related Publications

• A 15-year follow-up study of 4606 primary total knee replacements.
• Application of the theory of planned behavior to understand intentions to engage in physical and psychosocial health behaviors after cancer diagnosis.
• Chapter 13: Current findings from prophylactic HPV vaccine trials.
• Chemotherapy for the treatment of hormone-refractory prostate cancer.
• Does bone quality predict loosening of cemented total hip replacements?
• Elevated mean diffusivity in widespread brain regions in congenital central hypoventilation syndrome.
• Extensive venous/lymphatic malformations causing life-threatening haematological complications.
• Feature selection and classification model construction on type 2 diabetic patients' data.
• Has vertebrate chemesthesis been a selective agent in the evolution of arthropod chemical defenses?
• Individual differences in food perceptions and calorie estimation: an examination of dieting status, weight, and gender.
• Issues in older person nursing.
• Laser Doppler flowmetry for assessing localized scleroderma in children.
• Minimising risk of Legionella.
• No strings attached: the nature of casual sex in college students.
• Overlooked, misunderstood and at-risk: exploring the lives and HIV risk of ethnic minority male-to-female transgender youth.
• Pharmacy access to emergency contraception: Perspectives of pharmacists at a chain pharmacy in San Francisco.
• Post-diagnostic cardiac catheterization: development and evaluation of an evidence-based standard of care.
• Pretransplant albumin dialysis in erythropoietic protoporphyria: A costly detour.
• RAPID COMMUNICATIONS: Older Adults' Preferences for Exercising Alone Versus in Groups: Considering Contextual Congruence.
• Sex isn't that simple: culture and context in HIV prevention interventions for gay and bisexual male adolescents.
• Supporting breastfeeding mothers in hospital: part 2a.
• Supporting breastfeeding mothers in hospital: part 2b.
• Technical Note: grading the vertical cup:disc ratio and the effect of scaling.
• The effect of infused fat emulsions on reticuloendothelial function in the rabbit.
• The energetic implications of uncoupling protein-3 in skeletal muscle.
• The morphology of the inner ear from the domestic pig (Sus scrofa).
• Translating ethics: Researching public health and medical practices in Nepal.
• Uncertainty Determination for Nondestructive Chemical Analytical Methods Using Field Data and Application to XRF Analysis for Lead.
• Vocational outcomes of state vocational rehabilitation clients with traumatic brain injury: a review of the Missouri Model Brain Injury System Studies.
• What did Simon say? Revisiting the bilingual advantage.