Mining Three-Dimensional Anthropometric Body Surface Scanning Data for Hypertension Detection

• Published in: IEEE transactions on information technology in biomedicine Vol. 11; no. 3; pp. 264 - 273
• Main Authors: Chaochang Chiu, Kuang-Hung Hsu, Hsu, P.-L., Hsu, C.-I., Po-Chi Lee, Wen-Ko Chiou, Thu-Hua Liu, Yi-Chou Chuang, Chorng-Jer Hwang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2007
• Subjects: Algorithms; Anthropometric data; Anthropometry - methods; Artificial Intelligence; association rule; Association rules; Chaos; Classification tree analysis; classification trees; Data mining; Diseases; Genetic algorithms; genetic algorithms (GAs); Health information management; Humans; Hypertension; Hypertension - diagnosis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Information management; Information Storage and Retrieval - methods; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Spatial databases; Whole Body Imaging - methods
• ISSN: 1089-7771
• DOI: 10.1109/TITB.2006.884362

Hypertension is a major disease, being one of the top ten causes of death in Taiwan. The exploration of three-dimensional (3-D) anthropometry scanning data along with other existing subject medical profiles using data mining techniques becomes an important research issue for medical decision support. This research attempts to construct a prediction model for hypertension using anthropometric body surface scanning data. This research adopts classification trees to reveal the relationship between a subject's 3-D scanning data and hypertension disease using the hybrid of the association rule algorithm (ARA) and genetic algorithms (GAs) approach. The ARA is adopted to obtain useful clues based on which the GA is able to proceed its searching tasks in a more efficient way. The proposed approach was experimented and compared with a regular genetic algorithm in predicting a subject's hypertension disease. Better computational efficiency and more accurate prediction results from the proposed approach are demonstrated