Translational and High End Computing of Clinical Data in India

Abstract

Healthcare sector is generating large amount of data pertaining to diagnosis, disease identification and treatment of an individual. Mining knowledge and providing scientific decision-making for the diagnosis and treatment from the clinical dataset is therefore increasingly becoming necessary. Aim of this research study was to assess the applicability of knowledge discovery on a clinical warehouse. A major contribution of the study consists of significant extensions to the data modelling for the structure of clinical warehouse. The data stored in the warehouse was subjected to data mining in form of case studies. Also, a novel temporal mining algorithm is being proposed in the study to augur state of disease for a particular patient. Clinical data used in this study was collected during the period of Oct. 2010 - Apr. 2012 from various hospitals and diagnostic centres across India. Data for all the human subjects have been analyzed anonymously. Based on NOC (No objection certificate) received from the hospitals in India, all the patient information was received corresponding to IDs (Identification Number). Utmost care has been taken for non-disclosure of the hospital names or patient information in this study. newline Patient s records are increasing at an exponential rate, thus adding to the problem of data management and storage. Major problem being faced corresponding to temporal storage of this clinical data, is the varied dimensionality, ranging from images to qualitative and quantitative form. Therefore there is a need for development of efficient data model which can handle this multi-dimensionality data issue and store the data in temporal aspect.