Personalized Medicine Case Study

Words: 1314
Pages: 6

Personalized medicine relies on Big Data
The core objective of personalized medicine is to generate a structure that exploits patients’ electronic health records (EHRs) and OMICS (primarily genomics) data to facilitate clinical decision-making that is predictive, personalized, preventive, and participatory (P4 Medicine) [26, 27]. To study personalized medicine, we need to collect and integrate biological data (e.g. gene, protein sequences, functions, biological process and pathways) and clinical information (e.g. medical images, medical diagnosis, and patient histories) which have varied formats and are produced from distinctive and heterogeneous sources. The emphasis is to customize medical treatment according to the individual characteristics

It is estimated that by year 2020 there will be 5,200 gigabytes of data for every human being on the earth [30] and healthcare data will reach 25,000 petabytes (petabytes = 1,000,000,000,000,000 bytes = 1015 bytes = 1000 terabytes = 1 million gigabytes), equivalent to a 50-fold increase from year 2012 [31]. Medical information is doubling every 5 years, but 90% of digital medical data was developed in just the past 2 years, and 80% of it is raw and unstructured data. Big Data must be more than a data catalogue or data dump [29]. Therefore, management of such information will demand immediate attention and action.
Nevertheless, having the huge amount of data itself does not solve any problem in personalized medicine. The data needs to be summarized or abstracted in the meaningful way so as to be translated into information, knowledge and finally wisdom. We need to investigate in order to effectively translate a large number of data for utilizing in decision-making. To handle the vast amount of data, tools such like Hadoop software can assist us to accelerate our data processing and querying

The process of personalized medicine could be facilitated with the comparison of a new patient to patients with similar characteristics. This could result in faster and more accurate diagnoses and consideration of therapeutic options. Nevertheless, before the full potential of Big Data can be realized for healthcare generally, and for personalized medicine particularly, several challenges related to data processing, integration, and analytics, visualization and interpretation need to be addressed