Calendar

October 2017
M T W T F S S
« Jul    
 1
2345678
9101112131415
16171819202122
23242526272829
3031  

Calendar

October 2017
M T W T F S S
« Jul    
 1
2345678
9101112131415
16171819202122
23242526272829
3031  

Follow us on…

  • {name}
  • Google Profile
  • LinkedIn
  • Twitter
  • Facebook
  • YouTube
  • slideshare

Facebook

Recent videos

Posted on: September 22-2015 | By : Deepika Das | In: Analytics,Big Data,Business Agility,Digital Solutions,Enterprise Technology,Healthcare Informatics,Regulation and Compliance | 2 Comments

The significance of personalized medicine/precision medicine and its benefits is still new to the masses. However, the number of personalized medicine products has more than quadrupled in recent years. From the meagre 13 personalized medicine products available in 2006 to more than 70 in 2012, experts predict the American market for these drugs will double – increasing the market share from $9.2 billion in 2013 to $18.2 billion in 2019.
 
Although the numbers are promising, the underlying question is — what will help drive computational genome analysis in associating genomes to clinical features?

One can say that all the fuss about precision medicine is more in labs than in clinics. Yet, there is no doubt that computational and algorithmic improvement will help analyze the vast genome variations and map them to more clinically meaningful insights.

 

Big data analytics provides the right set of technology which can help fulfil this requirement. Evolving analytical models and extended infrastructure capabilities, address the issue of better analysis and visualization along with the basic need to compute a large set of data across multiple touch points.
Let us consider the following example of cancer care for a single patient:

 

As the visual illustrates, when a physician orders a genetic test, he tries to identify a cancer–related problem in the genome. Decoding a complete genome would take up 600 – 700 GB space (in our case ~700 MB for a small section of genome) for each patient. Apart from the test, data needs to be extracted from various other sources such as data from medical sensors, where a single scan of an organ can generate around 10 GB of data per second. Further, the test results need to be compared with clinical trials and genome databases to make a conclusive decision.

 

It is evident how big data helps analyze a huge volume of data across multiple touch points, and offers precision medicines and solutions for a patient.

Research organizations and pharmaceutical giants are lagging in implementing such technology. These organizations will have to eventually approach IT organizations to include big data analytics into their IT strategy roadmap.

 

Despite data security concerns, high operational costs, and complicated workflows, big data forms the stepping stone in making personalized medicine a reality.

 

References:

• Decision Resources, What You Need to Know to Create or Sustain a Personalized Medicine Strategy for Your Company (2013).

1 Star2 Stars3 Stars4 Stars5 Stars (2 votes, average: 4.50 out of 5)
Loading ... Loading ...

Deepika Das


Dr.Deepika a Dentist by profession, and an MBA in Healthcare IT has around 3 years of experience in...

Read More...

 
 
  1. Moumita Adhikary on November 30, 2015 at 10:24 pm Says:

    That’s an impressive study I got to read.

    However, what is the flexibility of an expensive Analytics approach through Big Data possibly for specific use in domains apart from Healthcare?

  2. Pestcom India on April 16, 2016 at 4:33 pm Says:

    I had been searching for the information for a long. And I think I have found a satisfying answer.
    business healthcare solutions

Leave a Reply

 

*

© 2017 Syntel, Inc.