• Subscribe

3 things you didn't know big data could do

Speed read
  • Data analytics may predict death in terminal patients
  • Facebook proves that emotions are contagious on social media
  • Smartphones give medical researchers access to unprecedented numbers of participants

The data deluge is here. According to IBM, humans create roughly 2.5 quintillion bytes of data every day. That number is constantly growing, with around 90% of the world’s data having been created within the last two years.

While larger developments within big data often make the news, smaller and stranger discoveries get lost in the shuffle. After all, it’s BIG data, and there’s a lot of it. So let’s take a look at three things you may not know big data can do.

1. Predict death

Improvements in medicine are allowing people to live longer, postponing death until an ever-older age. Sadly, this often translates to a slow and painful departure from the land of the living that may end with a stay in hospice care.

In fact, around 1.65 million US patients required hospice services in 2014. Globally in 2011, more than 29 million people died from diseases that required hospice care.

<strong> The final six months</strong> of a patient's life are often consumed by emergency visits and medical procedures. Could risk prediction help them find a more peaceful end? Courtesy Unsplash.Knowing when a loved one needs to move into hospice care is a hard decision, which is why risk prediction company KenSci decided to develop an algorithm that can help predict a patient’s date of death. According to their research paper, 28% of hospice patients die or are discharged within a week of care.

However, KenSci also found that the last six months of a patient’s life are often wrought with emergency visits and medical procedures. For many, this can feel like a loss of control over their loved one’s final days.

The goal for KenSci’s researchers was to find a way to more accurately predict a terminal patient’s mortality risk within the next 6 to 12 months. To do this, the company surveyed two datasets from patients in the US Pacific Northwest.

The company relied on Microsoft Azure cloud computing to sift large sets of electronic medical records, psychosocial, and financial information. The cloud-based nature of this research allowed scientists to incorporate new data as it was created.  

While some may worry this research will lead to doctors deciding a patient’s fate based on an algorithm, KenSci CTO Teredesai is quick to state that this work is about increasing quality of life.

Read more:

2. Emotional contagion is a real thing

The internet is a pretty emotional space. But, a research team from Facebook took this concept one step further and proved that user emotions can be easily transferred.

<strong>When Facebook manipulated</strong> users' feeds so they saw only positive posts, their own posts mirrored that emotion. The same was true for negative posts. Courtesy Adam Jang/Unsplash.The researchers selected 689,000 Facebook users and manipulated their feeds to either show only positive or only negative posts. Using linguistic data analysis, the researchers tracked the use of positive and negative words.

After sifting through more than 3 million posts containing more than 122 million words, the researchers found that users who never saw positive content on their feeds made fewer positive posts. Similarly, those who didn’t see negative content had fewer negative posts.

The idea of becoming more positive by surrounding yourself with positivity certainly isn’t new, but this latest research demonstrates the ease of mass emotional manipulation in a social media era.

Read more:

3. Make medical discoveries

Perhaps the biggest contributor to the current data wave is the smartphone. According to the Pew Research Center, around 77% of Americans and one-third of the global population own at least one internet-connected smart device.

Enter ResearchKit, an open source framework designed by Apple for iPhones. The technology gives medical researchers access to the data of users in order to receive more accurate information.

<strong>Flexible data.</strong> Apple's ResearchKit allowed scientists to collect data from users reporting air quality as an asthma trigger during the 2017 Washington state wildfires. Courtesy SFC Jason Kriess, Washington National Guard.ResearchKit study participants still must consent and enroll in the trials. Even so, researchers are able to acquire data more frequently than in traditional studies and from a larger and more varied study group.

In one study, around 50,000 iPhone owners downloaded an app to tell researchers how they treat their asthma. The app also retrieved information about geographic location and air quality. This allowed the scientists to receive incredibly accurate data about asthma, such as how the 2017 wildfires in Washington state affected asthma patients.

One of the most important aspects of this study is that it proved that apps can reliably provide health information to researchers. Dr. Yvonne Chan, the principal investigator of this project, believes the study “demonstrates the power of mobile health tools to scale and accelerate clinical research.”

Read more:

Perhaps the greatest strength of big data lies in its flexibility. Data is being created all the time, and researchers finally have the tools and know-how to make the most of this information. The only limit is their imagination—and it’s impossible not to get excited about that.

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2018 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.