Busara Centre for Behavioral Economics hosts its first annual data hackathon as it moves to develop model for predicting depression

After hours of a grueling battle, Allan Chepkoy, a three-time hackathon champion emerged victorious and walked away with Sh20,000 ($200).

___9118081___2018___11___19___9___Busara+3
  • On November 17th 2018, Busara Centre for Behavioral Economics held its first annual data hackathon to find the best statistical model to predict depression.
  • WHO estimates that 1.3 million Kenyans suffer from depression and Africa has the highest rate of untreated depression of any continent.
  • After hours of a grueling battle, Allan Chepkoy, a three-time hackathon champion emerged victorious and walked away with Sh20,000 ($200).

With this in mind, the Busara Centre for Behavioral Economics, a research and advisory nonprofit organization based in Nairobi, is determined to change this narrative using technology and breathe to life the century old saying that ‘prevention is better than cure’.

On November 17th 2018, the centre decided to challenge the Nairobi data science community to apply their skills to address this pressing problem by hosting its first annual data hackathon. 70 attendees competed to find the best statistical model to predict who is likely to be suffering from depression before it is too late.

“This hackathon and other community events are important because there are lot of talented people in the tech community, such as developers and students, who know a little about machine learning but need a way to start applying their skills - this is a simple challenge in an encouraging, mentored environment. Also, calling the tech community’s attention to mental health is important. There are a lot of areas where data science can help alleviate problems in health care and mental well-being, so hopefully this event will plant ideas in people's mind for future projects,” said Daniel Mellow, Busara Centre’s Data Specialist.

Using data from a 2015 study conducted by the Busara Center in Siaya County, in which over 2800 individuals from 1440 households were surveyed about their family composition, economic activity, financial position and health, participants raced to create the best model to predict who is likely to be suffering from depression.

“The information and data we get from such hackathons is invaluable. Going forward we look forward to incorporate more stakeholders in such events so that the learnings we get can have direct impact on the ground,” asserted Alfred Ongere from AI Kenya.

“It feels great especially after long hours of sitting in the house teaching myself how to be a machine learning engineer.The learning curve has been very steep and winning justifies the hard work and perseverance. It validates the adage that anyone can do anything,” said Allan, who also recently won BBCs Beyond Fake News hackathon challenge.

Sh50,000 ($500) were up for grabs with the winner walking away with Sh20,000, second runners up Sh10,000, third position Sh7500, fourth position Sh5000 and fifth position clinching Sh2500.

In Kenya, while household surveys are routine and relatively cheap to collect, the screening process for depression is sensitive and needs to be carried out with protocols in place for referring serious cases.

Unfortunately, mental health resources are scarce. Using machine learning to better target these resources could allocate treatment where it is needed most and improve an untold number of lives.

If the machine learning community could find a way to use routine survey data to predict who is at risk of depression, clinicians might be able save time and energy by going straight to those cases.

JOIN OUR PULSE COMMUNITY!

Eyewitness? Submit your stories now via social or:

Email: news@pulselive.co.ke