Okaya is focused on building the best-of-breed wellbeing diagnosis API. To do so, we use the concept of a check-in. A check-in is a 15 second video selfie. We then take this video and voice information, along with other external data to see how someone is trending. This approach often begs the question of why we use so many factors to analyze someone’s wellbeing when others take a more limited approach. After all, why not just analyse someone’s mood based on a video alone or just looking at contents from a chat-bot? It comes down to this: Data, especially in a silo, lies all the time and is hugely biased. This is why it is critical that you cross-check the information returned by your data and algorithm.
Let me give you an example: If you see this sentence, how do you think the person is doing?
I am leaving the house because my son and my brother had a huge fight. I don’t know whose fault it is. I’m really afraid that he is going to hurt him.
Algorithms are no different than humans: We take this sentence and process it, based on our biases and assumptions. And we make a decision based on the information we have.
But, obviously, this decision is absolutely incomplete and akin to guessing. So now let’s contrast this single information point with adding extra layers. Let’s look at 2 videos showing an actor speaking the same text but with very contrasting emotions.
Can you see how much the facial expressions, tone of voice, and overall attitude make a difference in our understanding of the original message? Already based on this information we would change our perception of how the person is doing and potentially how we would help them cope. This is already one layer of cross-checking the information returned by your data and algorithm.
This perception would be further altered based on how past understanding of the person or external circumstances we know of.
Look, we’ve all heard at some point that communication is 93% non-verbal. This is true. And if we want to reduce bias in our algorithm, we need to take these elements into account. The fewer elements we take into account, the more likely we are to have inaccurate assessments and evaluations.
The Health Industry relies on mental assessments to identify and assist people who are in need. Unfortunately, using the current method, up to 66% of such diagnoses are incorrect. Misdiagnoses have huge financial costs. They also take a toll on patients’ health, and sometimes, their lives.
To change this Okaya is changing the way mental health is assessed. This is why we’re taking this comprehensive approach with our API and are always cross-checking the information returned by our data and algorithm.