AI can now detect depression just from your voice🗣️
One summer, I set out on a 2-week journey with just a backpack. I traveled solo with no reservations and no list of places to visit. The only plan was to tour the Himalayan region. I stopped at random places and did what I felt like at the moment. I visited 20 cities across two countries spanning 650 miles. It was one of the best trips I ever made!
I was reminded of this dream trip by an auto-curated album from Google Photos that said “Memories from 6 years ago”. After a nostalgic look at the blog I wrote on this solo backpacking trip, I resumed planning our next 2-hour hiking trip with my kids. When moving out of the house has become a luxury, this is a trip I’m now excited about.😄
This newsletter will take you about 5 minutes to read.
I. Spotlight: AI can now detect depression just from your voice🗣️
Rima Seiilova-Olson moved to San Francisco as a research analyst in 2015. A few years later, when she gave birth to her first child, she experienced postpartum “baby blues.” Most mothers experience mood swings in the first few weeks after delivery. But for some, this develops into a more severe condition called postpartum depression.
Seiilova-Olson decided to seek professional help. She remembers making frantic calls to her healthcare provider for appointments. After many attempts, she managed to schedule a visit with a therapist. The appointment was more than two months away.
She had no option but to wait.
Around this time, Seiilova-Olson met Grace Chang in the Bay Area’s Open AI Hackathon. Chang faced similar frustrations in getting help for mental health. This meeting led to the founding of Kintsugi, a startup that uses AI to democratize mental health.
Mental healthcare faces two main issues. Firstly, it is not easy to get access to mental health professionals on a timely basis. Secondly, for patients who manage to get professional help, the diagnostic process and quality of care are not consistent.
With one in every two Americans projected to suffer from depression post-pandemic, these challenges are more important than ever.
Startups like Kintsugi and Sonde Health are tapping into the power of AI to solve these critical roadblocks in mental health. Thanks to recent breakthroughs, AI can now detect depression just by listening to someone speak a few sentences.
Surprisingly, the language or the words spoken aren’t as important as how you say it.
(Photo by Patrick Fore on Unsplash)
How can you diagnose complex health conditions just from the human voice?
“When we listen to a person speaking, we notice variations in pitch, energy, tonal quality, and rhythm,” says David Liu, CEO of Sonde Health. “By processing this audio, we can break down a few seconds of voice recording into a signal with thousands of unique characteristics.”
What’s less known is that small changes in someone’s voice every few milliseconds can result from changes in their body and health conditions. With this rich data, it is possible to identify which vocal features map to particular disease symptoms.
Using data from thousands of individuals who suffer from certain health conditions, we can teach AI algorithms to detect the vocal patterns that are common among these patients. These vocal features or ‘vocal biomarkers’ can then help diagnose when anyone starts experiencing depressive symptoms.
“We discovered that our AI model’s results did not depend on the language the people were speaking, their age or gender, or even the part of the world they lived in,” says Seiilova-Olson. The deep signals in one’s voice transcend all these differences.
With just 20 seconds of an audio clip, Kintsugi’s AI solution detects mental health issues with over 80% clinical accuracy. Compared to practitioners' accuracy, which stands at 47.3%, AI can almost double the effectiveness of patient diagnoses.
How are healthcare providers using these AI solutions to aid clinicians today? How can consumers access them on their smartphones? My latest Forbes article shares some real-world examples and risks of the technology.
II. Industry Roundup:
1. Over 72% of data leaders are heavily involved in Digital Transformation
3 minutes | Gartner
The latest CDO (Chief Data Officer) survey from Gartner found that data leaders are playing an instrumental role in digital transformations over the past year. The top 3 priorities reported by CDOs were: data quality, ROI from data investments, and data sharing. Respondents say it’s not enough to manage data or create insights. For better influence, CDOs must deliver measurable outcomes on business KPIs.
2. European initiative to improve AI literacy
3 minutes | University of Helsinki, Reaktor
With an aim to strengthen digital leadership in the EU, Finland launched an online course ‘Elements of AI.’ Rolled out in 21 EU countries in their own languages the 6-week course has over 650,000 learners. In last week’s edition, we discussed the importance of data literacy for enterprises. This initiative aims to train 1% of EU citizens on AI literacy. This is a welcome global initiative and we need more of these.
3. Rogue killer drone autonomously ‘hunted down’ a human target
2 minutes | Business Insider | Joshua Zitser
A UN report says that weaponized drones were used in the Libyan conflict last year. It adds that one of these killer drones hunted down a human target without being told to do so. Technology being put to unethical or harmful use is one of the biggest risks we face today. The spread of killer robots has already begun😔. While we celebrate the advances of AI, we urgently need stringent regulations to prevent its misuse.
III. From my Desk:
1. Video: 5 Steps to transform into a data-driven organization
In my Gramener webinar last week, I shared the latest industry trends on how the pandemic has impacted data teams. I showed how data maturity can act as your compass to help you navigate and become a data-driven organization.
-> Check out the Video & Slides
2. Article: AI can now detect depression and it’s twice as accurate as human practitioners
Depression is a huge challenge today. Can AI help detect, manage & treat the condition just by listening to your voice? The article reveals the technology behind this breakthrough and how it’s disrupting mental healthcare.
-> Read the Forbes Article (Preview shared in the spotlight above)
There’s a Gartner Hype Cycle for Emerging Quarantines😷! This one is not from Gartner, but it’s a light-hearted, brilliant meme for the pandemic.🤣
Thank you for subscribing and reading the newsletter. I appreciate your attention,
Ganes.
PS: Did someone forward this to you? You can subscribe here.
My Website | LinkedIn | Twitter | YouTube
I’m Ganes Kesari. I publish ‘Data-Driven Future’ to help understand how data shapes our world, explore key trends, and explain what they mean for you today. I speak and write to demystify data science for decision-makers and organizations.
Recent Issues: