Tech startup Kintsugi is attempting to use technology to measure the likelihood of depression by listening to a patient's voice, TechCrunch reported May 31.
Co-founders Grace Chang and Rima Seiilova-Olson were inspired to create Kintsugi by their individual struggles finding therapy while they experienced depression. The two engineers sought to build an application programming interface capable of detecting signs of depression through voice.
"We saw this as an infrastructure problem where you have so many people trying to jam through that front door, but not a lot of visibility as to who is severely depressed and who is in this low to moderate phase. And if we can provide this information to those practitioners, we can really deeply affect the specific problem," Ms. Chang told TechCrunch.
Clinicians have noticed the tendency for those dealing with depression to have a flat voice, and according to Ms. Seiilova-Olson, this occurs regardless of language or culture.
Kitsugi aims to use technology to analyze a patient's voice and measure the likelihood of depression on two scales, both of which use higher numbers to indicate higher severity, and once granted permission from the patient, the clinician can get immediate feedback based on the score provided.
"Our neural network model has been trained on tens of thousands of depressed voices. So it can be like a set of psychiatrists, but it's much more sensitive. It can pick it up even when the depression is at mild or moderate levels," Ms. Seiilova-Olson told TechCrunch.
The software will be used to listen to patient voices during intake processes to determine if they may be struggling with depression in a short window of time, for example during outgoing calls to patients.
The startup raised an initial $8 million seed round last year followed by $20 million in series A funding this year and has contracts with a couple of large healthcare companies, while looking to expand further this year.