Topics
Latest
AI
Amazon
Image Credits:Callyope
Apps
Biotech & Health
clime
Image Credits:Callyope
Cloud Computing
Commerce Department
Crypto
Enterprise
EVs
Fintech
fund raise
contraption
Gaming
Government & Policy
Hardware
Layoffs
Media & Entertainment
Meta
Microsoft
Privacy
Robotics
Security
societal
blank
Startups
TikTok
Transportation
Venture
More from TechCrunch
Events
Startup Battlefield
StrictlyVC
Podcasts
video
Partner Content
TechCrunch Brand Studio
Crunchboard
get through Us
French startupCallyopeisn’t your average startup as it is address a very intemperate problem in a extremely regulated industry . The inauguration is building a outback patient monitoring platform for mass living with schizophrenia , bipolar disorders and potentially other genial health subject . And the party is using the affected role ’s voice for this monitoring creature .
Callyope recently raised a $ 2.4 million ( € 2.2 million ) financial backing round cobalt - led by 360 Capital and Bpifrance ’s Digital Venture fund . No Label Ventures and several holy man investors are also participating in the round .
In Fance , 600,000 people endure with schizophrenic disorder . More than a million masses experience bipolar upset . Many of them see a psychiatrist on a regular basis . But psychiatrists are overwhelmed and can only see each affected role every four to six weeks .
“ You have good deal of speck that have been around since the 1970s to more or less stabilise hoi polloi . And yet , when you go to a psychiatrical infirmary , half of the citizenry there regress in the same twelvemonth , ” co - founder and CEO Martin Denais differentiate me .
When you see a psychiatrist on a regular basis , they can normally prevent backsliding before it ’s too recently . That ’s why Callyope wants to “ enhance ” psychiatrists with a patient monitoring system that can alarm health professional person . This mode , they can hold a time slot for the patient the next day .
Instead of asking patient to fill out a form , Callyope uses speech realisation and other soft biomarkers ( such as sleep , physical and societal activity ) to chequer in with patients on a regular basis . That ’s because patients often have emergence with the self - percept of their symptoms . They finger like they ’re doing finely even though thing are worse than the late week .
“ On the patient ’s side , we ’re still in the former stages of intersection development , ” Denais said . Callyope does n’t require to monitor you 24/7 . alternatively , the startup could require you to suffice some simple questions using voice messages . Denais shared some examples , such as “ Are you sleeping well at the moment ? Does your medication seem to be working well ? ”
Join us at TechCrunch Sessions: AI
Exhibit at TechCrunch Sessions: AI
Of naturally , some patient role might not actively record a voice message every week . In that lawsuit , a infirmary nurse might call you and record the call for psychoanalysis purpose .
In addition to the message of the conversation , Callyope study other symptoms . For example , “ with schizophrenia , you have seven symptoms — and one of them is disorganized spoken language , ” Denais say . “ With bipolar disorder , you have four or five symptoms . When people are too well , there ’s one symptom , which is accelerated speech . ”
Training on sensitive data
Unlike other industry , Callyope has to think in Cartesian product milestones . Once the first interlingual rendition of its proprietary model is trained , it has to freeze development on this version and put in it to wellness authority to get the relevant credentials .
“ Today , we have very good initial results in the cosmopolitan population , ” Denais say . “ We get them to fill in curt ego - questionnaires on anxiety and depression . And we require them to talk to see if we can detect modest signs early on . So we ’ve already handle to show that it works very well , and we ’re going to publish a scientific newspaper early on next year . ” After that , the company plans to reuse the same engineering on patient suffering from depression and schizophrenia .
The startup is currently work with psychiatrical hospitals to get data and prepare its model on this proprietary datum with privacy in idea . Eventually , the company wants to have a model that can analyze audio straight on gimmick so that it only sends the results to the psychiatrist .
“ Basically , this data will enable us to meliorate the functioning of our algorithm , always with the cardinal point that we only use what the patient wants to give us , and in a completely safe style from a technical point of view , so that in the foresighted term we do n’t have accession to anything , ” Denais say .
