top of page
Shows people coming together to collaborate on research

Industry Leading Research

Ellipsis Health leads in clinical and speech technology research, establishing best practices, and contributing to the field of Vocal Biomarkers for mental health and well-being.

Clinical Validation: 

APRIL 8, 2022

frontiers in psychology

Feasibility of Machine-Learning Based Smartphone Application in Detecting Depression and Anxiety in a Generally Senior Population

Abstract: Depression and anxiety create a large health burden and increase the risk of premature mortality. Mental health screening is vital, but more sophisticated screening and monitoring methods are needed. The Ellipsis Health App addresses this need by using semantic information from recorded speech to screen for depression and anxiety.

Independent Review Board Studies:

desert oasis healthcare.png
vanderbilt medical center.png
mayo clinic.png
university of denver.png
university of michigan.png
md anderson.png
desert oasis healthcare.png

Clinical Validation in Senior Population

Ellipsis Health conducted a study with 250+ patients with a previous history of depression at a Healthcare facility in Palm Springs, CA. The majority of patients were seniors (65+.) Each subject performed six voice screenings at least one week apart, with each session consisting of three minutes of answering open-ended questions about their mental state. The Ellipsis Health app not only demonstrated feasibility in use as a screening tool among all age groups who participated, but 30% of participants also spent longer than the required time necessary to conduct the survey, indicating that the process was engaging.

Peer-Reviewed Speech Technology Publications

December 5, 2023

Probabilistic Performance Bounds for Evaluating Depression Models Given Noisy Self-Report Labels


Advances in AI for health applications rely on evaluating performance against labeled test data. In the area of mental health, self-report labels from surveys such as the Patient Health Questionnaire (PHQ) for depression, are useful but noisy. This "fuzzy label" problem is not currently reflected in reporting model performance, adding to the challenge of comparing results across diverse corpora, data sizes, metrics, and test label distributions. To address this issue, we develop an approach inspired by Bayes Error to estimate a model’s upper and lower performance bounds. Unlike past work, our approach can be used for both regression and classification. The method starts with a perfect match between target and prediction vectors, then applies label noise to degrade performance. To obtain confidence intervals, we use test-set bootstrapping to produce prediction and target vectors. We present results using voice-based deep learning models that predict depression risk from a conversational speech sample. Models capture both language and acoustic information. For label noise, we introduce results from a corpus in which 5625 unique subjects completed the PHQ-8 twice, separated by a short distraction task. Speech test data come from three real-world corpora encompassing over 3500 total datapoints. The test sets differ in speech elicitation, speech length, and speaker demographics among other factors. Results illustrate how probabilistic performance bounds based on PHQ-8 label noise affect the interpretation and comparison of models over corpora and metrics. Implications for science, technology, and future directions are discussed.

White Papers

Published Papers

Ellipsis Health + Ceras Healthalysis of Calls for Depression 1.jpg

Transforming Care Management Through AI-Driven Analysis of Calls for Depression

A shifting healthcare landscape is moving towards personalized and data-driven care management. Within this care transformation, Ceras Health and Ellipsis Health began a partnership to better understand and support the mental health of chronically ill patients by using voice and artificial intelligence (AI).

Full Research Bibliography (PLACEHOLDER SECTION)

Published Papers

Doctor's Desk

Download our Full Bibliography of Technical and Medical Research Here

Stay Up to Date on New Research

Sign up to receive updates on Ellipsis Health's research: 

Thanks for submitting!

bottom of page