ADAMMA - Core for AI & Digital Biomarker Research

Software Tools

Our open-source initiatives are built on CLAID, a robust and versatile platform that serves as the foundation for our research and deployment efforts. We are also focused on developing specialized analysis packages tailored for various types of sensor data.

CosinorAge Calculator - Towards a Digital Biomarker of Aging
CosinorAge Calculator - Towards a Digital Biomarker of Aging

CosinorAge Calculator is a research platform that introduces CosinorAge - a novel aging biomarker calculated from accelerometer data. While CosinorAge is our main feature, we also provide comprehensive analysis of sleep patterns, physical activity levels, and circadian rhythms through sophisticated algorithms.

OpenTSLM - Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
OpenTSLM - Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

OpenTSLM models can reason over multiple time series of any length at once, generating findings, captions, and rationales in natural language. We tested these models across a wide range of tasks spanning Human Activity Recognition (HAR) from 3-axis acceleration data, sleep staging from EEG readings, 12-lead ECG question answering, and time series captioning.

CLAID - Closing the Loop on AI and Data Collection
CLAID - Closing the Loop on AI and Data Collection

CLAID is an open-source initiative to develop, validate and share AI models, digital biomarkers and healthcare applications. Our goal is to transfer research findings from the lab into the real-world. We invite researchers, clinicians and developers to use and contribute packages and to participate in our community.

CHARM - Circadian Rhythm Metrics based on Activity, body temperature and Heart rate
CHARM - Circadian Rhythm Metrics based on Activity, body temperature and Heart rate

In this project, we validated the efficacy of commercial devices for monitoring circadian rhythm and developed a multi-modal model to predict circadian rhythm using acceleration, body temperature, and heart rate data.

TripletCough - Cougher Identification and Verification from Contact-Free Smartphone-Based Audio Recordings Using Metric Learning
TripletCough - Cougher Identification and Verification from Contact-Free Smartphone-Based Audio Recordings Using Metric Learning

In this project, we developed an open-source machine learning model specifically designed to accurately attribute cough events to individual users.