AmaHealth LLC
UArizona researchers have created an AI powered data-driven tool to forecast a personalized due date window for expectant mothers utilizing data from commonly worn personal devices like smart rings at various periods in gestation.
The Problem
Pregnancy is often a time of great excitement juxtaposed with uncertainty or fear. One common uncertainty is that labor is unpredictable and the ‘due date’ is usually wrong, sometimes by a matter of weeks. Care providers have no ability to predict when labor will start. Amahealth, LLC is a partnership between obstetric researchers and data scientists, which aims to personalize pregnancy care. We have created an AI-driven tool that offers an accurate forecast of upcoming labor. This advance will allow families to arrange their lives around their new baby’s arrival, and clinicians to make personalized recommendations about testing and childbirth.
The Solution
Amahealth scientists were inspired by mammalian research showing that birth could be predicted by monitoring patterns in maternal vital signs. We have tested this concept in human pregnancy, developed a deep neural network solution providing an accurate forecast of how much time is remaining in pregnancy. Our model was trained and generated using non-invasive wearable physiological monitoring devices that are commercially available. The comfort and ease of use of the device make the solution both highly feasible and acceptable to pregnant clients.
The Opportunity
FemTech is a booming opportunity with global VC likely to reach $3 billion by end of the decade, according to PitchBook. While dozens of direct-to-consumer pregnancy apps exist, as well as several growing e-health pregnancy care platforms—no products directly address the uncertainty of labor onset by providing a real-time prediction of the duration of remaining pregnancy. Beyond labor prediction, Amahealth has a vision to build more tools for aiding other common pregnancy complications by generating clinically-actionable data from wearable-derived metrics (patterns in pregnancy sleep, stress, signs of illness, or glucose monitoring).
Status
We have both proof-of-concept data and a testable prototype ready to operationalize in a new or existing digital ecosystem. Our current team delivers expertise in data science, predictive modeling, reproductive physiology and translation to the obstetric clinical environment and patient experience. We aim to grow by connecting with other maternal health innovators or business-developers with an eye on both wellness (DTC) and FDA pathways as well as connect to other wearable device companies where our solution could be tested/implemented.
Meet the Team
Elise Erickson PhD
College of Nursing
Shravan Aras PhD
Center for Biomedical Informatics & Biostatistics
Tech Launch Arizona
Contact us today.
Check out more Digital Health startups.
View All Startups & Inventions
The fall detection system runs on built-in instability metrics that assess the fall precursors and assist users in correcting posture and regaining balance. Using a stream of data from multiple cameras, our algorithm calculates, in real-time, several posture metrics for identifying potential falls. It then provides individualized posture correction feedback using both audio and a wearable haptic device or can trigger wearable robotics for fall protection.
UArizona researchers have created an AI powered data-driven tool to forecast a personalized due date window for expectant mothers utilizing data from commonly worn personal devices like smart rings at various periods in gestation.
The SeVA platform is a composite AI device that can be effectively deployed in hospital, nursing homes and home settings. It has the capability to track a patient’s mental and physical state and signal early signs of risks such as delirium, falls or impending illness. It provides emotional support to the patient and their family by indulging in a natural conversation and facilitating their needs. When fully deployed, the product can serve as a platform which allays worry for people and their caregivers and will reduce healthcare costs by identifying the early signs of severe illness.
