2024 Global Health Equity Challenge
NiADA (Non-invasive Anemia Detection w/AI)
NiADA is a non-invasive, point-of-care, real-time solution that uses Artificial Intelligence to detect and monitor anemia using a smartphone app.
What is the name of your solution?
NiADA (Non-invasive Anemia Detection w/AI)
Provide a one-line summary of your solution.
NiADA is a non-invasive, point-of-care, real-time solution that uses Artificial Intelligence to detect and monitor anemia using a smartphone app.
In what city, town, or region is your solution team headquartered?
Lehi, UT, USAIn what country is your solution team headquartered?
What type of organization is your solution team?
For-profit, including B-Corp or similar models
Film your elevator pitch.
What specific problem are you solving?
Anemia is a dangerous condition of low hemoglobin level in blood.
Globally, 2+ billion people suffer from anemia. Globally anemia prevalence has been particularly persistent among reproductive age women and young children despite intervention. WHO estimates 571M women and 269M young children are anemic.
There are no specific symptoms for anemia. The risks associated with anemia increase as hemoglobin levels decrease. If undetected for long enough, anemia often becomes fatal.
- Anemia in women & children:
- CDC WIC program supports pregnant & postpartum women and more than 50% of all infants born in the USA with nutritional supplements to help prevent iron deficiency anemia. And yet, WIC reports 13% increase in anemia in the last decade impacting minority communities disproportionately .
- 800 million children around the world are anemic. In the USA , 20% of all children will experience anemia one time or another. These kids and our future are at risk of impaired cognitive development and cognitive loss, obesity and increased years lived with disabilities(YLD).
Today, the world sees 1 maternal death every 2 mins.
- Maternal anemia in pregnancy is a reversible risk factor. And yet, maternal anemia is estimated to contribute to 20% of maternal deaths (Black, et al., 2008).
- Growing evidence that anemia is linked to greater risk of postpartum hemorrhage(PPH) (Kavle, et al., 2008).
- PPH is responsible for 25 percent of maternal deaths globally
- Anemia in pregnancy can lead to premature birth, poor brain development in infants.
- Antepartum anemia is most prevalent among historically marginalized pregnant patients, contributes to disparities in severe maternal morbidity(SMM) and postpartum depression.
- While anemia prevalence more than doubled from 2011 to 2020 for all racial groups in the USA, Black and American Indian–Alaska Native mothers are affected most. A significant and persistent disparity(12 percent point difference) in anemia exists between Black(21.5% prevalence) and White(9.6%) pregnant patients over the last decade.
3. Anemia in non-pregnant female population , seniors & chronic disease patients:
- Anemia in reproductive-age women, costs more than 4% of global GDP.
- In the USA, purely anemia diagnoses account for 5,900 non-maternal deaths, 623,000 emergency visits, and 2.5 M primary care visits, annually.
- The cost of care for an inpatient with anemia is 1.5 times higher.
- Cancer and chronic kidney disease (CKD) patients experience 30-90% upstaging due to anemia causing frequent hospitalization or death.
Currently, there is no accessible, easy, affordable and non-invasive way to monitor hemoglobin level regularly at home or at the point of care.
The current state of the art hemoglobin measurement process
1. is invasive, it requires painful blood draw.
2. requires skilled technicians.
3. Lab test takes hours or even days and lacks routine monitoring.
4. Finally, the tests are often expensive for lower-income and minority communities who need anemia screening the most.
What is your solution?
We propose a radical solution to this multi-dimensional long-standing anemia prevalence problem by developing a novel artificial intelligence system - Non-invasive Anemia Detection with AI (NiADA).
NiADA is a smartphone app that analyzes eyelid images to estimate and display hemoglobin level on the screen in real-time. Hemoglobin level is used to decide whether a user has anemia or not. The estimates can be saved for regular and long term monitoring for an individual or at the population level.
NiADA is an SaMD (Software as Medical Device) . NiADA is built upon a framework of integrated solution for anemia screening, monitoring and intervention.
The solution is developed with deep learning as the core technology , which is securely deployed on AWS cloud with full redundancy and data privacy in place. NIADA app uses the cloud AI & Data platform through an API and hence it is integration ready for other telemedicine and remote monitoring app and websites.
Product demo
We have a product demo recorded by me - https://www.youtube.com/watch?v=OMDQjb_tREg
NiADA on app store:
The app is now available on google paly store and Apple testflight for informational purpose only as we work on break-through device FDA clearance application.
The app comes with 100 free tests now. We love feedback .
Android - https://play.google.com/store/apps/details?id=ai.monere.niada&pcampaignid=web_share
Apple Testflight - https://testflight.apple.com/join/o8y79AEV
Who does your solution serve, and in what ways will the solution impact their lives?
Target population groups who require regular anemia surveillance are as follows:
- Children
- Reproductive age women
- Patients with chronic disease like cancer and chronic kidney disease, thalassemia who require regular hemoglobin monitoring
- Seniors
- Health conscious people
- Population from underserved/rural areas
NiADA helps these users and their healthcare providers/administrators to be able to test for anemia regularly and track it for appropriate intervention.
The value propositions and impact of NiADA for these user groups are multi-faceted.
1. The current state of the art hemoglobin measurement process is invasive, requiring a blood draw. Invasive tests are hard to perform not only on children, but study also shows 6 out of 10 adults avoid testing due to the fear of needle. NiADA introduces a painless non-invasive, on-the-spot, accurate, quantifiable way for measuring hemoglobin level.
2. For rural areas, travelling to a lab for a test can cost a day at work. Moreover, it takes hours if not days to produce test results. Our solution produces real-time results.
3. The tests are often expensive for lower-income and minority communities and daily-wagers who need the anemia screening most. NIADA is inexpensive because it is a smartphone app (SaMD).
4. Hemoglobin is an essential biomarker of anemia. Anemia can affect the body’s physical processes like metabolism directly. But anemia is ignored as the symptoms are non-specific only to become fatal with time. This radical solution will pioneer preventive care in both developed and developing countries by decreasing Years Lived with Disability (YLD) and even preventing death.
5. As NiADA naturally tracks anemia trends for individuals and at population level, it will empower healthcare providers and administrators to employ better and appropriate global and local policies for mothers and infants at the population level to help reach UN sustainability goals 2.2 & 3.
6. For governments and healthcare administrators around the world: Preventive anemia management and intervention for pregnant and non-pregnant women with young children has highly positive economic returns globally. Every $1 dollar invested in anemia prevention for women, returns $12 USD in return.
How are you and your team well-positioned to deliver this solution?
Two of our three co-founders are reproductive-age women and personally experienced adverse effects of anemia. Our journey for developing NiADA started with the extreme experiences faced by two of my close childhood friends. Their incidents took me by surprise. It prompted me to conduct a Google survey within my extended circle of friends to gather feedback from women of reproductive age in India and the USA.
Friends from our university days, many of whom are now public health professionals, run community-driven organizations that hold health camps and awareness-building workshops for women and other underrepresented communities where we occasionally participate or fund. They were of immense help, providing crucial insights during our primary market research and then as an early adopters and inspiring us for the community-driven solution design for NiADA.
As we have expanded team Monere, we have attracted like-minded individuals who are equally excited to participate in this journey. The experienced leadership team at Monere now possesses over half a century of combined expertise in public health and artificial intelligence. Their diverse skill sets were essential in establishing an efficient data collection network with hospitals and developing a deep learning algorithm based on quality-assured data.
With our close ties to the medical community in India and in the USA and the tech world, team Monere built the software platform and a data collector team within two months to support a daily flow of 300 eye images from eight hospitals. A year later, we have screened over 85,000 individual patients to train NiADA and initiated clinical trials in India and in US.
We are networking with NGOs and school boards in India through our friends, who are actively working on the anemia eradication program via the Anemia Mukt Bharat, aka Anemia Free India program.
I am confident that the team is exceptionally committed to working on this solution. We know that impediments, such as stagnation, lack of funding, can kill start-ups. I am convinced that this team will not stop working on this solution under any amount of stress. Our like-minded early investors are equally excited to take part in this journey. As the ship's captain, I am convinced that team Monere has the conviction and the operational chops to bring it within the reach of millions of people in their everyday lives.
Which dimension of the Challenge does your solution most closely address?
Increase access to and quality of health services for medically underserved groups around the world (such as refugees and other displaced people, women and children, older adults, and LGBTQ+ individuals).Which of the UN Sustainable Development Goals does your solution address?
What is your solution’s stage of development?
PilotWhy are you applying to Solve?
We are hoping to get access to MIT's network to
- be part of a diverse and vibrant network for any help building effective GTM strategy for global market.
- be part of an innovative peer group where we can participate in meaningful exchange for improving the solution .
- be able to attract exceptional and passionate talent to work with us.
- get us some regulatory help for the process of registering our App as SaMD(Software As Medical Device) 510k cleared.
- connect ourselves to potential funding and partnership opportunities which are dedicated to solve women's health issue problem as Anemia is one.
In which of the following areas do you most need partners or support?
Who is the Team Lead for your solution?
Mou Nandi
What makes your solution innovative?
Monere pioneers a radical solution to a multi-dimensional long-standing problem by developing a novel artificial intelligence system - Non-invasive Anemia Detection with AI (NiADA).
Novel AI technology - For centuries and now, medical experts have made clinical decisions about the severity of anemia by assessing the patient's specific circumstances and the visual evaluation of paleness in the inner eyelid, skin, palm, and nail. In the absence of a proper quantitative method, visual estimation is used to assess the amount of blood loss during and beyond childbirth to estimate hemoglobin level or anemia severity in a new mother and children. These visual methods are subjective and imprecise, contributing to poor clinical outcomes.
NiADA takes the idea of the subjective empirical knowledge and encodes it into a tailored & personalized algorithm that can produce precise & accurate hemoglobin level in real-time. The algorithm learns on continual basis by using physical markers like smartphone generated images of a person’s conjunctival pallor (inner area of lower eyelid) combined with known medical history and demographic information and maps them to the hemoglobin result from a lab test, which is a biomarker for anemia.
This automated learning of features from multimodal data collected using commonplace technology like a smartphone ( instead of a specialized medical imaging device) is very useful for progressing development of more noninvasive procedures for medical diagnosis and continuous monitoring as part of preventive healthcare. It can greatly reduce the cost of medical care in outdoor or emergency rooms with early detection at home or at primary care centers.
The sophisticated algorithm is packaged within a simple smartphone app that has following qualities.
Easy to use -NiADA is a smart phone app that takes a photo of inner eyelid to show the result.
Painless as it is non-invasive - NiADA does not require blood test for Anemia screening.
Accessible -
- NiADA is usable in both internet and no-internet areas using mobile friendly model.
- No travel to lab is required just for an anemia screening.
Inbuilt monitoring - NiADA shows history and trend at patient level and also at population level and for different demographic groups as applicable for the customers/users.
Community oriented - NiADA can motivative & connect users in preventive objective-driven communities online.
Scalable, extendable & low-cost - NiADA grows with use as backend ecosystem is based on a separate Data & AI platform. It scales on-demand infinitely.
Integration-ready - Every feature of the solution is implemented as an API endpoint, making it suitable for integration-based subscription for other health and wellness platforms and insurance apps.
Describe in simple terms how and why you expect your solution to have an impact on the problem.
1. Hemoglobin is an essential biomarker of anemia. Anemia can affect the body’s physical processes like metabolism directly. But anemia is ignored as the symptoms are non-specific only to become fatal with time, increasing Years Lived with Disability (YLD) and even death. This radical solution will pioneer preventive (maternal) care in both developed and developing countries.
2. Postpartum hemorrhage is a leading cause for maternal morbidity and mortality globally, mainly because the blood loss is estimated by visual inspection that leads to inadequate care that is needed for a new mother. The solution will introduce a quantitative method for estimating blood loss during and after childbirth.
3. As NiADA naturally tracks anemia trends for individuals and at population level, it will empower healthcare providers and administrators to employ better and appropriate global and local policies for women, infants and children (Like CDC WIC) at the population level to help reach UN sustainability goals 2.2 & 3.
4. Preventive anemia management and intervention for pregnant and non-pregnant women with young children has highly positive economic returns globally.
5.Being a painless non-invasive method, it is extremely effective for children.
What are your impact goals for your solution and how are you measuring your progress towards them?
Our solution directly relates to UN sustainability goal of 2.2 & 3 .
The first step to managing a problem is to monitor it.
NiADA, an integrated solution for both screening and monitoring, is created for public health administrators for anemia surveillance at population level. NiADA can create watchlists and reports/dashboards based on age, sex, location/area, pregnancy and menopausal status to measure the anemia management progress in a target population over an extended period of time for informed decision making.
Public officials can use NiADA to administer/recommend/distribute supplements and food in an equitable way instead of subjective assessment.
NiADA can scale globally with ease at the lowest cost possible.
SDG 2.2.3
Anemia causes both health and economic harm and affects women disproportionately. As part of UN SDG 2 target , it aims to halving the prevalence of Anemia among reproductive age women by 2030. The indicator 2.2.3 is designed for UN SDG 2 to measure the change in prevalence of anemia in women aged 15 to 49 years, by pregnancy status (percentage).
We are already piloting NiADA in six schools for State Government of Arunachal Pradesh, India, as part of "Anemia Mukt Bharat" (Anemia free India) program to test and monitor anemia among school girls throughout the year.
SDG 3.1
Anemia is one of the top risk factors for post partum hemorrhage which is the leading cause for maternal mortality globally. NiADA will help establish and monitor a birth planning for pregnant women to detect and track anemia through out pregnancy and can help prevent deaths by providing a quantitative method for measuring blood loss during delivery.
We are piloting NiADA in Matri Sadan Hospital, Kolkata, India to track hemoglobin level throughout pregnancy including at the time of birth.
In general, anemia surveillance is limited as the current process involves invasive testing , medical waste management and a manual data collection and storing process for trend management at scale.
NiADA can be used more frequently as it is just a painless test using a smartphone app. NIADA being a software has an inbuilt system to track pregnancy status (or any other demographic attribute) vs presence of anemia for the target population.
Describe the core technology that powers your solution.
Multi-modal data processing including image, sound and text to build our proprietary AI model is in NIADA's core.
Proprietary AI models:
1. Validation of captured photo of inner part of the lower eyelid - photo is validated using a proprietary deep learning AI model to extract regions of interest, palpebral conjunctiva and sclera part of the eye. Palpebral conjunctiva (inner lower eyelid) is used for hemoglobin level detection, and sclera (the white part of the eye) is used for white balancing.
2. Detecting hemoglobin level and anemia - The extracted regions of interest along with other medical data (age, sex, pregnancy status, medical history) are passed through the hemoglobin (Hb) inference AI model to predict Hb level .
3. Recommendation on next steps - The Hb result is used with medical history through a recommendation AI model to provide users with possible next steps.
4. Data augmentation model is used to generate synthetic data to remove imbalance in collected data based on Hb level, age, and sex categories.
Proprietary data sets for training the models:
NiADA is the user facing app that is built on the proprietary data platform which hosts the data we collect from our partner hospitals .
The framework & the platform:
We have built
- a dedicated data collection framework, Andromeda, which includes a separate smartphone app to collect and validate data in an organized way to reduce human error in the process and
- a data access and storage platform to provide selective access through API. The platform hosts both organic and derived data created as part of the whole model building and recommendation process .
Datasets details:
- We currently host more than 85000 connected datasets and it is growing at a rate of 300 data points daily.
- Each data unit consists of at least two lower eyelid images ( left and right eye) , lab-tested hemoglobin value , sex, age , pregnancy and menopausal status , some contextual information like outside temperature , last water intake , time travelled to lab , travel medium and other medical history lie cancer/kidney disease existence and any medication taken by the patient.
Data Validation:
Several automatic validation steps are part of the app to ensure all required data components are collected for each patient.
- We employ human-in-the-loop data validation process to produce curated data .
- Doctors validate collected data using the Andromeda app to accept or reject the data collected .
- This doctor's validation process is gamified using a test & reward model where the doctors predict the hemoglobin level before they see the actual lab-tested value for accepted data. This data enables us to test model accuracy wrt human doctors.
- This rejected data is used as adversary examples for data augmentation.
Here's the high level overview of our core technology:
Which of the following categories best describes your solution?
A new technology
How do you know that this technology works?
There are previous research on this. Please see a list below. We have taken those into account to develop our own deep learning algorithm We have gone through prototyping and pre-clinical and going through clinical trial steps .
Pre-clinical or bench tests:
- Our result from tests ran to validate NiADA against human doctors' performance
2. Tests to estimate hemoglobin level
We have developed a proprietary platform of purpose-built 85,000 connected datasets that is used for building our model. Datasets are not public(yet) . Our pre-clinical bench test gives us the following results.
First one data from single mobile phone. The second one from many different mobile phone to test generalizability.
3. We have submitted a paper for this year's 2024 AIME , yet to receive an acceptance.
4. We are working on the paper to publish the clinical trial results.
5. Previous related works which uses conjunctiva images just like ours for proof of concept. Previous works were limited to either only one type of mobile, images taken with special camera , older statistical method with a much worse result than ours.
We use a custom deep learning technology that we have submitted for patent(application number - 63/563,023).
1] Akhtar M, Hassan I. Severe Anemia during late pregnancy. Case Reports in Ob-
stetrics and Gynecology. 2012; 2012:3 pages.485452
[2] Vivek RG, Halappanavar AB, Vivek PR, Halki SB, Maled VS, Deshpande PS. Prev-
alence of Anemia and its epidemiological. Determinants in Pregnant
Women. 2012;5(3):216–223.
[3] Salhan S, Tripathi V, Singh R, Gaikwad HS. Evaluation of hematological parame-
ters in partial exchange and packed cell transfusion in treatment of severe anemia in
pregnancy. Anemia. 2012; 2012:7 pages.608-658
[4] WHO/CDC. Worldwide Prevalence of Anemia 1993–2005: WHO Global Data-
base on Anemia. Geneva, Switzerland: WHO Press; 2008.
[5] Giovanni Dimauro, Maria Elena Griseta, Mauro Giuseppe Camporeale, Felice
Clemente, Attilio Guarini, Rosalia Maglietta. An intelligent non-invasive system for au-
tomated diagnosis of anemia exploiting a novel dataset
[https://www.sciencedirect.com/science/article/pii/S0933365722002299]
[6] Yuwen Chen, Kunhua Zhong, Yiziting Zhu2 and Qilong Sun. Two-stage hemoglo-
bin prediction based on prior causality.
[[https://www.frontiersin.org/journals/publichealth/arti-
cles/10.3389/fpubh.2022.1079389/full]
[7] Peter Appiahene , Kunal Chaturvedi, Justice Williams Asare, Emmanuel Timmy
Donkoh ,Mukesh Prasad. CP-Anemic: A conjunctival pallor dataset and benchmark for
anemia detection in children.
[https://www.sciencedirect.com/science/article/pii/S2590093523000395]
[8] Olaf Ronneberger, Philipp Fischer, Thomas Brox .U-Net: Convolutional Net-
works for Biomedical Image Segmentation
[https://arxiv.org/abs/1505.04597]
Please select the technologies currently used in your solution:
If your solution has a website or an app, provide the links here:
www.monere.ai , https://www.linkedin.com/company/monere-corp/mycompany/verification/?viewAsMember=true
In which countries do you currently operate?
Which, if any, additional countries will you be operating in within the next year?
How many people work on your solution team?
Total - 23 (18 fulltime + 5 parttime).
Founding team - 3 members (1 engineer, 1 data scientist and 1 medical doctor, Pathology, MD)
India founding team - 1 member.
Advisor - 4 members
Engineer - 3 members
Data scientist - 1 member
Cloud System Administrator - 1 member
Data Collector - 8 members
Sales Manager - 1 member, part-time
Lawyer - 1 member, part-time
A medical board - 3 doctors, part-time
How long have you been working on your solution?
We have been working on our solution for just about a year now.
I started exploring the idea in last December 2022 and put together my founding team of three.
We started PMR (Primary market research) in January 2023.
We established partnership with hospitals in India and started collecting data in April 2023.
We released NiADA v1 for few more pilots in December 2023.
Tell us about how you ensure that your team is diverse, minimizes barriers to opportunity for staff, and provides a welcoming and inclusive environment for all team members.
Our leadership team comprises of 60% women, 80% person of color.
As a longtime proponent and practitioner of DE&I at workplace, we strive to hire women in the team. Currently we have 6 women in the team, out of total 20.
While hiring through the HR agencies, we instruct them to advertise our passion for bringing more women to high paying, hi-tech, challenging and interesting jobs. While sorting resumes, we make sure we pay more attention to unconscious bias before discarding a woman's resume.
We are solving a problem that affects mostly women, women's perspective is such a valuable tool for our business to succeed.
What is your business model?
We employ a B2G or B2B business model, primarily.
NiADA is accessed
- as an smartphone App directly to user or medical professionals or
- as an integration with
- existing wellness and telemedicine apps
- EHR/EMR solution
Pricing and coverage in the USA
For USA , we are working on reimbursement code assignment parallelly with FDA clearance application so that we may charge for the NiADA with a fee-for-service from a payer(insurance or govt).
Reimbursement code and coverage through commercial insurance payer and govt(Medicare & Medicaid) targeting community medicine first.
- Serves participants in CDC WIC (Women Infants Children) - coverage through Medicaid and procurement through designated state agency and
- Seniors doctor's visits through Medicare Part B
- Hospital and skilled nursing facility and home healthcare services through Medicare part A
- pregnant women checkups and at home monitoring through insurance
- NiADA as part of general tests in OPD through insurance
- NiADA for chronic disease management ( cancer and kidney disease patients requires regular anemia screening and management)
Pricing and coverage - International
In India and in other parts of South Asia and Africa, NiADA is sold with a subscription based pricing model .
Except for a few key initial direct sales to customers( like Health & Education ministry in India ) the distribution in international market is mostly done through channel partners like national and regional distributors.
NiADA is already being piloted in India state govt run schools and private hospitals and NGOs using subscription model .
Future B2C model is possible we are testing NiADA in selected groups like cancer patients online communities.
Do you primarily provide products or services directly to individuals, to other organizations, or to the government?
Government (B2G)What is your plan for becoming financially sustainable, and what evidence can you provide that this plan has been successful so far?
Currently, I am actively fund raising for our pre-seed round upto $1M from angel investors to cover our expenses for the next year.
So far, we have been bootstrapping and also raised from friends and family - a total of $275,000 to fund our work.
We are also looking for grants and competing for it as we are working on generating revenue from international market.
We are working on FDA 510k in USA and in the meantime we have activated sales in India and South Asia.
As NiADA is a very low risk, Software as Medical Device (SaMD). It is independently validated by Indian hospitals in pilot phase to be used at hospital outdoors, in community medicine and in school health camps while we work on FDA( or CDSCO - Indian FDA) clearance.
Traction so far :
Direct sales:
- We currently have an LOI(Letter of Intent) from the State Govt of Arunachal Pradesh as they are going through a pilot for adolescent girls in six schools.
- We are about to start a paid pilot in National High School with 2000 tests
- We have an agreement from an NGO in north-east India for 10000 tests a year
- Few more leads for direct sales in big hospitals like AMRI and Medanta in India
Distributor led sales:
- a health foundation with a requirement of daily 200 tests in western India.
- In discussion with distributors in Nigeria, Bangladesh, Malaysia, and in the region of Kashmir, India
We estimate to see revenue by end of third quarter this year, 2024 from international market and from USA by the end of second quarter, 2025.
Solution Team
-
Ms. Mou Nandi Cofounder & CEO, Monere
to Top
Our Organization
Monere Corporation