What is the name of your solution?
STRIATA AI
Provide a one-line summary of your solution.
STRIATA AI for human resource for health optimization
What specific problem are you solving?
Optimizing human resources for health (HRH) and ensuring equitable access to health workers is vital in accelerating progress towards achieving universal health coverage (UHC).
The 2016 World Health Organization Global Strategy on Human Resources for Health: Workforce 2030, states that Health systems can only function with health workers; improving health service coverage and realizing the right to the enjoyment of the highest attainable standard of health is dependent on their [human resource] availability, accessibility, acceptability, and quality.
However, a serious shortage of health workers around the world and particularly in Africa is undermining access to and provision of health services. WHO AFRO projects that the shortage of health workers in Africa will reach 6.1 million by 2030. [https://www.afro.who.int/news/chronic-staff-shortfalls-stifle-africas-health-systems-who-study#:~:text=It%20is%20projected%20that%20the,in%20Africa%20has%20daunting%20implications.]
A study titled “The health workforce status in the WHO African Region: findings of a cross-sectional study” which surveyed 47 African countries, found that Africa’s long-standing health worker shortage stems from several factors including inadequate training capacity, rapid population growth, weak governance of the health workforce as well as poor deployment of health personnel. The analysis showed that most sub-Saharan countries fell far below the 4.45 health workers per 1000 population needed to achieve UHC goals (see map 1).
MAP 1 – DENSITY OF HEALTH WORKERS BY COUNTRY.
https://gh-bmj-com.ezproxy.canberra.edu.au/content/7/S...
As a first step in addressing health worker shortages and reinforcing Africa’s health system, figuring out how to deal with persistent shortages and poor distribution of the existing health workforce is critical. Countries need to significantly increase investments for building the health workforce to meet their current and future needs but more importantly there is a need to improve and optimize deployment of their existing health workforce.
Today, few systems can answer critical questions related to workforce distribution. In most countries, the allocation of human resources is governed by national norms which determine the number of staff based on the type of health facility and population estimates. This approach has significant limitations which result in situations where there is overstaffing in some locations and understaffing in others, and often overlooks questions surrounding:
Equitable distribution and accessibility to services
Specialized service delivery skills
Health workers ability to meet demand for services
Historical trends in patient visits
Health worker motivated to deliver quality care, and
Whether they are supported by the health system.
To address these issues, many countries conducted health workforce workload assessments to better understand facility level health care worker requirements. Some countries opted to apply a tool developed by the WHO called Workload Indicator Staffing Need (WISN). The idea was that when complete, the WISN process would provide a new set of norms and standards for each location. However, after several countries implemented the tool, the WHO found that “...the approaches to using the WISN results are varied and sometimes inadequate. They lack(ed) consistency, while the rules for implementing the established norms and standards are difficult for managers to understand and apply.” [Regional guide for determining health workforce staffing norms and standards for health facilities ISBN: 978-929023456-2 © WHO Regional Office for Africa 2021].
While the WHO has developed further guidance on how to apply WISN to determine staffing needs across the country, the outputs are susceptible to shifts in health policy, the evolution of health services and changes in the country’s epidemiological profile. The solution Macro-Eyes is proposing takes these factors into consideration by maximizing the use of existing data and setting in place a continuous learning cycle which will help establish a path to future proof the problem of health worker supply.
What is your solution?
Macro-Eyes artificial intelligence (AI) powered technology STRIATA provides enhanced capability to forecast consumption, position infrastructure, and predict behavior, even in low data and high uncertainty environments. Regardless of location, every resource is put to its greatest use. STRIATA comprises three modules: FORECAST, VISIBILITY, and BEHAVIOR. Imprecise forecasting and lack of geo-intelligence results in mismatches of supply to demand. If you don’t have up-to-date data about each point in your network, you won’t send supply where it can and will be used.
Designed with and for HRH professionals, STRIATA provides Ministry leaders with something new–AI generated recommendations on how to better allocate existing human resources for health based on patient data and the WHO’s Workload Staffing Indicator Needs (WISN) calculations.
In the context of human resources, STRIATA delivers more precise real-time visibility into workforce optimization. STRIATA applies the power of machine learning to existing WISN calculations, human resource information, health management information system data, and population surveys to improve the distribution of staff and increase health service coverage. Built for resiliency, it has the ability to learn from and adapt to future changes such as: new service delivery models, increases in access or services, investments in infrastructure or equipment, and/or introduction of health insurance or free health care. It provides national and regional HRH planners and managers with easy-to-use information on the location, number and type of primary health care worker needed to meet changing demand for services.
The HRH optimization that STRIATA provides is adaptable to local context and provides dynamic views of the number, type, and distance that staff need to move to maximize the available workforce at district, state, or provincial level. It also provides recommendations on the number and cadre of additional human resources needed to bridge gaps in the workforce.
Developed and tested with the Sierra Leone MOH, the HRH solution first focuses on identifying how current distribution of health workers differs from national norms, then uses WISN, HR information and historical DHIS2 data to calculate new site level norms. Finally, the new norms are compared against existing staff and machine learned recommendations are made on the best distribution of staff across the network.
Who does your solution serve, and in what ways will the solution impact their lives?
“Without adequate health workforce, tackling challenges such as maternal and infant mortality, infectious diseases, noncommunicable illnesses and providing essential basic services like vaccination remains an uphill battle.” Dr. Matshidiso Moeti, WHO Regional Director for Africa.
STRIATA serves vulnerable populations in complex, low data environments. From Sierra Leone to California, STRIATA is focused on improving health care delivery for the underserved. STRIATA empowers decision makers in governments and is in use today in Cote d'Ivoire, DRC, Mozambique, Serbia, Sierra Leone, Tanzania, and in California.
STRIATA was developed to help reinforce health systems by optimizing the distribution of the already scarce human resources. STRIATA provides actionable intelligence that is achievable within the constraints of even extremely resource-constrained settings. The deployment of STRIATA for HRH has a ripple effect on the health system as it ensures identified human resource gaps are addressed resulting in the access and provision of health services.
How are you and your team well-positioned to deliver this solution?
With nearly 50% staff across administration, technical and programmatic/deployment teams based in multiple African countries, Macro-Eyes through close engagement and collaboration with governments and its partners has established solid relationships with in-country stakeholders resulting in a deep understanding and knowledge of the past and current bottlenecks faced by health systems.
Macro-Eyes works directly with local stakeholders to establish fit for purpose processes to compare how existing health worker distribution compares to norms and how existing distribution compares to machine learned workload. In Sierra Leone, through a memorandum of understanding (MoU), we partnered with the Ministry of Health through the Directorate of Human Resources and the establishment of an intelligent health systems technical working group whose members include decision makers and users at national, provincial, district and facility level to develop a solid understanding of the HRH situation.
With support from the MOH, and hands-on facilitation by our Sierra Leone in-country Deployment Managers, we leveraged existing data and systems to develop models to help stakeholders interpret the data and support the meaningful use of recommended distribution at district and national levels.
As a result of our deliberate approach to learning from and engaging local experts, we have obtained support from multiple Ministries of Health in several African countries including Burkina Faso.
The MOH in Burkina Faso have asked that we work with national and provincial level stakeholders to apply the results from their recent WISN staffing norm setting process to provide recommendations on how to optimize the distribution of human resources in the country.
As we apply STRIATA to this context and as we continue to work with the MOH in Sierra Leone, we would like to develop and test new ways of measuring the impact of using ML in the HRH context.
Which dimension of the Challenge does your solution most closely address?
Where our solution team is headquartered or located:
Fall City, WA, USAOur solution's stage of development:
GrowthHow many people does your solution currently serve?
STRIATA is providing intelligence across more than 7000 health facilities globally. In 2021, Macro-Eyes AI analyzed data from 1,087,535 patients, 2645 health facilities, and 8,029,159 medical events. Outputs are being used or have been used for decision making in California, DRC, Mozambique, Ghana, Nigeria, Serbia, Sierra Leone, and Tanzania. In Sierra Leone, our users include the Ministry of Health through the Directorate of Human Resource at national, provincial and district level. When existing staff within a district are optimized for relocation within a 25km distance, up to 65% of facilities will meet workload demand. In Koinadugu District, by just moving 5 staff, coverage increases almost 10% from 32% (pre-optimization) to 41% (post-optimization).
Why are you applying to Solve?
Development challenges are often allocation problems, presented solely as resource problems. People are turned away from the services and products they need due to stockouts and misallocation, while elsewhere supply is unused and precious goods/services go to waste. We believe supply chains pose the most important, unsolved optimization problem on earth. Globally, Macro-Eyes technology addresses the fundamental challenge of matching scarce supply to uncertain demand in the most difficult settings.
While we understand the need of an efficient HRH system, we recognize the importance of measuring the impact of what such a system can have both on lives served and saved, and how it overall improves and strengthens the health system. Developing and deploying STRIATA for HRH is a global digital good that can easily be scaled and adapted across geographies but only if we can demonstrate and measure the impact. This is the growth part of our journey. Measuring and demonstrating the impact of our technology is the next step of our growth journey that we believe will lead us to scale. We are applying to the MIT Solve Challenge to leverage its network and resources for lessons and research in how to measure impact for AI technology that does not directly save but serves lives.
We are in the final stages of negotiating a memorandum of understanding with the MOH in Burkina Faso to deploy STRIATA for HRH. We will leverage existing funding to test and deploy new ways of monitoring and measuring the impact of ML on health systems in Burkina and Sierra Leone.
Who is the Team Lead for your solution?
Benjamin Fels , CEO
What makes your solution innovative?
STRIATA is different in how it treats conventional data, and different in how it interprets the external dimensions of data. Core algorithms learn to segment time-series data to extract maximum signal, to scan for similarity and to determine meaningful shifts, allowing the model to learn in a nonlinear way all the while delivering outputs from an early stage. Hundreds of dimensions of ‘alternative data’ are incorporated.
Each deployment of our core technology leverages existing data alongside the tools we have developed to deploy STRIATA at national scale in diverse countries, from the USA to Tanzania and Sierra Leone.
What makes STRIATA AI for human resource for health innovative is that it enables governments/its users to better understand how its workforce is distributed, align investment in HRH with the current and future needs of the population and health systems as well as strengthens HRH information systems. The WHO estimates that 15 million more health workers are needed worldwide by 2030, primarily in low- and middle-income countries. As shortage of health workers in Africa remains a challenge, maximizing the use of existing heath workers needs to be a focus.
STRIATA radically extends what is possible with scarce resources. In Africa, health worker are a scare resource. Using multiple data sets, STRIATA learns the location of current gaps in human resources. Using DHIS2, WISN, location, population and HR data it learns what HR cadre is needed per health facility and, recommends where HR should go based on need.
What are your impact goals for the next year and the next five years, and how will you achieve them?
In the next year our goals are as follows:
Better understand, document, and track the impact of STRIATA
Expansion of our HR deployments into 2 additional countries
DHIS2 integration
mSupply integration
OpenMRS integration
In the next 5 years our goals are as follows:
Expansion fully integrated and used in all countries where STRIATA is deployed
Measurable impact of STRIATA on lives saved, systems optimized and costs and waste reduced.
Integration with non-specific systems – to become system agnostic.
How are you measuring your progress toward your impact goals?
Impact is a balance of scale and efficiency. Currently we measure the number of people our technology reaches, the number of countries we engage successfully, the reduction in cost to our customers as we increase implementations, speed of technology integration and we hope to measure our financial impact over time. The latter will take additional time in country – likely over 5 years – before a meaningful trend statistics can be captured. Technology performance is measured against a baseline of the status quo, and statistical measures of model accuracy (internally as F1 or R-squared, externally as a percentage of accuracy of prediction based on preliminary retrospective analysis).
Understanding impact is one of the drivers behind our application to this challenge – a recognition that monitoring and tracking the impact of new technology, in a global health context, is very challenging. This grant will enable our team to test new measurement such as waste, return on investment, and cost that focus on providing our main partners (governments and donors) with the feedback they need to understand what is working and where improvements are needed.
What is your theory of change?
NEED
Stakeholders (MOH, Donors) have limited visibility into the distribution of primary care level health workers (facility and Community Health Workers). These are therefore not optimized to deliver health services to the population, gaps in coverage are unknown and access to health services is not equitable.
INPUTS
Adapt and deploy STRIATA machine learning models via an interface (or written directly to existing platforms such as DHIS2 or iHRIS) to display the machine learned/AI distribution of health workers, identify gaps and provide recommendations on how to optimize the distribution of staff across the health system.
OUTPUTS
Outputs deliver both the existing distribution of health workers, gaps in coverage and recommendations on how to optimize across the health system.
INTERMEDIATE OUTCOMES
Decision makers will have access to more complete and accurate data and can use human resource optimization in program decision making.
IMPACT
Improved use of human resources, identification of gaps, and improved health worker coverage leads to improved access and availability of services, reduced waste, improved health outcomes and ultimately decreased mortality.
Describe the core technology that powers your solution.
Macro-Eyes built STRIATA to learn continuously from data new and old - sensitive to changes in the country and in the market. Each deployment of our core technology leverages existing data alongside the tools we have developed to deploy STRIATA at national scale in 14 countries.
Learning from thousands of inputs extracted from a multitude of data sources (satellite imagery, demographics, and public data), STRIATA comprises three pillars: FORECAST, VISIBILITY, and BEHAVIOR.
Forecasting: STRIATA-Forecast uses revolutionary machine learning tools to drive predictive analysis in supply chains. It brings new insights into forecasting for commodities such as medicine, vaccines, equipment, human resources, technology, supplies and services. It makes forecasting intelligent and enables efficient resource allocation. When you accurately anticipate the need, you can effectively fulfill it.
Predicting Behavior: Matching supply to demand is the objective of every supply chain and when it comes to demand -for various products and/or services-, behavior is driven by many factors that, in combination, create new dynamics. STRIATA-Behavior allows users to predict human behavior in a specific context, seeing patterns by group as well as by individual. When you understand behavior, you can guide interventions.
Providing Visibility: Identifying inefficiencies, gaps and roadblocks that can hinder service delivery strengthens real-time informed and reliable decisions. STRIATA-Visibility provides a dynamic view into the current infrastructure of a system that includes assets, vulnerabilities, supply-chain demands, human resource readiness, compliance, and infrastructure. It strengthens real-time informed and reliable decisions in areas such as resource management, education, and health care systems. This insight empowers key decision-makers to allocate and act with optimal efficiency.
Together, precision forecasting, predictive behavior, and real time visibility form the framework for a predictive health system and can be deployed individually or as a suite embedded within existing digital systems via API into an existing system or as a standalone interface.
Which of the following categories best describes your solution?
A new application of an existing technology
Please select the technologies currently used in your solution:
Which of the UN Sustainable Development Goals does your solution address?
In which countries do you currently operate?
In which countries will you be operating within the next year?
Who collects the primary health care data for your solution?
We do not collect new data. STRIATA is designed to work with existing data. We access the data through data sharing agreements or through the public domain. Macro-Eyes has Memorandum of Understanding with Ministries of Health in Sierra Leone, the DRC, Chad and soon Burkina Faso. We also access country data through our development partners on USAID global awards (CHISU and DataFi). These agreements outline what and how we access and use health data.
What type of organization is your solution team?
For-profit, including B-Corp or similar models
How many people work on your solution team?
Macro-Eyes currently employs 49 fully remote employees across Administration, Operations, Machine Learning, Software Engineering, Program Management, and Communications fields. Macro-Eyes is proud of our diversity of staff, including over 50% female directors providing leadership.
How long have you been working on your solution?
9 years
What is your approach to incorporating diversity, equity, and inclusivity into your work?
Internally, Macro-Eyes staffing practices, recruitment policy and guidelines are inclusive, culturally sensitive and promote a diverse workforce. Leadership is from diverse backgrounds. 50% identify as female. As a multinational and multicultural organization, Macro-Eyes believes diversity enriches our work and enhances impact and effectiveness both internally and within communities we serve. We develop, implement, and communicate initiatives that reflect the value we place on DEIB (Diversity, Equity, Inclusion and Belonging)
Our approach to learning and development, performance management and opportunities for growth, promotions and any other benefits is on the basis of merit. We oppose all forms of unlawful and unfair discrimination.
Externally, we work with front line communities and local partners to incorporate equity into intelligent supply chains. This requires engaging with groups who are most at risk of impact from inefficient supply chains - both in terms of access to services and impact of carbon emissions that result from inefficient supply chains. Macro-Eyes is intentional in our stakeholder management, collaborating with governments and local organizations and partners to inform integration and to educate on data use in decision making. Through this engagement we are able to work with and not just for the communities most affected by inequitable health service delivery and climate impacts of waste in supply chains.
What is your business model?
Macro-Eyes builds products on a foundation of proprietary artificial intelligence. In addition to these products, Macro-Eyes provides the professional services (consulting) required to deliver the product impact to challenging environments. The most challenging part of the product to impact cycle is adoption. Our professional services often focus on accelerating and expanding adoption of our technologies through ease of use, interaction with existing systems, automation, and demonstrating value.
Our existing products are focused on increasing the efficiency and effectiveness of supply chains across sectors. We predict the future of the network needs and recommend changes in the supply chain to improve outcomes of the business, health system, or organization. Our professional services provide experts in measuring, integrating, and communicating the products. Customers need these products to ensure every resource in their system has the greatest possible positive impact on their customers and organizations. Supply chain is the mechanism for advancing operational efficiency across and entire organization.
We focus on delivering impact to the most challenging places on earth. We’ve worked extensively in low and middle income settings and use sparse data to deliver impact to the last mile. We are currently generating our income primarily from grants. We have recently expanded to direct licenses with government agencies, and are working with private industry to increase the balance of our portfolio toward longer term, SaaS licensing agreements.
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?
Macro-Eyes was founded in 2013 and has been generating revenue since 2014 without having raised venture funding. We intend to continue to build resilience into the business and increase our ability to scale rapidly. We are proactively moving away from grants heavy portfolio to SaaS licensing to ensure the scalability of our deployments. We are developing streamlined SaaS pricing that can incorporate the scale (more nodes + commodities) required by our enterprise customers. Fixed implementation fee and discounts for larger customers. We base the implementation fee on integration costs and the effort to discover and obtain data (we augment what can be learned from customer data with learning from satellite imagery and from the public internet). We’re exploring pricing discounts/premiums based on logistics modalities and the size of asset (trucks and TEU/FEU) fleets.
Solution Team
-
Drew Arenth Chief Business Officer, macro-eyes
-
Benjamin Fels CEO, macro-eyes
-
RM
-
JS
Jeni Stockman Macro-Eyes
-
DT
Daren Trudeau Macro-Eyes
to Top
Our Organization
Macro-Eyes