Chitra: Supporting localized healthcare provision by community health workers using a mobile mapping and visualization tool
Mobile platform for health workers to map community environments and disease incidence. Leverages machine learning for contextualized care.
Health workers using initial prototypes for data collection.
Initial mockup of the Chitra mobile application
Explain your project idea (2,000 characters)
Around 1,000,000 community health workers (CHWs) collect demographic, environmental, and medical data across India, using paper forms. Despite huge efforts to collect data in the first place, this data is frequently underutilized. There is a huge scope for (1) digitizing the data collection process, and (2) analyzing collected data to help healthcare providers deliver personalized care to communities. Particularly, low-resource communities that rarely access hospitals and clinics could benefit greatly from targeted interventions.
To meet this need, we propose Chitra - a mobile application that (1) helps community health workers (CHWs) collect hyperlocal data through map annotations, and (2) builds community profiles by applying machine learning on collected data. This can help CHWs and healthcare providers provide personalized care to communities.
Health and health-seeking behaviors are a product of environmental, socioeconomic, and cultural factors. Recording and understanding these location-based factors (planet) can help develop health interventions that take into account these aspects and community resources. This can result in improved health outcomes, particularly among underserved communities that are most affected by their surroundings (prosperity).
How does it work?
We build upon existing open source mapping tools such as Local Ground and ODK to enable hyperlocal data collection using map annotations. We aggregate collected data based on location and then apply machine learning algorithms to help identify communities that are at risk of disease and the underlying factors that may be responsible for the threat. User-friendly insights are presented as community profiles to health providers such as doctors, community health workers, and policymakers to help them make data-driven decisions. The project thus leverages and supports healthcare providers' existing competencies and deep understanding of local communities.
Who are the beneficiaries? (1,000 characters)
For the timeline of this project, our beneficiaries are residents of slums along the Yamuna river in South-East Delhi. A major goal of the project is prolonged engagement between communities and health workers. Health workers in the area routinely visit communities once every 4-5 months for data collection. Apart from that, they only visit for maternal and child health because there is little structure and support for other health interventions. We hope to deliver this support and encourage health activism by providing health workers a means of monitoring and addressing community health including risk factors of disease.
Our targeted beneficiaries, slums along the Yamuna river.
We will open source the developed mobile application at the end of the project so that other communities may benefit from it. Additionally, we hope to scale our efforts in India in partnership with more community health workers as well as health organizations for whom data collection is a primary effort.
How is your idea unique? (1,000 characters)
Current players in this space are global organizations such as Medic Mobile, DHIS2, Dimagi, and Nafundi. All of these are data collection companies with a particular focus on working with community health workers. However, current efforts to analyze collected data rarely go beyond recording disease outbreak and service coverage. This results in underutilization of rich collected data despite massive efforts to obtain them in the first place.
Our core competency lies in the use of machine learning techniques to provide customized care. We go beyond current efforts that are focused on data collection to also analyze the collected data and make hyperlocal disease predictions and healthcare delivery recommendations. We thus complement and build upon existing efforts. We also follow a human-centered approach---working closely with health workers on the ground and understanding their current data workflows and work priorities to be able to leverage and support them meaningfully.
Idea Proposal Stage (choose one)
Prototype: I have done some small tests or experiments with prospective users to continue developing the idea.
Tell us more about your organization/company (1 sentence and website URL)
The core work on the project is being carried out by the Chitra organization. Website: http://chitrahealth.com
It is being developed and deployed in collaboration with the Technology and Design for Empowerment (TanDEm) lab at the Georgia Institute of Technology, Atlanta, Georgia, USA. Website: https://tandemlab.tech
Organization Filing Status
No, but we plan to register in the future.
No, but we are a formal initiative through a university.
In 3-4 sentences, tell us the inspiration or story that encouraged you to start this project.
From May to August 2016, we conducted ethnography in an underserved region of Delhi. Our goal was to gain a ground-level perspective on private and public healthcare infrastructure. Through interviews and observations, we found a major disconnect between patients and healthcare providers. Health was often a product of circumstances (environment, culture, economics) unknown to healthcare providers. This motivated Chitra, which aims to deliver healthcare providers a picture of target communities.
Please explain how your selected topic areas are influenced, in the local context of your project (1,000 characters).
In the underserved communities targeted by Chitra, health is often an outcome of community surroundings. This includes the physical environment, which slum residents are exposed to in their open and close dwellings (e.g. the polluted Yamuna river). It also includes the cultural backdrop where certain unhealthy practices may be culturally acceptable (e.g. tobacco chewing and open defecation) and healthy practices may not be part of daily life (e.g. hand washing and institutional deliveries). It also includes infrastructure (e.g. electricity, water, and sanitation) and social context (e.g. community support). Thus, health is closely tied to Planet.
Prosperity is directly affected by health. Poor health results in lost days of work and decreased productivity. In the target context, families frequently slip into debt because of health issues and often forgo visiting a hospital or clinic in favor of work and money in the pocket. Hence, non-clinical alternative interventions are needed.
Who will work alongside your organization in the project idea? (1,000 characters)
We are closely working with community health workers and slum communities in Delhi on this project. We follow an iterative process, taking input from health workers on the functionality, design, and appropriateness of our proposed intervention. We make them primary stakeholders and privilege their superior understanding of local communities.
So far, we have conducted participant observation with community health workers to better understand their interactions with local communities and the challenges they face. From January to May 2018, we deployed an initial data collection prototype with 5 community health workers and 600 slum residents. The collected data is being analyzed and preliminary machine learning algorithms have been developed. In February 2018, we also conducted 2 co-design sessions with 17 community health workers for the mobile application. Using insights we gained during the co-design process, we have developed an initial design for the mobile application.
Please share some of the top strengths identified in the community which your project will serve (500 characters)
Some of the strengths that we have identified in the community include close-knit relationships with community health workers, strong support networks among community members, and activism of local mosques which often hold local gatherings and announcements.
This particular project will target underserved slum communities in South-East Delhi, India.
How many months are required for the project idea? (500 characters)
We will first conduct co-design exercises with CHWs to determine appropriate visualizations and modalities for mapping and presenting community health profiles (3 mths). Using these insights, we will develop a mobile mapping application (4 mths). After training (1 mth), we will carry out mapping exercises with 20 CHWs and 20,000 people (4 mths). We will tune machine learning algorithms (4 mths). Finally, we will monitor healthcare provision activities during deployment (15 mths).
Did you submit this idea to our 2017 BridgeBuilder Challenge? (Y/N)