Lokarpit Voice Forum and Database

Lokarpit Voice Forum and Database

India
Organization type: 
nonprofit/ngo/citizen sector
Budget: 
$10,000 - $50,000
Project Summary
Elevator Pitch

Concise Summary: Help us pitch this solution! Provide an explanation within 3-4 short sentences.

Our organization works in the northern Indian state of Uttar Pradesh, one of the poorest states in India. The area is predominantly rural and has for centuries been plagued by abject poverty. High birth rates (5-8 children per household) and high infant mortality rates are the norm. There's a severe lack of basic knowledge of maternal health. For example, one of the local traditions is to smear cow dung on a recently cut umbilical cord; another example is the custom of reserving the job of cutting the umbilical cord exclusively to low-caste helpers, and when such helpers need to be fetched from afar, the umbilical cord remains attached for as long as 24 to 48 hours, worsening infection rates. Many of these customs and misconceptions are not widely known or practiced elsewhere so one-size-fits-all "experts" or pamphlets rarely adequately address such misconceptions or concerns.

The problem of lack of such basic awareness and knowledge is badly compounded by the lack of access to basic care. A clinic or hospital is often far away; transportation is difficult to arrange; villagers are concerned about being charged a high fee that they can't afford if they seek care; a conservative culture dictates that most do not feel comfortable with the idea of a woman traveling alone (to seek care) without the company of a husband or father, who are needed in the fields or at other work places (like a brick factory). Due to the difficulty of seeking care, people tend to overlook their illness until it's perceived to be serious. Often, instead of trekking to a district hospital that can be tens of kilometers away, people tend to seek advice from local quacks, who typically end up doing more harm than good. Better access to maternal health information would have helped in preventing and identifying less urgent problems earlier before they worsen.

Traditionally, there are several approaches of addressing maternal health information. Because the qualified doctors, nurses, and organizations who truly understand the local problems are few, the concerned geographical area is large, and the infrastructure (such as roads) is poor, the commonly adopted model is a so-called "cascaded training" model, where the experts train the trainers, the trainers train the next-level trainers, and so on. There is often a loss of fidelity and, furthermore, there is a large degree of diversity and complexity of the problems at the local level that, due to the disconnect between the experts and the ones who truly need help, cannot be adequately addressed.

Another theme of approaches that has been tried is to use some form of technology: kiosks equipped with computers, or smart-phone-based solutions, to name just two. The practicality of such solutions is limited due to the cost, usability, and infrastructural issues (such as lack of electricity to power a kiosk or the lack of data network coverage--while voice coverage is pervasive, data coverage isn't). The low literacy rates of the community that we serve further compounds the difficulty of these technology-based solutions. Our experience is that even an SMS-based solution is difficult to made work in this environment.

In the past six months or so, we have been developing and test-deploying a "voice forum." In its simplest form, one may think of it as a web-enabled voice mail system and a voice database. The villagers that we serve access the system with their regular voice phones. (In our experience, virtually all of those who don't have their own phones have access to someone else's.) The villagers can leave their personal queries, receive personal responses (that address their specific concerns), or receive broadcast messages (that are of interest to larger groups). For those who have access to more sophisticated technologies, such as staff, nurses, doctors and some of the trainers, the voice system is accessible via a web database interface. The incoming messages are categorized, filtered, and assigned to groups of potential responders. Those who choose to respond or are tasked to respond may submit answers via either the web interface or their own cell phones. The responses are then sent at their preferred times back to the villagers who made the initial queries.

Voice mail systems are obviously not new. We discuss how our system is technically and functionally innovative. Traditionally, such an application (such as the well-regarded "Lifelines" system) is typically developed with expensive and proprietary PBX equipment and software, often with the blessing of carriers. The traditional approach is costly, difficult to customize, and difficult to justify for small groups of targeted users. The carriers' main interest is a large-scale one-size-fits-all system that can earn non-trivial revenue and can be administered centrally. In contrast, our system is built on top of cheap ISDN line cards plugged into conventional PCs and the open-source Asterisk framework. (The voice servers simply sit in our regional offices, as opposed to being inside telecom carriers' machine room closets.) The decentralized development and deployment is low-cost, provides extreme ease of local customization, and makes it feasible for us to experiment with tailor-made solutions for small local populations and experts. The solution can be easily and cheaply replicated at many locations, and because these distributed systems are networked, the information can be easily shared across the entire network of voice servers.

Functionally, the system that we have built is much more than a voice mail system. A vanilla voice system mostly just provides one-to-one exchanges. In our system, on the other hand, for example, an exchange between a villager and a nurse is stored in a voice database, and if deemed appropriate (and with proper privacy precautions), the same exchange can be either re-used for another villager or re-broadcast to an even larger group (such as an interest group created for pregnancy or child nutrition). Indeed, one extra outlet of the voice database is community radio systems, which can be enlisted to beam frequently asked questions and answers to selected communities. (We are also building and experimenting with "phone radio boxes," boxes that behave like radios but receive their programming from cellphone links and can be interactive.) Furthermore, as discussed above, voice data initially gathered at one locale can be shared with other peer networked voice servers serving other locations. The knowledge accumulation in such a voice database and the strategic re-use of the information is critical in addressing the "expert bandwidth" problem.

Another area of our innovation that lies somewhere in between low-level underlying technology and high-level functionality is usability. For example, we have found that for some of our poorest areas, even the cost incurred during the making of a cellphone call is a non-trivial burden. Our solution is that our system can be programmed to automatically dial villagers who have signed up to participate in our system and have specified at which times they prefer to receive calls (once a week, for example), and at these preferred times they can record their new queries or concerns and hear new messages intended for them. (Receiving calls is free in India.) We have found that our users' ability to specify their preferred times of receiving automated calls is critical. This example is but one of the many usability issues that we have worked on to make our system easier for our users to participate in.

An important functionality of this networked voice forum is that it allows potential contributers to work together in an easy and flexible way. For example, in addition to doctors who work in our target areas, potential contributers elsewhere, such as medical school students and even professionals working in the US, can easily listen to queries submitted from rural Uttar Pradesh
and submit their own responses. The language problem can be overcome when volunteer translators, who possess no special medical knowledge, transcribe voice submissions and record newly translated outgoing responses through the system. Healthcare workers who possess less specialized knowledge can at least perform duties such as categorizing and sorting incoming messages and assigning them to the right kinds of potential responders who have more specialized knowledge. This division of responsibilities and the ability of people with diverse skills to work together, across potentially widely separated space and time, is a powerful force multiplier.

Of course, the role of the system should be largely informational, not "playing doctor" in emergency situations--we fully recognize that we cannot expect to cure people over just a voice mail system. The hope is that by making access to health information much easier, we can catch milder problems before they develop into emergencies, and in cases of real emergencies, the best we can do is to advise seeking in-person care at a clinic or hospital as soon as possible. In the future, we plan to tie the voice forum to existing physical activities, such as regular "camp runs" of van visits staffed by doctors and nurses from participating local hospitals and clinics.

Let us also briefly discuss how the other challenges (discussed earlier) facing traditional maternal health awareness projects are addressed by the proposed system. The fidelity loss problem of traditional cascaded training model is addressed by the voice forum's ability of directly connecting questioners and expert answerers. In addition, the voice forum database itself can become a good training tool, as mid-level responders can increasingly familiarize themselves with the types of questions and expert answers being exchanged, so that they become increasingly capable of "filtering" the questions first, further reducing the burden on the experts whose times are most valuable.

The need to avoid relying too much on traditional one-size-fits-all broadcasts (including approaches like distributing brochures) that cannot effectively address diverse local customs and concerns is addressed by the fact that the information exchange in our voice forum is on the one hand driven by real-life queries from villagers, and is on the other hand driven by professionals with the greatest local practice experience. (Our system also allows discussions of important issues that are not strictly health-related, such as women's rights, alcohol abuse (by husbands), and girl child's education.)

The need to avoid using complex and expensive technologies that are inappropriate for a largely illiterate population is addressed by the fact that the only equipment the villagers would need to access our system is simple voice phones. Furthermore, the underlying technology powering the voice servers is such that the infrastructure serving the voice forum can be scaled cheaply, easily and gradually (if necessary). Our hope is that one day, we will be running a large network of these voice servers, buzzing 24 hours a day with queries and answers coming into the system from everywhere, ranging from villagers of the remotest locales to professionals from the most prestigious institutions, constantly serving a large population that need help the most.

About Project

Problem: What problem is this project trying to address?

The primary problem that our system addresses is lack of easy and regular access to healthcare information that is timely and locally relevant (or even personal). Many of the customs and misconceptions that need to be addressed are not necessarily widely known or practiced elsewhere so one-size-fits-all mediums, such as pamphlets and radio broadcasts, rarely adequately address such misconceptions or concerns. The problem is exacerbated by poverty, poor infrastructure (including transportation and means of communication), and a conservative culture that has aspects that make it difficult for women to independently seek care. Traditional approaches such as "cascaded training" tend to lose fidelity and insulate the experts from those they serve. Traditional technology-centric approaches are handicapped by the low literacy rates of our target population, these solutions' high costs, and (again) lack of infrastructure support.
About You
Organization:
Digital StudyHall
Visit website
Section 1: About You
First Name

Randolph

Last Name

Wang

Organization

Digital StudyHall

Country

, UP

Are you an individual between the ages of 18 and 35 who would like to apply for a nine month Young Champions Program mentored by an Ashoka Fellow?

No

Section 2: About Your Organization
Organization Name

Digital StudyHall

Organization Phone

+91 0522 4027694

Organization Address

C-3/67 Vipul Khand 3, Gomti Nagar, Lucknow 226010, UP, India

Organization Country

, UP

The information you provide here will be used to fill in any parts of your profile that have been left blank, such as interests, organization information, and website. No contact information will be made public. Please uncheck here if you do not want this to happen..

Your idea
Country your work focuses on

, UP

Innovation
What makes your idea unique?

Voice mail systems are not new. Traditionally, such a system (like "Lifelines") is typically built with expensive and proprietary PBX equipment and software, often with the blessing of carriers. Such an approach is costly, difficult to customize, and difficult to justify for small groups of targeted users. In contrast, our system is built on top of cheap ISDN line cards plugged into conventional PCs and the open-source Asterisk framework. The voice servers simply sit in our regional offices, as opposed to being inside telecom carriers' machine rooms. The decentralized development and deployment is cheap, provides extreme ease of local customization, and makes it feasible for us to experiment with tailor-made solutions for small local populations and experts. The solution can be easily and cheaply replicated at many locations, and because these distributed systems are networked, the information can be easily shared across the entire network of voice servers.

Functionally, the system that we have built is much more than a vanilla voice mail system. which mostly just provides one-to-one exchanges. In our system, for example, an exchange between a villager and a nurse is stored in a voice database, and if deemed appropriate (and with proper privacy precautions), the same exchange can be re-used for another villager or re-broadcast to an even larger group (such as an interest group created for pregnancy or child nutrition). Indeed, one extra outlet of the voice database is community radio systems, which can beam out frequently asked questions and answers. We are also building "phone radio boxes," boxes that behave like radios but receive their programming from cellular links and can be interactive. Furthermore, voice data initially gathered at one locale can be shared with other peer voice servers serving other locations. The knowledge accumulation in this manner and the strategic re-use of the information is critical in addressing the "expert bandwidth" problem.

Do you have a patent for this idea?

Impact
What impact have you had?

The proposed system is new. The initial software and hardware development was completed only in 2009. Since March, we have begun a test deployment at the rate of adding one target village per week. We are currently fielding 10-20 messages per village per week.

While the experience with the proposed system is limited due to its newness, the system is a "spin-off" of a similar voice forum that we have built connecting rural teachers with their urban counterparts, as a part of the larger Digital StudyHall project (http://dsh.cs.washington.edu/info/voice.html). The teachers' voice forum has been piloting for about seven months and has been very successful. We have invited about 250 teachers from about two dozen schools and teacher-training institutes to participate in the pilot. The system has so far logged 2800 calls, spanning more than 6000 minutes, covering diverse topics such as girl child education, caste bias, child labor, child marriage, pedagogical tips (such as how to conduct group activities), specific subject matter questions, student activities, and many more. The system allows the teachers to seek advice, receive feedback, share experiences, conduct virtual student and teacher activities. Teachers have told us that the kind of sophisticated in-depth discussions that they can hear and participate in is something that would have been impossible in these rural area schools without the system.

Actions

(1) Technology development. While the bulk of software development has been recently completed, we expect to continue adapting the system based on field experiences. (2) Publicizing the system among our rural target audience and educating the audience about using the system. We work with several partner organizations that have their own field staff; the system is introduced as part of these organizations' current field work. We're currently adding about one village per week to the system. (3) Building the network of doctors and other health professionals who field the questions submitted to the system. This is again something that we work on together with our partner organizations. We will create panels of professionals with various expertise, along with volunteer staff who perform roles of filtering, categorizing, and forwarding of incoming messages and administering the system. (4) Surveys and evaluations. We will study to what extent our partner organizations' work is improved by the system, what behavior change we may observe in our target audience, and "bottom-line" results such as improvement in infant mortality rates.

Results

(described earlier.)

What will it take for your project to be successful over the next three years? Please address each year separately, if possible.

Beyond the actions discussed above (of which, evaluation is particularly important), we plan to scale up the system to serve beyond the villages that we currently work with in Uttar Pradesh of India. An important advantage of our system (compared to traditional proprietary systems) is its decentralized architecture--it allows organizations at different geographical locations to easily set up their own voice servers, which serve their immediate neighboring areas. Such an organization will be responsible for publicizing their own service number in the target areas where they work, recruiting volunteer doctors and professionals to field questions on the voice system, staffing the system with their own office workers. All these voice servers are networked with each other so they can share voice information with each other. Our tentative goal is to grow to a new geographical area during each of the next three years. One of them is likely to be a partner organization in Nepal that we are already planning with.

What would prevent your project from being a success?

During the initial months of piloting our prototype, we have seen promising signs that the system appears to work quite well: diverse queries submitted by the villagers that we serve, timely information and advice provided by volunteer doctors. At least at the moment, we do not foresee scenarios that will completely doom our growing effort in the immediate future. We could, however, discuss some factors that could further amplify the impact of the system. An example is resources for further physical followup. The system, as described so far, is strictly informational. To make it even more effective, our partner organizations could identify the critical cases gathered in the phone system and organize, for example, a van trip that visits callers identified in these cases, transporting some to clinics or hospitals for further checkup, or dropping off specific medicines. The lack of additional resources for such physical followup could limit the impact of a strictly informational system.

How many people will your project serve annually?

1001‐10,000

What is the average monthly household income in your target community, in US Dollars?

Less than $50

Does your project seek to have an impact on public policy?

Yes

Sustainability
What stage is your project in?

Operating for less than a year

Is your initiative connected to an established organization?

Yes

If yes, provide organization name.

Digital StudyHall, Lokarpit, Mona Foundation

How long has this organization been operating?

More than 5 years

Does your organization have a Board of Directors or an Advisory Board?

Yes

Does your organization have a non-monetary partnerships with NGOs?

Yes

Does your organization have a non-monetary partnerships with businesses?

Does your organization have a non-monetary partnerships with government?

Yes

Please tell us more about how these partnerships are critical to the success of your innovation.

We work with partner organizations such as health-related NGOs and hospitals that have an extensive track record of outreach programs. Our initial prototype is piloted in conjunction with "Lokarpit." A partner organization plays several important roles. Its field staff publicizes the system in the target areas served by the organization and educates the rural users about how to use the system. The organization recruits and organizes professionals who provide advice on the voice forum. Its office staff administers the system, performing daily chores such as "routing" queries on certain topics to professionals of certain expertise, and "routing" responses from the professionals back to the original questioners; all of these administering duties can be performed on a computer or a phone with minimum technical skill. If a partner organization intends a copy of the system under its control to grow to a larger scale, it's responsible for organizing resources to fund the expansion.

What are the three most important actions needed to grow your initiative or organization?

(1) Growing within our current set of partners and evaluation of results. We work with our partners to expand the circle of contributing professionals and rural user community. Based on feedback from the users and contributors, we fine-tune the system and the process. We will work with our partners on evaluating behavior change and bottom-line improvements (such as infant morality rates) as a result of adopting the system. (2) Growing beyond the current set of partners. We identify partner organizations that have had extensive experience of outreach programs in maternal health, understand their work, and discuss with the partners how a voice forum connecting their audience and professionals can help. We set up a copy of the voice system for the partners and train their staff to operate the system, gradually customizing the system in the process. We facilitate voice data sharing among the multiple partner organizations via the system. (3) Helping selected partners grow to a larger scale. An important advantage of our system is that it could accommodate an organization and audience of arbitrary size. While a traditional proprietary system cannot be cost-effective for a small-scale operation, our system can work for organizations that are small or large. Most organizations might just run a voice server on a single office PC. We expect to see a small set of particularly promising partnerships that have potential to scale, and in those cases, we will work with these partners to raise resources for more significant expansions.

The Story
What was the defining moment that you led to this innovation?

In the past two years or so, our organization has been working with our partners on a project that shares community-generated videos to improve health-awareness in rural India. (We may submit a separate proposal for that effort.) As we visit the many recipient villages during our work, it became painfully clear that the lack of systematic access and communication of snippets of diverse health-related information is a major problem. Virtually all of the existing projects (ours and others') share this handicap: once the project staff leaves an area, there is virtually no good way for villagers to ask questions and receive advice, so there is a disconnect between the staff and the community they serve. In some sense, each of our visits became an incremental "defining moment."

One may naively ask why the staff doesn't simply give out their own phone numbers or a number belonging to the organization. This simple solution doesn't really work because the person who happens to pick up the phone is rarely in a position to provide competent advice. Besides, the staff doesn't really want to give out their own phone numbers, fearing, say, getting woken up in the middle of the night by strangers. Furthermore, a good advice, following a good question, is used only once in a regular phone conversation; it would have been better if we could save it and re-use it. When the staff does visit a place in a "health camp," they always get swamped as entire villages empty out to see them; among other things, this is an indication of long "bottled-up" thirst for information, which either never comes, or comes way too infrequently, too irregularly, or too late.

These problems suggest to us that we need a better system for connecting the project staff with the rural community. The system should allow experts to easily contribute at convenient times of their own choosing; the system should allow the staff to source from a large pool of potential expert contributors; the system should be able to systematically "remember" and re-use prior exchange; the system should operate in a de-centralized fashion, yet still connecting the knowledge bases of the different organizations together; the system should be cheap, nimble, easy to customize and operate. The prototype we have today is the cumulative result of many small "defining moments" of realizing these needs.

Tell us about the social innovator behind this idea.

Randolph Wang graduated with a PhD in computer science from the University of California Berkeley. He was a professor at the computer science department at Princeton University where the Digital StudyHall project started. Randolph's research interest was in operating systems and networking systems. DSH was started at a time when Randolph became interested in applying technology to solving compelling problems in developing world settings. In 2005, Randolph moved from New Jersey to Lucknow, India, where he has lived and worked to this date.

How did you first hear about Changemakers?

Email from Changemakers

If through another, please provide the name of the organization or company