multipronged approaches to engaging clients for improved health

Jacaranda Health’s two-way text messaging platform (PROMPTS) educates and empowers mothers in Kenya to seek care at the right time. It is rapidly scaling, with 40,000 users projected by the end of 2019. A feature of the platform that has high demand is the ability for mothers to have their questions answered by helpdesk agents. The helpdesk has responded to >30,000 unique questions to date. Although many of the questions are general in nature and non-urgent, almost thirty percent of incoming messages indicate the need for further and often urgent medical attention – such as bleeding or sepsis. We asked: How can these red-flag questions or comments be identified quickly, while maintaining the overall efficiency and quality of the helpdesk? In this session, we will share our approach to using Natural Language Processing (NLP) on the rich conversational data contained in the platform to rapidly identify mothers who need additional care. Our goal is a response time of less than 1 hour for these urgent questions. We designed and tested an NLP bot, with an integrated Swahili translation component, that reads each incoming question and assigns a priority level and provides a suggested response to each message. The priority levels and suggested responses are used by the helpdesk agents to respond more quickly to high priority messages (e.g. bleeding). Preliminary assessments indicate that integration of this bot has resulted in a 50% reduction in response time to urgent questions. We will discuss how this approach leverages a powerful source material for Machine Learning: a well-characterized corpus of data of individuals and their health outcomes that can be used to better understand complex conversations and intents.

In 2016, Babylon healthcare, a UK digital health company, entered Rwanda on invitation from the Government of Rwanda to adapt and launch its' innovative digital health service in Rwanda. Babyl, from its call centre in Kigali, provides a nationwide digital health service on both feature and smart phones, including virtual consultations with nurses and doctors, digital prescriptions and laboratory tests issued via SMS code. In partnership and licensed by the Ministry of Health (MoH), Babyl began clinical operations in September 2016. Based on their early success, Babyl signed MoUs with the MoH for integration with primary health facilities and with the Rwandan Social Security Board (RSSB) to enable Babyl's patients to obtain prescriptions and laboratory tests covered by their public health insurance scheme. Babyl has now integrated its platform into 418 of 507 health centres in all 30 districts in Rwanda, trained staff in over 538 partner health facilities to deliver digital health services, and placed agents in over 150 health facilities to support help to use Babyl. They have also trained over 10,000 Community Based Health Workers on the use of digital health. More than 2million Rwandans are registered with the service, over 550,000 consultations have been provided by the team of 106 nurses, 80 doctors, support and management staff and they currently deliver 2,500 and 3,000 consultations a day. In order to understand the reach, acceptability, and cost-effectiveness of this digital first primary health service, Babyl commissioned an independent study conducted by Dalberg Partners with support from the Bill and Melinda Gates Foundation and USAID. The study which was completed in March 2019, provides valuable insights to operational improvements and more importantly, demonstrates the potential of digital health interventions to make transformative contributions to accelerating Universal Health Coverage.

The Mobile Alliance for Maternal Action (MAMA), a global consortium with public-private funding, has delivered vital health information to pregnant women, new mothers and their families through SMS text messages and interactive voice calls (IVR) using their mobile phones their mobile phones with messages that are specifically designed for behavior change. Through an “ages and stages” model, the messages correspond to what a woman is experiencing in her pregnancy or in her child’s development, creating a trusting relationship between the end user and the MAMA Service. With an intentional focus on countries where high maternal and newborn mortality rates intersect with an increasing proliferation of mobile phones, MAMA directly supported country programs in Bangladesh, India, and South Africa and in 2015, launched a program in Nigeria, branded as HelloMama. The HelloMama project operated in Nigeria with the goal to improve the health outcomes and quality of life for pregnant women, newborns, children and their families through a nationally scaled, locally led, and universally accessible demand generation service. HelloMama’s theory of change is based on evidence that when a woman has appropriate information about her health, her child’s health and services that she should use, then she is more likely to adopt health behaviors and use services that will lead to improved health outcomes. Recognizing that husbands/ partners, also have influence on a woman’s maternal and child health care, a set of free messages was also developed for this target population