Headquarters location
Operates in: GH, KE, SZ
Mission
Improving quality of care and outcomes for every mother and every newborn.
Current technology use
PROMPTS (Pregnancy Remote Outreach using Mobile & Personalized Texting Support) is an AI-Powered Mobile Health Platform that empowers women with information via SMS to make informed choices about their health care, ask questions during and after pregnancy, and receive targeted support and referral if a risk is identified during the exchange.
Data Analytics: PULSE combines real-time data from mothers, nurses, and facilities into actionable dashboards that help governments better understand and address the gaps preventing the provision of timely, quality care in maternal health systems.
Uses AWS cloud services to increase visibility of how PROMPTS impacts key health indicators.
Press and research
- Academic work
Maternal Health Task Force. (n.d.). Jacaranda Health. Harvard T.H. Chan School of Public Health.
https://hsph.harvard.edu/research/maternal-health-task-force/21217-2/
- Academic work
Microsoft Research. (n.d.). Jacaranda PROMPTS: Optimizing maternal health messaging with reinforcement learning. Microsoft Research Projects.
https://www.microsoft.com/en-us/research/project/jacaranda-prompts/
- Academic work
Duke Global Health Innovation Center. (2021). Jacaranda Health case study. In Takeda Case Studies: Global Health Innovation. Duke University.
- Academic work
Ochieng' S, Hariharan N, Abuya T, Okondo C, Ndwiga C, Warren CE, Wickramanayake A, Rajasekharan S. Exploring the implementation of an SMS-based digital health tool on maternal and infant health in informal settlements. BMC Pregnancy Childbirth. 2024 Mar 27;24(1):222. doi: 10.1186/s12884-024-06373-7. PMID: 38539140; PMCID: PMC10967085.
https://pubmed.ncbi.nlm.nih.gov/38539140/
Background: The rapid urbanization of Kenya has led to an increase in the growth of informal settlements. There are challenges with access to maternal, newborn, and child health (MNCH) services and higher maternal mortality rates in settlements. The Kuboresha Afya Mitaani (KAM) study aimed to improve access to MNCH services. We evaluate one component of the KAM study, PROMPTS (Promoting Mothers through Pregnancy and Postpartum), an innovative digital health intervention aimed at improving MNCH outcomes. PROMPTS is a two-way AI-enabled SMS-based platform that sends messages to pregnant and postnatal mothers based on pregnancy stage, and connects mothers with a clinical help desk to respond and refer urgent cases in minutes. Methods: PROMPTS was rolled out in informal settlements in Mathare and Kawangware in Nairobi County. The study adopted a pre-post intervention design, comparing baseline and endline population outcomes (1,416 participants, Baseline = 678, Endline = 738). To further explore PROMPTS's effect, outcomes were compared between endline participants enrolled and not enrolled in PROMPTS (738 participants). Outcomes related to antenatal (ANC) and postnatal (PNC) service uptake and knowledge were assessed using univariate and multivariate linear and logistic regression. Results: Between baseline and enldine, mothers were 1.85 times more likely to report their babies and 1.88 times more likely to report themselves being checked by a provider post-delivery. There were improvements in moms and babies receiving care on time. 45% of the 738 endline participants were enrolled in the PROMPTS program, with 87% of these participants sending at least one message to the system. Enrolled mothers were 2.28 times more likely to report completing four or more ANC visits relative to unenrolled mothers. Similarly, enrolled mothers were 4.20 times more likely to report their babies and 1.52 times more likely to report themselves being checked by a provider post-delivery compared to unenrolled mothers. Conclusions: This research demonstrates that a digital health tool can be used to improve care-seeking and knowledge levels among pregnant and postnatal women in informal settlements. Additional research is needed to refine and target solutions amongst those that were less likely to enroll in PROMPTS and to further drive improved MNCH outcomes amongst this population. Keywords: Antenatal care; Digital health; Informal settlements; Kenya; Maternal health; Postnatal care.
- Academic work
Zhang, W., Guo, H., Ranganathan, P., Patel, J., Rajasekharan, S., Danayak, N., … Yadav, A. (2023). A Continual Pre-training Approach to Tele-Triaging Pregnant Women in Kenya. Proceedings of the AAAI Conference on Artificial Intelligence, 37(12), 14620–14627.
https://doi.org/10.1609/aaai.v37i12.26709
Access to high-quality maternal health care services is limited in Kenya, which resulted in ∼36,000 maternal and neonatal deaths in 2018. To tackle this challenge, Jacaranda Health (a non-profit organization working on maternal health in Kenya) developed PROMPTS, an SMS based tele-triage system for pregnant and puerperal women, which has more than 350,000 active users in Kenya. PROMPTS empowers pregnant women living far away from doctors and hospitals to send SMS messages to get quick answers (through human helpdesk agents) to questions about their medical symptoms and pregnancy status. Unfortunately, ∼1.1 million SMS messages are received by PROMPTS every month, which makes it challenging for helpdesk agents to ensure that these messages can be interpreted correctly and evaluated by their level of emergency to ensure timely responses and/or treatments for women in need. This paper reports on a collaborative effort with Jacaranda Health to develop a state-of-the-art natural language processing (NLP) framework, TRIM-AI (TRIage for Mothers using AI), which can automatically predict the emergency level (or severity of medical condition) of a pregnant mother based on the content of their SMS messages. TRIM-AI leverages recent advances in multi-lingual pre-training and continual pre-training to tackle code-mixed SMS messages (between English and Swahili), and achieves a weighted F1 score of 0.774 on real-world datasets. TRIM-AI has been successfully deployed in the field since June 2022, and is being used by Jacaranda Health to prioritize the provision of services and care to pregnant women with the most critical medical conditions. Our preliminary A/B tests in the field show that TRIM-AI is ∼17% more accurate at predicting high-risk medical conditions from SMS messages sent by pregnant Kenyan mothers, which reduces the helpdesk’s workload by ∼12%.
- Academic work
Vatsa R, Chang W, Akinyi S, Little S, Gakii C, Mungai J, et al. (2025) Impact evaluation of a digital health platform empowering Kenyan women across the pregnancy-postpartum care continuum: A cluster randomized controlled trial. PLoS Med 22(2): e1004527.
https://doi.org/10.1371/journal.pmed.1004527
Abstract Background Accelerating improvements in maternal and newborn health (MNH) care is a major public health priority in Kenya. While use of formal health care has increased, many pregnant and postpartum women do not receive the recommended number of maternal care visits. Even when they do, visits are often short with many providers not offering important elements of evaluation and counseling, leaving gaps in women’s knowledge and preparedness. Digital health tools have been proposed as a complement to care that is provided by maternity care facilities, but there is limited evidence of the impact of digital health tools at scale on women’s knowledge, preparedness, and the content of care they receive. We evaluated a digital health platform (PROMPTS (Promoting Mothers in Pregnancy and Postpartum Through SMS)) composed of informational messages, appointment reminders, and a two-way clinical helpdesk, which had enrolled over 750,000 women across Kenya at the time of our study, on 6 domains across the pregnancy-postpartum care continuum. Methods and findings We conducted an unmasked, 1:1 parallel arm cluster randomized controlled trial in 40 health facilities (clusters) across 8 counties in Kenya. A total of 6,139 pregnant individuals were consented at baseline and followed through pregnancy and postpartum. Individuals recruited from treatment facilities were invited to enroll in the PROMPTS platform, with roughly 85% (1,453/1,700) reporting take-up. Our outcomes were derived from phone surveys conducted with participants at 36 to 42 weeks of gestation and 7 to 8 weeks post-childbirth. Among eligible participants, 3,399/3,678 women completed antenatal follow-up and 5,509/6,128 women completed postpartum follow-up, with response rates of 92% and 90%, respectively. Outcomes were organized into 6 domains: knowledge, birth preparedness, routine care seeking, danger sign care seeking, newborn care, and postpartum care content. We generated standardized summary indices to account for multiple hypothesis testing but also analyzed individual index components. Intention-to-treat analyses were conducted for all outcomes at the individual level, with standard errors clustered by facility. Participants recruited from treatment facilities had a 0.08 standard deviation (SD) (95% CI [0.03, 0.12]; p = 0.002) higher knowledge index, a 0.08 SD (95% CI [0.02, 0.13]; p = 0.018) higher birth preparedness index, a 0.07 SD (95% CI [0.03, 0.11]; p = 0.003) higher routine care seeking index, a 0.09 SD (95% CI [0.07, 0.12]; p < 0.001) higher newborn care index, and a 0.06 SD (95% CI [0.01, 0.12]; p = 0.043) higher postpartum care content index than those recruited from control facilities. No significant effect on the danger sign care seeking index was found (95% CI [−0.01, 0.08]; p = 0.096). A limitation of our study was that outcomes were self-reported, and the study was not powered to detect effects on health outcomes. Conclusions Digital health tools indicate promise in addressing shortcomings in pregnant and postpartum women’s health care, amidst systems that do not reliably deliver a minimally adequate standard of care. Through providing women with critical information and empowering them to seek recommended care, such tools can improve individuals’ preparation for safe childbirth and receipt of more comprehensive postpartum care. Future work is needed to ascertain the impact of at-scale digital platforms like PROMPTS on health outcomes. Trial Registration ClinicalTrials.gov ID: NCT05110521; AEA RCT Registry ID: R-0008449