Cutting-edge Technologies White Oak B Panel
Dec 10, 2019 09:00 AM - 10:15 AM(America/New_York)
20191210T0900 20191210T1015 America/New_York Artificial Intelligence and Machine Learning applications in global health White Oak B 2019 Global Digital Health Forum gdhf2019@dryfta.org
70 attendees saved this session
How design research complemented data science efforts towards building a predictive model to aid in targeted care in rural Kenya
Panel PresentationData Use Strategies, People and Processes 09:00 AM - 10:15 AM (America/New_York) 2019/12/10 14:00:00 UTC - 2019/12/10 15:15:00 UTC
The soaring levels of health inequity have prompted experts in various fields to come together and team up to think through innovative ways of providing targeted care. One such consideration is leveraging predictive analytics to determine which individuals are most at risk of negative health outcomes so that health workers can focus efforts on helping prevent those outcomes from occurring or to mitigate their impact when they do. In October 2018, Medic Mobile and Living Goods launched a pilot aimed to improve health worker efficiency and effectiveness by equipping a group of 67 health workers with tools driven by machine learning algorithms and statistical models. In this session, we will outline the design research approaches employed while building a predictive model from an analysis of historical population data, to the validation of data trends with health workers and beneficiaries, to prioritizing risks, to engaging users to provide feedback and input. After development and deployment of the model, a data-driven iteration approach was adopted to guide in refining and optimizing the model. The approach included quantitative analyses of those flagged as high-risk and data accumulated on interventions delivered during the pilot, as well as interviews conducted with beneficiaries and health workers to help us better understand the observed data trends and gather insights on their experiences with the model outputs. We shall highlight how health workers are delivering care to some vulnerable populations and how the built predictive models can be utilized to complement their work. We shall also discuss the important lessons learned and guide the group on how design research complements data efforts.
Presenters Isaac Holeman
Co-founder And Chief Research Officer , Medic Mobile
Co-Authors
MM
Maryanne Mureithi
Senior Service Designer, Medic Mobile
Alix Emden
Operations Associate, Medic Mobile
LINK, DETECT, PREDICT – using national centralised lab data to identify and predict risk of MTCT transmission routes in South Africa
Panel PresentationCutting-edge Technologies 09:00 AM - 10:15 AM (America/New_York) 2019/12/10 14:00:00 UTC - 2019/12/10 15:15:00 UTC
CONTEXT - transmission of HIV can occurred between mother and baby in broadly three opportunity phases: in utero, intra-partum or postnatal (likely breastfeeding) PROBLEM - despite the new guideline and broad adoption of both treatment and EID testing, south Africa has not been able to routinely establish the *route* of the few babies who are testing positive. SOLUTION - in this session, Palindrome will explain its collaboration with NICD and BU who have used a combination of National centralised DNA PCR lab data, Machine Learning for record linking as well as advanced analytics to show how transmission routes can be measured more accurately across the country.
Presenters
KS
Kieran Sharpey-Schafer
Managing Partner, Palindrome Data
Large-scale digitalized IMCI in Subsaharan Africa: on how AI can help decrease child mortality & morbidity, and predict epidemic outbreaks.
Panel PresentationCutting-edge Technologies 09:00 AM - 10:15 AM (America/New_York) 2019/12/10 14:00:00 UTC - 2019/12/10 15:15:00 UTC
The time is ripe for employing big data to detect epidemics and improve health care. Doing so can help battle child mortality in Burkina Faso where 1 in 10 children do not survive to the age of 5 today. Terre des hommes built an e-diagnostic tool for childcare, IeDA, which starting in 2014 now covers nearly half of all health centers in Burkina Faso. IeDA digitalizes the IMCI (Integrated Management of Childhood Illness) protocol of WHO (World Health Organization). The application has been developed on the CommCare platform, and runs on Android tablets. Thus far IeDA has been deployed in 730+ health care centers in Burkina Faso. An audit by the London School of Hygiene & Tropical Medicine, revealed that in these centers 92% of the frontline health workers now adhere to the digitalized IMCI protocol. Because of the great success of IeDA, the country has data on 4 million children’s consultations, each tagged with a timestamp and geographic location. In collaboration with the Cloudera Foundation, the faculty of Medicine of the University of Geneva, Tableau and the Burkina Faso Ministry of Health (MoH), we are now moving to the next stage of data driven decision making & analysis. We are in the process of setting up a data pipeline, that aims to: (1) predict epidemic outbreaks, (2) improve the quality of work of the frontline health workers, and (3) deploy smart dashboards serving better and more relevant information to the people making decisions. The project represents a unique opportunity to make a large impact given that the IeDA infrastructure is well in place and is expanding constantly: by 2023 the entire country will be covered. By complementing IeDA with state-of-the-art data science, funded by the Cloudera Foundation, we can make a leap in childcare efficacy.
Presenters Wessel Valkenburg
Data Scientist, Terre Des Hommes
Co-Authors
AA
Amara Amara
ICT4D Strategist, Terre Des Hommes
Data scientist
,
Terre des hommes
Managing Partner
,
Palindrome Data
Co-founder and Chief Research Officer
,
Medic Mobile
 Heidi Good Boncana
Senior Digital Health Advisor
,
Johns Hopkins Bloomberg School of Public Health
Ms. Rose Nzyoka
Country Representative,Palladium Kenya
,
Palladium Group
Prof. Hoon Sang  Lee
Visiting Professor
,
Yonsei University School of Global Health Security
Mr. Trevor Mwiu
Global Fund Programme Manager
,
World Vision UK
Upcoming Sessions
625 visits