Harnessing Data Science to Promote Equity in Injury and Surgery for Africa

Project Summary The Data Science Center for the Study of Surgery, Injury, and Equity in Africa (D-SINE-Africa) is an NIH U54- funded research hub located at the University of Buea (Buea) in Cameroon through the current Data Science in Africa (DS-I Africa) initiative (U54TW012087). D-SINE Africa is a strategic partnership between the Buea,

the University of California (Los Angeles (UCLA) and Berkeley), the Cameroonian Ministry of Public Health, the African Institute for Mathematical Sciences in Cameroon, and the University of Cape Town (UCT) in South Africa. This coalition is built upon a long-standing collaboration between Buea and UCLA focused on decreasing

the burden of surgical diseases in Cameroon and other sub-Saharan African (SSA) countries. Injuries and other surgically treated diseases comprise a significant burden of disease in SSA, but opportunities for research and funding are lacking. Our work on injury and other surgical emergencies has identified deep inequities that are

particularly unmasked in acute care settings. The intersection between injury and equity is our priority area of study, as the inequities revealed by trauma are often symptomatic of larger, systemic, cross-cutting issues. Our mission is to leverage data science to decrease the impact of trauma, surgical disease, and disparities on the

population of Cameroon and SSA by promoting collaborative research, networking, and capacity building. We are accomplishing this through three Center Cores (Administrative, Capacity Building, and Data Management and Analysis Cores) and two Research Projects, one on using data science methods to develop Socioeconomic

Status Surveillance tools and another on using machine learning to enhance trauma patient follow-up after discharge from the hospital. At the heart of D-SINE Africa’s two Research Projects is the Cameroon Trauma Registry (CTR), a 10-hospital, ongoing, centralized trauma data bank that collects data on demographics,

context, clinical care, and outcomes for injured patients. To date, the CTR has collected data on over 5000 Cameroonian trauma patients and, at approximately 450 patients per month, is projected to house information on over additional 16,000 patients over the next 3-years. While these data are essential for the completion of

our two projects, they also have significant potential for other secondary analyses by scientists outside of D- SINE to tackle the critical, yet vitally understudied, area of injury in Africa, where trauma causes the most death and disability in the world. The goal of this supplement is to facilitate more secure, private, and streamlined

data-sharing by using ML techniques and differential privacy to generate private synthetic datasets that retain the statistical properties of the original CTR data, while preventing the disclosure of sensitive information; thus, safeguarding patient privacy while still allowing broad access to the data for research purposes. This will aid

our objective of reducing the burden of injury, achieving equity in access to surgery, and training the next generation of data scientists in SSA.