Summer 2026 FT Research Fellowship: "Risk for Hospitalization and Mortality of Young Infants Based on Machine Learning Analysis of Demographic and Clinical Data From South Asia and Sub-Saharan Africa"
The King Center on Global Development's Summer Undergraduate Full-Time Research Assistant Program offers opportunities for fieldwork and research experience to matriculated, Stanford, undergraduates interested in global poverty and development across all academic disciplines.
When Stanford University travel policies allow, selected students spend up to 12 weeks in a low- or middle-income country conducting full-time research for a King Center faculty affiliate. Each research assistant receives a stipend of approximately $8,500 that covers most associated costs including travel, lodging, and incidental expenses. Financial aid of up to $1,500 is also awarded to students who qualify.
Students are welcome to apply to multiple opportunities but must apply to each faculty research project separately. Students may only accept one project if they are offered multiple opportunities.
If you have problems submitting your application, please report issues through the SOLO platform with a screenshot that includes the URL and the full page. Please email kingcenter_programs@stanford.edu to also let us know of your issue(s).
RESEARCH PROJECT SUMMARY:
Community health workers (CHWs) play a critical role in low- and middle-income countries in identifying and managing sick young infants. The World Health Organization (WHO) has developed clinical algorithms - known as Integrated Management of Childhood Illness - to guide CHW clinical assessments and management. We are collaborating with WHO and have assembled and harmonized global data from multiple sites in South Asia and sub-Saharan Africa for analysis of risks for hospitalization and mortality associated with various clinical signs identified in young infants under 2 months of age. We have conducted initial, novel machine learning analysis and will complete machine learning and time varying Cox regression analyses of the data to predict risk for hospitalization and mortality. Results will be used to inform WHO global recommendations for the identification and management of sick young infants. This is the first study to apply machine learning analytical approaches to global data on risks for hospitalization and mortality of young infants. We are looking for a highly motivated student with experience in data analysis - ideally with machine learning - to pick up this exciting and impactful project.
Research mentor: Associate Dean for Maternal and Child Health, Professor Gary Darmstadt
Dates: A minimum of ten weeks during summer quarter 2026.
WHAT YOU WILL DO:
The research assistant will work closely together and in collaboration with the research team to:
- Data analysis, including Cox regression and machine learning.
- Regular presentations and discussion of progress, challenges and next steps.
- Participation in preparation of manuscript(s).
- Stanford undergraduate students in good academic standing, and planning to return to Stanford in autumn 2026, are eligible to apply (co-terms in graduate tuition status are ineligible)
- Not currently doing an honors thesis or receiving funding from other sources during the summer
- Not working other summer jobs
- All majors are welcome
- Strong research and writing skills
- Must have good interpersonal skills and an ability to adapt well to cross-cultural contexts
In addition, specific qualification requirements:
- Proficiency in R and preferably experience with regression and machine learning methods
- Experience in data management and analysis
Time Commitment:
- All research assistants are required to work full time, i.e., 35-40 hours per week for a minimum of 10 weeks during the summer quarter. This should be your only commitment during this time period.
To Apply:
Along with the application, applicants are asked to submit a resume or CV, and a Stanford transcript.
Please also answer:
- Briefly describe your experience with data management and analysis, including regression and machine learning.
For questions regarding this opportunity, please contact:
