Predicting Infection


Infection is a widespread concern that has become increasingly urgent with the advent of antibiotic resistance.  Infections not only increase the cost of healthcare, but can also result in death.  Even in the world’s wealthiest countries, approximately 2-5% of hospital surgical patients develop infections, resulting in approximately 0.64% of hospital deaths.  Infection is a particular challenge in developing countries and low-resource areas, where access to washing water, good sanitation, and medical expertise is more scarce.  Detecting and predicting infection is critical in order to decide when to give or not give antibiotics.

Our group is collaborating with Harvard Medical School to develop algorithms and methods that can better predict infection in surgical wounds.  We are part of a study in Rwanda that is providing community health care workers with mobile phones and tablets that are used to capture images of wounds (as well as other measurements) and help detect infection.

Students: Olasubomi Olubeko, Harsh Sonthalia, Joanna Ashby

Collaborators: Bethany Hedt-Gauthier (Harvard), Robert Rivielo (Harvard), Fredrick Kateera (Rwanda, PIH), Theoneste Nkurunziza (Rwanda, PIH)