Screenshots of the Vitalk app. Photo credit: Vitalk

Using the Vitalk virtual chatbot had a significant positive effect on anxiety, depression, and burnout in health workers in Malawi compared with passive online resources, according to an 8-week randomized control trial (RCT) involving 1,584 people. The results were published in preview form as a journal article in medRxiv.

Vitalk is an AI-powered virtual health assistant available through a phone app created by a team in Brazil. Previously, Vitalk partnered with USAID and the Human Resources for Health Project (HRH2030) to pilot test the app among health workers there.

“A significant number of health workers could benefit from this kind of mental health support,” said lead author Dr. Eckhard Kleinau, Director, Research and Evaluation, URC. “In Malawi, 1 in 8 health workers reported anxiety and depression, 3 in 4 suffered from burnout, and 1 in 4 had low resilience. Help for these issues is not readily available in Malawi, but we found that Vitalk has the potential to fill this gap.”

Effectiveness of the Vitalk Chatbot in Improving the Mental Wellbeing of Health Workers in Malawi

URC was the lead principal investigator of this trial, collaborating closely with the University of Malawi. URC developed the research protocol and data collection instruments; and URC’s Institutional Review Board did the ethical review of the protocol, providing detailed technical feedback that was incorporated into the research design. URC then performed the analysis of all quantitative data and wrote the journal article with contributions from the study team.

This is the first RCT of a mental health app for healthcare workers during the COVID-19 pandemic in Southern Africa combining multiple mental wellbeing outcomes and measuring resilience and resilience-building activities.

The improvement in risk levels consistently was greater in the treatment than in the control group, with the effect on anxiety greater than on depression or burnout. Depression showed the least amount of change, with about two-thirds of participants staying at the same risk level pre- and post-intervention. Most significantly, the proportion of participants increasing resilience-building activities by at least one level was almost twice as high in the treatment group compared to the control group.