“Before we could have four deaths [of children] in a week or 15 days, but now we record maybe one death,” says Blessings Juma, head of the pediatric ward at Mangochi District Hospital in Malawi. The health worker attributes this change to IMPALA, a monitoring system with artificial intelligence designed to detect early deterioration in hospitalized patients and thus reduce child mortality in low-resource clinics.
The project, whose name corresponds to the acronym Innovative Monitoring in Pediatrics in Low-resource Settings (IMPALA), combines bedside monitoring devices with an artificial intelligence system that can alert medical staff when it detects signs of deterioration. The goal is simple: help doctors and nurses intervene before an emergency occurs.
This is especially important in countries like Malawi. In 2024, the under-five mortality rate was 48.7 deaths per 1,000 live births. That same year, 32,177 children aged under five died, according to the latest estimates from the United Nations Inter-agency Group for Child Mortality Estimation.
As in other low-resource settings, limited funding, lack of facilities and medical supplies, and a severe shortage of health personnel — an estimated 0.1 doctors per 1,000 inhabitants in 2022, according to World Bank data — make reducing child deaths a major challenge. Spain, for example, had 4.3 doctors per 1,000 inhabitants in 2022, according to the same institution. The World Health Organization estimates a ratio of 2.3 skilled health professionals (doctors, nurses, and midwives) per 1,000 inhabitants to achieve adequate coverage.
the device can predict illnesses up to three hours before they occur, or alert nursing staff hours before a child’s condition worsens
William Nkhono, project IMPALA
In this context, IMPALA’s backers believe the technology can help offset some of those shortcomings. “We started with monitoring systems, but then I thought of adding more value by incorporating artificial intelligence. With the help of this technology, the device can predict illnesses up to three hours before they occur, or alert nursing staff hours before a child’s condition worsens,” Dr. William Nkhono, a Malawian innovator behind the AI patient-monitoring system, tells EL PAÍS by videoconference.
The device allows medical staff to monitor multiple patients in real time, quickly identify those at highest risk, and detect complications early. It has portable batteries to prevent disconnection during power cuts and is very simple to use. Through an intuitive tablet app, the system analyzes vital signs, prioritizes the most urgent cases with alerts, and facilitates clinical decision-making.
“Many of the problems that arise in hospitals are due to late detection [of illnesses] or not attending to children in time. Thanks to the AI monitors installed at the beds in pediatric wards, the system issues a red signal to alert nurses and prioritize care for the most at-risk children,” Nkhono says.
“For example, if oxygen saturation is low, the device sounds an alarm,” says Chifundo Katundu, pediatric clinical assistant at Mangochi District Hospital. The system also makes it easier to record the vital signs of all patients in the pediatric ward, something that was not possible before due to scarce resources, Katundu adds.
Behind the project is a consortium made up of the Amsterdam Institute for Global Health and Development, Amsterdam University Medical Center, Goal 3, Imperial College London, Kamuzu University of Health Sciences, Malawi University of Business and Applied Sciences, the National eHealth Laboratory, and the Training Excellence Unit.
The system has also helped reduce the workload of medical staff. “Before introducing the monitor, discharge processes could take up to three hours; now they are completed in about 1.8 hours. In addition, we provide continuous training to nursing staff, since there is frequent rotation and every three or four months there are new hires,” Nkhono adds.
When you invest in this technology, the investment is recovered in lives saved: hospital stays are shortened, facilities need less medical equipment and social costs are reduced
Job Calis, IMPALA principal investigator
The IMPALA clinical center recorded between 40% and 51% fewer deaths in two Malawian hospitals during the 2023–2024 period, compared with an equivalent period in 2022–2023, before the monitoring system was introduced. To date, more than 100,000 patients have been admitted to hospital wards where the monitoring system has been implemented.
Moreover, 91% of the nurses and doctors surveyed — 116 people in total — said their workload and stress levels decreased.
Scalability of technology
The founder and chief executive of Goal 3, Niek Versteegde, one of the companies leading the innovation, explains that the technology created in Malawi is a reproducible model elsewhere. “But to scale it up and integrate it into all other hospitals, we need the government to step in,” he says. The system also operates in Tanzania and Rwanda and the technology costs between $105 and $208 per life saved. “The investment pays off because hospitals spend less on medicines trying to fix a problem that has already worsened. And for parents, hospital stays are shorter, so they also save a considerable amount of money,” Versteegde clarifies.
“When you invest in this technology, the investment is recovered in lives saved: hospital stays are shortened, facilities need less medical equipment and social costs are reduced,” adds IMPALA’s principal investigator, Dr. Job Calis, in a videoconference interview. The system is currently present in more than 20 hospitals in Malawi, with over 300 monitors installed, and generally in more than 50 hospitals across sub-Saharan Africa in countries such as Tanzania, Rwanda, Kenya, Zimbabwe and Gabon, with more than 800 monitors installed. “We are continuously expanding our installed base,” Versteegde concludes.
Sign up for our weekly newsletter to get more English-language news coverage from EL PAÍS USA Edition
