AI Transforms Healthcare: From Epidemic Response to Clinical Decision Support

Since May, response teams in the Democratic Republic of Congo (DRC) have been combating the Bundibugyo strain of the Ebola virus. Each day, community health workers visit households to provide guidance, document recoveries and fatalities, and refer individuals with suspicious symptoms to medical facilities.

ADVERTISEMENT

ADVERTISEMENT

According to a report by AI company Anthropic, the knowledge these health workers gather—whose notebooks reflect the condition of entire communities—has been digitized. Who has fallen ill? Who did they contact, and where were they staying before realizing they were infected? To evaluate these reports, Anthropic’s Claude model was deployed alongside partners including CEPI, the WHO Regional Office for Africa, and the national biomedical research institute INRB.

AI Accelerates Epidemic Assessment

“A situation report is now produced within an hour instead of taking an entire working day,” explains Dr. Marie Roseline Darnycka Belizaire, Director for Emergency Preparedness and Response at the WHO Regional Office for Africa. Speaking at the World Health Summit, she noted that artificial intelligence can help assess the spread of epidemics more rapidly and target medical assistance more precisely.

During data analysis, potential outbreak hotspots were identified and preparations initiated, such as pre-positioning medical supplies at key hubs and high-risk areas. This capability can be decisive in an emergency: the earlier health authorities respond to a potential outbreak, the better they can prepare and organize care. AI is designed to process information from diverse sources more quickly and support decision-making by those in charge.

This positive example of AI in healthcare illustrates a level of deployment with relatively little risk. Experts, however, see far broader possibilities for the technology’s future use.

AI as Support for Overstretched Healthcare Staff

Global demand for healthcare is rising while many regions face shortages of staff, time, and equipment. For Dr. Thomas Zapata, Director of the WHO Academy in Lyon, this gap represents a key starting point for artificial intelligence.

“We have to think about a paradox we are currently facing. We have more health professionals worldwide than ever before, and we have unprecedented technologies at our disposal,” Zapata said during a panel discussion at the World Health Summit. “Yet there is still an enormous shortage of healthcare workers. Demand for health services keeps on rising.”

He views AI as a way to narrow that gap, emphasizing that it must not be seen as an end in itself but as a tool integrated into existing health systems.

“AI is an enabler, a means to an end. At the moment we are very fascinated by technology and AI, but I think we need to place it in the right context within the health system,” Zapata warns. He identifies two areas where artificial intelligence fits: transforming how care is organized, and adapting training and continuing education for health workers to new possibilities.

Ultimately, AI can help reduce workloads, streamline administrative tasks, improve clinical decision-making, and enhance diagnostic processes. For Zapata, it is particularly important that the technology frees up time for what cannot and should not be automated: caring for patients.

Above all, the Ebola crisis in the DRC has shown that trust in local health systems remains lacking.

Giving Doctors More Time for Patients

Automated processes can make a particular difference where healthcare staff work under intense time pressure. Dr. Cecilia Mbaca, Senior Technical Adviser for Health and Emergencies at the aid organization CARE, knows these challenges from more than 15 years on the front line.

For her, three questions are crucial: Can AI support clinical decision-making? Can it take over repetitive tasks? And does it help tailor care more closely to individual patient needs?

“If AI does this work very well, that leaves more time for the personal aspects of care, so that we can ask questions, listen, examine patients and refer them on to the next level of care,” explains Dr. Cecilliah Mbaka, Senior Technical Adviser for Health and Emergencies at CARE.

She herself spent more than 15 years working on the front line with limited support, scarce resources, and a heavy workload.

In epidemics especially, it is not just about medical data. Trust within the population also plays a critical role. People must be able to trust that they will be protected and properly cared for in a health facility. In affected communities, this trust can determine whether people seek medical help in time.

Epidemiologist Maximilian Gertler estimates that around 50 percent of deaths in DRC villages occur outside medical facilities. The local health system is under pressure and was unprepared for the Ebola outbreak. Thousands of protective suits are needed daily to shield nursing staff from contamination. Germany recently increased its aid by 21 million euros.

AI can therefore support the organization of care. On its own, however, it cannot ensure that people trust medical facilities. As AI experts themselves note, the path leading to a diagnosis often remains opaque.

The Transparency Problem: How Does AI Reach Its Diagnosis?

Modern AI systems can analyze large volumes of data and detect patterns humans might miss. Yet in many cases it remains unclear exactly how they reach their results.

Dr. Thomas Thesen, Professor of Medical Education and Informatics at the Geisel School of Medicine at Dartmouth University in the United States, describes the problem: “They are extremely good at recognizing patterns, but they are really bad at explaining to us what those patterns actually are.” Chatbots and large language models such as Claude or ChatGPT have what he calls an explanation problem—in this respect, artificial intelligence remains a black box.

This so-called black-box problem is particularly relevant in healthcare. When a system provides a diagnosis or treatment recommendation, medical professionals need to be able to judge whether it makes sense in the specific case. A result on its own is not always enough; the path leading to it must also be traceable.

“That is the problem of explainability. They cannot explain in human-understandable language how they arrive at these conditions.”

This issue concerns not only transparency but also responsibility: who is liable if an AI provides a wrong recommendation? That is why, for Dr. Mbaka, it is crucial that AI does not simply output results but genuinely supports decision-making.

Expert: AI Must Not Replace Learning in Training

Artificial intelligence can also assist in training medical professionals, for instance by making information more accessible or helping with repetitive tasks. But when it comes to learning itself, Thesen sees risks.

He points to a study comparing conventional search engines with an AI chatbot for information retrieval. Students who used the chatbot ended up with more superficial knowledge that was less firmly anchored.

“These so-called desirable difficulties are actually very important for the learning process. And if you outsource all the cognitive work of learning to a chatbot—which may be highly efficient—you do not actually learn anything.”

Anyone who needs to retain knowledge long-term should not, in his view, let an AI take over every mental step. Especially in medicine, it can be crucial to make the right decisions even when technological support is unavailable.

Thesen therefore recommends using AI primarily where it reduces workload. Where the aim is to understand and retain knowledge long-term, independent learning must continue to have its place.

Source link