Artificial Intelligence and Mobile Health Technologies for Improved Healthcare Access: Design and Pilot Evaluation of an Integrated Digital Health Platform for a Nigerian Teaching Hospital
This study presents the design and pilot evaluation of a locally deployed, AI-assisted mobile health platform at the University of Abuja Teaching Hospital, demonstrating its technical feasibility, high usability, and substantial clinical concordance in improving healthcare access for Nigerian university students.
Original paper licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of a preprint that has not been peer-reviewed. It is not medical advice. Do not make health decisions based on this content. Read full disclaimer
In many parts of the world, getting medical care is not just a matter of having a hospital nearby; it is a complex puzzle of timing, cost, distance, and trust. For university students in low-income countries, these barriers are often invisible to the outside world but deeply felt in daily life. When a student falls ill, they may face long waits, a lack of available doctors, or the fear of being turned away. To solve this, researchers have begun looking at mobile health, which uses smartphones to deliver medical services, and artificial intelligence, which can act as a digital assistant to sort through symptoms and decide how urgent a problem is. The goal is not to replace doctors, but to create a bridge that helps people reach the right care faster and more easily, especially in places where resources are scarce and the gap between need and availability is wide.
In a recent study at the University of Abuja Teaching Hospital in Nigeria, researchers set out to build and test exactly such a bridge. They designed a mobile application specifically for students that combined a digital waiting room with an intelligent assistant. The app allowed students to schedule appointments, view their medical records, and talk to a doctor via video call. Its most innovative feature was an artificial intelligence tool that acted as a triage nurse. When a student opened the app to describe their symptoms, the AI asked a series of follow-up questions, much like a human doctor would, to understand the situation. Based on the conversation, the system categorized the student's condition as routine, urgent, or an emergency. If the situation was an emergency, the app immediately directed the student to seek in-person care. Crucially, the entire system ran on servers located physically within the hospital, ensuring that student data remained on local soil rather than traveling to distant cloud servers, a significant concern for data privacy in the region.
To see if this digital tool worked, the researchers invited fifty students to use the platform for thirty days. During this time, the students used the app as they normally would, seeking help whenever they felt unwell. The team then measured how the experience changed the students' ability to access healthcare. They looked at five specific areas: whether care was available when needed, how easy it was to reach, whether the hours and location fit the students' lives, if the cost was manageable, and whether the students felt comfortable with the system. They also asked the students to rate how easy the app was to use. Finally, to ensure the artificial intelligence was safe and accurate, two independent human doctors reviewed the same conversations the students had with the app, without knowing what the AI had decided, to see if their judgments matched.
The results offered a promising glimpse into the future of healthcare in resource-limited settings. The artificial intelligence proved to be remarkably reliable. When the system analyzed a student's symptoms, it reached the same conclusion as the human doctors in more than ninety percent of the cases. The agreement between the AI and the doctors was particularly strong when the conversation was longer and more detailed, suggesting that the system benefits from having enough time to understand the full story. In terms of speed, the AI responded to student questions in an average of thirty-four seconds, and its performance did not slow down even as more people used it. When the students were asked about the app's usability, the average score they gave was significantly higher than the standard benchmark for good software, indicating that the tool was intuitive and easy to navigate.
Regarding the broader impact on healthcare access, the study showed positive trends, though the small size of the group meant the results were not statistically definitive. The data suggested that the app made healthcare feel more accessible and available, with students reporting that they could get help more easily than before. However, the study did not find a significant difference in how the app worked for students living on campus versus those living off campus, a question that would need a much larger group of people to answer with certainty. The researchers were careful to note that while the system worked well in this pilot test, it was a feasibility study designed to prove the concept could work, not a final proof that it solves all problems. The study confirmed that a locally built, AI-assisted platform could function effectively in a Nigerian university setting, offering a viable path forward for improving how students access medical care. The next step, according to the authors, is to expand the study to include more participants and test the system across different languages to ensure it serves everyone equally.
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.