For doctors in developing countries, career fulfilment is more than a personal aspiration. It is a matter of national survival. With hospitals understaffed, resources stretched, and migration rates soaring, retaining skilled professionals has become one of the most pressing challenges for governments across Africa and Asia. Now, groundbreaking research by Dara Thomas titled: “Explainability of artificial neural network in predicting career fulfilment among medical doctors in developing nations: Applicability and implications” offers a powerful new tool: Artificial Intelligence. In a widely cited study published in Social Science & Medicine, Thomas and his collaborators applied Artificial Neural Networks (ANN) and Explainable AI (XAI) methods to predict what drives doctors’ satisfaction and retention in Nigeria and China.

The results are remarkable. The AI model achieved near-perfect predictive accuracy, but more importantly, it was able to explain why doctors felt fulfilled or dissatisfied. Using SHAP and LIME, Thomas demonstrated the relative weight of factors such as intrinsic motivators, workload, income, and institutional support. “Doctors don’t leave simply because of pay or workload,” Thomas said. “They leave because of how these factors combine with recognition, growth opportunities, and professional dignity. AI gives us the ability to map these relationships clearly and in real time.”

A Data-Driven Career Compass

The study was built on extensive datasets from medical professionals in Nigeria and China, two countries that, despite their differences, share the challenge of doctor retention. The ANN model analysed socio-economic, psychological, and professional variables, capturing the non-linear ways in which they interact. For Nigerian doctors, professional growth opportunities emerged as the strongest motivator, while extrinsic factors such as working conditions were key to preventing dissatisfaction. For Chinese doctors, recognition and autonomy played a more decisive role. These insights allow policymakers to go beyond generic retention strategies. Instead, they can tailor interventions to the unique cultural and institutional contexts of each country.

Policy and Practice Impact

Thomas is quick to emphasise the practical applications. Ministries of Health can use these models to design evidence-driven retention packages. Hospital administrators can identify at-risk staff before they consider migration. Career counsellors can provide personalised guidance based on data rather than anecdote. “This is not just an academic exercise,” Thomas noted. “It’s a policy tool, a management tool, and a human tool.” Already, health agencies in West Africa are exploring how to integrate such models into workforce planning. By identifying dissatisfaction triggers early, they hope to reduce turnover and stabilise fragile healthcare systems.

The Role of Explainable AI

What makes the study especially powerful is its commitment to transparency. Traditional AI models are often criticised as “black boxes,” producing predictions without explanations. By incorporating SHAP and LIME visualisations, Thomas ensured that doctors, managers, and policymakers could see and understand why certain factors mattered. This transparency builds trust and allows stakeholders to act with confidence. For example, if the model highlights recognition as a top motivator, hospital leadership can design targeted recognition programmes, knowing they will have measurable impact.

Global Relevance

Though focused on Nigeria and China, the research carries lessons for developing nations worldwide. From India to Brazil, similar dynamics of migration and dissatisfaction exist, and AI could be used to address them. “Career fulfilment is universal, but its drivers are context-specific,” Thomas explained. “That’s why models like ours need to be adaptable, explainable, and sensitive to local realities.”

Humanising AI

Perhaps most striking is how Thomas frames AI not as a replacement for human judgement, but as a partner in addressing human challenges. By applying sophisticated algorithms to deeply personal questions of motivation, he demonstrates how technology can support, not supplant human dignity. “Doctors are not just data points,” he said. “They are professionals with hopes, frustrations, and aspirations. AI helps us respect that complexity while finding solutions that work.”