Evidence brief: Tuberculosis in households with infectious cases in Kampala city: Harnessing health data science for new insights on an ancient disease with persistent, unresolved problems

Abstract

Tuberculosis (TB) is prevalent in Uganda and overlaps with a high rate of HIV/TB coinfection. While nearly all hospital-based TB cases in Kampala, the capital of Uganda, show clear TB symptoms, 30% or more of undiagnosed TB cases found through active screening are asymptomatic. Additionally, the host risk factors for TB in Kampala cannot be distinguished from environmental risk factors. These TB-specific challenges are just part of the complexity, especially in areas with high HIV/AIDS burden. Data science techniques, especially Artificial Intelligence (AI) and Machine Learning (ML) algorithms, could help untangle this complexity by identifying factors related to the host, pathogen, and environment, which are difficult to explain or predict with traditional/conventional methods. In this project, we will use health data science approaches (AI/ML) to identify factors driving TB transmission within households and reasons for anti-TB treatment failure. We will utilize the computational resources at Makerere University and available demographic, clinical, and laboratory data from TB patients and their contacts to develop AI and ML algorithms. These will aim to: (1) identify patients at baseline (month 0) unlikely to convert their sputum or culture results by months 2 and 5, thus at risk of failing TB treatment; (2) identify household contacts of TB cases who are at risk of developing TB disease, as well as contacts who may resist TB infection despite repeated exposure to M. tuberculosis. Achieving these objectives will provide evidence that data science methods are effective for early detection of potential TB cases and high-risk patients, thereby helping to reduce TB transmission in the community. The study protocol received approval from the School of Biomedical Sciences IRB, protocol number SBS-2023-495.

Introduction

Tuberculosis (TB) remains a major global public health concern, ranking as one of the deadliest infectious diseases alongside HIV/AIDS and malaria [1]. It’s an ancient disease, as old as humankind, that still results in over a million deaths each year around the world [2]. In 2024, about 8.3 million people were newly diagnosed and officially recorded with TB, slightly up from 8.2 million cases in 2023 [3].

In Uganda, a low-income country (LIC) with roughly 50 million residents, nearly 1 million new TB cases have been reported since 2010. The TB incidence has overtaken HIV in the country [4]; in 2024, 197 new TB cases per 100,000 people were reported, including 65 per 100,000 among those HIV-positive [3]. That year, Uganda was among the top 30 countries with the highest TB burden, overlapping with areas heavily impacted by TB/HIV coinfection [3].

Mycobacterium tuberculosis, the main causative agent of TB in humans, is among the most successful intracellular pathogens due to its high infectivity, widespread distribution [5], and capacity to adapt and evolve alongside humans [6]. People are usually exposed to aerosols from infected individuals, which can trigger immune responses that lead to various clinical outcomes [5,7]. On one end is “TB resistance,” where the innate immune system clears bacteria from the respiratory mucosa, preventing infection and/or disease. On the other end is “active TB,” featuring symptoms similar to pneumonia—such as a persistent cough with bacteria-laden sputum—along with fever, systemic inflammation, and lung damage visible on X-ray [5,8]. Active TB can first appear as primary active TB after infection or emerge later as post-primary, reactivated TB. Between resistance and active disease, there is TB infection with no symptoms (sometimes referred to as latent TB), and asymptomatic active TB (referred to as ‘subclinical TB’) [5,9,10]. These conditions exist on a spectrum, ranging from completely asymptomatic cases to those with subtle symptoms that might go unnoticed or be difficult to detect during screening [7,11]. Note that ‘subclinical TB’ can oscillate between ‘TB infection’, with no symptoms, and overt TB disease. Moreover, it has recently been confirmed that subclinical TB is transmissible despite the absence of symptoms (or failure to detect symptoms), highlighting the need for targeted control measures [12,13].