This is an open-access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Lee discussed the use of artificial intelligence (AI) and machine learning in family medicine [1], highlighting its role in recognizing early symptoms of disease and predicting health outcomes. Chronic disease management requires supportive tools due to the extended duration of illness, and tuberculosis (TB) is one such chronic disease that necessitates additional support. There are at least two proposed applications for AI in enhancing treatment success for patients with TB: predicting patient adherence and outcomes, and detecting comorbidities in patients with TB.
Predicting patient adherence and treatment outcomes
Data from the initiation of TB treatment can be analyzed to identify factors influencing patient adherence and treatment outcomes. Machine learning algorithms enable systems to learn from data by analyzing several parameters to provide accurate predictions. This approach has considerable potential when integrated with decision-support systems; however, expert interpretation remains essential to understand the results effectively.
Detecting comorbidities in patients with tuberculosis
Mental health conditions are crucial considerations, as TB patients often experience anxiety or depression due to social stigma, disease-related concerns, and treatment challenges. Depression significantly impacts treatment adherence, outcomes, and mortality in TB patients [2].
Depression also increases susceptibility to other health conditions, including TB. Determining the primary condition can be challenging, as TB is often linked to poverty, exacerbating the perception of TB as a ‘shameful’ condition. Furthermore, the contagious nature of TB strengthens the associated stigma.
Several studies have suggested that social stigma is a significant risk factor for depression. Negative attitudes toward TB can foster feelings of shame, disgust, and guilt among patients, leading to discrimination, social isolation, and ultimately, depression. Consequently, patients may become reluctant or non-adherent to treatment routines.
Patient-centered care is a primary focus in family medicine, where a biopsychosocial diagnostic approach is essential. Monitoring treatment progress of the patient from home, however, remains challenging. Technological advances have made remote, real-time diagnosis feasible.
Natural language processing (NLP) is an advanced AI tool enabling computers to accurately interpret, process, and generate text data. Text analysis through NLP assists in extracting valuable information from scientific literature, including identifying specific words and meanings [3]. NLP aims to help computers understand statements or words in human lanlanguage [4]. The processed language must be symbolically represented for NLP to comprehend the nuances of human language.
NLP technology has been developed to detect depression in vulnerable populations, such as the older people [5]. However, no specific NLP applications currently exist for TB patients, despite their risk for depression due to the prolonged treatment process, which may involve side effects and challenges, including discrimination within family, workplace, and community environments.
The proposed solution is to develop NLP tools to detect depression in TB patients and provide treatment recommendations. Early detection could enable timely intervention for depression, improving treatment adherence and outcomes. Nonetheless, a confirmed diagnosis still requires physician evaluation.
Article Information
Conflict of interest
No potential conflict of interest relevant to this article was reported.
Funding
None.
Data availability
Not applicable.
Author contribution
All the work for the preparation of this letter was done by all authors.
References
1. Lee J. Clinical applicability of machine learning in family medicine. Korean J Fam Med 2024;45:123-4.
2. Ruiz-Grosso P, Cachay R, de la Flor A, Schwalb A, Ugarte-Gil C. Association between tuberculosis and depression on negative outcomes of tuberculosis treatment: a systematic review and meta-analysis. PLoS One 2020;15:e0227472.
3. Tyagi N, Bhushan B. Demystifying the role of natural language processing (NLP) in smart city applications: background, motivation, recent advances, and future research directions. Wirel Pers Commun 2023;130:857-908.
4. Khurana D, Koli A, Khatter K, Singh S. Natural language processing: state of the art, current trends and challenges. Multimed Tools Appl 2023;82:3713-44.
5. DeSouza DD, Robin J, Gumus M, Yeung A. Natural language processing as an emerging tool to detect late-life depression. Front Psychiatry 2021;12:719125.
Artificial intelligence integration and human interaction in detecting depression in tuberculosis patients Mylene Icamina Maravilla Korean Journal of Family Medicine.2025; 46(3): 212. CrossRef
When AI Meets Pakikiramdam: Humanizing Digital Health in Philippine Family Practice Ivan Efreaim A. Gozum Journal of General and Family Medicine.2025; 26(6): 663. CrossRef
