Screening of Long Non-coding RNAs Biomarkers for the Diagnosis of Tuberculosis and Preliminary Construction of a Clinical Diagnosis Model

Recent progress in tuberculosis diagnosis: insights into blood-based biomarkers and emerging technologies

Tuberculosis (TB) remains a global health challenge, with timely and accurate diagnosis being critical for effective disease management and control. Recent advancements in the field of TB diagnostics have focused on the identification and utilization of blood-based biomarkers, offering a non-invasive, rapid, and scalable approach to disease detection. This review provides a comprehensive overview of the latest progress in blood-based biomarkers for TB, highlighting their potential to revolutionize diagnostic strategies. Furthermore, we explore emerging technologies such as NGS, PET-CT, Xpert and line probe assays, which have enhanced the sensitivity, specificity, and accessibility of biomarker-based diagnostics. The integration of artificial intelligence (AI) and machine learning (ML) in biomarker analysis is also examined, showcasing its potential to improve diagnostic accuracy and predictive capabilities. This review underscores the need for multidisciplinary collaboration and continued innovation to translate these promising technologies into practical, point-of-care solutions. By addressing these challenges, blood-based biomarkers and emerging technologies hold the potential to significantly improve TB diagnosis, ultimately contributing to global efforts to eradicate this devastating disease.

Diagnostic Performance of Artificial Intelligence-Based Methods for Tuberculosis Detection: Systematic Review

BACKGROUND

Tuberculosis (TB) remains a significant health concern, contributing to the highest mortality among infectious diseases worldwide. However, none of the various TB diagnostic tools introduced is deemed sufficient on its own for the diagnostic pathway, so various artificial intelligence (AI)-based methods have been developed to address this issue.

OBJECTIVE

We aimed to provide a comprehensive evaluation of AI-based algorithms for TB detection across various data modalities.

METHODS

Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) 2020 guidelines, we conducted a systematic review to synthesize current knowledge on this topic. Our search across 3 major databases (Scopus, PubMed, Association for Computing Machinery [ACM] Digital Library) yielded 1146 records, of which we included 152 (13.3%) studies in our analysis. QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies version 2) was performed for the risk-of-bias assessment of all included studies.

RESULTS

Radiographic biomarkers (n=129, 84.9%) and deep learning (DL; n=122, 80.3%) approaches were predominantly used, with convolutional neural networks (CNNs) using Visual Geometry Group (VGG)-16 (n=37, 24.3%), ResNet-50 (n=33, 21.7%), and DenseNet-121 (n=19, 12.5%) architectures being the most common DL approach. The majority of studies focused on model development (n=143, 94.1%) and used a single modality approach (n=141, 92.8%). AI methods demonstrated good performance in all studies: mean accuracy=91.93% (SD 8.10%, 95% CI 90.52%-93.33%; median 93.59%, IQR 88.33%-98.32%), mean area under the curve (AUC)=93.48% (SD 7.51%, 95% CI 91.90%-95.06%; median 95.28%, IQR 91%-99%), mean sensitivity=92.77% (SD 7.48%, 95% CI 91.38%-94.15%; median 94.05% IQR 89%-98.87%), and mean specificity=92.39% (SD 9.4%, 95% CI 90.30%-94.49%; median 95.38%, IQR 89.42%-99.19%). AI performance across different biomarker types showed mean accuracies of 92.45% (SD 7.83%), 89.03% (SD 8.49%), and 84.21% (SD 0%); mean AUCs of 94.47% (SD 7.32%), 88.45% (SD 8.33%), and 88.61% (SD 5.9%); mean sensitivities of 93.8% (SD 6.27%), 88.41% (SD 10.24%), and 93% (SD 0%); and mean specificities of 94.2% (SD 6.63%), 85.89% (SD 14.66%), and 95% (SD 0%) for radiographic, molecular/biochemical, and physiological types, respectively. AI performance across various reference standards showed mean accuracies of 91.44% (SD 7.3%), 93.16% (SD 6.44%), and 88.98% (SD 9.77%); mean AUCs of 90.95% (SD 7.58%), 94.89% (SD 5.18%), and 92.61% (SD 6.01%); mean sensitivities of 91.76% (SD 7.02%), 93.73% (SD 6.67%), and 91.34% (SD 7.71%); and mean specificities of 86.56% (SD 12.8%), 93.69% (SD 8.45%), and 92.7% (SD 6.54%) for bacteriological, human reader, and combined reference standards, respectively. The transfer learning (TL) approach showed increasing popularity (n=89, 58.6%). Notably, only 1 (0.7%) study conducted domain-shift analysis for TB detection.

CONCLUSIONS

Findings from this review underscore the considerable promise of AI-based methods in the realm of TB detection. Future research endeavors should prioritize conducting domain-shift analyses to better simulate real-world scenarios in TB detection.

TRIAL REGISTRATION

PROSPERO CRD42023453611; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023453611.

Integrating pathogen- and host-derived blood biomarkers for enhanced tuberculosis diagnosis: a comprehensive review

This review explores the evolving landscape of blood biomarkers in the diagnosis of tuberculosis (TB), focusing on biomarkers derived both from the pathogen and the host. These biomarkers provide critical insights that can improve diagnostic accuracy and timeliness, essential for effective TB management. The document highlights recent advancements in molecular techniques that have enhanced the detection and characterization of specific biomarkers. It also discusses the integration of these biomarkers into clinical practice, emphasizing their potential to revolutionize TB diagnostics by enabling more precise detection and monitoring of the disease progression. Challenges such as variability in biomarker expression and the need for standardized validation processes are addressed to ensure reliability across different populations and settings. The review calls for further research to refine these biomarkers and fully harness their potential in the fight against TB, suggesting a multidisciplinary approach to overcome existing barriers and optimize diagnostic strategies. This comprehensive analysis underscores the significance of blood biomarkers as invaluable tools in the global effort to control and eliminate TB.

Identification of a circulating long non-coding RNA signature panel in plasma as a novel biomarker for the detection of acute/early-stage HIV-1 infection

BACKGROUND

Individuals with acute / early HIV-1 infection are often unaware that they are infected with HIV-1 and may be involved in high-risk behavior leading to transmission of HIV-1. Identifying individuals with acute / early HIV-1 infection is critical to prevent further HIV-1 transmission, as diagnosis can lead to several effective HIV-1 prevention strategies. Identification of disease-stage specific non-viral host biomarkers would be useful as surrogate markers to accurately identify new HIV-1 infections. The goal of this study was to identify a panel of host derived plasma long non-coding RNAs (lncRNAs) that could serve as prognostic and predictive biomarkers to detect early/acute HIV-1 infection.

METHODS

A total of 84 lncRNAs were analyzed in sixteen plasma samples from HIV-1 infected individuals and four healthy controls using the lncRNA PCR-array. Twenty-one lncRNAs were selected and validated in 80 plasma samples from HIV-1 infected individuals [HIV-1 infected patients in the eclipse stage (n = 20), acute stage (n = 20), post-seroconversion p31 negative stage (n = 20), and post-seroconversion p31 positive stage (n = 20) of infection] and 20 healthy controls. The validation study results were used to develop a plasma lncRNA panel that was evaluated in the panel test phase to detect early/acute HIV-1 infection in 52 independent samples.

RESULTS

We identified a lncRNA panel (Pmodel-I) containing eight lncRNAs (DISC2, H19, IPW, KRASP1, NEAT1, PRINS, WT1-AS and ZFAS1) that could distinguish HIV-1 infection from healthy controls with high AUC 0·990 (95% CI 0.972-1.000), sensitivity (98.75%), and specificity (95%). We also found that Pmodel-II and Pmodel-III demonstrates 100% sensitivity and specificity (AUC 1·00; 95%CI:1·00-1·00) and could distinguish eclipse stage and acute stage of HIV-1 infection from healthy controls respectively. Antiretroviral treatment (ART) cumulatively restored the levels of lncRNAs to healthy controls levels.

CONCLUSION

lncRNA expression changes significantly in response to HIV-1 infection. Our findings also highlight the potential of using circulating lncRNAs to detect both the eclipse and acute stages of HIV-1 infection, which may help to shorten the window period and facilitate early detection and treatment initiation. Initiating ART treatment at this stage would significantly reduce HIV-1 transmission. The differentially expressed lncRNAs identified in this study could serve as potential prognostic and diagnostic biomarkers of HIV-1 infection, as well as new therapeutic targets.

Advances of Long Non-Coding RNAs as Potential Biomarkers for Tuberculosis: New Hope for Diagnosis?

Tuberculosis (TB), one of the top ten causes of death globally induced by the infection of Mycobacterium tuberculosis (Mtb), remains a grave public health issue worldwide. With almost one-third of the world's population getting infected by Mtb, between 5% and 10% of these infected individuals are predicted to develop active TB disease, which would not only result in severe tissue damage and necrosis, but also pose serious threats to human life. However, the exact molecular mechanisms underlying the pathogenesis and immunology of TB remain unclear, which significantly restricts the effective control of TB epidemics. Despite significant advances in current detection technologies and treatments for TB, there are still no appropriate solutions that are suitable for simultaneous, early, rapid, and accurate screening of TB. Various cellular events can perturb the development and progression of TB, which are always associated with several specific molecular signaling events controlled by dysregulated gene expression patterns. Long non-coding RNAs (lncRNAs), a kind of non-coding RNA (ncRNA) with a transcript of more than 200 nucleotides in length in eukaryotic cells, have been found to regulate the expression of protein-coding genes that are involved in some critical signaling events, such as inflammatory, pathological, and immunological responses. Increasing evidence has claimed that lncRNAs might directly influence the susceptibility to TB, as well as the development and progression of TB. Therefore, lncRNAs have been widely expected to serve as promising molecular biomarkers and therapeutic targets for TB. In this review, we summarized the functions of lncRNAs and their regulatory roles in the development and progression of TB. More importantly, we widely discussed the potential of lncRNAs to act as TB biomarkers, which would offer new possibilities in novel diagnostic strategy exploration and benefit the control of the TB epidemic.

Immune regulation and emerging roles of noncoding RNAs in Mycobacterium tuberculosis infection

Tuberculosis, caused by Mycobacterium tuberculosis, engenders an onerous burden on public hygiene. Congenital and adaptive immunity in the human body act as robust defenses against the pathogens. However, in coevolution with humans, this microbe has gained multiple lines of mechanisms to circumvent the immune response to sustain its intracellular persistence and long-term survival inside a host. Moreover, emerging evidence has revealed that this stealthy bacterium can alter the expression of demic noncoding RNAs (ncRNAs), leading to dysregulated biological processes subsequently, which may be the rationale behind the pathogenesis of tuberculosis. Meanwhile, the differential accumulation in clinical samples endows them with the capacity to be indicators in the time of tuberculosis suffering. In this article, we reviewed the nearest insights into the impact of ncRNAs during Mycobacterium tuberculosis infection as realized via immune response modulation and their potential as biomarkers for the diagnosis, drug resistance identification, treatment evaluation, and adverse drug reaction prediction of tuberculosis, aiming to inspire novel and precise therapy development to combat this pathogen in the future.