Background: To reach WHO End tuberculosis (TB) targets, countries need a quality-assured laboratory network equipped with rapid diagnostics for tuberculosis diagnosis and drug susceptibility testing. Diagnostic network analysis aims to inform instrument placement, sample referral, staffing, geographical prioritization, integration of testing enabling targeted investments and programming to meet priority needs.
Methods: Supply chain modelling and optimization software was used to map Lesotho's TB diagnostic network using available data sources, including laboratory and programme reports and health and demographic surveys. Various scenarios were analysed, including current network configuration and inclusion of additional GeneXpert and/or point of care instruments. Different levels of estimated demand for testing services were modelled (current [30,000 tests/year], intermediate [41,000 tests/year] and total demand needed to find all TB cases [88,000 tests/year]).
Results: Lesotho's GeneXpert capacity is largely well-located but under-utilized (19/24 sites use under 50% capacity). The network has sufficient capacity to meet current and near-future demand and 70% of estimated total demand. Relocation of 13 existing instruments would deliver equivalent access to services, maintain turnaround time and reduce costs compared with planned procurement of 7 more instruments. Gaps exist in linking people with positive symptom screens to testing; closing this gap would require extra 11,000 tests per year and result in 1000 additional TB patients being treated. Closing the gap in linking diagnosed patients to treatment would result in a further 629 patients being treated. Scale up of capacity to meet total demand will be best achieved using a point-of-care platform in addition to the existing GeneXpert footprint.
Conclusions: Analysis of TB diagnostic networks highlighted key gaps and opportunities to optimize services. Network mapping and optimization should be considered an integral part of strategic planning. By building efficient and patient-centred diagnostic networks, countries will be better equipped to meet End TB targets.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7269260 | PMC |
| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0233620 | PLOS |
Publication Analysis
Top Keywords
Similar Publications
Prenatal diagnosis following preimplantation genetic testing (PGT): recommendations of the Italian Society of Human Genetics (SIGU).
J Assist Reprod Genet
January 2025
Medical Genetics & Genomics Unit, AULSS8 Berica, Vicenza, Italy.
This document aims to provide good practice recommendations in order to support maternal-foetal medicine specialists, clinical geneticists and clinical laboratory geneticists in the management of pregnancies obtained after the transfer of an embryo tested with preimplantation genetic testing (PGT). It was drafted by geneticists expert in preimplantation genetics and prenatal genetic diagnosis belonging to the "Working Group in Cytogenomics, Prenatal and Reproductive Genetics" of the "Italian Society of Human Genetics" (SIGU). In particular, the paper addresses the diagnostic algorithm to be applied in prenatal follow-up depending on the type of PGT performed, the results obtained and the related diagnostic value based on the most recent literature data and Italian and international recommendations.
View Article and Find Full Text PDFIn Vivo Confocal Microscopy for Automated Detection of Meibomian Gland Dysfunction: A Study Based on Deep Convolutional Neural Networks.
J Imaging Inform Med
January 2025
Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, National Clinical Research Center for Eye Disease, Shanghai, 200080, China.
The objectives of this study are to construct a deep convolutional neural network (DCNN) model to diagnose and classify meibomian gland dysfunction (MGD) based on the in vivo confocal microscope (IVCM) images and to evaluate the performance of the DCNN model and its auxiliary significance for clinical diagnosis and treatment. We extracted 6643 IVCM images from the three hospitals' IVCM database as the training set for the DCNN model and 1661 IVCM images from the other two hospitals' IVCM database as the test set to examine the performance of the model. Construction of the DCNN model was performed using DenseNet-169.
View Article and Find Full Text PDFSystematic Review of Hybrid Vision Transformer Architectures for Radiological Image Analysis.
J Imaging Inform Med
January 2025
School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ, USA.
Vision transformer (ViT)and convolutional neural networks (CNNs) each possess distinct strengths in medical imaging: ViT excels in capturing long-range dependencies through self-attention, while CNNs are adept at extracting local features via spatial convolution filters. While ViT may struggle with capturing detailed local spatial information, critical for tasks like anomaly detection in medical imaging, shallow CNNs often fail to effectively abstract global context. This study aims to explore and evaluate hybrid architectures that integrate ViT and CNN to leverage their complementary strengths for enhanced performance in medical vision tasks, such as segmentation, classification, reconstruction, and prediction.
View Article and Find Full Text PDFAssessing the Image Quality of Digitally Reconstructed Radiographs from Chest CT.
J Imaging Inform Med
January 2025
Leiden University Medical Center (LUMC), Leiden, the Netherlands.
Rising computed tomography (CT) workloads require more efficient image interpretation methods. Digitally reconstructed radiographs (DRRs), generated from CT data, may enhance workflow efficiency by enabling faster radiological assessments. Various techniques exist for generating DRRs.
View Article and Find Full Text PDFMulti-class Classification of Retinal Eye Diseases from Ophthalmoscopy Images Using Transfer Learning-Based Vision Transformers.
J Imaging Inform Med
January 2025
College of Engineering, Department of Computer Engineering, Koç University, Rumelifeneri Yolu, 34450, Sarıyer, Istanbul, Turkey.
This study explores a transfer learning approach with vision transformers (ViTs) and convolutional neural networks (CNNs) for classifying retinal diseases, specifically diabetic retinopathy, glaucoma, and cataracts, from ophthalmoscopy images. Using a balanced subset of 4217 images and ophthalmology-specific pretrained ViT backbones, this method demonstrates significant improvements in classification accuracy, offering potential for broader applications in medical imaging. Glaucoma, diabetic retinopathy, and cataracts are common eye diseases that can cause vision loss if not treated.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!