Background: Tuberculosis (TB) remains a significant global health challenge, as current diagnostic methods are often resource-intensive, time-consuming, and inaccessible in many high-burden communities, necessitating more efficient and accurate diagnostic methods to improve early detection and treatment outcomes. Objective: This study aimed to evaluate the performance of 6 convolutional neural network architectures—Visual Geometry Group-16 (VGG16), VGG19, Residual Network-50 (ResNet50), ResNet101, ResNet152, and Inception-ResNet-V2—in classifying chest x-ray (CXR) images as either normal or TB-positive. The impact of data augmentation on model performance, training times, and parameter counts was also assessed. Methods: The dataset of 4200 CXR images, comprising 700 labeled as TB-positive and 3500 as normal cases, was used to train and test the models. Evaluation metrics included accuracy, precision, recall, F₁-score, and area under the receiver operating characteristic curve. The computational efficiency of each model was analyzed by comparing training times and parameter counts. Results: VGG16 outperformed the other architectures, achieving an accuracy of 99.4%, precision of 97.9%, recall of 98.6%, F₁-score of 98.3%, and area under the receiver operating characteristic curve of 98.25%. This superior performance is significant because it demonstrates that a simpler model can deliver exceptional diagnostic accuracy while requiring fewer computational resources. Surprisingly, data augmentation did not improve performance, suggesting that the original dataset’s diversity was sufficient. Models with large numbers of parameters, such as ResNet152 and Inception-ResNet-V2, required longer training times without yielding proportionally better performance. Conclusions: Simpler models like VGG16 offer a favorable balance between diagnostic accuracy and computational efficiency for TB detection in CXR images. These findings highlight the need to tailor model selection to task-specific requirements, providing valuable insights for future research and clinical implementations in medical image classification.

One of the most challenging problems faced by ecologists and other biological re- searchers today is to analyze the massive amounts of data being collected by advanced monitoring systems like camera traps, wireless sensor networks, high-frequency radio track- ers, global positioning systems, and satellite tracking systems being used today. It has become expensive, laborious, and time-consuming to analyze this huge data using man- ual and traditional statistical techniques. Recent developments in the deep learning field are showing promising results towards automating the analysis of these extremely large datasets. The primary objective of this study was to test the capabilities of the state-of- the-art deep learning architectures to detect birds in the webcam captured images. A total of 10592 images were collected for this study from the Cornell Lab of Ornithology live stream feeds situated in six unique locations in United States, Ecuador, New Zealand, and Panama. To achieve the main objective of the study, we studied and evaluated two con- volutional neural network object detection meta-architectures, single-shot detector (SSD) and Faster R-CNN in combination with MobileNet-V2, ResNet50, ResNet101, ResNet152, and Inception ResNet-V2 feature extractors. Through transfer learning, all the models were initialized using weights pre-trained on the MS COCO (Microsoft Common Objects in Context) dataset provided by TensorFlow 2 object detection API. The Faster R-CNN model coupled with ResNet152 outperformed all other models with a mean average preci- sion of 92.3%. However, the SSD model with the MobileNet-V2 feature extraction network achieved the lowest inference time (110ms) and the smallest memory capacity (30.5MB) compared to its counterparts. The outstanding results achieved in this study confirm that deep learning-based algorithms are capable of detecting birds of different sizes in differ- ent environments and the best model could potentially help ecologists in monitoring and identifying birds from other species.

The Ebola virus disease (EVD) is an extremely contagious and fatal illness caused by the Ebola virus. Recently, Uganda witnessed an outbreak of EVD, which generated much attention on various social media platforms. To ensure effective communication and implementation of targeted health interventions, it is crucial for stakeholders to comprehend the sentiments expressed in the posts and discussions on these online platforms. In this study, we used deep learning techniques to analyse the sentiments expressed in Ebola-related tweets during the outbreak. We explored the application of three deep learning techniques to classify the sentiments in 8395 tweets as positive, neutral, or negative. The techniques examined included a 6-layer convolutional neural network (CNN), a 6-layer long short-term memory model (LSTM), and an 8-layer Bidirectional Encoder Representations from Transformers (BERT) model. The study found that the BERT model outperformed both the CNN and LSTM-based models across all the evaluation metrics, achieving a remarkable classification accuracy of 95%. These findings confirm the reported effectiveness of Transformer-based architectures in tasks related to natural language processing, such as sentiment analysis.

Achieving high retention of people living with HIV (PLHIV) in care remains a challenge in Uganda, despite substantial progress towards UNAIDS 95–95-95 targets. The purpose of this study was to apply and compare machine learning and deep learning models using de-identified longitudinal clinical data collected from HIV clinics in Uganda to predict clients at high risk of missing treatment appointments. Predictions were made at the visit level, and a missed appointment was defined as failure to attend a scheduled clinical visit within 28 days of the assigned return data in accordance with the PEPFAR definition of loss to follow-up. We compared the performance of traditional machine learning models (i.e. commonly used non-sequential models such as Decision Tree, Random Forest, AdaBoost, and XGBoost) and the Bidirectional Encoder Representations from Transformers (BERT) model, which is designed to model sequential and contextual information in longitudinal data. Feature importance using the Shapley additive exPlanations method was used to identify the most influential predictors. We also evaluated the impact of various sampling techniques, i.e. undersampling, oversampling, and synthetic minority oversampling, to address class imbalance and improve model performance. Model performance was evaluated using accuracy, precision, recall, F1-score, and the Area Under the Curve-Receiver Operating Characteristic (AUC-ROC) metrics. The study was based on a longitudinal dataset of 66,206 PLHIV who initiated HIV care during 2000–2023 in 86 health facilities. The data comprised 1,479,121 clinical visits, an average of 22 clinical visits per client; 158,266 (10.7%) missed appointments, and 49,588 (74.9%) of clients missed at least one appointment. Median (interquartile range [IQR]) age was 38.0 [29.0–47.0] years, and the majority (n = 43,132, 65.1%) were female. The BERT model achieved the highest performance in predicting missed appointments, with an AUC of 0.96 [CI: 0.94–0.97], precision of 89.0% [CI: 87.1%–90.9%], recall of 100% [CI: 100.0%–100.0%], and an F1-score of 94.0% [CI: 92.5%–95.5%] for the missed appointment class. In comparison, the best-performing traditional model, XGBoost with undersampling, achieved an AUC of 0.90 [CI: 0.87–0.92], precision of 33.2% [CI: 30.3%–36.1%], recall of 79.7% [CI: 77.2%–82.2%], and an F1-score of 46.8% [CI: 43.7%–49.9%] for the missed appointment class. Feature importance analysis showed that treatment adherence, visit frequency, treatment duration, and visits on the current regimen were the most influential predictors of appointment interruption. In this retrospective analysis, transformer-based sequential modeling showed promising performance for visit-level prediction of missed HIV appointments compared with the non-sequential models evaluated. These findings should be interpreted cautiously, as further temporal and external validation is required. If validated prospectively, such models may support EMR workflows by identifying clients at higher risk of missed visits, potentially enabling more targeted outreach and retention support in HIV care programs. The online version contains supplementary material available at 10.1186/s12911-026-03434-z.

Introduction: Cervical cancer is the fourth most prevalent cancer among women worldwide and is a significant contributor to cancer-related deaths, with an estimated 300,000 women losing their lives to the disease annually. Most of these fatalities occur in low and middle- income countries (LMICs), such as Uganda, where access to screening and treatment options is limited. Early detection of cervical cancer is crucial to improve the chances of survival for patients. Currently, cervical cancer screening is typically performed through Pap smears, which involve manual examination of cervical samples for abnormalities by medical experts. This process is costly, time-consuming, and prone to errors, leading to inaccurate diagnoses. Therefore, it is essential to find more effective and efficient alternative methods for cervical cancer screening to improve access in LMICs and alleviate the burden of cervical cancer. Objective: The purpose of this study is to develop an automated pre-cervical cancer screening algorithm to detect precancerous cervical lesions. Methodology: We developed a cancer screening algorithm using a 21-layer deep-learning convolution neural network trained on a dataset of 2300 images collected from local sources and some obtained from Kaggle. Results: The best-performing classifier had an AUC of the accuracy of 91.37%, a precision of 88.80%, a recall of 94.69%, an F1 score of 91.65%, and an AUC of 96.0%. Conclusion: The development and implementation of automated pre-cervical cancer screening algorithms have the potential to revolutionize cervical cancer detection and contribute significantly to reducing the burden of the disease, particularly in resource-limited settings.