Status and future prospects for mobile phone-enabled diagnostics in Tanzania.

INTRODUCTION: Diagnosis is a key step towards the provision of medical intervention and saving lives. However, in low- and middle-income countries, diagnostic services are mainly centralized in large cities and are costly. Point of care (POC) diagnostic technologies have been developed to fill the diagnostic gap for remote areas. The linkage of POC testing onto smartphones has leveraged the ever-expanding coverage of mobile phones to enhance health services in low- and middle-income countries. Tanzania, like most other middle-income countries, is poised to adopt and deploy the use of mobile phone-enabled diagnostic devices. However, there is limited information on the situation on the ground with regard to readiness and capabilities of the veterinary and medical professionals to make use of this technology. METHODS: In this study we survey awareness, digital literacy and prevalent health condition to focus on in Tanzania to guide development and future implementation of mobile phoned-enable diagnostic tools by veterinary and medical professionals. Data was collected using semi-structured questionnaire with closed and open-ended questions, guided in-depth interviews and focus group discussion administered to the participants after informed consent was obtained. RESULTS: A total of 305 participants from six regions of Tanzania were recruited in the study. The distribution of participants across the six regions was as follows: Kilimanjaro (37), Arusha (31), Tabora (68), Dodoma (61), Mwanza (58), and Iringa (50). Our analysis reveals that only 48.2% (126/255) of participants demonstrated significant awareness of mobile phone-enabled diagnostics. This awareness varies significantly across age groups, professions and geographical locations. Interestingly, while 97.4% of participants own and can operate a smartphone, 62% have never utilized their smartphones for health services, including disease diagnosis. Regarding prevalent health condition to focus on when developing mobile phone -enabled diagnostics tools for Tanzania; there was disparity between medical and veterinary professionals. For medical professionals the top 4 priority diseases were Malaria, Urinary Tract Infections, HIV and Diabetes, while for veterinary professionals they were Brucellosis, Anthrax, Newcastle disease and Rabies. DISCUSSION: Despite the widespread ownership of smartphones among healthcare providers (both human and animal), only a small proportion have utilized these devices for healthcare practices, with none reported for diagnostic purposes. This limited utilization may be attributed to factors such as a lack of awareness, absence of policy guidelines, limited promotion, challenges related to mobile data connectivity, and adherence to cultural practices. CONCLUSION: The majority of medical and veterinary professionals in Tanzania possess the necessary digital literacy to utilize mobile phone-enabled diagnostics and demonstrate readiness to adopt digital technologies and innovations to enhance diagnosis. However, effective implementation will require targeted training and interventions to empower them to effectively apply such innovations for disease diagnosis and other healthcare applications.

Common beans imagery dataset for early detection of bean rust and bean anthracnose diseases.

Common bean plays a crucial role in the agricultural sector in Tanzania. To most smallholder farmers, the crop serves as a principal source of protein and an essential source of income. Despite its significance, common bean production is often affected by diseases, particularly bean rust and bean anthracnose, resulting in low yields and diminished economic returns. To address this challenge, a comprehensive dataset of common bean leaf images has been collected by using smartphone cameras to capture the visual characteristics of healthy and diseased leaves. The dataset contains more than 59,072 labeled images, offering a valuable resource for developing machine learning models and user-friendly tools capable of early detection and diagnosis of bean rust and bean anthracnose diseases. The aim of generating this dataset is to facilitate the development of machine learning tools that will empower agricultural extension officers, smallholder farmers, and other stakeholders in agriculture to promptly identify and diagnose affected crops, enabling timely and effective interventions before causing significant economic loss. By equipping farmers with the knowledge and tools to combat these diseases, we can safeguard bean production, enhance food security, and strengthen the economic well-being of smallholder farmers in Tanzania and other parts of Africa.

Corrigendum: Poultry diseases diagnostics models using deep learning.

[This corrects the article DOI: 10.3389/frai.2022.733345.].

Poultry diseases diagnostics models using deep learning.

Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.