Since 2013, the French Animal Health Epidemic Intelligence System (in French: Veille Sanitaire Internationale, VSI) has been monitoring signals of the emergence of new and exotic animal infectious diseases worldwide. Once detected, the VSI team verifies the signals and issues early warning reports to French animal health authorities when potential threats to France are detected. To improve detection of signals from online news sources, we designed the Platform for Automated extraction of Disease Information from the web (PADI-web). PADI-web automatically collects, processes and extracts English-language epidemiological information from Google News. The core component of PADI-web is a combined information extraction (IE) method founded on rule-based systems and data mining techniques. The IE approach allows extraction of key information on diseases, locations, dates, hosts and the number of cases mentioned in the news. We evaluated the combined method for IE on a dataset of 352 disease-related news reports mentioning the diseases involved, locations, dates, hosts and the number of cases. The combined method for IE accurately identified (F-score) 95% of the diseases and hosts, respectively, 85% of the number of cases, 83% of dates and 80% of locations from the disease-related news. We assessed the sensitivity of PADI-web to detect primary outbreaks of four emerging animal infectious diseases notifiable to the World Organisation for Animal Health (OIE). From January to June 2016, PADI-web detected signals for 64% of all primary outbreaks of African swine fever, 53% of avian influenza, 25% of bluetongue and 19% of foot-and-mouth disease. PADI-web timely detected primary outbreaks of avian influenza and foot-and-mouth disease in Asia, i.e. they were detected 8 and 3 days before immediate notification to OIE, respectively.

Lyme disease is one of the most common infectious vector-borne diseases in the world. In the early stage, the disease manifests itself in most cases with erythema migrans (EM) skin lesions. Better diagnosis of these early forms would allow improving the prognosis by preventing the transition to a severe late form thanks to appropriate antibiotic therapy. Recent studies show that convolutional neural networks (CNNs) perform very well to identify skin lesions from the image 2 but, there is not much work for Lyme disease prediction from EM lesion images. The main objective of this study is to extensively analyze the effectiveness of CNNs for diagnosing Lyme disease from images and to find out the best CNN architecture for the purpose. There is no publicly available EM image dataset for Lyme disease prediction mainly because of privacy concerns. In this study, we utilized an EM dataset consisting of images collected from Clermont-Ferrand University Hospital Center (CF-CHU) of France and the internet. CF-CHU collected the images from several hospitals in France. This dataset was labeled by expert dermatologists and infectiologists from CF-CHU. First, we benchmarked this dataset for twenty-three well-known CNN architectures in terms of predictive performance metrics, computational complexity metrics, and statistical significance tests. Second, to improve the performance of the CNNs, we used transfer learning from ImageNet pre-trained models as well as pre-trained the CNNs with the skin lesion dataset "Human Against Machine with 10000 training images (HAM1000)". In that process, we searched for the best performing number of layers to unfreeze during transfer learning finetuning for each of the CNNs. Third, for model explainability, we utilized Gradient-weighted Class Activation Mapping to visualize the regions of input that are significant to the CNNs for making predictions. Fourth, we provided guidelines for model selection based on predictive performance and computational complexity. Our study confirmed the effectiveness and potential of even some lightweight CNNs for building Lyme disease pre-scanner mobile applications to assist people with an initial diagnosis in the absence of an expert dermatologist. We also made all the trained models publicly available at https://dappem.limos.fr/download.html, which can be used by others for transfer learning and building pre-scanners for Lyme disease.

No abstract