Leveraging human resources for outbreak analysis: lessons from an international collaboration to support the sub-Saharan African COVID-19 response.

Emerging infectious diseases are a growing threat in sub-Saharan African countries, but the human and technical capacity to quickly respond to outbreaks remains limited. Here, we describe the experience and lessons learned from a joint project with the WHO Regional Office for Africa (WHO AFRO) to support the sub-Saharan African COVID-19 response.In June 2020, WHO AFRO contracted a number of consultants to reinforce the COVID-19 response in member states by providing actionable epidemiological analysis. Given the urgency of the situation and the magnitude of work required, we recruited a worldwide network of field experts, academics and students in the areas of public health, data science and social science to support the effort. Most analyses were performed on a merged line list of COVID-19 cases using a reverse engineering model (line listing built using data extracted from national situation reports shared by countries with the Regional Office for Africa as per the IHR (2005) obligations). The data analysis platform The Renku Project ( https://renkulab.io ) provided secure data storage and permitted collaborative coding.Over a period of 6 months, 63 contributors from 32 nations (including 17 African countries) participated in the project. A total of 45 in-depth country-specific epidemiological reports and data quality reports were prepared for 28 countries. Spatial transmission and mortality risk indices were developed for 23 countries. Text and video-based training modules were developed to integrate and mentor new members. The team also began to develop EpiGraph Hub, a web application that automates the generation of reports similar to those we created, and includes more advanced data analyses features (e.g. mathematical models, geospatial analyses) to deliver real-time, actionable results to decision-makers.Within a short period, we implemented a global collaborative approach to health data management and analyses to advance national responses to health emergencies and outbreaks. The interdisciplinary team, the hands-on training and mentoring, and the participation of local researchers were key to the success of this initiative.

Fine-grained knowledge about manipulable objects is well-predicted by contrastive language image pre-training.

Object recognition is an important ability that relies on distinguishing between similar objects (e.g., deciding which utensil(s) to use at different stages of meal preparation). Recent work describes the fine-grained organization of knowledge about manipulable objects via the study of the constituent dimensions that are most relevant to human behavior, for example, vision, manipulation, and function-based properties. A logical extension of this work concerns whether or not these dimensions are uniquely human, or can be approximated by deep learning. Here, we show that behavioral dimensions are generally well-predicted by CLIP-ViT - a multimodal network trained on a large and diverse set of image-text pairs. Moreover, this model outperforms comparison networks pre-trained on smaller, image-only datasets. These results demonstrate the impressive capacity of CLIP-ViT to approximate fine-grained object knowledge. We discuss the possible sources of this benefit relative to other models (e.g., multimodal vs. image-only pre-training, dataset size, architecture).

Developing a novel prediction model in opioid overdose using machine learning; a pilot analytical study.

Background and Aims: The opioid epidemic has extended to many countries. Data regarding the accuracy of conventional prediction models including the Simplified Acute Physiologic Score (SAPS) II and acute physiology and chronic health evaluation (APACHE) II are scarce in opioid overdose cases. We evaluate the efficacy of adding quantitative electroencephalogram (qEEG) data to clinical and paraclinical data in the prediction of opioid overdose mortality using machine learning. Methods: In a prospective study, we collected clinical/paraclinical, and qEEG data of 32 opioid-poisoned patients. After preprocessing and Fast Fourier Transform analysis, absolute power was computed. Also, SAPS II was calculated. Eventually, data analysis was performed using SAPS II as a benchmark at three levels to predict the patient's course in comparison with SAPS II. First, the qEEG data set was used alone, secondly, the combination of the clinical/paraclinical, SAPS II, qEEG datasets, and the SAPS II-based model was included in the pool of classifier models. Results: Seven out of 32 (22%) died. SAPS II (cut-off of 50.5) had a sensitivity/specificity/positive/negative predictive values of 85.7%, 84.0%, 60.0%, and 95.5% in predicting mortality, respectively. Adding majority voting on random forest with qEEG and clinical data, improved the model sensitivity, specificity, and positive and negative predictive values to 71.4%, 96%, 83.3%, and 92.3% (not significant). The model fusion level has 40% less prediction error. Conclusion: Considering the higher specificity and negative predictive value in our proposed model, it could predict survival much better than mortality. The model would constitute an indicator for better care of opioid poisoned patients in low resources settings, where intensive care unit beds are limited.