Search

BackgroundLiterature reviews (LRs) identify, evaluate, and synthesize relevant papers to a particular research question to advance understanding and support decision-making. However, LRs, especially traditional systematic reviews, are slow, resource-intensive, and become outdated quickly. ObjectiveLiteRev is an advanced and enhanced version of an existing automation tool designed to assist researchers in conducting LRs through the implementation of cutting-edge technologies such as natural language processing and machine learning techniques. In this paper, we present a comprehensive explanation of LiteRev’s capabilities, its methodology, and an evaluation of its accuracy and efficiency to a manual LR, highlighting the benefits of using LiteRev. MethodsBased on the user’s query, LiteRev performs an automated search on a wide range of open-access databases and retrieves relevant metadata on the resulting papers, including abstracts or full texts when available. These abstracts (or full texts) are text processed and represented as a term frequency-inverse document frequency matrix. Using dimensionality reduction (pairwise controlled manifold approximation) and clustering (hierarchical density-based spatial clustering of applications with noise) techniques, the corpus is divided into different topics described by a list of the most important keywords. The user can then select one or several topics of interest, enter additional keywords to refine its search, or provide key papers to the research question. Based on these inputs, LiteRev performs a k-nearest neighbor (k-NN) search and suggests a list of potentially interesting papers. By tagging the relevant ones, the user triggers new k-NN searches until no additional paper is suggested for screening. To assess the performance of LiteRev, we ran it in parallel to a manual LR on the burden and care for acute and early HIV infection in sub-Saharan Africa. We assessed the performance of LiteRev using true and false predictive values, recall, and work saved over sampling. ResultsLiteRev extracted, processed, and transformed text into a term frequency-inverse document frequency matrix of 631 unique papers from PubMed. The topic modeling module identified 16 topics and highlighted 2 topics of interest to the research question. Based on 18 key papers, the k-NNs module suggested 193 papers for screening out of 613 papers in total (31.5% of the whole corpus) and correctly identified 64 relevant papers out of the 87 papers found by the manual abstract screening (recall rate of 73.6%). Compared to the manual full text screening, LiteRev identified 42 relevant papers out of the 48 papers found manually (recall rate of 87.5%). This represents a total work saved over sampling of 56%. ConclusionsWe presented the features and functionalities of LiteRev, an automation tool that uses natural language processing and machine learning methods to streamline and accelerate LRs and support researchers in getting quick and in-depth overviews on any topic of interest.

Abstract 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.

Many African countries have reported relatively low numbers of COVID-19 cases but the true scale of the epidemic is unclear. Here, the authors conduct a population-based survey in a province of Cameroon and estimate 29% seroprevlance, >300 fold higher than the nationwide attack rate implied by case counts.

Introduction High yield HIV testing strategies are critical to reach epidemic control in high prevalence and low-resource settings such as East and Southern Africa. In this study, we aimed to predict the HIV status of individuals living in Angola, Burundi, Ethiopia, Lesotho, Malawi, Mozambique, Namibia, Rwanda, Zambia and Zimbabwe with the highest precision and sensitivity for different policy targets and constraints based on a minimal set of socio-behavioural characteristics. Methods We analysed the most recent Demographic and Health Survey from these 10 countries to predict individual’s HIV status using four different algorithms (a penalized logistic regression, a generalized additive model, a support vector machine, and a gradient boosting trees). The algorithms were trained and validated on 80% of the data, and tested on the remaining 20%. We compared the predictions based on the F1 score, the harmonic mean of sensitivity and positive predictive value (PPV), and we assessed the generalization of our models by testing them against an independent left-out country. The best performing algorithm was trained on a minimal subset of variables which were identified as the most predictive, and used to 1) identify 95% of people living with HIV (PLHIV) while maximising precision and 2) identify groups of individuals by adjusting the probability threshold of being HIV positive (90% in our scenario) for achieving specific testing strategies. Results Overall 55,151 males and 69,626 females were included in the analysis. The gradient boosting trees algorithm performed best in predicting HIV status with a mean F1 score of 76.8% [95% confidence interval (CI) 76.0%-77.6%] for males (vs [CI 67.8%-70.6%] for SVM) and 78.8% [CI 78.2%-79.4%] for females (vs [CI 73.4%-75.8%] for SVM). Among the ten most predictive variables for each sex, nine were identical: longitude, latitude and, altitude of place of residence, current age, age of most recent partner, total lifetime number of sexual partners, years lived in current place of residence, condom use during last intercourse and, wealth index. Only age at first sex for male (ranked 10th) and Rohrer’s index for female (ranked 6th) were not similar for both sexes. Our large-scale scenario, which consisted in identifying 95% of all PLHIV, would have required testing 49.4% of males and 48.1% of females while achieving a precision of 15.4% for males and 22.7% for females. For the second scenario, only 4.6% of males and 6.0% of females would have had to be tested to find 55.7% of all males and 50.5% of all females living with HIV. Conclusions We trained a gradient boosting trees algorithm to find 95% of PLHIV with a precision twice higher than with general population testing by using only a limited number of socio-behavioural characteristics. We also successfully identified people at high risk of infection who may be offered pre-exposure prophylaxis or voluntary medical male circumcision. These findings can inform the implementation of new high-yield HIV tests and help develop very precise strategies based on low-resource settings constraints.

IntroductionHigh yield HIV testing strategies are critical to reach epidemic control in high prevalence and low-resource settings such as East and Southern Africa. In this study, we aimed to predict the HIV status of individuals living in Angola, Burundi, Ethiopia, Lesotho, Malawi, Mozambique, Namibia, Rwanda, Zambia and Zimbabwe with the highest precision and sensitivity for different policy targets and constraints based on a minimal set of socio-behavioural characteristics.MethodsWe analysed the most recent Demographic and Health Survey from these 10 countries to predict individual's HIV status using four different algorithms (a penalized logistic regression, a generalized additive model, a support vector machine, and a gradient boosting trees). The algorithms were trained and validated on 80% of the data, and tested on the remaining 20%. We compared the predictions based on the F1 score, the harmonic mean of sensitivity and positive predictive value (PPV), and we assessed the generalization of our models by testing them against an independent left-out country. The best performing algorithm was trained on a minimal subset of variables which were identified as the most predictive, and used to 1) identify 95% of people living with HIV (PLHIV) while maximising precision and 2) identify groups of individuals by adjusting the probability threshold of being HIV positive (90% in our scenario) for achieving specific testing strategies.ResultsOverall 55,151 males and 69,626 females were included in the analysis. The gradient boosting trees algorithm performed best in predicting HIV status with a mean F1 score of 76.8% [95% confidence interval (CI) 76.0%-77.6%] for males (vs [CI 67.8%-70.6%] for SVM) and 78.8% [CI 78.2%-79.4%] for females (vs [CI 73.4%-75.8%] for SVM). Among the ten most predictive variables for each sex, nine were identical: longitude, latitude and, altitude of place of residence, current age, age of most recent partner, total lifetime number of sexual partners, years lived in current place of residence, condom use during last intercourse and, wealth index. Only age at first sex for male (ranked 10th) and Rohrer's index for female (ranked 6th) were not similar for both sexes. Our large-scale scenario, which consisted in identifying 95% of all PLHIV, would have required testing 49.4% of males and 48.1% of females while achieving a precision of 15.4% for males and 22.7% for females. For the second scenario, only 4.6% of males and 6.0% of females would have had to be tested to find 55.7% of all males and 50.5% of all females living with HIV.ConclusionsWe trained a gradient boosting trees algorithm to find 95% of PLHIV with a precision twice higher than with general population testing by using only a limited number of socio-behavioural characteristics. We also successfully identified people at high risk of infection who may be offered pre-exposure prophylaxis or voluntary medical male circumcision. These findings can inform the implementation of new high-yield HIV tests and help develop very precise strategies based on low-resource settings constraints.

Background: We aimed to estimate the disease burden of Tuberculosis (TB) and return on investment of TB care in selected high-burden countries of the Western Pacific Region (WPR) until 2030. Methods: We projected the TB epidemic in Viet Nam and Lao People's Democratic Republic (PDR) 2020–2030 using a mathematical model under various scenarios: counterfactual (no TB care); baseline (TB care continues at current levels); and 12 different diagnosis and treatment interventions. We retrieved previous modeling results for China and the Philippines. We pooled the new and existing information on incidence and deaths in the four countries, covering >80% of the TB burden in WPR. We estimated the return on investment of TB care and interventions in Viet Nam and Lao PDR using a Solow model. Findings: In the baseline scenario, TB incidence in the four countries decreased from 97•0/100,000/year (2019) to 90•1/100,000/year (2030), and TB deaths from 83,300/year (2019) to 71,100/year (2030). Active case finding (ACF) strategies (screening people not seeking care for respiratory symptoms) were the most effective single interventions. Return on investment (2020–2030) for TB care in Viet Nam and Lao PDR ranged US$4-US$49/dollar spent; additional interventions brought up to US$2•7/dollar spent. Interpretation: In the modeled countries, TB incidence will only modestly decrease without additional interventions. Interventions that include ACF can reduce TB burden but achieving the End TB incidence and mortality targets will be difficult without new transformational tools (e.g. vaccine, new diagnostic tools, shorter treatment). However, TB care, even at its current level, can bring a multiple-fold return on investment. Funding: World Health Organization Western Pacific Regional Office; Swiss National Science Foundation Grant 163878.

The recent lifting of COVID-19 related restrictions in Switzerland causes uncertainty about the future of the epidemic. We developed a compartmental model for SARS-CoV-2 transmission in Switzerland and projected the course of the epidemic until the end of year 2020 under various scenarios. The model was age-structured with three categories: children (0-17), adults (18-64) and seniors (65- years). Lifting all restrictions according to the plans disclosed by the Swiss federal authorities by mid-May resulted in a rapid rebound in the epidemic, with the peak expected in July. Measures equivalent to at least 76% reduction in all contacts were able to eradicate the epidemic; a 54% reduction in contacts could keep the intensive care unit occupancy under the critical level and delay the next wave until October. In scenarios where strong contact reductions were only applied in selected age groups, the epidemic could not be suppressed, resulting in an increased risk of a rebound in July, and another stronger wave in September. Future interventions need to cover all age groups to keep the SARS-CoV-2 epidemic under control.