Drivers of Geographic Patterns in Outpatient Antibiotic Prescribing in the United States.

In a retrospective, ecological analysis of US medical claims, visit rates explained more of the geographic variation in outpatient antibiotic prescribing rates than per-visit prescribing. Efforts to reduce antibiotic use may benefit from addressing the factors that drive higher rates of outpatient visits, in addition to continued focus on stewardship.

Machine-Learning-Based Forecasting of Dengue Fever in Brazilian Cities Using Epidemiologic and Meteorological Variables.

Dengue is a serious public health concern in Brazil and globally. In the absence of a universal vaccine or specific treatments, prevention relies on vector control and disease surveillance. Accurate and early forecasts can help reduce the spread of the disease. In this study, we developed a model for predicting monthly dengue cases in Brazilian cities 1 month ahead, using data from 2007-2019. We compared different machine learning algorithms and feature selection methods using epidemiologic and meteorological variables. We found that different models worked best in different cities, and a random forests model trained on monthly dengue cases performed best overall. It produced lower errors than a seasonal naive baseline model, gradient boosting regression, a feed-forward neural network, or support vector regression. For each city, we computed the mean absolute error between predictions and true monthly numbers of dengue cases on the test data set. The median error across all cities was 12.2 cases. This error was reduced to 11.9 when selecting the optimal combination of algorithm and input features for each city individually. Machine learning and especially decision tree ensemble models may contribute to dengue surveillance in Brazil, as they produce low out-of-sample prediction errors for a geographically diverse set of cities.

Forecasting new diseases in low-data settings using transfer learning.

Recent infectious disease outbreaks, such as the COVID-19 pandemic and the Zika epidemic in Brazil, have demonstrated both the importance and difficulty of accurately forecasting novel infectious diseases. When new diseases first emerge, we have little knowledge of the transmission process, the level and duration of immunity to reinfection, or other parameters required to build realistic epidemiological models. Time series forecasts and machine learning, while less reliant on assumptions about the disease, require large amounts of data that are also not available in early stages of an outbreak. In this study, we examine how knowledge of related diseases can help make predictions of new diseases in data-scarce environments using transfer learning. We implement both an empirical and a synthetic approach. Using data from Brazil, we compare how well different machine learning models transfer knowledge between two different dataset pairs: case counts of (i) dengue and Zika, and (ii) influenza and COVID-19. In the synthetic analysis, we generate data with an SIR model using different transmission and recovery rates, and then compare the effectiveness of different transfer learning methods. We find that transfer learning offers the potential to improve predictions, even beyond a model based on data from the target disease, though the appropriate source disease must be chosen carefully. While imperfect, these models offer an additional input for decision makers for pandemic response.

Country Case Studies in Economic Fitness: Mexico and Brazil.

We leverage a new complexity framework called Economic Fitness, which characterizes an economy's level of diversification and its capabilities to produce more complex products. It can be used to predict economic growth and competitiveness. This paper describes an application of Economic Fitness called the Country Opportunity Spotlight (COS) that assesses a country's current level of capabilities and demonstrates which industries have upgrade and diversification potential given those capabilities. It helps unlock the explanatory and predictive power of Economic Fitness for policymakers. COS results serve as a starting point for policymakers to shape and validate priorities, compare countries, asses the capabilities needed in specific industries and begin identifying constraints to growth. We showcase the use of this framework for Mexico and Brazil. These countries provide an interesting case study, as they have similar growth outlooks yet demonstrate different productive capabilities. Examining Mexico and Brazil side by side illustrates the value this analysis can have on deciphering structural change and decision making and at the same time reinforces the need for a nuanced consideration of each country's unique context.

Molecular surveillance to monitor the prevalence of tetracycline resistance in Neisseria gonorrhoeae.

Doxycycline post-exposure prophylaxis (Doxy-PEP) reduces bacterial sexually transmitted infections (STIs) but may select for tetracycline resistance in Neisseria gonorrhoeae and co-resistance to other antibiotics, including ceftriaxone.. The implementation of doxy-PEP should be accompanied by monitoring doxycycline resistance, but the optimal strategy to detect changes in the prevalence of resistance has not been established. We used a deterministic compartmental model of gonorrhea transmission to evaluate the performance of two strategies in providing early warning signals for rising resistance: (1) phenotypic testing of cultured isolates and (2) PCR for tetM in remnants from positive Nucleic Acid Amplification Tests (NAATs) used for gonorrhea diagnosis. For each strategy, we calculated the resistance proportion with 90% simulation intervals as well as the time under each sampling strategy to achieve 95% confidence that the resistance proportion exceeded a resistance threshold ranging from 11-30%. Given the substantially larger available sample size, PCR for tetM in remnant NAATs detected increased high-level tetracycline resistance with high confidence faster than phenotypic testing of cultured specimens. Our results suggest that population surveillance using molecular testing for tetM can complement culturebased surveillance of tetracycline resistance in N. gonorrhoeae and inform policy considerations for doxy-PEP.

Optimal environmental testing frequency for outbreak surveillance.

Public health surveillance for pathogens presents an optimization problem: we require enough sampling to identify intervention-triggering shifts in pathogen epidemiology, such as new introductions or sudden increases in prevalence, but not so much that costs due to surveillance itself outweigh those from pathogen-associated illness. To determine this optimal sampling frequency, we developed a general mathematical model for the introduction of a new pathogen that, once introduced, increases in prevalence exponentially. Given the relative cost of infection vs. sampling, we derived equations for the expected combined cost per unit time of disease burden and surveillance for a specified sampling frequency, and thus the sampling frequency for which the expected total cost per unit time is lowest.

Estimating changes in antibiotic consumption with the introduction of doxycycline post-exposure prophylaxis in the United States.

Doxycycline as post-exposure prophylaxis (doxy-PEP) reduces the risk of gonorrhea, chlamydia, and syphilis in studies of men who have sex with men (MSM) and transgender women (TGW) on HIV Pre-exposure Prophylaxis (PrEP) and people living with HIV (PLWH)). Doxy-PEP is an important tool to address the increasing burden of sexually transmitted infections (STIs), but there is concern that increased consumption of doxycycline may drive antimicrobial resistance. We estimated the expected increase in antibiotic use in the US under several doxy-PEP prescribing scenarios. We accounted for doses of antibiotics that may be averted due to the prevention of chlamydia, gonorrhea, and syphilis infections by doxy-PEP. Under a scenario of 75% adoption among the eligible population, with rates of consumption similar to the DoxyPEP trial population, monthly antibiotic consumption would increase by around 2.52 million doses, driven by doxy-PEP consumption of 2.58 million doses and less 62.1 thousand antibiotic doses that would otherwise have been used for chlamydia, gonorrhea, and syphilis treatment.

Diagnosis of autism spectrum disorder based on functional brain networks and machine learning.

Autism is a multifaceted neurodevelopmental condition whose accurate diagnosis may be challenging because the associated symptoms and severity vary considerably. The wrong diagnosis can affect families and the educational system, raising the risk of depression, eating disorders, and self-harm. Recently, many works have proposed new methods for the diagnosis of autism based on machine learning and brain data. However, these works focus on only one pairwise statistical metric, ignoring the brain network organization. In this paper, we propose a method for the automatic diagnosis of autism based on functional brain imaging data recorded from 500 subjects, where 242 present autism spectrum disorder considering the regions of interest throughout Bootstrap Analysis of Stable Cluster map. Our method can distinguish the control group from autism spectrum disorder patients with high accuracy. Indeed the best performance provides an AUC near 1.0, which is higher than that found in the literature. We verify that the left ventral posterior cingulate cortex region is less connected to an area in the cerebellum of patients with this neurodevelopment disorder, which agrees with previous studies. The functional brain networks of autism spectrum disorder patients show more segregation, less distribution of information across the network, and less connectivity compared to the control cases. Our workflow provides medical interpretability and can be used on other fMRI and EEG data, including small data sets.

Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments.

Ayahuasca is a blend of Amazonian plants that has been used for traditional medicine by the inhabitants of this region for hundreds of years. Furthermore, this plant has been demonstrated to be a viable therapy for a variety of neurological and mental diseases. EEG experiments have found specific brain regions that changed significantly due to ayahuasca. Here, we used an EEG dataset to investigate the ability to automatically detect changes in brain activity using machine learning and complex networks. Machine learning was applied at three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of the EEG time series, and (C) the complex network measures calculated from (B). Further, at the abstraction level of (C), we developed new measures of complex networks relating to community detection. As a result, the machine learning method was able to automatically detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are more important for the detection of ayahuasca. The most activated areas were the frontal and temporal lobe, which is consistent with the literature. F3 and PO4 were the most important brain connections, a significant new discovery for psychedelic literature. This connection may point to a cognitive process akin to face recognition in individuals during ayahuasca-mediated visual hallucinations. Furthermore, closeness centrality and assortativity were the most important complex network measures. These two measures are also associated with diseases such as Alzheimer's disease, indicating a possible therapeutic mechanism. Moreover, the new measures were crucial to the predictive model and suggested larger brain communities associated with the use of ayahuasca. This suggests that the dissemination of information in functional brain networks is slower when this drug is present. Overall, our methodology was able to automatically detect changes in brain activity during ayahuasca consumption and interpret how these psychedelics alter brain networks, as well as provide insights into their mechanisms of action.