Search

Purpose Metamodels are simplified approximations of more complex models that can be used as surrogates for the original models. Challenges in using metamodels for policy analysis arise when there are multiple correlated outputs of interest. We develop a framework for metamodeling with policy simulations to accommodate multivariate outcomes. Methods: We combine 2 algorithm adaptation methods—multitarget stacking and regression chain with maximum correlation—with different base learners including linear regression (LR), elastic net (EE) with second-order terms, Gaussian process regression (GPR), random forests (RFs), and neural networks. We optimize integrated models using variable selection and hyperparameter tuning. We compare the accuracy, efficiency, and interpretability of different approaches. As an example application, we develop metamodels to emulate a microsimulation model of testing and treatment strategies for hepatitis C in correctional settings. Results Output variables from the simulation model were correlated (average ρ = 0.58). Without multioutput algorithm adaptation methods, in-sample fit (measured by R2) ranged from 0.881 for LR to 0.987 for GPR. The multioutput algorithm adaptation method increased R2 by an average 0.002 across base learners. Variable selection and hyperparameter tuning increased R2 by 0.009. Simpler models such as LR, EE, and RF required minimal training and prediction time. LR and EE had advantages in model interpretability, and we considered methods for improving the interpretability of other models. Conclusions In our example application, the choice of base learner had the largest impact on R2; multioutput algorithm adaptation and variable selection and hyperparameter tuning had a modest impact. Although advantages and disadvantages of specific learning algorithms may vary across different modeling applications, our framework for metamodeling in policy analyses with multivariate outcomes has broad applicability to decision analysis in health and medicine.

Outbreaks of an endemic infectious disease can occur when the disease is introduced into a highly susceptible subpopulation or when the disease enters a network of connected individuals. For example, significant HIV outbreaks among people who inject drugs have occurred in at least half a dozen US states in recent years. This motivates the current study: how can limited testing resources be allocated across geographic regions to rapidly detect outbreaks of an endemic infectious disease? We develop an adaptive sampling algorithm that uses profile likelihood to estimate the distribution of the number of positive tests that would occur for each location in a future time period if that location were sampled. Sampling is performed in the location with the highest estimated probability of triggering an outbreak alarm in the next time period. The alarm function is determined by a semiparametric likelihood ratio test. We compare the profile likelihood sampling (PLS) method numerically to uniform random sampling (URS) and Thompson sampling (TS). TS was worse than URS when the outbreak occurred in a location with lower initial prevalence than other locations. PLS had lower time to outbreak detection than TS in some but not all scenarios, but was always better than URS even when the outbreak occurred in a location with a lower initial prevalence than other locations. PLS provides an effective and reliable method for rapidly detecting endemic disease outbreaks that is robust to this uncertainty.

Publishing in respected scholarly journals is critical to academic success. However, if journal editorial boards fail to reflect the diversity of thought in a field, worthy work may be overlooked. This study assesses the level of diversity in the editorial boards of the 16 INFORMS journals. We examine gender, whether an individual is an underrepresented minority, and institutional affiliation, and perform a network analysis to identify coauthor relationships between editorial board members. We find that the editorial boards have low levels of diversity: women comprise just under 20% of the editorial board members; fewer than 1% of editorial board members are underrepresented minorities; and 10 institutions (less than 5% of the total) account for more than 25% of the editors. We find a high level of connectivity between editorial board members (as measured by coauthor relationship) for some of the INFORMS journals, suggesting the influence of an “in crowd” of like-minded individuals. INFORMS can and should work to end this state of affairs: we provide a set of actionable recommendations for broadening diversity and reducing connectivity on the INFORMS journal editorial boards. In this way, INFORMS journals can support a diversity of backgrounds and views, enabling the publication of a broader range of ideas and invigorating academic discourse in our profession.

Background Personalizing medical treatments based on patient-specific risks and preferences can improve patient health. However, models to support personalized treatment decisions are often complex and difficult to interpret, limiting their clinical application. Methods We present a new method, using machine learning to create meta-models, for simplifying complex models for personalizing medical treatment decisions. We consider simple interpretable models, interpretable ensemble models, and noninterpretable ensemble models. We use variable selection with a penalty for patient-specific risks and/or preferences that are difficult, risky, or costly to obtain. We interpret the meta-models to the extent permitted by their model architectures. We illustrate our method by applying it to simplify a previously developed model for personalized selection of antipsychotic drugs for patients with schizophrenia. Results The best simplified interpretable, interpretable ensemble, and noninterpretable ensemble models contained at most half the number of patient-specific risks and preferences compared with the original model. The simplified models achieved 60.5% (95% credible interval [crI]: 55.2–65.4), 60.8% (95% crI: 55.5–65.7), and 83.8% (95% crI: 80.8–86.6), respectively, of the net health benefit of the original model (quality-adjusted life-years gained). Important variables in all models were similar and made intuitive sense. Computation time for the meta-models was orders of magnitude less than for the original model. Limitations The simplified models share the limitations of the original model (e.g., potential biases). Conclusions Our meta-modeling method is disease- and model- agnostic and can be used to simplify complex models for personalization, allowing for variable selection in addition to improved model interpretability and computational performance. Simplified models may be more likely to be adopted in clinical settings and can help improve equity in patient outcomes.

Background Personalizing medical treatment decisions based on patient-specific risks and/or preferences can improve health outcomes. Decision makers frequently select treatments based on partial personalization (e.g., personalization based on risks but not preferences or vice versa) due to a lack of data about patient-specific risks and preferences. However, partially personalizing treatment decisions based on a subset of patient risks and/or preferences can result in worse population-level health outcomes than no personalization and can increase the variance of population-level health outcomes. Methods We develop a new method for partially personalizing treatment decisions that avoids these problems. Using a case study of antipsychotic treatment for schizophrenia, as well as 4 additional illustrative examples, we demonstrate the adverse effects and our method for avoiding them. Results For the schizophrenia treatment case study, using a previously proposed modeling approach for personalizing treatment decisions and using only a subset of patient preferences regarding treatment efficacy and side effects, mean population-level health outcomes decreased by 0.04 quality-adjusted life-years (QALYs; 95% credible interval [crI]: 0.02–0.06) per patient compared with no personalization. Using our new method and considering the same subset of patient preferences, mean population-level health outcomes increased by 0.01 QALYs (95% crI: 0.00–0.03) per patient as compared with no personalization, and the variance decreased. Limitations We assumed a linear and additive utility function. Conclusions Selecting personalized treatments for patients should be done in a way that does not decrease expected population-level health outcomes and does not increase their variance, thereby resulting in worse risk-adjusted, population-level health outcomes compared with treatment selection with no personalization. Our method can be used to ensure this, thereby helping patients realize the benefits of treatment personalization without the potential harms.

Background Analyses of the effectiveness of infectious disease control interventions often rely on dynamic transmission models to simulate intervention effects. We aim to understand how the choice of network or compartmental model can influence estimates of intervention effectiveness in the short and long term for an endemic disease with susceptible and infected states in which infection, once contracted, is lifelong. Methods We consider 4 disease models with different permutations of socially connected network versus unstructured contact (mass-action mixing) model and heterogeneous versus homogeneous disease risk. The models have susceptible and infected populations calibrated to the same long-term equilibrium disease prevalence. We consider a simple intervention with varying levels of coverage and efficacy that reduces transmission probabilities. We measure the rate of prevalence decline over the first 365 d after the intervention, long-term equilibrium prevalence, and long-term effective reproduction ratio at equilibrium. Results Prevalence declined up to 10% faster in homogeneous risk models than heterogeneous risk models. When the disease was not eradicated, the long-term equilibrium disease prevalence was higher in mass-action mixing models than in network models by 40% or more. This difference in long-term equilibrium prevalence between network versus mass-action mixing models was greater than that of heterogeneous versus homogeneous risk models (less than 30%); network models tended to have higher effective reproduction ratios than mass-action mixing models for given combinations of intervention coverage and efficacy. Conclusions For interventions with high efficacy and coverage, mass-action mixing models could provide a sufficient estimate of effectiveness, whereas for interventions with low efficacy and coverage, or interventions in which outcomes are measured over short time horizons, predictions from network and mass-action models diverge, highlighting the importance of sensitivity analyses on model structure. Highlights • We calibrate 4 models—socially connected network versus unstructured contact (mass-action mixing) model and heterogeneous versus homogeneous disease risk—to 10% preintervention disease prevalence. • We measure the short- and long-term intervention effectiveness of all models using the rate of prevalence decline, long-term equilibrium disease prevalence, and effective reproduction ratio. • Generally, in the short term, prevalence declined faster in the homogeneous risk models than in the heterogeneous risk models. • Generally, in the long term, equilibrium disease prevalence was higher in the mass-action mixing models than in the network models, and the effective reproduction ratio was higher in network models than in the mass-action mixing models.

Background For certain communicable disease outbreaks, mass prophylaxis of uninfected individuals can curtail new infections. When an outbreak emerges, decision makers could benefit from methods to quickly determine whether mass prophylaxis is cost-effective. We consider 2 approaches: a simple decision model and machine learning meta-models. The motivating example is plague in Madagascar. Methods We use a susceptible-exposed-infectious-removed (SEIR) epidemic model to derive a decision rule based on the fraction of the population infected, effective reproduction ratio, infection fatality rate, quality-adjusted life-year loss associated with death, prophylaxis effectiveness and cost, time horizon, and willingness-to-pay threshold. We also develop machine learning meta-models of a detailed model of plague in Madagascar using logistic regression, random forest, and neural network models. In numerical experiments, we compare results using the decision rule and the meta-models to results obtained using the simulation model. We vary the initial fraction of the population infected, the effective reproduction ratio, the intervention start date and duration, and the cost of prophylaxis. Limitations We assume homogeneous mixing and no negative side effects due to antibiotic prophylaxis. Results The simple decision rule matched the SEIR model outcome in 85.4% of scenarios. Using data for a 2017 plague outbreak in Madagascar, the decision rule correctly indicated that mass prophylaxis was not cost-effective. The meta-models were significantly more accurate, with an accuracy of 92.8% for logistic regression, 95.8% for the neural network model, and 96.9% for the random forest model. Conclusions A simple decision rule using minimal information about an outbreak can accurately evaluate the cost-effectiveness of mass prophylaxis for outbreak mitigation. Meta-models of a complex disease simulation can achieve higher accuracy but with greater computational and data requirements and less interpretability. Highlights We use a susceptible-exposed-infectious-removed model and net monetary benefit to derive a simple decision rule to evaluate the cost-effectiveness of mass prophylaxis. We use the example of plague in Madagascar to compare the performance of the analytically derived decision rule to that of machine learning meta-models trained on a stochastic dynamic transmission model. We assess the accuracy of each approach for different combinations of disease dynamics and intervention scenarios. The machine learning meta-models are more accurate predictors of mass prophylaxis cost-effectiveness. However, the simple decision rule is also accurate and may be a preferred substitute in low-resource settings.

A safe supply of blood for transfusion is a critical component of the healthcare system in all countries. Most health systems manage the risk of transfusion-transmissible infections (TTIs) through a portfolio of blood safety interventions. These portfolios must be updated periodically to reflect shifting epidemiological conditions, emerging infectious diseases, and new technologies. However, the number of available blood safety portfolios grows exponentially with the number of available interventions, making it impossible for policymakers to evaluate all feasible portfolios without the assistance of a computer model. We develop a novel optimization model for evaluating blood safety portfolios that enables systematic comparison of all feasible portfolios of deferral, testing, and modification interventions to identify the portfolio that is preferred from a cost-utility perspective. We present structural properties that reduce the state space and required computation time in certain cases, and we develop a linear approximation of the model. We apply the model to retrospectively evaluate U.S. blood safety policies for Zika and West Nile virus for the years 2017, 2018, and 2019, defining donor groups based on season and geography. We leverage structural properties to efficiently find an optimal solution. We find that the optimal portfolio varies geographically, seasonally, and over time. Additionally, we show that for this problem the approximated model yields the same optimal solution as the exact model. Our method enables systematic identification of the optimal blood safety portfolio in any setting and any time period, thereby supporting decision makers in efforts to ensure the safety of the blood supply.

To assess the effectiveness and cost-effectiveness of office-based buprenorphine treatment (OBBT) in the U.S.We performed a model-based analysis of buprenorphine treatment provided in a primary care setting for the U.S. population with OUD.Buprenorphine treatment provided in a primary care setting.Fatal and nonfatal overdoses and deaths over five years, discounted lifetime quality-adjusted life years (QALYs), costs.For a cohort of 100,000 untreated individuals who enter OBBT, approximately 9350 overdoses would be averted over five years; of these, approximately 900 would have been fatal. OBBT compared to no treatment would yield 1.07 incremental lifetime QALYs per person at an incremental cost of $17,000 per QALY gained when using a healthcare perspective. If OBBT is half as effective and twice as expensive as assumed in the base case, the incremental cost when using a healthcare perspective is $25,500 per QALY gained. Using a limited societal perspective that additionally includes patient costs and criminal justice costs, OBBT is cost-saving compared to no treatment even under pessimistic assumptions about efficacy and cost.Expansion of OBBT would be highly cost-effective compared to no treatment when considered from a healthcare perspective, and cost-saving when reduced criminal justice costs are included. Given the continuing opioid crisis in the U.S., expansion of this care option should be a high priority.

Low adherence to prescribed medications causes substantial health and economic burden. We analyzed primary data from electronic medical records of 250,000 random patients from Israel's Maccabi Healthcare services from 2007 to 2017 to predict whether a patient will purchase a prescribed antibiotic. We developed a decision model to evaluate whether an intervention to improve purchasing adherence is warranted for the patient, considering the cost of the intervention and the cost of non-adherence. The best performing prediction model achieved an average area under the receiver operating characteristic curve (AUC) of 0.684, with 82% accuracy in detecting individuals who had less than 50% chance of purchasing a prescribed drug. Using the decision model, an adherence intervention targeted to patients whose predicted purchasing probability is below a specified threshold can increase the number of prescriptions filled while generating significant savings compared to no intervention - on the order of 6.4% savings and 4.0% more prescriptions filled for our dataset. We conclude that analysis of large-scale patient data from electronic medical records can help predict the probability that a patient will purchase a prescribed antibiotic and can provide real-time predictions to physicians, who can then counsel the patient about medication importance. More broadly, in-depth analysis of patient-level data can help shape the next generation of personalized interventions.

High prevalence of depression among people living with HIV (PLHIV) impedes antiretroviral therapy (ART) adherence and viral suppression. We estimate the effectiveness and cost-effectiveness of strategies to treat depression among PLHIV in Sub-Saharan Africa (SSA). We developed a microsimulation model of HIV disease and care in Uganda which captured individuals' depression status and the relationship between depression and HIV behaviors. We consider a strategy of screening for depression and providing antidepressant therapy with fluoxetine at ART initiation or re-initiation (if a patient has dropped out). We estimate that over 10 years this strategy would reduce prevalence of depression among PLHIV by 16.0% [95% uncertainty bounds 15.8%, 16.1%] from a baseline prevalence of 28%, increase adherence to ART by 1.0% [1.0%, 1.0%], and decrease rates of loss to followup by 3.7% [3.4%, 4.1%]. This would decrease first-line ART failure rates by 2.5% [2.3%, 2.8%] and increase viral suppression rates by 1.0% [1.0%, 1.0%]. This strategy costs $15/QALY compared to the status quo, and was highly cost-effective over a broad range of sensitivity analyses. We conclude that screening for and treating depression among PLHIV in SSA with fluoxetine would be effective in improving HIV treatment outcomes and would be highly cost-effective.

The problem of optimally allocating a limited supply of vaccine to control a communicable disease has broad applications in public health and has received renewed attention during the COVID-19 pandemic. This allocation problem is highly complex and nonlinear. Decision makers need a practical, accurate, and interpretable method to guide vaccine allocation. In this paper we develop simple analytical conditions that can guide the allocation of vaccines over time. We consider four objectives: minimize new infections, minimize deaths, minimize life years lost, or minimize quality-adjusted life years lost due to death. We consider an SIR model with interacting population groups. We approximate the model using Taylor series expansions, and develop simple analytical conditions characterizing the optimal solution to the resulting problem for a single time period. We develop a solution approach in which we allocate vaccines using the analytical conditions in each time period based on the state of the epidemic at the start of the time period. We illustrate our method with an example of COVID-19 vaccination, calibrated to epidemic data from New York State. Using numerical simulations, we show that our method achieves near-optimal results over a wide range of vaccination scenarios. Our method provides a practical, intuitive, and accurate tool for decision makers as they allocate limited vaccines over time, and highlights the need for more interpretable models over complicated black box models to aid in decision making.

Background: The opioid epidemic causes significant morbidity and mortality in the United States, and has been exacerbated by COVID-19. Methods: We extend and update a previously developed model to assess the effectiveness of the following interventions, alone and combined, for controlling the U.S. opioid epidemic: reduced prescribing, drug rescheduling, prescription monitoring programs, tamper-resistant drug reformulation, excess opioid disposal, naloxone availability, needle exchange, pharmacotherapy, and psychosocial treatment. We measure life years, quality-adjusted life years (QALYs), and opioid-related deaths over five and ten years. Findings: Under the status quo, our model predicts that approximately 522,000 opioid-related deaths will occur from 2020 to 2024 (range 424,000 - 575,000), rising to 1,172,000 (range 956,000 - 1,308,000) by 2029. Expansion of naloxone availability had the largest effect: with 30% expansion, approximately 25% of opioid deaths would be averted. Pharmacotherapy, needle exchange, and psychosocial treatment are uniformly beneficial, reducing opioid-related deaths while leading to gains in life years and QALYs. Reduced prescribing for acute and transitioning pain (at the end of the first month of acute pain) would reduce lives lost over five and ten years. Reducing chronic pain prescribing, rescheduling drugs, and increasing excess opioid disposal programs would increase total deaths over five years as some opioid users escalate to heroin, but decrease deaths over ten years. Combined interventions would lead to greater increases in life years, QALYs, and deaths averted, although in many cases the results are subadditive. Interpretation: A combination of expanded health services for addicted individuals and reduced opioid prescribing would moderately lessen the severity of the opioid crisis over the next decade. Tragically, even with improved public policies, significant morbidity and mortality is inevitable. Funding: Grant R37-DA15612 from the National Institute on Drug Abuse and a grant from Stanford University School of Medicine to support the Stanford-Lancet Commission on the North American Opioid Crisis. Declaration of Interests: The authors have no conflict of interest to report.

BackgroundThe rapid rise in hospitalizations associated with the Delta-driven COVID-19 resurgence, and the imminent risk of hospital overcrowding, led the Israeli government to initialize a national third (booster) COVID-19 vaccination campaign in early August 2021, offering the BNT162b2 mRNA vaccine to individuals who received their second dose over five months ago. However, the safety of the third (booster) dose has not been fully established yet.ObjectiveEvaluate the short-term, self-reported and physiological reactions to the third BNT162b2 mRNA COVID-19 (booster) vaccine dose.DesignA prospective observational study, in which participants are equipped with a smartwatch and fill in a daily questionnaire via a dedicated mobile application for a period of 21 days, starting seven days before the vaccination.SettingAn Israel-wide third (booster) vaccination campaign.ParticipantsA group of 1,609 (18+ years of age) recipients of at least one dose of the BNT162b2 vaccine between December 20, 2020, and September 15, 2021, out of a larger cohort of 2,912 prospective study participants. 1,344 of the participants were recipients of the third vaccine dose.MeasurementsDaily self-reported questionnaires regarding local and systemic reactions, mood level, stress level, sport duration, and sleep quality. Heart rate, heart rate variability and blood oxygen saturation level were continuously measured by Garmin Vivosmart 4 smartwatches.ResultsThe extent of systemic reactions reported following the third (booster) dose administration is similar to that reported following the second dose (p-value=0.305) and considerably greater than that reported following the first dose (p-valueLimitationsParticipants may not adequately represent the vaccinated population in Israel and elsewhere.ConclusionOur work further supports the safety of a third COVID-19 BNT162b2 mRNA (booster) vaccine dose from both a subjective and an objective perspective, particularly in individuals 65+ years of age and those with underlying medical conditions.Primary funding sourceEuropean Research Council (ERC) project #949850

Plague (Yersinia pestis) remains endemic in certain parts of the world. We assessed the cost-effectiveness of plague control interventions recommended by the World Health Organization with particular consideration to intervention coverage and timing. We developed a dynamic model of the spread of plague between interacting populations of humans, rats, and fleas and performed a cost-effectiveness analysis calibrated to a 2017 Madagascar outbreak. We assessed three interventions alone and in combination: expanded access to antibiotic treatment with doxycycline, mass distribution of doxycycline prophylaxis, and mass distribution of malathion. We varied intervention timing and coverage levels. We calculated costs, quality-adjusted life years (QALYs), and incremental cost-effectiveness ratios from a healthcare perspective. The preferred intervention, using a cost-effectiveness threshold of $1350/QALY (GDP per capita in Madagascar), was expanded access to antibiotic treatment with doxycycline with 100% coverage starting immediately after the first reported case, gaining 543 QALYs at an incremental cost of $1023/QALY gained. Sensitivity analyses support expanded access to antibiotic treatment and leave open the possibility that mass distribution of doxycycline prophylaxis or mass distribution of malathion could be cost-effective. Our analysis highlights the potential for rapid expansion of access to doxycycline upon recognition of plague outbreaks to cost-effectively prevent future large-scale plague outbreaks and highlights the importance of intervention timing.

Background The World Health Organization and US Centers for Disease Control and Prevention recommend that both infected and susceptible people wear face masks to protect against COVID-19. Methods We develop a dynamic disease model to assess the effectiveness of face masks in reducing the spread of COVID-19, during an initial outbreak and a later resurgence, as a function of mask effectiveness, coverage, intervention timing, and time horizon. We instantiate the model for the COVID-19 outbreak in New York, with sensitivity analyses on key natural history parameters. Results During the initial epidemic outbreak, with no social distancing, only 100% coverage of masks with high effectiveness can reduce the effective reproductive number [Formula: see text] below 1. During a resurgence, with lowered transmission rates due to social distancing measures, masks with medium effectiveness at 80% coverage can reduce [Formula: see text] below 1 but cannot do so if individuals relax social distancing efforts. Full mask coverage could significantly improve outcomes during a resurgence: with social distancing, masks with at least medium effectiveness could reduce [Formula: see text] below 1 and avert almost all infections, even with intervention fatigue. For coverage levels below 100%, prioritizing masks that reduce the risk of an infected individual from spreading the infection rather than the risk of a susceptible individual from getting infected yields the greatest benefit. Limitations Data regarding COVID-19 transmission are uncertain, and empirical evidence on mask effectiveness is limited. Our analyses assume homogeneous mixing, providing an upper bound on mask effectiveness. Conclusions Even moderately effective face masks can play a role in reducing the spread of COVID-19, particularly with full coverage, but should be combined with social distancing measures to reduce [Formula: see text] below 1. [Box: see text]

Objectives. To estimate health outcomes of policies to mitigate the opioid epidemic. Methods. We used dynamic compartmental modeling of US adults, in various pain, opioid use, and opioid addiction health states, to project addiction-related deaths, life years, and quality-adjusted life years from 2016 to 2025 for 11 policy responses to the opioid epidemic. Results. Over 5 years, increasing naloxone availability, promoting needle exchange, expanding medication-assisted addiction treatment, and increasing psychosocial treatment increased life years and quality-adjusted life years and reduced deaths. Other policies reduced opioid prescription supply and related deaths but led some addicted prescription users to switch to heroin use, which increased heroin-related deaths. Over a longer horizon, some such policies may avert enough new addiction to outweigh the harms. No single policy is likely to substantially reduce deaths over 5 to 10 years. Conclusions. Policies focused on services for addicted people improve population health without harming any groups. Policies that reduce the prescription opioid supply may increase heroin use and reduce quality of life in the short term, but in the long term could generate positive health benefits. A portfolio of interventions will be needed for eventual mitigation.

Background Contact mixing plays a key role in the spread of COVID-19. Thus, mobility restrictions of varying degrees up to and including nationwide lockdowns have been implemented in over 200 countries. To appropriately target the timing, location, and severity of measures intended to encourage social distancing at a country level, it is essential to predict when and where outbreaks will occur, and how widespread they will be. Methods We analyze aggregated, anonymized health data and cell phone mobility data from Israel. We develop predictive models for daily new cases and the test positivity rate over the next 7 days for different geographic regions in Israel. We evaluate model goodness of fit using root mean squared error (RMSE). We use these predictions in a five-tier categorization scheme to predict the severity of COVID-19 in each region over the next week. We measure magnitude accuracy (MA), the extent to which the correct severity tier is predicted. Results Models using mobility data outperformed models that did not use mobility data, reducing RMSE by 17.3% when predicting new cases and by 10.2% when predicting the test positivity rate. The best set of predictors for new cases consisted of 1-day lag of past 7-day average new cases, along with a measure of internal movement within a region. The best set of predictors for the test positivity rate consisted of 3-days lag of past 7-day average test positivity rate, along with the same measure of internal movement. Using these predictors, RMSE was 4.812 cases per 100,000 people when predicting new cases and 0.79% when predicting the test positivity rate. MA in predicting new cases was 0.775, and accuracy of prediction to within one tier was 1.0. MA in predicting the test positivity rate was 0.820, and accuracy to within one tier was 0.998. Conclusions Using anonymized, macro-level data human mobility data along with health data aids predictions of when and where COVID-19 outbreaks are likely to occur. Our method provides a useful tool for government decision makers, particularly in the post-vaccination era, when focused interventions are needed to contain COVID-19 outbreaks while mitigating the collateral damage from more global restrictions.

Background Chikungunya and dengue are emerging diseases that have caused large outbreaks in various regions of the world. Both are both spread by Aedes aegypti and Aedes albopictus mosquitos. We developed a dynamic transmission model of chikungunya and dengue, calibrated to data from Colombia (June 2014 –December 2017). Methodology/Principal findings We evaluated the health benefits and cost-effectiveness of residual insecticide treatment, long-lasting insecticide-treated nets, routine dengue vaccination for children aged 9, catchup vaccination for individuals aged 10–19 or 10–29, and portfolios of these interventions. Model calibration resulted in 300 realistic transmission parameters sets that produced close matches to disease-specific incidence and deaths. Insecticide was the preferred intervention and was cost-effective. Insecticide averted an estimated 95 chikungunya cases and 114 dengue cases per 100,000 people, 61 deaths, and 4,523 disability-adjusted life years (DALYs). In sensitivity analysis, strategies that included dengue vaccination were cost-effective only when the vaccine cost was 14% of the current price. Conclusions/Significance Insecticide to prevent chikungunya and dengue in Colombia could generate significant health benefits and be cost-effective. Because of limits on diagnostic accuracy and vaccine efficacy, the cost of dengue testing and vaccination must decrease dramatically for such vaccination to be cost-effective in Colombia. The vectors for chikungunya and dengue have recently spread to new regions, highlighting the importance of understanding the effectiveness and cost-effectiveness of policies aimed at preventing these diseases., Author summary Chikungunya and dengue are emerging diseases that have caused large outbreaks in various regions of the world. Both are both spread by Aedes aegypti and Aedes albopictus mosquitos. To evaluate the effectiveness and cost-effectiveness of interventions aimed at controlling either of these diseases, it is important to consider the potential effects on both diseases, as an intervention that reduces the mosquito population will reduce the spread of both diseases. We developed a dynamic transmission model of chikungunya and dengue, calibrated to data from Colombia. We evaluated the health benefits and cost-effectiveness of the following interventions: residual insecticide treatment, long-lasting insecticide-treated nets, routine dengue vaccination for children aged 9, catchup dengue vaccination for individuals aged 10–19 or 10–29, and portfolios of these interventions. In all vaccination scenarios, we considered testing for previous exposure to dengue. We found that insecticide to prevent chikungunya and dengue in Colombia could generate significant health benefits and be cost-effective. While the dengue vaccine was effective in preventing cases and deaths, costs of diagnostic testing and vaccination must decrease for dengue vaccination to be considered cost-effective.