Temporal and spatial analysis of over 7,000 measles cases outbreak from 2018 to 2019 in the Brazilian Amazon.

OBJECTIVE: This study aimed to present a temporal and spatial analysis of the 2018 measles outbreak in Brazil, particularly in the metropolitan city of Manaus in the Amazon region, and further introduce a new tool for spatial analysis. METHODS: We analyzed the geographical data of the residences of over 7,000 individuals with measles in Manaus during 2018 and 2019. Spatial and temporal analyses were conducted to characterize various aspects of the outbreak, including the onset and prevalence of symptoms, demographics, and vaccination status. A visualization tool was also constructed to display the geographical and temporal distribution of the reported measles cases. RESULTS: Approximately 95% of the included participants had not received vaccination within the past decade. Heterogeneity was observed across all facets of the outbreak, including variations in the incubation period and symptom presentation. Age distribution exhibited two peaks, occurring at one year and 18 years of age, and the potential implications of this distribution on predictive analysis were discussed. Additionally, spatial analysis revealed that areas with the highest case densities tended to have the lowest standard of living. CONCLUSION: Understanding the spatial and temporal spread of measles outbreaks provides insights for decision-making regarding measures to mitigate future epidemics.

Temporal and spatial analysis of over 7,000 measles cases outbreak from 2018 to 2019 in the Brazilian Amazon

ABSTRACT Objective: This study aimed to present a temporal and spatial analysis of the 2018 measles outbreak in Brazil, particularly in the metropolitan city of Manaus in the Amazon region, and further introduce a new tool for spatial analysis. Methods: We analyzed the geographical data of the residences of over 7,000 individuals with measles in Manaus during 2018 and 2019. Spatial and temporal analyses were conducted to characterize various aspects of the outbreak, including the onset and prevalence of symptoms, demographics, and vaccination status. A visualization tool was also constructed to display the geographical and temporal distribution of the reported measles cases. Results: Approximately 95% of the included participants had not received vaccination within the past decade. Heterogeneity was observed across all facets of the outbreak, including variations in the incubation period and symptom presentation. Age distribution exhibited two peaks, occurring at one year and 18 years of age, and the potential implications of this distribution on predictive analysis were discussed. Additionally, spatial analysis revealed that areas with the highest case densities tended to have the lowest standard of living. Conclusion: Understanding the spatial and temporal spread of measles outbreaks provides insights for decision-making regarding measures to mitigate future epidemics.

New PK/PD model directly links diabetes drug dose to blood glucose level for personalized care.

The management of diabetes mellitus focuses on close monitoring of a patient's blood glucose level while the clinician experiments with a dosing strategy using clinical guidelines and his/her own experience. We propose a pharmacokinetic and pharmacodynamics model that characterizes the dose-response of patients receiving anti-diabetic drug therapy. We derive and establish a direct relationship between drug dosage and blood glucose level. This new drug-dose drug-effect model, combined with a linear disease progression model, is used to fit the patient's daily self-monitored blood glucose (SMBG) data to obtain the personalized treatment effect for each patient. The model predicts the long-term drug effect using the prescribed dose, thus allowing for dose optimization. The model is evaluated on patients with gestational diabetes mellitus. SMBG data collected during the first month of treatment is used to train the model. The model is able to characterize the personalized dose-response and disease progression. Moreover, when compared to a descriptive autoregression model, our model gives a better long-term prediction of the drug effect on the trend of the blood glucose level. This mechanism-based treatment effect model utilizes daily recorded blood glucose data to estimate and predict a patient's personalized dose-response and disease progression. Such evidence can be used by clinicians to individualize and optimize dose regimens to achieve better treatment outcomes.

Analyzing Strategies for Containing Avian Influenza.

In this paper, we couple a general-purpose infectious disease theory with a computational modeling framework to analyze strategies for avian influenza containment. We focus on virus transmission among domestic poultry populations to optimize and evaluate the effectiveness of three containment strategies and their combinations: reducing the contact rate among domestic birds, reducing the population of infected birds, and reducing the transportation of infected birds. We illustrate their usage during a two-wave avian flu outbreak in Nigeria. Our findings show that reducing contacts by 20% via cluster isolation early in the first wave can achieve containment rapidly. It also helps avert the second wave. Slaughtering infected birds is not as effective, requiring scheduled killings of over 80% of the poultry while failing to avert the second wave. This practice also risks damaging the local economy and potential secondary infections from the carcasses of infected birds. Reducing transportation between northern and southern Nigeria does not offer good containment since the disease spread began in both regions simultaneously. Reducing transportation has an impact when applied to neighboring regions and cities, or when the initial incidence of the disease is localized. Combination strategies prove to be the most practical and cost-effective to implement. The use of 3D-effectiveness visualized plots allows policymakers to evaluate multiple combination strategies and choose the one that optimizes containment while also adhering to budget constraints, resource availability, and management preference. The generalized mathematical theory and modeling framework is highly flexible and can be applied to other diseases, including those with multiple hosts, multiple species involvement, and across a broad array of heterogeneous regions.

Strategies for Vaccine Prioritization and Mass Dispensing.

We propose a system that helps decision makers during a pandemic find, in real time, the mass vaccination strategies that best utilize limited medical resources to achieve fast containments and population protection. Our general-purpose framework integrates into a single computational platform a multi-purpose compartmental disease propagation model, a human behavior network, a resource logistics model, and a stochastic queueing model for vaccination operations. We apply the modeling framework to the current COVID-19 pandemic and derive an optimal trigger for switching from a prioritized vaccination strategy to a non-prioritized strategy so as to minimize the overall attack rate and mortality rate. When vaccine supply is limited, such a mixed vaccination strategy is broadly effective. Our analysis suggests that delays in vaccine supply and inefficiencies in vaccination delivery can substantially impede the containment effort. Employing an optimal mixed strategy can significantly reduce the attack and mortality rates. The more infectious the virus, the earlier it helps to open the vaccine to the public. As vaccine efficacy decreases, the attack and mortality rates rapidly increase by multiples; this highlights the importance of early vaccination to reduce spreading as quickly as possible to lower the chances for further mutations to evolve and to reduce the excessive healthcare burden. To maximize the protective effect of available vaccines, of equal importance are determining the optimal mixed strategy and implementing effective on-the-ground dispensing. The optimal mixed strategy is quite robust against variations in model parameters and can be implemented readily in practice. Studies with our holistic modeling framework strongly support the urgent need for early vaccination in combating the COVID-19 pandemic. Our framework permits rapid custom modeling in practice. Additionally, it is generalizable for different types of infectious disease outbreaks, whereby a user may determine for a given type the effects of different interventions including the optimal switch trigger.

Strategies for Disease Containment: A Biological-Behavioral-Intervention Computational Informatics Framework.

In this study, we describe the development and use of a biological-behavior-intervention computational informatics framework that combines disease modelling for infectious virus with stratifications for social behavior and employment, and resource logistics. The framework incorporates heterogeneous group behavior and interaction dynamics, and optimizes intervention and resources for effective containment. We demonstrate its usage by analyzing and optimizing containment strategies for the 2014-2016 West Africa Ebola outbreak, and its implementation for responses to the 2020 COVID-19 pandemic in the United States. Our analysis shows that timely action within 1.5 months from the onset of confirmed cases can cut down 90% of overall infections and bring rapid containment within 6-8 months. The additional medical resources required are minor and would ensure proper treatment and quarantine of patients while reducing the risk of infections among healthcare workers. The benefit (in infection / death control) would be reduced by 10 to over 100 fold and time to containment would increase by 2-4 fold when intervention and medical resources are injected within 5 months. In contrast, the additional resources needed to bring down the overall infection in a delayed intervention are significant, with inferior results. The disease module can be tailored for different pathogens. It expands the well-used SEIR model to include social and intervention activities, asymptomatic and post-recovery transmission, hospitalization, outcome of recovery, and funeral events. The model also examines the transmission rate of health care workers and allows for heterogenous infection factors among different groups. It also captures time-variant human behavior during the horizon of the outbreak. The framework optimizes the intervention timeline and resource allocation during an infectious disease outbreak and offers insights on how resource availability in time and quantity can affect the disease trends and containment significantly. This can inform policy, disease management and resource allocation. While focusing on bed availability for quarantine and treatment appears to be simplistic, their necessity for Ebola responses cannot be overemphasized. We link these insights to a web-based tool to provide quick and intuitive observations for decision making and investigation of the disease outbreak situation. Subsequent use of the system to determine the optimal timing and effectiveness and tradeoffs analysis of various non-pharmaceutical intervention strategies for COVID-19 provide a foundation for policy makers to execute the first-step response. These results have been implemented on the ground since March 2020. The web-based tool pinpoints accurately the import of disease from global travels and associated disease spread and health burdens. This prospectively affirms the importance of such a real-time computational system, and its availability before onset of a pandemic.

A systems approach to examine hospital-acquired infections in a paediatric CICU.

OBJECTIVE: We aimed to apply systems engineering principles to address hospital-acquired infections in the paediatric intensive care setting. DESIGN: Mixed method approach involving four steps: perform time-motion study of cardiac intensive care unit (CICU) care processes, establish a meaningful schema to classify observations, design a web-based system to manage and analyse data, and design a prototypical computer-based training system to assist with hygiene compliance. SETTING: Paediatric CICU at the Children's Healthcare of Atlanta. PATIENTS: Paediatric patients undergoing congenital heart surgery. INTERVENTIONS: Extensive time-motion study of CICU care processes. MEASUREMENTS: Non-compliances were recorded for each care process observed during the time-motion study. RESULTS: Guided by our observations, we introduced a novel categorisation schema with action types, observation categories, severity classes, procedure classifications, and personnel categories that offer a systematic and efficient mechanism for reporting and classifying non-compliance and violations. Utilising these categories, a web-based database management system was designed that allows observers to input their data. This web analytic tool offers easy summarisation, data analysis, and visualisation of findings. A computer-based training system with modules to educate visitors in hospital-acquired infections hygiene was also created. CONCLUSION: Our study offers a checklist of non-compliance situations and potential development of a proactive surveillance system of awareness of infection-prone situations. Working with quality improvement experts and stakeholders, recommendations and actionable practice will be synthesised for implementation in clinical settings. Careful design of the implementation protocol is needed to measure and quantify the potential improvements in outcomes.

CERC: an interactive content extraction, recognition, and construction tool for clinical and biomedical text.

BACKGROUND: Automated summarization of scientific literature and patient records is essential for enhancing clinical decision-making and facilitating precision medicine. Most existing summarization methods are based on single indicators of relevance, offer limited capabilities for information visualization, and do not account for user specific interests. In this work, we develop an interactive content extraction, recognition, and construction system (CERC) that combines machine learning and visualization techniques with domain knowledge for highlighting and extracting salient information from clinical and biomedical text. METHODS: A novel sentence-ranking framework multi indicator text summarization, MINTS, is developed for extractive summarization. MINTS uses random forests and multiple indicators of importance for relevance evaluation and ranking of sentences. Indicative summarization is performed using weighted term frequency-inverse document frequency scores of over-represented domain-specific terms. A controlled vocabulary dictionary generated using MeSH, SNOMED-CT, and PubTator is used for determining relevant terms. 35 full-text CRAFT articles were used as the training set. The performance of the MINTS algorithm is evaluated on a test set consisting of the remaining 32 full-text CRAFT articles and 30 clinical case reports using the ROUGE toolkit. RESULTS: The random forests model classified sentences as "good" or "bad" with 87.5% accuracy on the test set. Summarization results from the MINTS algorithm achieved higher ROUGE-1, ROUGE-2, and ROUGE-SU4 scores when compared to methods based on single indicators such as term frequency distribution, position, eigenvector centrality (LexRank), and random selection, p < 0.01. The automatic language translator and the customizable information extraction and pre-processing pipeline for EHR demonstrate that CERC can readily be incorporated within clinical decision support systems to improve quality of care and assist in data-driven and evidence-based informed decision making for direct patient care. CONCLUSIONS: We have developed a web-based summarization and visualization tool, CERC ( https://newton.isye.gatech.edu/CERC1/ ), for extracting salient information from clinical and biomedical text. The system ranks sentences by relevance and includes features that can facilitate early detection of medical risks in a clinical setting. The interactive interface allows users to filter content and edit/save summaries. The evaluation results on two test corpuses show that the newly developed MINTS algorithm outperforms methods based on single characteristics of importance.

Antigenicity prediction and vaccine recommendation of human influenza virus A (H3N2) using convolutional neural networks.

The rapid evolution of influenza A viruses poses a great challenge to vaccine development. Analytical and machine learning models have been applied to facilitate the process of antigenicity determination. In this study, we designed deep convolutional neural networks (CNNs) to predict Influenza antigenicity. Our model is the first that systematically analyzed 566 amino acid properties and 141 amino acid substitution matrices for their predictability. We then optimized the structure of the CNNs using particle swarm optimization. The optimal neural networks outperform other predictive models with a blind validation accuracy of 95.8%. Further, we applied our model to vaccine recommendations in the period 1997 to 2011 and contrasted the performance of previous vaccine recommendations using traditional experimental approaches. The results show that our model outperforms the WHO recommendation and other existing models and could potentially improve the vaccine recommendation process. Our results show that WHO often selects virus strains with small variation from year to year and learns slowly and recovers once coverage dips very low. In contrast, the influenza strains selected via our CNN model can differ quite drastically from year to year and exhibit consistently good coverage. In summary, we have designed a comprehensive computational pipeline for optimizing a CNN in the modeling of Influenza A antigenicity and vaccine recommendation. It is more cost and time-effective when compared to traditional hemagglutination inhibition assay analysis. The modeling framework is flexible and can be adopted to study other type of viruses.

Methods for predicting vaccine immunogenicity and reactogenicity.

Subjects receiving the same vaccine often show different levels of immune responses and some may even present adverse side effects to the vaccine. Systems vaccinology can combine omics data and machine learning techniques to obtain highly predictive signatures of vaccine immunogenicity and reactogenicity. Currently, several machine learning methods are already available to researchers with no background in bioinformatics. Here we described the four main steps to discover markers of vaccine immunogenicity and reactogenicity: (1) Preparing the data; (2) Selecting the vaccinees and relevant genes; (3) Choosing the algorithm; (4) Blind testing your model. With the increasing number of Systems Vaccinology datasets being generated, we expect that the accuracy and robustness of signatures of vaccine reactogenicity and immunogenicity will significantly improve.

Investigating a Needle-Based Epidural Procedure in Obstetric Anesthesia.

This study investigates the safety and efficacy of a large-dose, needle-based epidural technique in obstetric anesthesia. The technique differs from a standard, catheter-based approach in that the anesthetic dose is administered through an epidural needle prior to insertion of the epidural catheter. Using a data-driven informatics and machine learning approach, our findings show that the needle-based technique is faster and more dose-effective in achieving sensory level. We also find that injecting large doses in the epidural space through the epidural needle is safe, with complication rates similar to those reported in published literature for catheter-based technique. Further, machine learning reveals that if the needle dose is kept under 18 ml, the resulting hypotension rate will be significantly lower than published results. The machine learning framework can predict the incidence of hypotension with 85% accuracy. The findings from this investigation facilitate delivery improvement and establish an improved clinical practice guideline for training and for dissemination of safe practice.

Systems analysis of protective immune responses to RTS,S malaria vaccination in humans.

RTS,S is an advanced malaria vaccine candidate and confers significant protection against Plasmodium falciparum infection in humans. Little is known about the molecular mechanisms driving vaccine immunity. Here, we applied a systems biology approach to study immune responses in subjects receiving three consecutive immunizations with RTS,S (RRR), or in those receiving two immunizations of RTS,S/AS01 following a primary immunization with adenovirus 35 (Ad35) (ARR) vector expressing circumsporozoite protein. Subsequent controlled human malaria challenge (CHMI) of the vaccinees with Plasmodium-infected mosquitoes, 3 wk after the final immunization, resulted in ∼50% protection in both groups of vaccinees. Circumsporozoite protein (CSP)-specific antibody titers, prechallenge, were associated with protection in the RRR group. In contrast, ARR-induced lower antibody responses, and protection was associated with polyfunctional CD4+ T-cell responses 2 wk after priming with Ad35. Molecular signatures of B and plasma cells detected in PBMCs were highly correlated with antibody titers prechallenge and protection in the RRR cohort. In contrast, early signatures of innate immunity and dendritic cell activation were highly associated with protection in the ARR cohort. For both vaccine regimens, natural killer (NK) cell signatures negatively correlated with and predicted protection. These results suggest that protective immunity against P. falciparum can be achieved via multiple mechanisms and highlight the utility of systems approaches in defining molecular correlates of protection to vaccination.

A Computational Framework for a Digital Surveillance and Response Tool: Application to Avian Influenza.

Avian influenza viruses have caused infections and deaths in wild birds, commercial poultry, and humans. It poses an increasing threat of a pandemic. To understand the transmission dynamics of avian influenza viruses and assess the effectiveness of different containment strategies, we develop a flexible modeling framework based on multi-layer compartmental models for digital disease surveillance and response in combating pandemics. The model can accommodate other disease outbreaks under diverse settings. We demonstrate its usage on avian influenza and derive the basic reproduction number and spread characteristics. We contrast the effectiveness of different containment strategies and their combination effect in protecting both the human and the bird populations. Our system, a digital surveillance and response system (RealOpt-ASSURE), can record, monitor, and predict avian influenza outbreaks. It combines with intervention strategies to return policies and on-the-ground operations/actions that are needed for best population protection. RealOpt-ASSURE can accept heterogeneous types of surveillance data. It can help decision makers to evaluate the risk of a pandemic and choose proper containment strategies to rapidly mitigate the outbreak.

Utilizing a Collaborative Learning Model to Promote Early Extubation Following Infant Heart Surgery.

OBJECTIVE: To determine whether a collaborative learning strategy-derived clinical practice guideline can reduce the duration of endotracheal intubation following infant heart surgery. DESIGN: Prospective and retrospective data collected from the Pediatric Heart Network in the 12 months pre- and post-clinical practice guideline implementation at the four sites participating in the collaborative (active sites) compared with data from five Pediatric Heart Network centers not participating in collaborative learning (control sites). SETTING: Ten children's hospitals. PATIENTS: Data were collected for infants following two-index operations: 1) repair of isolated coarctation of the aorta (birth to 365 d) and 2) repair of tetralogy of Fallot (29-365 d). There were 240 subjects eligible for the clinical practice guideline at active sites and 259 subjects at control sites. INTERVENTIONS: Development and application of early extubation clinical practice guideline. MEASUREMENTS AND MAIN RESULTS: After clinical practice guideline implementation, the rate of early extubation at active sites increased significantly from 11.7% to 66.9% (p < 0.001) with no increase in reintubation rate. The median duration of postoperative intubation among active sites decreased from 21.2 to 4.5 hours (p < 0.001). No statistically significant change in early extubation rates was found in the control sites 11.7% to 13.7% (p = 0.63). At active sites, clinical practice guideline implementation had no statistically significant impact on median ICU length of stay (71.9 hr pre- vs 69.2 hr postimplementation; p = 0.29) for the entire cohort. There was a trend toward shorter ICU length of stay in the tetralogy of Fallot subgroup (71.6 hr pre- vs 54.2 hr postimplementation, p = 0.068). CONCLUSIONS: A collaborative learning strategy designed clinical practice guideline significantly increased the rate of early extubation with no change in the rate of reintubation. The early extubation clinical practice guideline did not significantly change postoperative ICU length of stay.

Rationale and methodology of a collaborative learning project in congenital cardiac care.

BACKGROUND: Collaborative learning is a technique through which individuals or teams learn together by capitalizing on one another's knowledge, skills, resources, experience, and ideas. Clinicians providing congenital cardiac care may benefit from collaborative learning given the complexity of the patient population and team approach to patient care. RATIONALE AND DEVELOPMENT: Industrial system engineers first performed broad-based time-motion and process analyses of congenital cardiac care programs at 5 Pediatric Heart Network core centers. Rotating multidisciplinary team site visits to each center were completed to facilitate deep learning and information exchange. Through monthly conference calls and an in-person meeting, we determined that duration of mechanical ventilation following infant cardiac surgery was one key variation that could impact a number of clinical outcomes. This was underscored by one participating center's practice of early extubation in the majority of its patients. A consensus clinical practice guideline using collaborative learning was developed and implemented by multidisciplinary teams from the same 5 centers. The 1-year prospective initiative was completed in May 2015, and data analysis is under way. CONCLUSION: Collaborative learning that uses multidisciplinary team site visits and information sharing allows for rapid structured fact-finding and dissemination of expertise among institutions. System modeling and machine learning approaches objectively identify and prioritize focused areas for guideline development. The collaborative learning framework can potentially be applied to other components of congenital cardiac care and provide a complement to randomized clinical trials as a method to rapidly inform and improve the care of children with congenital heart disease.

CSF complement 3 and factor H are staging biomarkers in Alzheimer's disease.

INTRODUCTION: CSF levels of established Alzheimer's disease (AD) biomarkers remain stable despite disease progression, and non-amyloid non-tau biomarkers have the potential of informing disease stage and progression. We previously identified complement 3 (C3) to be decreased in AD dementia, but this change was not found by others in earlier AD stages. We hypothesized that levels of C3 and associated factor H (FH) can potentially distinguish between mild cognitive impairment (MCI) and dementia stages of AD, but we also found their levels to be influenced by age and disease status. RESULTS: We developed a biochemical/bioinformatics pipeline to optimize the handling of complex interactions between variables in validating biochemical markers of disease. We used data from the Alzheimer's Disease Neuro-imaging Initiative (ADNI, n = 230) to build parallel machine learning models, and objectively tested the models in a test cohort (n = 73) of MCI and mild AD patients independently recruited from Emory University. Whereas models incorporating age, gender, APOE ε4 status, and CSF amyloid and tau levels failed to reliably distinguish between MCI and mild AD in ADNI, introduction of CSF C3 and FH levels reproducibly improved the distinction between the two AD stages in ADNI (p < 0.05) and the Emory cohort (p = 0.014). Within each AD stage, the final model also distinguished between fast vs. slower decliners (p < 0.001 for MCI, p = 0.007 for mild AD), with lower C3 and FH levels associated with more advanced disease and faster progression. CONCLUSIONS: We propose that CSF C3 and FH alterations may reflect stage-associated biomarker changes in AD, and can complement clinician diagnosis in diagnosing and staging AD using the publically available ADNI database as reference.

A Compartmental Model for Zika Virus with Dynamic Human and Vector Populations.

The Zika virus (ZIKV) outbreak in South American countries and its potential association with microcephaly in newborns and Guillain-Barré Syndrome led the World Health Organization to declare a Public Health Emergency of International Concern. To understand the ZIKV disease dynamics and evaluate the effectiveness of different containment strategies, we propose a compartmental model with a vector-host structure for ZIKV. The model utilizes logistic growth in human population and dynamic growth in vector population. Using this model, we derive the basic reproduction number to gain insight on containment strategies. We contrast the impact and influence of different parameters on the virus trend and outbreak spread. We also evaluate different containment strategies and their combination effects to achieve early containment by minimizing total infections. This result can help decision makers select and invest in the strategies most effective to combat the infection spread. The decision-support tool demonstrates the importance of "digital disease surveillance" in response to waves of epidemics including ZIKV, Dengue, Ebola and cholera.

Symmetric Directional False Discovery Rate Control.

This research is motivated from the analysis of a real gene expression data that aims to identify a subset of "interesting" or "significant" genes for further studies. When we blindly applied the standard false discovery rate (FDR) methods, our biology collaborators were suspicious or confused, as the selected list of significant genes was highly unbalanced: there were ten times more under-expressed genes than the over-expressed genes. Their concerns led us to realize that the observed two-sample t-statistics were highly skewed and asymmetric, and thus the standard FDR methods might be inappropriate. To tackle this case, we propose a symmetric directional FDR control method that categorizes the genes into "over-expressed" and "under-expressed" genes, pairs "over-expressed" and "under-expressed" genes, defines the p-values for gene pairs via column permutations, and then applies the standard FDR method to select "significant" gene pairs instead of "significant" individual genes. We compare our proposed symmetric directional FDR method with the standard FDR method by applying them to simulated data and several well-known real data sets.

Systems Analysis of Immunity to Influenza Vaccination across Multiple Years and in Diverse Populations Reveals Shared Molecular Signatures.

Systems approaches have been used to describe molecular signatures driving immunity to influenza vaccination in humans. Whether such signatures are similar across multiple seasons and in diverse populations is unknown. We applied systems approaches to study immune responses in young, elderly, and diabetic subjects vaccinated with the seasonal influenza vaccine across five consecutive seasons. Signatures of innate immunity and plasmablasts correlated with and predicted influenza antibody titers at 1 month after vaccination with >80% accuracy across multiple seasons but were not associated with the longevity of the response. Baseline signatures of lymphocyte and monocyte inflammation were positively and negatively correlated, respectively, with antibody responses at 1 month. Finally, integrative analysis of microRNAs and transcriptomic profiling revealed potential regulators of vaccine immunity. These results identify shared vaccine-induced signatures across multiple seasons and in diverse populations and might help guide the development of next-generation vaccines that provide persistent immunity against influenza.

Medical alert management: a real-time adaptive decision support tool to reduce alert fatigue.

With the adoption of electronic medical records (EMRs), drug safety alerts are increasingly recognized as valuable tools for reducing adverse drug events and improving patient safety. However, even with proper tuning of the EMR alert parameters, the volume of unfiltered alerts can be overwhelming to users. In this paper, we design an adaptive decision support tool in which past cognitive overriding decisions of users are learned, adapted and used for filtering actions to be performed on current alerts. The filters are designed and learned based on a moving time window, number of alerts, overriding rates, and monthly overriding fluctuations. Using alerts from two separate years to derive filters and test performance, predictive accuracy rates of 91.3%-100% are achieved. The moving time window works better than a static training approach. It allows continuous learning and capturing of the most recent decision characteristics and seasonal variations in drug usage. The decision support system facilitates filtering of non-essential alerts and adaptively learns critical alerts and highlights them prominently to catch providers' attention. The tool can be plugged into an existing EMR system as an add-on, allowing real-time decision support to users without interfering with existing EMR functionalities. By automatically filtering the alerts, the decision support tool mitigates alert fatigue and allows users to focus resources on potentially vital alerts, thus reducing the occurrence of adverse drug events.