A systematic review of aberration detection algorithms used in public health surveillance

Evaluation of the application of sequence data to the identification of outbreaks of disease using anomaly detection methods

Anomaly detection methods have a great potential to assist the detection of diseases in animal production systems. We used sequence data of Porcine Reproductive and Respiratory Syndrome (PRRS) to define the emergence of new strains at the farm level. We evaluated the performance of 24 anomaly detection methods based on machine learning, regression, time series techniques and control charts to identify outbreaks in time series of new strains and compared the best methods using different time series: PCR positives, PCR requests and laboratory requests. We introduced synthetic outbreaks of different size and calculated the probability of detection of outbreaks (POD), sensitivity (Se), probability of detection of outbreaks in the first week of appearance (POD1w) and background alarm rate (BAR). The use of time series of new strains from sequence data outperformed the other types of data but POD, Se, POD1w were only high when outbreaks were large. The methods based on Long Short-Term Memory (LSTM) and Bayesian approaches presented the best performance. Using anomaly detection methods with sequence data may help to identify the emergency of cases in multiple farms, but more work is required to improve the detection with time series of high variability. Our results suggest a promising application of sequence data for early detection of diseases at a production system level. This may provide a simple way to extract additional value from routine laboratory analysis. Next steps should include validation of this approach in different settings and with different diseases.

Comparison of statistical methods for the early detection of disease outbreaks in small population settings

Objectives

This study examines the performance of 6 aberration detection algorithms for the early detection of disease outbreaks in small population settings using syndrome-based early warning surveillance data collected by the Pacific Syndromic Surveillance System (PSSS). Although previous studies have proposed statistical methods for detecting aberrations in larger datasets, there is limited knowledge about how these perform in the presence of small numbers of background cases.

Methods

To address this gap a simulation model was developed to test and compare the performance of the 6 algorithms in detecting outbreaks of different magnitudes, durations, and case distributions.

Results

The study found that while the Early Aberration Reporting System-C1 algorithm developed by Hutwagner et al. outperformed others, no single approach provided reliable monitoring across all outbreak types. Furthermore, aberration detection approaches could only detect very large and acute outbreaks with any reliability.

Conclusion

The findings of this study suggest that algorithm-based approaches to outbreak signal detection perform poorly when applied to settings with small numbers of background cases and should not be relied upon in these contexts. This highlights the need for alternative approaches for accurate and timely outbreak detection in small population settings, particularly those that are resource-constrained.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

•

An overview of systematic reviews on the application of AI including 129 studies.

•

AI use is prominent in Universal Health Coverage, featuring image analysis in neoplasms.

•

Half of the reviews did not evaluate validation procedures nor reporting guidelines.

•

Risk of bias was only included un a third of the reviews.

•

There is not sufficient evidence to transfer AI to actual healthcare delivery.

Background

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people’s health. It is necessary to assess the current status on the application of AI towards the improvement of people’s health in the domains defined by WHO’s Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

Objective

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people’s health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

Methods

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO’s PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

Results

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

Conclusion

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Anomaly Detection on Natural Language Processing to Improve Predictions on Tourist Preferences

Argumentation-based dialogue models have shown to be appropriate for decision contexts in which it is intended to overcome the lack of interaction between decision-makers, either because they are dispersed, they are too many, or they are simply not even known. However, to support decision processes with argumentation-based dialogue models, it is necessary to have knowledge of certain aspects that are specific to each decision-maker, such as preferences, interests, and limitations, among others. Failure to obtain this knowledge could ruin the model’s success. In this work, we sought to facilitate the information acquisition process by studying strategies to automatically predict the tourists’ preferences (ratings) in relation to points of interest based on their reviews. We explored different Machine Learning methods to predict users’ ratings. We used Natural Language Processing strategies to predict whether a review is positive or negative and the rating assigned by users on a scale of 1 to 5. We then applied supervised methods such as Logistic Regression, Random Forest, Decision Trees, K-Nearest Neighbors, and Recurrent Neural Networks to determine whether a tourist likes/dislikes a given point of interest. We also used a distinctive approach in this field through unsupervised techniques for anomaly detection problems. The goal was to improve the supervised model in identifying only those tourists who truly like or dislike a particular point of interest, in which the main objective is not to identify everyone, but fundamentally not to fail those who are identified in those conditions. The experiments carried out showed that the developed models could predict with high accuracy whether a review is positive or negative but have some difficulty in accurately predicting the rating assigned by users. Unsupervised method Local Outlier Factor improved the results, reducing Logistic Regression false positives with an associated cost of increasing false negatives.

Popularity of Delta-8 THC on the Internet Across US States, 2021

Objectives. To assess the popularity of an emergent drug, delta-8 tetrahydrocannabinol (THC), and compare interest levels between US states with or without legalized recreational cannabis. Methods. We used Google Trends to assess the growth of interest among delta-8 THC-related search terms from May 17, 2020, to May 9, 2021. We examined differences between states with or without legalized cannabis using state-level Google Trends data from February 13 to May 13, 2021, and policy data from the National Conference of State Legislatures. Results. Interest in delta-8 THC increased starting in mid-June 2020, with search volumes for delta-8 THC queries currently at 35% of the "marijuana" query. States where recreational cannabis is illegal had higher relative queries than did states with legalized recreational cannabis (52.3 vs 14.8; t = 40.9; P < .001). Conclusions. There has been rapid growth in interest in delta-8 THC. Findings between state policy contexts likely indicate delta-8 THC's role as a substitute good for delta-9 THC. Public Health Implications. Digital signals such as search volumes may point to an emergent use trend in the substance delta-8 THC. Further studies are needed to assess potential harms and correlates of delta-8 THC use. (Am J Public Health. 2022;112(2):296-299. https://doi.org/10.2105/AJPH.2021.306586).

NextGen Public Health Surveillance and the Internet of Things (IoT)

Recent advances in technology have led to the rise of new-age data sources (e.g., Internet of Things (IoT), wearables, social media, and mobile health). IoT is becoming ubiquitous, and data generation is accelerating globally. Other health research domains have used IoT as a data source, but its potential has not been thoroughly explored and utilized systematically in public health surveillance. This article summarizes the existing literature on the use of IoT as a data source for surveillance. It presents the shortcomings of current data sources and how NextGen data sources, including the large-scale applications of IoT, can meet the needs of surveillance. The opportunities and challenges of using these modern data sources in public health surveillance are also explored. These IoT data ecosystems are being generated with minimal effort by the device users and benefit from high granularity, objectivity, and validity. Advances in computing are now bringing IoT-based surveillance into the realm of possibility. The potential advantages of IoT data include high-frequency, high volume, zero effort data collection methods, with a potential to have syndromic surveillance. In contrast, the critical challenges to mainstream this data source within surveillance systems are the huge volume and variety of data, fusing data from multiple devices to produce a unified result, and the lack of multidisciplinary professionals to understand the domain and analyze the domain data accordingly.

Spatiotemporal epidemiology and forecasting of dengue in the state of Punjab, India: Study protocol

Dengue burden in India is a major public health problem. The present study has been designed to understand mechanisms by which routine data generate evidence. Secondary data analysis of routine datasets to understand spatiotemporal epidemiology and forecast dengue will be conducted. Data science approach will be adopted to generate a reproducible framework in the R environment. The lab-confirmed dengue reported by the state health authorities from 01 January 2015 to 31 December 2019 will be included. Multiple climatic variables from satellite imagery, climatic models, vegetation and built-up indices, and sociodemographic variables will be explored as risk factors. Exploratory data analysis followed by statistical analysis and machine learning will be performed. Data analysis will include geospatial information analysis, time series analysis, and spatiotemporal analysis. The study will provide value addition to the existing disease surveillance mechanisms by developing a framework for incorporating multiple routine data sources available in the country.

Real-time monitoring of COVID-19 dynamics using automated trend fitting and anomaly detection

As several countries gradually release social distancing measures, rapid detection of new localized COVID-19 hotspots and subsequent intervention will be key to avoiding large-scale resurgence of transmission. We introduce ASMODEE (automatic selection of models and outlier detection for epidemics), a new tool for detecting sudden changes in COVID-19 incidence. Our approach relies on automatically selecting the best (fitting or predicting) model from a range of user-defined time series models, excluding the most recent data points, to characterize the main trend in an incidence. We then derive prediction intervals and classify data points outside this interval as outliers, which provides an objective criterion for identifying departures from previous trends. We also provide a method for selecting the optimal breakpoints, used to define how many recent data points are to be excluded from the trend fitting procedure. The analysis of simulated COVID-19 outbreaks suggests ASMODEE compares favourably with a state-of-art outbreak-detection algorithm while being simpler and more flexible. As such, our method could be of wider use for infectious disease surveillance. We illustrate ASMODEE using publicly available data of National Health Service (NHS) Pathways reporting potential COVID-19 cases in England at a fine spatial scale, showing that the method would have enabled the early detection of the flare-ups in Leicester and Blackburn with Darwen, two to three weeks before their respective lockdown. ASMODEE is implemented in the free R package trendbreaker. This article is part of the theme issue 'Modelling that shaped the early COVID-19 pandemic response in the UK'.

Exploiting Scanning Surveillance Data to Inform Future Strategies for the Control of Endemic Diseases: The Example of Sheep Scab

Scanning surveillance facilitates the monitoring of many endemic diseases of livestock in Great Britain, including sheep scab, an ectoparasitic disease of major welfare and economic burden. There is, however, a drive to improve the cost-effectiveness of animal health surveillance, for example by thoroughly exploiting existing data sources. By analysing the Veterinary Investigation Diagnosis Analysis (VIDA) database, this study aimed to enhance the use of existing scanning surveillance data for sheep scab to identify current trends, highlighting geographical "hotspots" for targeted disease control measures, and identifying a denominator to aid the interpretation of the diagnostic count data. Furthermore, this study collated and assessed the impact of past targeted disease control initiatives using a temporal aberration detection algorithm, the Farrington algorithm, to provide an evidence base towards developing cost-effective disease control strategies. A total of 2,401 positive skin scrapes were recorded from 2003 to 2018. A statistically significant decline in the number of positive skin scrapes diagnosed (p < 0.001) occurred across the study period, and significant clustering was observed in Wales, with a maximum of 47 positive scrapes in Ceredigion in 2007. Scheduled ectoparasite tests was also identified as a potential denominator for the interpretation of positive scrapes by stakeholders. Across the study period, 11 national disease control initiatives occurred: four in Wales, three in England, and four in Scotland. The majority (n = 8) offered free diagnostic testing while the remainder involved knowledge transfer either combined with free testing or skills training and the introduction of the Sheep Scab (Scotland) Order 2010. The Farrington algorithm raised 20 alarms of which 11 occurred within a period of free testing in Wales and one following the introduction of the Sheep Scab (Scotland) Order 2010. In summary, our analysis of the VIDA database has greatly enhanced our knowledge of sheep scab in Great Britain, firstly by identifying areas for targeted action and secondly by offering a framework to measure the impact of future disease control initiatives. Importantly this framework could be applied to inform future strategies for the control of other endemic diseases.

Risk Diagrams Based on Primary Care Electronic Medical Records and Linked Real-Time PCR Data to Monitor Local COVID-19 Outbreaks During the Summer 2020: A Prospective Study Including 7,671,862 People in Catalonia

Monitoring transmission is a prerequisite for containing COVID-19. We report on effective potential growth (EPG) as a novel measure for the early identification of local outbreaks based on primary care electronic medical records (EMR) and PCR-confirmed cases. Secondly, we studied whether increasing EPG precedes local hospital and intensive care (ICU) admissions and mortality. Population-based cohort including all Catalan citizens' PCR tests, hospitalization, intensive care (ICU) and mortality between 1/07/2020 and 13/09/2020; linked EMR covering 88.6% of the Catalan population was obtained. Nursing home residents were excluded. COVID-19 counts were ascertained based on EMR and PCRs separately. Weekly empirical propagation (ρ₇) and 14-day cumulative incidence (A₁₄) and 95% confidence intervals were estimated at care management area (CMA) level, and combined as EPG = ρ₇ × A₁₄. Overall, 7,607,201 and 6,798,994 people in 43 CMAs were included for PCR and EMR measures, respectively. A14, ρ₇, and EPG increased in numerous CMAs during summer 2020. EMR identified 2.70-fold more cases than PCRs, with similar trends, a median (interquartile range) 2 (1) days earlier, and better precision. Upticks in EPG preceded increases in local hospital admissions, ICU occupancy, and mortality. Increasing EPG identified localized outbreaks in Catalonia, and preceded local hospital and ICU admissions and subsequent mortality. EMRs provided similar estimates to PCR, but some days earlier and with better precision. EPG is a useful tool for the monitoring of community transmission and for the early identification of COVID-19 local outbreaks.

Glossary for public health surveillance in the age of data science

Public health surveillance is the ongoing systematic collection, analysis and interpretation of data, closely integrated with the timely dissemination of the resulting information to those responsible for preventing and controlling disease and injury. With the rapid development of data science, encompassing big data and artificial intelligence, and with the exponential growth of accessible and highly heterogeneous health-related data, from healthcare providers to user-generated online content, the field of surveillance and health monitoring is changing rapidly. It is, therefore, the right time for a short glossary of key terms in public health surveillance, with an emphasis on new data-science developments in the field.

Community perspectives on the benefits and risks of technologically enhanced communicable disease surveillance systems: a report on four community juries

Background

Outbreaks of infectious disease cause serious and costly health and social problems. Two new technologies – pathogen whole genome sequencing (WGS) and Big Data analytics – promise to improve our capacity to detect and control outbreaks earlier, saving lives and resources. However, routinely using these technologies to capture more detailed and specific personal information could be perceived as intrusive and a threat to privacy.

Method

Four community juries were convened in two demographically different Sydney municipalities and two regional cities in New South Wales, Australia (western Sydney, Wollongong, Tamworth, eastern Sydney) to elicit the views of well-informed community members on the acceptability and legitimacy of:

making pathogen WGS and linked administrative data available for public health research

using this information in concert with data linkage and machine learning to enhance communicable disease surveillance systems

Fifty participants of diverse backgrounds, mixed genders and ages were recruited by random-digit-dialling and topic-blinded social-media advertising. Each jury was presented with balanced factual evidence supporting different expert perspectives on the potential benefits and costs of technologically enhanced public health research and communicable disease surveillance and given the opportunity to question experts.

Results

Almost all jurors supported data linkage and WGS on routinely collected patient isolates for the purposes of public health research, provided standard de-identification practices were applied. However, allowing this information to be operationalised as a syndromic surveillance system was highly contentious with three juries voting in favour, and one against by narrow margins. For those in favour, support depended on several conditions related to system oversight and security being met. Those against were concerned about loss of privacy and did not trust Australian governments to run secure and effective systems.

Conclusions

Participants across all four events strongly supported the introduction of data linkage and pathogenomics to public health research under current research governance structures. Combining pathogen WGS with event-based data surveillance systems, however, is likely to be controversial because of a lack of public trust, even when the potential public health benefits are clear. Any suggestion of private sector involvement or commercialisation of WGS or surveillance data was unanimously rejected.

Forecasting the Prevalence of Diabetes Mellitus Using Econometric Models

INTRODUCTION

The prevalence of diabetes in Kazakhstan has reached epidemic proportions, and this disease is becoming a major financial burden. In this research, regression analysis methods were employed to build models for predicting the number of diabetic patients in Kazakhstan in 2019, as this should aid the costing and policy-making performed by medical institutions and governmental offices regarding diabetes prevention and treatment strategies.

METHODS

A brief review of mathematical models that are potentially useful for the task of interest was performed, and the most suitable methods for building predictive models were selected. The chosen models were applied to explore the correlation between population growth and the number of patients with diabetes as well as the correlation between the increase in gross regional product and the growth in the number of patients with diabetes. Moreover, the relationship of population growth and gross domestic product with the growth in the number of patients with diabetes in Kazakhstan was determined. Our research made use of the scikit-learn library for the Python programming language and functions for regression analysis built into the Microsoft Excel software.

RESULTS

The predictive models indicated that the prevalence of diabetes in Kazakhstan will increase in 2019.

CONCLUSION

Mathematical models were used to find patterns in a comprehensive statistical dataset on registered diabetes patients in Kazakhstan over the last 15 years, and these patterns were then used to build models that can accurately predict the prevalence of diabetes in Kazakhstan.