A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic.

Innovative applications of artificial intelligence in zoonotic disease management

Zoonotic diseases, transmitted between humans and animals, pose a substantial threat to global public health. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the fight against diseases. This comprehensive review discusses the innovative applications of AI in the management of zoonotic diseases, including disease prediction, early diagnosis, drug development, and future prospects. AI-driven predictive models leverage extensive datasets to predict disease outbreaks and transmission patterns, thereby facilitating proactive public health responses. Early diagnosis benefits from AI-powered diagnostic tools that expedite pathogen identification and containment. Furthermore, AI technologies have accelerated drug discovery by identifying potential drug targets and optimizing candidate drugs. This review addresses these advancements, while also examining the promising future of AI in zoonotic disease control. We emphasize the pivotal role of AI in revolutionizing our approach to managing zoonotic diseases and highlight its potential to safeguard the health of both humans and animals on a global scale.

A fairness assessment of mobility-based COVID-19 case prediction models

In light of the outbreak of COVID-19, analyzing and measuring human mobility has become increasingly important. A wide range of studies have explored spatiotemporal trends over time, examined associations with other variables, evaluated non-pharmacologic interventions (NPIs), and predicted or simulated COVID-19 spread using mobility data. Despite the benefits of publicly available mobility data, a key question remains unanswered: are models using mobility data performing equitably across demographic groups? We hypothesize that bias in the mobility data used to train the predictive models might lead to unfairly less accurate predictions for certain demographic groups. To test our hypothesis, we applied two mobility-based COVID infection prediction models at the county level in the United States using SafeGraph data, and correlated model performance with sociodemographic traits. Findings revealed that there is a systematic bias in models' performance toward certain demographic characteristics. Specifically, the models tend to favor large, highly educated, wealthy, young, and urban counties. We hypothesize that the mobility data currently used by many predictive models tends to capture less information about older, poorer, less educated and people from rural regions, which in turn negatively impacts the accuracy of the COVID-19 prediction in these areas. Ultimately, this study points to the need of improved data collection and sampling approaches that allow for an accurate representation of the mobility patterns across demographic groups.

Forecasting COVID-19 spreading through an ensemble of classical and machine learning models: Spain's case study

In this work the applicability of an ensemble of population and machine learning models to predict the evolution of the COVID-19 pandemic in Spain is evaluated, relying solely on public datasets. Firstly, using only incidence data, we trained machine learning models and adjusted classical ODE-based population models, especially suited to capture long term trends. As a novel approach, we then made an ensemble of these two families of models in order to obtain a more robust and accurate prediction. We then proceed to improve machine learning models by adding more input features: vaccination, human mobility and weather conditions. However, these improvements did not translate to the overall ensemble, as the different model families had also different prediction patterns. Additionally, machine learning models degraded when new COVID variants appeared after training. We finally used Shapley Additive Explanation values to discern the relative importance of the different input features for the machine learning models' predictions. The conclusion of this work is that the ensemble of machine learning models and population models can be a promising alternative to SEIR-like compartmental models, especially given that the former do not need data from recovered patients, which are hard to collect and generally unavailable.

Network Biology and Medicine to Rescue: Applications for Retinal Disease Mechanisms and Therapy

Inherited retinal degenerations (IRDs) are clinically and genetically heterogenous blinding diseases that manifest through dysfunction of target cells, photoreceptors, and retinal pigment epithelium (RPE) in the retina. Despite knowledge of numerous underlying genetic defects, current therapeutic approaches, including gene centric applications, have had limited success, thereby asserting the need of new directions for basic and translational research. Human diseases have commonalities that can be represented in a network form, called diseasome, which captures relationships among disease genes, proteins, metabolites, and patient meta-data. Clinical and genetic information of IRDs suggest shared relationships among pathobiological factors, making these a model case for network medicine. Characterization of the diseasome would considerably improve our understanding of retinal pathologies and permit better design of targeted therapies for disrupted regions within the integrated disease network. Network medicine in synergy with the ongoing artificial intelligence revolution can boost therapeutic developments, especially gene agnostic treatment opportunities.

On the accuracy of Covid-19 forecasting methods in Russia for two years

The effectiveness of predicting the dynamics of the coronavirus pandemic for Russia as a whole and for Moscow is studied for a two-year period beginning March 2020. The comparison includes well-proven population models and statistic methods along with a new data-driven model based on the LSTM neural network. The latter model is trained on a set of Russian regions simultaneously, and predicts the total number of cases on the 14-day forecast horizon. Prediction accuracy is estimated by the mean absolute percent error (MAPE). The results show that all the considered models, both simple and more complex, have similar efficiency. The lowest error achieved is 18% MAPE for Moscow and 8% MAPE for Russia.

National and subnational short-term forecasting of COVID-19 in Germany and Poland during early 2021

Background

During the COVID-19 pandemic there has been a strong interest in forecasts of the short-term development of epidemiological indicators to inform decision makers. In this study we evaluate probabilistic real-time predictions of confirmed cases and deaths from COVID-19 in Germany and Poland for the period from January through April 2021.

Methods

We evaluate probabilistic real-time predictions of confirmed cases and deaths from COVID-19 in Germany and Poland. These were issued by 15 different forecasting models, run by independent research teams. Moreover, we study the performance of combined ensemble forecasts. Evaluation of probabilistic forecasts is based on proper scoring rules, along with interval coverage proportions to assess calibration. The presented work is part of a pre-registered evaluation study.

Results

We find that many, though not all, models outperform a simple baseline model up to four weeks ahead for the considered targets. Ensemble methods show very good relative performance. The addressed time period is characterized by rather stable non-pharmaceutical interventions in both countries, making short-term predictions more straightforward than in previous periods. However, major trend changes in reported cases, like the rebound in cases due to the rise of the B.1.1.7 (Alpha) variant in March 2021, prove challenging to predict.

Conclusions

Multi-model approaches can help to improve the performance of epidemiological forecasts. However, while death numbers can be predicted with some success based on current case and hospitalization data, predictability of case numbers remains low beyond quite short time horizons. Additional data sources including sequencing and mobility data, which were not extensively used in the present study, may help to improve performance.

We compare forecasts of weekly case and death numbers for COVID-19 in Germany and Poland based on 15 different modelling approaches. These cover the period from January to April 2021 and address numbers of cases and deaths one and two weeks into the future, along with the respective uncertainties. We find that combining different forecasts into one forecast can enable better predictions. However, case numbers over longer periods were challenging to predict. Additional data sources, such as information about different versions of the SARS-CoV-2 virus present in the population, might improve forecasts in the future.

Bracher et al. compare 15 forecasting models of COVID-19 cases and deaths in Germany and Poland between January and mid-April 2021. Many, though not all, models outperform a simple baseline model up to four weeks ahead, with ensemble methods showing very good relative performance.

Explanation of hand, foot, and mouth disease cases in Japan using Google Trends before and during the COVID-19: infodemiology study

Background

Coronavirus Disease 2019 (COVID-19) pandemic affects common diseases, but its impact on hand, foot, and mouth disease (HFMD) is unclear. Google Trends data is beneficial for approximate real-time statistics and because of ease in access, is expected to be used for infection explanation from an information-seeking behavior perspective. We aimed to explain HFMD cases before and during COVID-19 using Google Trends.

Methods

HFMD cases were obtained from the National Institute of Infectious Diseases, and Google search data from 2009 to 2021 in Japan were downloaded from Google Trends. Pearson correlation coefficients were calculated between HFMD cases and the search topic “HFMD” from 2009 to 2021. Japanese tweets containing “HFMD” were retrieved to select search terms for further analysis. Search terms with counts larger than 1000 and belonging to ranges of infection sources, susceptible sites, susceptible populations, symptoms, treatment, preventive measures, and identified diseases were retained. Cross-correlation analyses were conducted to detect lag changes between HFMD cases and search terms before and during the COVID-19 pandemic. Multiple linear regressions with backward elimination processing were used to identify the most significant terms for HFMD explanation.

Results

HFMD cases and Google search volume peaked around July in most years, excluding 2020 and 2021. The search topic “HFMD” presented strong correlations with HFMD cases, except in 2020 when the COVID-19 outbreak occurred. In addition, the differences in lags for 73 (72.3%) search terms were negative, which might indicate increasing public awareness of HFMD infections during the COVID-19 pandemic. The results of multiple linear regression demonstrated that significant search terms contained the same meanings but expanded informative search content during the COVID-19 pandemic.

Conclusions

The significant terms for the explanation of HFMD cases before and during COVID-19 were different. Awareness of HFMD infections in Japan may have improved during the COVID-19 pandemic. Continuous monitoring is important to promote public health and prevent resurgence. The public interest reflected in information-seeking behavior can be helpful for public health surveillance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07790-9.

The projections of global and regional rheumatic heart disease burden from 2020 to 2030

Background

Rheumatic heart disease (RHD) remains the leading cause of preventable death and disability in children and young adults, killing an estimated 320,000 individuals worldwide yearly.

Materials and methods

We utilized the Bayesian age-period cohort (BAPC) model to project the change in disease burden from 2020 to 2030 using the data from the Global Burden of Disease (GBD) Study 2019. Then we described the projected epidemiological characteristics of RHD by region, sex, and age.

Results

The global age-standardized prevalence rate (ASPR) and age-standardized incidence rate (ASIR) of RHD increased from 1990 to 2019, and ASPR will increase to 559.88 per 100,000 population by 2030. The global age-standardized mortality rate (ASMR) of RHD will continue declining, while the projected death cases will increase. Furthermore, ASPR and cases of RHD-associated HF will continue rising, and there will be 2,922,840 heart failure (HF) cases in 2030 globally. Female subjects will still be the dominant population compared to male subjects, and the ASPR of RHD and the ASPR of RHD-associated HF in female subjects will continue to increase from 2020 to 2030. Young people will have the highest ASPR of RHD among all age groups globally, while the elderly will bear a greater death and HF burden.

Conclusion

In the following decade, the RHD burden will remain severe. There are large variations in the trend of RHD burden by region, sex, and age. Targeted and effective strategies are needed for the management of RHD, particularly in female subjects and young people in developing regions.

Algorithmic fairness in pandemic forecasting: lessons from COVID-19

Racial and ethnic minorities have borne a particularly acute burden of the COVID-19 pandemic in the United States. There is a growing awareness from both researchers and public health leaders of the critical need to ensure fairness in forecast results. Without careful and deliberate bias mitigation, inequities embedded in data can be transferred to model predictions, perpetuating disparities, and exacerbating the disproportionate harms of the COVID-19 pandemic. These biases in data and forecasts can be viewed through both statistical and sociological lenses, and the challenges of both building hierarchical models with limited data availability and drawing on data that reflects structural inequities must be confronted. We present an outline of key modeling domains in which unfairness may be introduced and draw on our experience building and testing the Google-Harvard COVID-19 Public Forecasting model to illustrate these challenges and offer strategies to address them. While targeted toward pandemic forecasting, these domains of potentially biased modeling and concurrent approaches to pursuing fairness present important considerations for equitable machine-learning innovation.

Analyzing Patient Trajectories With Artificial Intelligence

In digital medicine, patient data typically record health events over time (eg, through electronic health records, wearables, or other sensing technologies) and thus form unique patient trajectories. Patient trajectories are highly predictive of the future course of diseases and therefore facilitate effective care. However, digital medicine often uses only limited patient data, consisting of health events from only a single or small number of time points while ignoring additional information encoded in patient trajectories. To analyze such rich longitudinal data, new artificial intelligence (AI) solutions are needed. In this paper, we provide an overview of the recent efforts to develop trajectory-aware AI solutions and provide suggestions for future directions. Specifically, we examine the implications for developing disease models from patient trajectories along the typical workflow in AI: problem definition, data processing, modeling, evaluation, and interpretation. We conclude with a discussion of how such AI solutions will allow the field to build robust models for personalized risk scoring, subtyping, and disease pathway discovery.