From predictions to prescriptions: A data-driven response to COVID-19

Integrating artificial intelligence with mechanistic epidemiological modeling: a scoping review of opportunities and challenges

Integrating prior epidemiological knowledge embedded within mechanistic models with the data-mining capabilities of artificial intelligence (AI) offers transformative potential for epidemiological modeling. While the fusion of AI and traditional mechanistic approaches is rapidly advancing, efforts remain fragmented. This scoping review provides a comprehensive overview of emerging integrated models applied across the spectrum of infectious diseases. Through systematic search strategies, we identified 245 eligible studies from 15,460 records. Our review highlights the practical value of integrated models, including advances in disease forecasting, model parameterization, and calibration. However, key research gaps remain. These include the need for better incorporation of realistic decision-making considerations, expanded exploration of diverse datasets, and further investigation into biological and socio-behavioral mechanisms. Addressing these gaps will unlock the synergistic potential of AI and mechanistic modeling to enhance understanding of disease dynamics and support more effective public health planning and response.

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis

Proactive analysis of patient pathways helps healthcare providers anticipate treatment-related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient's complete health history to make informed decisions about future events. However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for clinicians to apply such models. Our work introduces PatWay-Net, an ML framework designed for interpretable predictions of admission to the intensive care unit (ICU) for patients with symptoms of sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks. Our evaluation includes both predictive performance - where PatWay-Net outperforms standard models such as decision trees, random forests, and gradient-boosted decision trees - and clinical utility, validated through structured interviews with clinicians. By providing improved predictive accuracy along with interpretable and actionable insights, PatWay-Net serves as a valuable tool for healthcare decision support in the critical case of patients with symptoms of sepsis.

Changing US Support for Public Health Data Use Through Pandemic and Political Turmoil

Policy Points This study examines the impact of several world-changing events in 2020, such as the pandemic and widespread racism protests, on the US population's comfort with the use of identifiable data for public health. Before the 2020 election, there was no significant difference between Democrats and Republicans. However, African Americans exhibited a decrease in comfort that was different from other subgroups. Our findings suggest that the public remained supportive of public health data activities through the pandemic and the turmoil of 2020 election cycle relative to other data use. However, support among African Americans for public health data use experienced a unique decline compared to other demographic groups.

CONTEXT

Recent legislative privacy efforts have not included special provisions for public health data use. Although past studies documented support for public health data use, several global events in 2020 have raised awareness and concern about privacy and data use. This study aims to understand whether the events of 2020 affected US privacy preferences on secondary uses of identifiable data, focusing on public health and research uses.

METHODS

We deployed two online surveys-in February and November 2020-on data privacy attitudes and preferences using a choice-based-conjoint analysis. Participants received different data-use scenario pairs-varied by the type of data, user, and purpose-and selected scenarios based on their comfort. A hierarchical Bayes regression model simulated population preferences.

FINDINGS

There were 1,373 responses. There was no statistically significant difference in the population's data preferences between February and November, each showing the highest comfort with population health and research data activities and the lowest with profit-driven activities. Most subgroups' data preferences were comparable with the population's preferences, except African Americans who showed significant decreases in comfort with population health and research.

CONCLUSIONS

Despite world-changing events, including a pandemic, we found bipartisan public support for using identifiable data for public health and research. The decreasing support among African Americans could relate to the increased awareness of systemic racism, its harms, and persistent disparities. The US population's preferences support including legal provisions that permit public health and research data use in US laws, which are currently lacking specific public health use permissions.

Integrating socio-economic vulnerability factors improves neighborhood-scale wastewater-based epidemiology for public health applications

Wastewater Based Epidemiology (WBE) of COVID-19 is a low-cost, non-invasive, and inclusive early warning tool for disease spread. Previously studied WBE focused on sampling at wastewater treatment plant scale, limiting the level at which demographic and geographic variations in disease dynamics can be incorporated into the analysis of certain neighborhoods. This study demonstrates the integration of demographic mapping to improve the WBE of COVID-19 and associated post-COVID disease prediction (here kidney disease) at the neighborhood level using machine learning. WBE was conducted at six neighborhoods in Seattle during October 2020 - February 2022. Wastewater processing and RT-qPCR were performed to obtain SARS-CoV-2 RNA concentration. Census data, clinical data of COVID-19, as well as patient data of acute kidney injury (AKI) cases reported during the study period were collected and the distribution across the city was studied using Geographic Information System (GIS) mapping. Further, we analyzed the data set to better understand socioeconomic impacts on disease prevalence of COVID-19 and AKI per neighborhood. The heterogeneity of eleven demographic factors (such as education and age among others) was observed within neighborhoods across the city of Seattle. Dynamics of COVID-19 clinical cases and wastewater SARS-CoV-2 varied across neighborhood with different levels of demographics. Machine learning models trained with data from the earlier stages of the pandemic were able to predict both COVID-19 and AKI incidence in the later stages of the pandemic (Spearman correlation coefficient of 0·546 - 0·904), with the most predictive model trained on the combination of wastewater data and demographics. The integration of demographics strengthened machine learning models' capabilities to predict prevalence of COVID-19, and of AKI as a marker for post-COVID sequelae. Demographic-based WBE presents an effective tool to monitor and manage public health beyond COVID-19 at the neighborhood level.

Predicting the spread of SARS-CoV-2 variants: An artificial intelligence enabled early detection

During more than 3 years since its emergence, SARS-CoV-2 has shown great ability to mutate rapidly into diverse variants, some of which turned out to be very infectious and have spread throughout the world causing waves of infections. At this point, many countries have already experienced up to six waves of infections. Extensive academic work has focused on the development of models to predict the pandemic trajectory based on epidemiological data, but none has focused on predicting variant-specific spread. Moreover, important scientific literature analyzes the genetic evolution of SARS-CoV-2 variants and how it might functionally affect their infectivity. However, genetic attributes have not yet been incorporated into existing epidemiological modeling that aims to capture infection trajectory. Thus, this study leverages variant-specific genetic characteristics together with epidemiological information to systematically predict the future spread trajectory of newly detected variants. The study describes the analysis of 9.0 million SARS-CoV-2 genetic sequences in 30 countries and identifies temporal characteristic patterns of SARS-CoV-2 variants that caused significant infection waves. Using this descriptive analysis, a machine-learning-enabled risk assessment model has been developed to predict, as early as 1 week after their first detection, which variants are likely to constitute the new wave of infections in the following 3 months. The model's out-of-sample area under the curve (AUC) is 86.3% for predictions after 1 week and 90.8% for predictions after 2 weeks. The methodology described in this paper could contribute more broadly to the development of improved predictive models for variants of other infectious viruses.

Covid-19 triage in the emergency department 2.0: how analytics and AI transform a human-made algorithm for the prediction of clinical pathways

The Covid-19 pandemic has pushed many hospitals to their capacity limits. Therefore, a triage of patients has been discussed controversially primarily through an ethical perspective. The term triage contains many aspects such as urgency of treatment, severity of the disease and pre-existing conditions, access to critical care, or the classification of patients regarding subsequent clinical pathways starting from the emergency department. The determination of the pathways is important not only for patient care, but also for capacity planning in hospitals. We examine the performance of a human-made triage algorithm for clinical pathways which is considered a guideline for emergency departments in Germany based on a large multicenter dataset with over 4,000 European Covid-19 patients from the LEOSS registry. We find an accuracy of 28 percent and approximately 15 percent sensitivity for the ward class. The results serve as a benchmark for our extensions including an additional category of palliative care as a new label, analytics, AI, XAI, and interactive techniques. We find significant potential of analytics and AI in Covid-19 triage regarding accuracy, sensitivity, and other performance metrics whilst our interactive human-AI algorithm shows superior performance with approximately 73 percent accuracy and up to 76 percent sensitivity. The results are independent of the data preparation process regarding the imputation of missing values or grouping of comorbidities. In addition, we find that the consideration of an additional label palliative care does not improve the results.

Data Science Implementation Trends in Nursing Practice: A Review of the 2021 Literature

OBJECTIVES

The goal of this work was to provide a review of the implementation of data science-driven applications focused on structural or outcome-related nurse-sensitive indicators in the literature in 2021. By conducting this review, we aim to inform readers of trends in the nursing indicators being addressed, the patient populations and settings of focus, and lessons and challenges identified during the implementation of these tools.

METHODS

We conducted a rigorous descriptive review of the literature to identify relevant research published in 2021. We extracted data on model development, implementation-related strategies and measures, lessons learned, and challenges and stakeholder involvement. We also assessed whether reports of data science application implementations currently follow the guidelines of the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by AI (DECIDE-AI) framework.

RESULTS

Of 4,943 articles found in PubMed (NLM) and CINAHL (EBSCOhost), 11 were included in the final review and data extraction. Systems leveraging data science were developed for adult patient populations and were primarily deployed in hospital settings. The clinical domains targeted included mortality/deterioration, utilization/resource allocation, and hospital-acquired infections/COVID-19. The composition of development teams and types of stakeholders involved varied. Research teams more frequently reported on implementation methods than implementation results. Most studies provided lessons learned that could help inform future implementations of data science systems in health care.

CONCLUSION

In 2021, very few studies report on the implementation of data science-driven applications focused on structural- or outcome-related nurse-sensitive indicators. This gap in the sharing of implementation strategies needs to be addressed in order for these systems to be successfully adopted in health care settings.

Modeling social, economic, and health perspectives for optimal pandemic policy decision-making

While different control strategies in the early stages of the COVID-19 pandemic have helped decrease the number of infections, these strategies have had an adverse economic impact on businesses. Therefore, optimal timing and scale of closure and reopening strategies are required to prevent both different waves of the pandemic and the negative economic impact of control strategies. This paper proposes a novel multi-objective mixed-integer linear programming (MOMILP) formulation, which results in the optimal timing of closure and reopening of states and industries in each state to mitigate the economic and epidemiological impact of a pandemic. The three objectives being pursued include: (i) the epidemiological impact, (ii) the economic impact on the local businesses, and (iii) the economic impact on the trades between industries. The proposed model is implemented on a dataset that includes 11 states, the District of Columbia, and 19 industries in the US. The solved by augmented ε-constraint approach is used to solve the multi-objective model, and a final strategy is selected from the set of Pareto-optimal solutions based on the least cubic distance of the solution from the optimal value of each objective. The Pareto-optimal solutions suggest that for any control decision (state and industry closure or reopening), the economic impact and the epidemiological impact change in the opposite direction, and it is more effective to close most states while keeping the majority of industries open during the planning horizon.

A multistate model and its standalone tool to predict hospital and ICU occupancy by patients with COVID-19

Objective

This study aims to build a multistate model and describe a predictive tool for estimating the daily number of intensive care unit (ICU) and hospital beds occupied by patients with coronavirus 2019 disease (COVID-19).

Material and methods

The estimation is based on the simulation of patient trajectories using a multistate model where the transition probabilities between states are estimated via competing risks and cure models. The input to the tool includes the dates of COVID-19 diagnosis, admission to hospital, admission to ICU, discharge from ICU and discharge from hospital or death of positive cases from a selected initial date to the current moment. Our tool is validated using 98,496 cases positive for severe acute respiratory coronavirus 2 extracted from the Aragón Healthcare Records Database from July 1, 2020 to February 28, 2021.

Results

The tool demonstrates good performance for the 7- and 14-days forecasts using the actual positive cases, and shows good accuracy among three scenarios corresponding to different stages of the pandemic: 1) up-scenario, 2) peak-scenario and 3) down-scenario. Long term predictions (two months) also show good accuracy, while those using Holt-Winters positive case estimates revealed acceptable accuracy to day 14 onwards, with relative errors of 8.8%.

Discussion

In the era of the COVID-19 pandemic, hospitals must evolve in a dynamic way. Our prediction tool is designed to predict hospital occupancy to improve healthcare resource management without information about clinical history of patients.

Conclusions

Our easy-to-use and freely accessible tool (https://github.com/peterman65) shows good performance and accuracy for forecasting the daily number of hospital and ICU beds required for patients with COVID-19.

COVID-19: Data-Driven optimal allocation of ventilator supply under uncertainty and risk

This study presents a new risk-averse multi-stage stochastic epidemics-ventilator-logistics compartmental model to address the resource allocation challenges of mitigating COVID-19. This epidemiological logistics model involves the uncertainty of untested asymptomatic infections and incorporates short-term human migration. Disease transmission is also forecasted through a new formulation of transmission rates that evolve over space and time with respect to various non-pharmaceutical interventions, such as wearing masks, social distancing, and lockdown. The proposed multi-stage stochastic model overviews different scenarios on the number of asymptomatic individuals while optimizing the distribution of resources, such as ventilators, to minimize the total expected number of newly infected and deceased people. The Conditional Value at Risk (CVaR) is also incorporated into the multi-stage mean-risk model to allow for a trade-off between the weighted expected loss due to the outbreak and the expected risks associated with experiencing disastrous pandemic scenarios. We apply our multi-stage mean-risk epidemics-ventilator-logistics model to the case of controlling COVID-19 in highly-impacted counties of New York and New Jersey. We calibrate, validate, and test our model using actual infection, population, and migration data. We also define a new region-based sub-problem and bounds on the problem and then show their computational benefits in terms of the optimality and relaxation gaps. The computational results indicate that short-term migration influences the transmission of the disease significantly. The optimal number of ventilators allocated to each region depends on various factors, including the number of initial infections, disease transmission rates, initial ICU capacity, the population of a geographical location, and the availability of ventilator supply. Our data-driven modeling framework can be adapted to study the disease transmission dynamics and logistics of other similar epidemics and pandemics.

Resource planning strategies for healthcare systems during a pandemic

We study resource planning strategies, including the integrated healthcare resources' allocation and sharing as well as patients' transfer, to improve the response of health systems to massive increases in demand during epidemics and pandemics. Our study considers various types of patients and resources to provide access to patient care with minimum capacity extension. Adding new resources takes time that most patients don't have during pandemics. The number of patients requiring scarce healthcare resources is uncertain and dependent on the speed of the pandemic's transmission through a region. We develop a multi-stage stochastic program to optimize various strategies for planning limited and necessary healthcare resources. We simulate uncertain parameters by deploying an agent-based continuous-time stochastic model, and then capture the uncertainty by a forward scenario tree construction approach. Finally, we propose a data-driven rolling horizon procedure to facilitate decision-making in real-time, which mitigates some critical limitations of stochastic programming approaches and makes the resulting strategies implementable in practice. We use two different case studies related to COVID-19 to examine our optimization and simulation tools by extensive computational results. The results highlight these strategies can significantly improve patient access to care during pandemics; their significance will vary under different situations. Our methodology is not limited to the presented setting and can be employed in other service industries where urgent access matters.

Exploring Latino Promotores/a de Salud (Community Health Workers) knowledge, attitudes, and perceptions of COVID-19 vaccines

Promotoras/promotores (i.e., community health workers) are uniquely positioned to provide much needed COVID-19 education and outreach in Latino communities, particularly in areas with disparities in vaccination rates. This study used qualitative methods to explore promotoras perspectives on COVID-19 vaccines, with a focus on understanding how vaccine knowledge and viewpoints among Latino communities can formulate recommendations to improve uptake of vaccination. Promotoras (N=22) were recruited to participate in semi-structured focus groups conducted virtually. Reflexive thematic analysis identified three overarching themes: (1) prevalence of misinformation (related to lack of trustworthy information, mistrust in the government, immigration status concerns, and conspiracy theories); (2) hesitancy (related to health concerns and eligibility confusion); and (3) recommendations for improving vaccine uptake. Delays in vaccination were not strictly due to doubts or fears but were also related to access barriers. The themes provide insight into the Latino communities' perceptions of COVID-19 vaccines and reasons why some remain unvaccinated. Promotoras' perspectives are integral to the development of strategies and approaches to address COVID-19 vaccine hesitancy, uptake, and implementation among underserved communities.

Multisite evaluation of prediction models for emergency department crowding before and during the COVID-19 pandemic

OBJECTIVE

To develop a machine learning framework to forecast emergency department (ED) crowding and to evaluate model performance under spatial and temporal data drift.

MATERIALS AND METHODS

We obtained 4 datasets, identified by the location: 1-large academic hospital and 2-rural hospital, and time period: pre-coronavirus disease (COVID) (January 1, 2019-February 1, 2020) and COVID-era (May 15, 2020-February 1, 2021). Our primary target was a binary outcome that is equal to 1 if the number of patients with acute respiratory illness that were ED boarding for more than 4 h was above a prescribed historical percentile. We trained a random forest and used the area under the curve (AUC) to evaluate out-of-sample performance for 2 experiments: (1) we evaluated the impact of sudden temporal drift by training models using pre-COVID data and testing them during the COVID-era, (2) we evaluated the impact of spatial drift by testing models trained at location 1 on data from location 2, and vice versa.

RESULTS

The baseline AUC values for ED boarding ranged from 0.54 (pre-COVID at location 2) to 0.81 (COVID-era at location 1). Models trained with pre-COVID data performed similarly to COVID-era models (0.82 vs 0.78 at location 1). Models that were transferred from location 2 to location 1 performed worse than models trained at location 1 (0.51 vs 0.78).

DISCUSSION AND CONCLUSION

Our results demonstrate that ED boarding is a predictable metric for ED crowding, models were not significantly impacted by temporal data drift, and any attempts at implementation must consider spatial data drift.

“A Voice to Uplift Other People”: A Case Study of Integrating Organizing Methods in an FQHC-Based COVID-19 Vaccine Initiative in Latinx Communities

The COVID-19 pandemic added another layer of trauma for working-class communities who have experienced trauma from systemic inequity and racism. Early pandemic response efforts failed to reach the most vulnerable Latinx communities in the United States due to historic disinvestment in these communities. Federally Qualified Health Centers (FQHCs) were uniquely positioned to respond to the pandemic through testing and vaccine implementation because of their footprint in these communities. However, to advance equitable COVID-19 recovery and long-term, trauma-informed community resilience, FQHCs need to expand their role beyond immediate response through testing and vaccine deployment. Applying Freirean principles of liberation to an integrated model for crisis recovery and community resilience-building, this article presents a case study of the implementation of a COVID-19 vaccine outreach and education initiative at AltaMed Health Services, one of the largest FQHCs in the United States. Findings suggest that leveraging organizing and empowerment strategies to implement COVID-19 vaccine distribution in working-class communities contributes to pathways for community health and well-being, infrastructure for crisis response and recovery, equitable service and information delivery ecosystems, and engaged and empowered communities. Lessons from this study can provide a blueprint for integrating strategies for long-term community resilience, capacity-building, and empowerment in crisis response and community harm mitigation initiatives. Findings from this study also present a model for enhancing the role of FQHCs to facilitate community organizing and engagement for health equity.

Mathematical optimization models for reallocating and sharing health equipment in pandemic situations

In this paper we provide a mathematical programming based decision tool to optimally reallocate and share equipment between different units to efficiently equip hospitals in pandemic emergency situations under lack of resources. The approach is motivated by the COVID-19 pandemic in which many Heath National Systems were not able to satisfy the demand of ventilators, sanitary individual protection equipment or different human resources. Our tool is based in two main principles: (1) Part of the stock of equipment at a unit that is not needed (in near future) could be shared to other units; and (2) extra stock to be shared among the units in a region can be efficiently distributed taking into account the demand of the units. The decisions are taken with the aim of minimizing certain measures of the non-covered demand in a region where units are structured in a given network. The mathematical programming models that we provide are stochastic and multiperiod with different robust objective functions. Since the proposed models are computationally hard to solve, we provide a divide-et-conquer math-heuristic approach. We report the results of applying our approach to the COVID-19 case in different regions of Spain, highlighting some interesting conclusions of our analysis, such as the great increase of treated patients if the proposed redistribution tool is applied.

Heterogeneous epidemic modelling within an enclosed space and corresponding Bayesian estimation

Since March 11th, 2020, COVID-19 has been a global pandemic for more than one years due to a long and infectious incubation period. This paper establishes a heterogeneous epidemic model that divides the incubation period into infectious and non-infectious and employs the Bayesian framework to model the 'Diamond Princess' enclosed space incident. The heterogeneity includes two different identities, two transmission methods, two different-size rooms, and six transmission stages. This model is also applicable to similar mixed structures, including closed schools, hospitals, and communities. As the COVID-19 pandemic continues, our mathematical modeling can provide management insights to the governments and policymakers on how the COVID-19 disease has spread and what prevention strategies still need to be taken.

Safety-Stock: Predicting the demand for supplies in Brazilian hospitals during the COVID-19 pandemic

Many challenges lie ahead when dealing with COVID-19, not only related to the acceleration of the pandemic, but also to the prediction of personal protective equipment sets consumption to accommodate the explosive demand. Due to this situation of uncertainty, hospital administration encourages the excess stock of these materials, over-stocking products in some hospitals, and provoking shortages in others. The number of available personal protective equipment sets is one of the three main factors that limit the number of patients at a hospital, as well as the number of available beds and the number of professionals per shift. In this scenario, we developed an easy-to-use expert system to predict the demand for personal protective equipment sets in hospitals during the COVID-19 pandemic, which can be updated in real-time for short term planning. For this system, we propose a naive statistical modeling which combines historical data of the consumption of personal protective equipment sets by hospitals, current protocols for their uses and epidemiological data related to the disease, to build predictive models for the demand for personal protective equipment in Brazilian hospitals during the pandemic. We then embed this modeling in the free Safety-Stock system, which provides useful information for the hospital, especially the safety-stock level and the prediction of consumption/demand for each personal protective equipment set over time. Considering our predictions, a hospital may have its needs related to specific personal protective equipment sets estimated, taking into account its historical stock levels and possible scheduled purchases. The tool allows for adopting strategies to control and keep the stock at safety levels to the demand, mitigating the risk of stock-out. As a direct consequence, it also enables the interchange and cooperation between hospitals, aiming to maximize the availability of equipment during the pandemic.

CovidVisualized: Visualized compilation of international updated models' estimates of COVID-19 pandemic at global and country levels

OBJECTIVES

To identify international and periodically updated models of the COVID-19 epidemic, compile and visualize their estimation results at the global, regional, and country levels, and periodically update the compilations. This compilation can serve as an early warning mechanism for countries about future surges in cases and deaths. When one or more models predict an increase in daily cases or infections and deaths in the next one to three months, technical advisors to the national and subnational decision-makers can consider this early alarm for assessment and suggestion of augmentation of preventive measures and interventions.

DATA DESCRIPTION

Five international and periodically updated models of the COVID-19 pandemic were identified, created by: (1) Massachusetts Institute of Technology, Cambridge, (2) Institute for Health Metrics and Evaluation, Seattle, (3) Imperial College, London, (4) Los Alamos National Laboratories, Los Alamos, and (5) University of Southern California, Los Angeles. Estimates of these five identified models were gathered, combined, and graphed at global and two country levels. Canada and Iran were chosen as countries with and without subnational estimates, respectively. Compilations of results are periodically updated. Three Github repositories were created that contain the codes and results, i.e., "CovidVisualizedGlobal" for the global and regional levels, "CovidVisualizedCountry" for a country with subnational estimates-Canada, and "covir2" for a country without subnational estimates-Iran.

CRISIS Ventilator: Pilot Study of a Three-Dimensional-Printed Gas-Powered Resuscitator in a Porcine Model

The coronavirus disease of 2019 (COVID-19) has altered medical practice around the globe and revealed critical deficiencies in hospital supply chains ranging from adequate personal protective equipment to life-sustaining ventilators for critically ill hospitalized patients. We developed the CRISIS ventilator, a gas-powered resuscitator that functions without electricity, and which can be manufactured using hobby-level three-dimensional (3D) printers and standard off-the-shelf equipment available at the local hardware store. CRISIS ventilators were printed and used to ventilate sedated female Yorkshire pigs over 24-h. Pulmonary and hemodynamic values were recorded throughout the 24-h run, and serial arterial blood samples were obtained to assess ventilation and oxygenation. Lung tissue was obtained from each pig to evaluate for signs of inflammatory stress. All five female Yorkshire pigs survived the 24-h study period without suffering from hypoxemia, hypercarbia, or severe hypotension requiring intervention. One animal required rescue at the beginning of the experiment with a traditional ventilator due to leakage around a defective tracheostomy balloon. The wet/dry ratio was 6.74 ± 0.19 compared to historical controls of 7.1 ± 4.2 (not significantly different). This proof-of-concept study demonstrates that our 3D-printed CRISIS ventilator can ventilate and oxygenate a porcine model over the course of 24-h with stable pulmonary and hemodynamic function with similar levels of ventilation-related inflammation when compared with a previous control porcine model. Our work suggests that virtual stockpiling with just-in-time 3D-printed equipment, like the CRISIS ventilator, can temporize shortages of critical infrastructure needed to sustain life for hospitalized patients.

Prognosis patients with COVID-19 using deep learning

Background

The coronavirus (COVID-19) is a novel pandemic and recently we do not have enough knowledge about the virus behaviour and key performance indicators (KPIs) to assess the mortality risk forecast. However, using a lot of complex and expensive biomarkers could be impossible for many low budget hospitals. Timely identification of the risk of mortality of COVID-19 patients (RMCPs) is essential to improve hospitals' management systems and resource allocation standards.

Methods

For the mortality risk prediction, this research work proposes a COVID-19 mortality risk calculator based on a deep learning (DL) model and based on a dataset provided by the HM Hospitals Madrid, Spain. A pre-processing strategy for unbalanced classes and feature selection is proposed. To evaluate the proposed methods, an over-sampling Synthetic Minority TEchnique (SMOTE) and data imputation approaches are introduced which is based on the K-nearest neighbour.

Results

A total of 1,503 seriously ill COVID-19 patients having a median age of 70 years old are comprised in the research work, with 927 (61.7%) males and 576 (38.3%) females. A total of 48 features are considered to evaluate the proposed method, and the following results are achieved. It includes the following values i.e., area under the curve (AUC) 0.93, F2 score 0.93, recall 1.00, accuracy, 0.95, precision 0.91, specificity 0.9279 and maximum probability of correct decision (MPCD) 0.93.

Conclusion

The results show that the proposed method is significantly best for the mortality risk prediction of patients with COVID-19 infection. The MPCD score shows that the proposed DL outperforms on every dataset when evaluating even with an over-sampling technique. The benefits of the data imputation algorithm for unavailable biomarker data are also evaluated. Based on the results, the proposed scheme could be an appropriate tool for critically ill Covid-19 patients to assess the risk of mortality and prognosis.

Perception Bias Effects on Healthcare Management in COVID-19 Pandemic: An Application of Cumulative Prospect Theory

Coronavirus disease 2019 (COVID-19) has posed severe threats to human safety in the healthcare sector, particularly in residents in long-term care facilities (LTCFs) at a higher risk of morbidity and mortality. This study aims to draw on cumulative prospect theory (CPT) to develop a decision model to explore LTCF administrators’ risk perceptions and management decisions toward this pandemic. This study employed the policy Delphi method and survey data to examine managers’ perceptions and attitudes and explore the effects of sociodemographic characteristics on healthcare decisions. The findings show that participants exhibited risk aversion for small losses but became risk-neutral when considering devastating damages. LTCF managers exhibited perception bias that led to over- and under-estimation of the occurrence of infection risk. The contextual determinants, including LTCF type, scale, and strategy, simultaneously affect leaders’ risk perception toward consequences and probabilities. Specifically, cost-leadership facilities behave in a loss-averse way, whereas hybrid-strategy LTCFs appear biased in measuring probabilities. This study is the first research that proposes a CPT model to predict administrators’ risk perception under varying mixed gain–loss circumstances involving considerations of healthcare and society in the pandemic context. This study extends the application of CPT into organizational-level decisions. The results highlight that managers counteract their perception bias and subjective estimation to avoid inappropriate decisions in healthcare operations and risk governance for a future health emergency.

A Time-Series Feature-based Recursive Classification Model to Optimize Treatment Strategies for Improving Outcomes and Resource Allocations of COVID-19 Patients

This paper presents a novel Lasso Logistic Regression model based on feature-based time series data to determine disease severity and when to administer drugs or escalate intervention procedures in patients with coronavirus disease 2019 (COVID-19). Advanced features were extracted from highly enriched and time series vital sign data of hospitalized COVID-19 patients, including oxygen saturation readings, and with a combination of patient demographic and comorbidity information, as inputs into the dynamic feature-based classification model. Such dynamic combinations brought deep insights to guide clinical decision-making of complex COVID-19 cases, including prognosis prediction, timing of drug administration, admission to intensive care units, and application of intervention procedures like ventilation and intubation. The COVID-19 patient classification model was developed utilizing 900 hospitalized COVID-19 patients in a leading multi-hospital system in Texas, United States. By providing mortality prediction based on time-series physiologic data, demographics, and clinical records of individual COVID-19 patients, the dynamic feature-based classification model can be used to improve efficacy of the COVID-19 patient treatment, prioritize medical resources, and reduce casualties. The uniqueness of our model is that it is based on just the first 24 hours of vital sign data such that clinical interventions can be decided early and applied effectively. Such a strategy could be extended to prioritize resource allocations and drug treatment for future pandemic events.

Impact of insufficient detection in COVID-19 outbreaks

The COVID-19 (novel coronavirus disease 2019) pandemic has tremendously impacted global health and economics. Early detection of COVID-19 infections is important for patient treatment and for controlling the epidemic. However, many countries/regions suffer from a shortage of nucleic acid testing (NAT) due to either resource limitations or epidemic control measures. The exact number of infective cases is mostly unknown in counties/regions with insufficient NAT, which has been a major issue in predicting and controlling the epidemic. In this paper, we propose a mathematical model to quantitatively identify the influences of insufficient detection on the COVID-19 epidemic. We extend the classical SEIR (susceptible-exposed-infections-recovered) model to include random detections which are described by Poisson processes. We apply the model to the epidemic in Guam, Texas, the Virgin Islands, and Wyoming in the United States and determine the detection probabilities by fitting model simulations with the reported number of infected, recovered, and dead cases. We further study the effects of varying the detection probabilities and show that low level-detection probabilities significantly affect the epidemic; increasing the detection probability of asymptomatic infections can effectively reduce the the scale of the epidemic. This study suggests that early detection is important for the control of the COVID-19 epidemic.

Task complexity moderates group synergy

Scientists and managers alike have been preoccupied with the question of whether and, if so, under what conditions groups of interacting problem solvers outperform autonomous individuals. Here we describe an experiment in which individuals and groups were evaluated on a series of tasks of varying complexity. We find that groups are as fast as the fastest individual and more efficient than the most efficient individual when the task is complex but not when the task is simple. We then precisely quantify synergistic gains and process losses associated with interacting groups, finding that the balance between the two depends on complexity. Our study has the potential to reconcile conflicting findings about group synergy in previous work.

Complexity—defined in terms of the number of components and the nature of the interdependencies between them—is clearly a relevant feature of all tasks that groups perform. Yet the role that task complexity plays in determining group performance remains poorly understood, in part because no clear language exists to express complexity in a way that allows for straightforward comparisons across tasks. Here we avoid this analytical difficulty by identifying a class of tasks for which complexity can be varied systematically while keeping all other elements of the task unchanged. We then test the effects of task complexity in a preregistered two-phase experiment in which 1,200 individuals were evaluated on a series of tasks of varying complexity (phase 1) and then randomly assigned to solve similar tasks either in interacting groups or as independent individuals (phase 2). We find that interacting groups are as fast as the fastest individual and more efficient than the most efficient individual for complex tasks but not for simpler ones. Leveraging our highly granular digital data, we define and precisely measure group process losses and synergistic gains and show that the balance between the two switches signs at intermediate values of task complexity. Finally, we find that interacting groups generate more solutions more rapidly and explore the solution space more broadly than independent problem solvers, finding higher-quality solutions than all but the highest-scoring individuals.

Pediatric quality measures: The leap from process to outcomes

Value-based reimbursement arrangements tie financial incentives to achieving quality measures to ensure savings are not from withholding care. For patients and their families, the delivery of high-quality care is simply the expectation. Defining and measuring pediatric quality, however, is not standardized which has led to a large proliferation of metrics across multiple stakeholders. The majority of these measures are process rather than outcomes metrics often chosen for the ease at which the data can be obtained. In order to drive greater value, outcomes measures should be preferentially selected. However, measuring outcomes in children presents multiple unique challenges. Compared to adults, children are generally healthier, their outcomes may take more time to manifest, and their clinical variability is greater. Another challenge is the amount of healthcare data being generated by providers, provider networks, payors, government agencies, and many others. This should help in understanding pediatric quality outcomes, but the massive volume of data requires new analytic tools. Artificial intelligence techniques such as machine learning offer faster, more precise, and larger scale evaluation of quality outcomes. Its implementation necessitates identifying expertise in the way of data scientists as well as additional infrastructure components to evaluate data governance, security, regulatory compliance, and ethics. Despite these prerequisites, much progress is being made in outcome insights that drive value benefiting children and families.

Effectively managing diagnostic tests to monitor the COVID-19 outbreak in Italy

Urged by the outbreak of the COVID-19 in Italy, this study aims at helping to tackle the spread of the disease by resorting to operations research techniques. In particular, we propose a mathematical program to model the problem of establishing how many diagnostic tests the Italian regions must perform in order to maximize the overall disease detection capability. An important feature of our approach is its simplicity: data we resort to are easy to obtain and one can employ standard optimization tools to address the problem. The results we obtain when applying our method to the Italian case seem promising.