Dataset Information

Optimal triage for COVID-19 patients under limited healthcare resources: Development of a parsimonious machine learning prediction model and threshold optimization using discrete-event simulation.

ABSTRACT:

Background

The coronavirus disease 2019 (COVID-19) pandemic has placed an unprecedented burden on healthcare systems.

Objective

To effectively triage COVID-19 patients within situations of limited data availability and to explore optimal thresholds to minimize mortality rates while maintaining healthcare system capacity.

Methods

A nationwide sample of 5,601 patients confirmed for COVID-19 up until April 2020 was retrospectively reviewed. XGBoost and logistic regression analysis were used to develop prediction models for the maximum clinical severity during hospitalization, classified according to the WHO Ordinal Scale for Clinical Improvement (OSCI). The recursive feature elimination technique was used to evaluate maintenance of the model performance when clinical and laboratory variables were eliminated. Using populations based on hypothetical patient influx scenarios, discrete-event simulation was performed to find an optimal threshold within limited resource environments that minimizes mortality rates.

Results

The cross-validated area under the receiver operating characteristics (AUROC) of the baseline XGBoost model that utilized all 37 variables was 0.965 for OSCI ≥ 6. Compared to the baseline model's performance, the AUROC of the feature-eliminated model that utilized 17 variables was maintained at 0.963 with statistical insignificance. Optimal thresholds were found to minimize mortality rates in a hypothetical patient influx scenario. The benefit of utilizing an optimal triage threshold was clear, reducing mortality up to 18.1%, compared to the conventional Youden Index.

Conclusions

Our adaptive triage model and its threshold optimization capability revealed that COVID-19 management can be achieved via the cooperation of both medical and healthcare management sectors for maximum treatment efficacy. The model is available online for clinical implementation.

Clinicaltrial

SUBMITTER: Kim JM

PROVIDER: S-EPMC8565604 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background. Increasing demand for provision of care to stroke survivors creates challenges for health care planners. A key concern is the optimal alignment of health care resources between provision of acute care, rehabilitation, and among different segments of rehabilitation, including inpatient rehabilitation, early supported discharge (ESD), and outpatient rehabilitation (OPR). We propose a novel application of discrete event simulation (DES) combined with a genetic algorithm (GA) to identify the optimal configuration of rehabilitation that maximizes patient benefits subject to finite health care resources. Design. Our stroke rehabilitation optimal model (sROM) combines DES and GA to identify an optimal solution that minimizes wait time for each segment of rehabilitation by changing care capacity across different segments. sROM is initiated by generating parameters for DES. GA is used to evaluate wait time from DES. If wait time meets specified stopping criteria, the search process stops at a point at which optimal capacity is reached. If not, capacity estimates are updated, and an additional iteration of the DES is run. To parameterize the model, we standardized real-world data from medical records by fitting them into probability distributions. A meta-analysis was conducted to determine the likelihood of stroke survivors flowing across rehabilitation segments. Results. We predict that rehabilitation planners in Alberta, Canada, have the potential to improve services by increasing capacity from 75 to 113 patients per day for ESD and from 101 to 143 patients per day for OPR. Compared with the status quo, optimal capacity would provide ESD to 138 (s = 29.5) more survivors and OPR to 262 (s = 45.5) more annually while having an estimated net annual cost savings of $25.45 (s = 15.02) million. Conclusions. The combination of DES and GA can be used to estimate optimal service capacity.HighlightsWe created a hybrid model combining a genetic algorithm and discrete event simulation to search for the optimal configuration of health care service capacity that maximizes patient outcomes subject to finite health system resources.We applied a probability distribution fitting process to standardize real-world data to probability distributions. The process consists of choosing the distribution type and estimating the parameters of that distribution that best reflects the data. Standardizing real-word data to a best-fitted distribution can increase model generalizability.In an illustrative study of stroke rehabilitation care, resource allocation to stroke rehabilitation services under an optimal configuration allows provision of care to more stroke survivors who need services while reducing wait time.Resources needed to expand rehabilitation services could be reallocated from the savings due to reduced wait time in acute care units. In general, the predicted optimal configuration of stroke rehabilitation services is associated with a net cost savings to the health care system.

Project description:It is recognized that the study of the disaster medical response (DMR) is a relatively new field. To date, there is no evidence-based literature that clearly defines the best medical response principles, concepts, structures and processes in a disaster setting. Much of what is known about the DMR results from descriptive studies and expert opinion. No experimental studies regarding the effects of DMR interventions on the health outcomes of disaster survivors have been carried out. Traditional analytic methods cannot fully capture the flow of disaster victims through a complex disaster medical response system (DMRS). Computer modelling and simulation enable to study and test operational assumptions in a virtual but controlled experimental environment. The SIMEDIS (Simulation for the assessment and optimization of medical disaster management) simulation model consists of 3 interacting components: the victim creation model, the victim monitoring model where the health state of each victim is monitored and adapted to the evolving clinical conditions of the victims, and the medical response model, where the victims interact with the environment and the resources at the disposal of the healthcare responders. Since the main aim of the DMR is to minimize as much as possible the mortality and morbidity of the survivors, we designed a victim-centred model in which the casualties pass through the different components and processes of a DMRS. The specificity of the SIMEDIS simulation model is the fact that the victim entities evolve in parallel through both the victim monitoring model and the medical response model. The interaction between both models is ensured through a time or medical intervention trigger. At each service point, a triage is performed together with a decision on the disposition of the victims regarding treatment and/or evacuation based on a priority code assigned to the victim and on the availability of resources at the service point. The aim of the case study is to implement the SIMEDIS model to the DMRS of an international airport and to test the medical response plan to an airplane crash simulation at the airport. In order to identify good response options, the model then was used to study the effect of a number of interventional factors on the performance of the DMRS. Our study reflects the potential of SIMEDIS to model complex systems, to test different aspects of DMR, and to be used as a tool in experimental research that might make a substantial contribution to provide the evidence base for the effectiveness and efficiency of disaster medical management.