skip to main content

Explore Research Products in the NSF-PAR

  • NSF Public Access
  • Search Results
  • Fitting a stochastic model of intensive care occupancy to noisy hospitalization time series during the COVID‐19 pandemic

This content will become publicly available on September 14, 2024

Title: Fitting a stochastic model of intensive care occupancy to noisy hospitalization time series during the COVID‐19 pandemic

Intensive care occupancy is an important indicator of health care stress that has been used to guide policy decisions during the COVID‐19 pandemic. Toward reliable decision‐making as a pandemic progresses, estimating the rates at which patients are admitted to and discharged from hospitals and intensive care units (ICUs) is crucial. Since individual‐level hospital data are rarely available to modelers in each geographic locality of interest, it is important to develop tools for inferring these rates from publicly available daily numbers of hospital and ICU beds occupied. We develop such an estimation approach based on an immigration‐death process that models fluctuations of ICU occupancy. Our flexible framework allows for immigration and death rates to depend on covariates, such as hospital bed occupancy and daily SARS‐CoV‐2 test positivity rate, which may drive changes in hospital ICU operations. We demonstrate via simulation studies that the proposed method performs well on noisy time series data and apply our statistical framework to hospitalization data from the University of California, Irvine (UCI) Health and Orange County, California. By introducing a likelihood‐based framework where immigration and death rates can vary with covariates, we find, through rigorous model selection, that hospitalization and positivity rates are crucial covariates for modeling ICU stay dynamics and validate our per‐patient ICU stay estimates using anonymized patient‐level UCI hospital data.

  more » « less
NSF-PAR ID:
10462874
Author(s) / Creator(s):
 ;  ;  ;  ;  
Publisher / Repository:
Wiley Blackwell (John Wiley & Sons)
Date Published:
Journal Name:
Statistics in Medicine
ISSN:
0277-6715
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ( , Anesthesia & Analgesia)
    BACKGROUND:

    Classification of perioperative risk is important for patient care, resource allocation, and guiding shared decision-making. Using discriminative features from the electronic health record (EHR), machine-learning algorithms can create digital phenotypes among heterogenous populations, representing distinct patient subpopulations grouped by shared characteristics, from which we can personalize care, anticipate clinical care trajectories, and explore therapies. We hypothesized that digital phenotypes in preoperative settings are associated with postoperative adverse events including in-hospital and 30-day mortality, 30-day surgical redo, intensive care unit (ICU) admission, and hospital length of stay (LOS).

     METHODS:

    We identified all laminectomies, colectomies, and thoracic surgeries performed over a 9-year period from a large hospital system. Seventy-seven readily extractable preoperative features were first selected from clinical consensus, including demographics, medical history, and lab results. Three surgery-specific datasets were built and split into derivation and validation cohorts using chronological occurrence. Consensusk-means clustering was performed independently on each derivation cohort, from which phenotypes’ characteristics were explored. Cluster assignments were used to train a random forest model to assign patient phenotypes in validation cohorts. We reconducted descriptive analyses on validation cohorts to confirm the similarity of patient characteristics with derivation cohorts, and quantified the association of each phenotype with postoperative adverse events by using the area under receiver operating characteristic curve (AUROC). We compared our approach to American Society of Anesthesiologists (ASA) alone and investigated a combination of our phenotypes with the ASA score.

     RESULTS:

    A total of 7251 patients met inclusion criteria, of which 2770 were held out in a validation dataset based on chronological occurrence. Using segmentation metrics and clinical consensus, 3 distinct phenotypes were created for each surgery. The main features used for segmentation included urgency of the procedure, preoperative LOS, age, and comorbidities. The most relevant characteristics varied for each of the 3 surgeries. Low-risk phenotype alpha was the most common (2039 of 2770, 74%), while high-risk phenotype gamma was the rarest (302 of 2770, 11%). Adverse outcomes progressively increased from phenotypes alpha to gamma, including 30-day mortality (0.3%, 2.1%, and 6.0%, respectively), in-hospital mortality (0.2%, 2.3%, and 7.3%), and prolonged hospital LOS (3.4%, 22.1%, and 25.8%). When combined with the ASA score, digital phenotypes achieved higher AUROC than the ASA score alone (hospital mortality: 0.91 vs 0.84; prolonged hospitalization: 0.80 vs 0.71).

     CONCLUSIONS:

    For 3 frequently performed surgeries, we identified 3 digital phenotypes. The typical profiles of each phenotype were described and could be used to anticipate adverse postoperative events.

     
    more » « less
  2. ; ; ; ; ; ( , Disaster Medicine and Public Health Preparedness)
    Abstract Objective: The aim of this study was to investigate the performance of key hospital units associated with emergency care of both routine emergency and pandemic (COVID-19) patients under capacity enhancing strategies. Methods: This investigation was conducted using whole-hospital, resource-constrained, patient-based, stochastic, discrete-event, simulation models of a generic 200-bed urban U.S. tertiary hospital serving routine emergency and COVID-19 patients. Systematically designed numerical experiments were conducted to provide generalizable insights into how hospital functionality may be affected by the care of COVID-19 pandemic patients along specially designated care paths, under changing pandemic situations, from getting ready to turning all of its resources to pandemic care. Results: Several insights are presented. For example, each day of reduction in average ICU length of stay increases intensive care unit patient throughput by up to 24% for high COVID-19 daily patient arrival levels. The potential of 5 specific interventions and 2 critical shifts in care strategies to significantly increase hospital capacity is also described. Conclusions: These estimates enable hospitals to repurpose space, modify operations, implement crisis standards of care, collaborate with other health care facilities, or request external support, thereby increasing the likelihood that arriving patients will find an open staffed bed when 1 is needed. 
    more » « less
  3. ; ; ; ; ( , BMC Infectious Diseases)
    Abstract Background

    The Mexican Institute of Social Security (IMSS) is the largest health care provider in Mexico, covering about 48% of the Mexican population. In this report, we describe the epidemiological patterns related to confirmed cases, hospitalizations, intubations, and in-hospital mortality due to COVID-19 and associated factors, during five epidemic waves recorded in the IMSS surveillance system.

     Methods

    We analyzed COVID-19 laboratory-confirmed cases from the Online Epidemiological Surveillance System (SINOLAVE) from March 29th, 2020, to August 27th, 2022. We constructed weekly epidemic curves describing temporal patterns of confirmed cases and hospitalizations by age, gender, and wave. We also estimated hospitalization, intubation, and hospital case fatality rates. The mean days of in-hospital stay and hospital admission delay were calculated across five pandemic waves. Logistic regression models were employed to assess the association between demographic factors, comorbidities, wave, and vaccination and the risk of severe disease and in-hospital death.

     Results

    A total of 3,396,375 laboratory-confirmed COVID-19 cases were recorded across the five waves. The introduction of rapid antigen testing at the end of 2020 increased detection and modified epidemiological estimates. Overall, 11% (95% CI 10.9, 11.1) of confirmed cases were hospitalized, 20.6% (95% CI 20.5, 20.7) of the hospitalized cases were intubated, and the hospital case fatality rate was 45.1% (95% CI 44.9, 45.3). The mean in-hospital stay was 9.11 days, and patients were admitted on average 5.07 days after symptoms onset. The most recent waves dominated by the Omicron variant had the highest incidence. Hospitalization, intubation, and mean hospitalization days decreased during subsequent waves. The in-hospital case fatality rate fluctuated across waves, reaching its highest value during the second wave in winter 2020. A notable decrease in hospitalization was observed primarily among individuals ≥ 60 years. The risk of severe disease and death was positively associated with comorbidities, age, and male gender; and declined with later waves and vaccination status.

     Conclusion

    During the five pandemic waves, we observed an increase in the number of cases and a reduction in severity metrics. During the first three waves, the high in-hospital fatality rate was associated with hospitalization practices for critical patients with comorbidities.

     
    more » « less
  4. ; ; ( , JMIR Medical Informatics)
    Background Heart failure is a leading cause of mortality and morbidity worldwide. Acute heart failure, broadly defined as rapid onset of new or worsening signs and symptoms of heart failure, often requires hospitalization and admission to the intensive care unit (ICU). This acute condition is highly heterogeneous and less well-understood as compared to chronic heart failure. The ICU, through detailed and continuously monitored patient data, provides an opportunity to retrospectively analyze decompensation and heart failure to evaluate physiological states and patient outcomes. Objective The goal of this study is to examine the prevalence of cardiovascular risk factors among those admitted to ICUs and to evaluate combinations of clinical features that are predictive of decompensation events, such as the onset of acute heart failure, using machine learning techniques. To accomplish this objective, we leveraged tele-ICU data from over 200 hospitals across the United States. Methods We evaluated the feasibility of predicting decompensation soon after ICU admission for 26,534 patients admitted without a history of heart failure with specific heart failure risk factors (ie, coronary artery disease, hypertension, and myocardial infarction) and 96,350 patients admitted without risk factors using remotely monitored laboratory, vital signs, and discrete physiological measurements. Multivariate logistic regression and random forest models were applied to predict decompensation and highlight important features from combinations of model inputs from dissimilar data. Results The most prevalent risk factor in our data set was hypertension, although most patients diagnosed with heart failure were admitted to the ICU without a risk factor. The highest heart failure prediction accuracy was 0.951, and the highest area under the receiver operating characteristic curve was 0.9503 with random forest and combined vital signs, laboratory values, and discrete physiological measurements. Random forest feature importance also highlighted combinations of several discrete physiological features and laboratory measures as most indicative of decompensation. Timeline analysis of aggregate vital signs revealed a point of diminishing returns where additional vital signs data did not continue to improve results. Conclusions Heart failure risk factors are common in tele-ICU data, although most patients that are diagnosed with heart failure later in an ICU stay presented without risk factors making a prediction of decompensation critical. Decompensation was predicted with reasonable accuracy using tele-ICU data, and optimal data extraction for time series vital signs data was identified near a 200-minute window size. Overall, results suggest combinations of laboratory measurements and vital signs are viable for early and continuous prediction of patient decompensation. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al ( , The Journal of Infectious Diseases)
    Abstract Background

    Four severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants predominated in the United States since 2021. Understanding disease severity related to different SARS-CoV-2 variants remains limited.

     Method

    Viral genome analysis was performed on SARS-CoV-2 clinical isolates circulating March 2021 through March 2022 in Cleveland, Ohio. Major variants were correlated with disease severity and patient outcomes.

     Results

    In total 2779 patients identified with either Alpha (n = 1153), Gamma (n = 122), Delta (n = 808), or Omicron variants (n = 696) were selected for analysis. No difference in frequency of hospitalization, intensive care unit (ICU) admission, and death were found among Alpha, Gamma, and Delta variants. However, patients with Omicron infection were significantly less likely to be admitted to the hospital, require oxygen, or admission to the ICU (χ2 = 12.8, P < .001; χ2 = 21.6, P < .002; χ2 = 9.6, P = .01, respectively). In patients whose vaccination status was known, a substantial number had breakthrough infections with Delta or Omicron variants (218/808 [26.9%] and 513/696 [73.7%], respectively). In breakthrough infections, hospitalization rate was similar regardless of variant by multivariate analysis. No difference in disease severity was identified between Omicron subvariants BA.1 and BA.2.

     Conclusions

    Disease severity associated with Alpha, Gamma, and Delta variants is comparable while Omicron infections are significantly less severe. Breakthrough disease is significantly more common in patients with Omicron infection.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email