scholarly journals Nonlinear time-series forecasts for decision support: short-term demand for ICU beds in Santiago, Chile during the 2021 COVID-19 pandemic

2021 ◽  
Author(s):  
Bernardo F. Quiroga ◽  
Cristián Vásquez ◽  
María Ignacia Vicuña
Keyword(s):  
Intensive Care Unit ◽  
Time Series ◽  
Intensive Care ◽  
Decision Support ◽  
Health Services ◽  
Nonlinear Time Series ◽  
Metropolitan Region ◽  
Short Term ◽  
Term Forecast ◽  
Forecast Models

Abstract In Chile, due to the explosive increase of new COVID-19 cases during the first part of 2021, the ability of health services to accommodate new incoming cases was jeopardized. It has become necessary to be able to manage intensive care unit (ICU) capacity, and for this purpose, monitoring both the evolution of new cases and the demand of ICU beds, has become urgent. This paper presents short-term forecast models for the number of new cases and the number of COVID-19 patients admitted to ICUs in the Metropolitan Region in Chile.

Predictors of and Trends in High-Intensity End-of-Life Care Among Children With Cancer: A Population-Based Study Using Health Services Data

2017 ◽  
Vol 35 (2) ◽  
pp. 236-242 ◽  
Author(s):  
Alisha Kassam ◽  
Rinku Sutradhar ◽  
Kimberley Widger ◽  
Adam Rapoport ◽  
Jason D. Pole ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Health Services ◽  
High Intensity ◽  
Hematologic Malignancies ◽  
Population Based ◽  
Children With Cancer ◽  
Eol Care ◽  
Related Mortality

Purpose Children with cancer often receive high-intensity (HI) medical care at the end-of-life (EOL). Previous studies have been limited to single centers or lacked detailed clinical data. We determined predictors of and trends in HI-EOL care by linking population-based clinical and health-services databases. Methods A retrospective decedent cohort of patients with childhood cancer who died between 2000 and 2012 in Ontario, Canada, was assembled using a provincial cancer registry and linked to population-based health-care data. Based on previous studies, the primary composite measure of HI-EOL care comprised any of the following: intravenous chemotherapy < 14 days from death; more than one emergency department visit; and more than one hospitalization or intensive care unit admission < 30 days from death. Secondary measures included those same individual measures and measures of the most invasive (MI) EOL care (eg, mechanical ventilation < 14 days from death). We determined predictors of outcomes with appropriate regression models. Sensitivity analysis was restricted to cases of cancer-related mortality, excluding treatment-related mortality (TRM) cases. Results The study included 815 patients; of these, 331 (40.6%) experienced HI-EOL care. Those with hematologic malignancies were at highest risk (odds ratio, 2.5; 95% CI, 1.8 to 3.6; P < .001). Patients with hematologic cancers and those who died after 2004 were more likely to experience the MI-EOL care (eg, intensive care unit, mechanical ventilation, odds ratios from 2.0 to 5.1). Excluding cases of TRM did not substantively change the results. Conclusion Ontario children with cancer continue to experience HI-EOL care. Patients with hematologic malignancies are at highest risk even when excluding TRM. Of concern, rates of the MI-EOL care have increased over time despite increased palliative care access. Linking health services and clinical data allows monitoring of population trends in EOL care and identifies high-risk populations for future interventions.

Short-term outcomes in older intensive care unit patients with dementia*

2005 ◽  
Vol 33 (6) ◽  
pp. 1371-1376 ◽  
Author(s):  
Margaret A. Pisani ◽  
Carrie A. Redlich ◽  
Lynn McNicoll ◽  
E Wesley Ely ◽  
Rebecca J. Friedkin ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Short Term

scholarly journals Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database

2016 ◽  
Vol 24 (3) ◽  
pp. 488-495 ◽  
Author(s):  
Mike Wu ◽  
Marzyeh Ghassemi ◽  
Mengling Feng ◽  
Leo A Celi ◽  
Peter Szolovits ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Time Series ◽  
Intensive Care ◽  
Receiver Operating Curve ◽  
Post Discharge ◽  
Control Hypotension ◽  
Health Records ◽  
Physiological Time ◽  
Large Populations ◽  
Switching State

Background: The widespread adoption of electronic health records allows us to ask evidence-based questions about the need for and benefits of specific clinical interventions in critical-care settings across large populations. Objective: We investigated the prediction of vasopressor administration and weaning in the intensive care unit. Vasopressors are commonly used to control hypotension, and changes in timing and dosage can have a large impact on patient outcomes. Materials and Methods: We considered a cohort of 15 695 intensive care unit patients without orders for reduced care who were alive 30 days post-discharge. A switching-state autoregressive model (SSAM) was trained to predict the multidimensional physiological time series of patients before, during, and after vasopressor administration. The latent states from the SSAM were used as predictors of vasopressor administration and weaning. Results: The unsupervised SSAM features were able to predict patient vasopressor administration and successful patient weaning. Features derived from the SSAM achieved areas under the receiver operating curve of 0.92, 0.88, and 0.71 for predicting ungapped vasopressor administration, gapped vasopressor administration, and vasopressor weaning, respectively. We also demonstrated many cases where our model predicted weaning well in advance of a successful wean. Conclusion: Models that used SSAM features increased performance on both predictive tasks. These improvements may reflect an underlying, and ultimately predictive, latent state detectable from the physiological time series.

Evaluation of short-term consequences of hypoglycemia in an intensive care unit*

2006 ◽  
Vol 34 (11) ◽  
pp. 2714-2718 ◽  
Author(s):  
Titia M. Vriesendorp ◽  
J Hans DeVries ◽  
Susanne van Santen ◽  
Hazra S. Moeniralam ◽  
Evert de Jonge ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Short Term

Correlation Properties and Complexity of Perioperative RR-Interval Dynamics in Coronary Artery Bypass Surgery Patients

2000 ◽  
Vol 93 (1) ◽  
pp. 69-80 ◽  
Author(s):  
Timo T. Laitio ◽  
Heikki V. Huikuri ◽  
Erkki S. H. Kentala ◽  
Timo H. Mäkikallio ◽  
Jouko R. Jalonen ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Heart Rate ◽  
Intensive Care ◽  
Artery Bypass ◽  
Scaling Exponent ◽  
Short Term ◽  
Cabg Surgery ◽  
Rr Interval ◽  
Heart Rate Dynamics ◽  
Dynamic Measures

Background Dynamic measures of heart rate variability (HRV) may uncover abnormalities that are not easily detectable with traditional time and frequency domain measures. The purpose of this study was to characterize changes in RR-interval dynamics in the immediate postoperative phase of coronary artery bypass graft (CABG) surgery using traditional and selected newer dynamic measures of HRV. Methods Continuous 24-h electrocardiograph recordings were performed in 40 elective CABG surgery patients up to 72 h postoperatively. In one half of the patients, Holter recordings were initiated 12-40 h before the surgery. Time and frequency domain measures of HRV were assessed. The dynamic measures included a quantitative and visual analysis of Poincaré plots, measurement of short- and intermediate-term fractal-like scaling exponents (alpha1 and alpha2), the slope (beta) of the power-law regression line of RR-interval dynamics, and approximate entropy. Results The SD of RR intervals (P &lt; 0.001) and the ultra-low-, very-low-, low-, and high-frequency power (P &lt; 0.01, P &lt; 0.001, P &lt; 0.001, P &lt; 0.01, respectively) measures in the first postoperative 24 h decreased from the preoperative values. Analysis of Poincaré plots revealed increased randomness in beat-to-beat heart rate behavior demonstrated by an increase in the ratio between short-term and long-term HRV (P &lt; 0.001) after CABG. Average scaling exponent alpha1 of the 3 postoperative days decreased significantly after CABG (from 1.22 +/- 0.15 to 0.85 +/- 0.20, P &lt; 0.001), indicating increased randomness of short-term heart rate dynamics (i.e., loss of fractal-like heart rate dynamics). Reduced scaling exponent alpha1 of the first postoperative 24 h was the best HRV measure in differentiating between the patients that had normal (&lt;/= 48 h, n = 33) or prolonged (&gt; 48 h, n = 7) intensive care unit stay (0.85 +/- 0.17 vs. 0.68 +/- 0.18; P &lt; 0.05). In stepwise multivariate logistic regression analysis including typical clinical predictors, alpha1 was the most significant independent predictor (P &lt; 0.05) of long intensive care unit stay. None of the preoperative HRV measures were able to predict prolonged intensive care unit stays. Conclusions In the selected group of patients studied, a decrease in overall HRV was associated with altered nonlinear heart rate dynamics after CABG surgery. Current results suggest that a more random short-term heart rate behavior may be associated with a complicated clinical course. Analysis of fractal-like dynamics of heart rate may provide new perspectives in detecting abnormal cardiovascular function after CABG.

Sign in / Sign up

Export Citation Format

Share Document