Comparison of Statistical Models of Predict the Factors Affecting the Length of Stay (LOS) in the Intensive Care Unit (ICU) of a Teaching Hospital (original) (raw)
Related papers
Statistical analysis on length of stay in hospital
Science & Technology Development Journal - Engineering and Technology, 2021
The rising financial problems of healthcare institutions make studies of resource distribution more and more important and valuable. Among these studies, identification of length of stay of hospital patients (LOS) has attracted many scientists recently since it contributes to better knowledge of hospital costs and helps these institutions control the costs. This paper is devoted to study the length of stay of inpatients in hospital. Although predicting the length of stay is difficul, it is actually useful and benificial if some key factors that have influence on patient length of stay could be determined. This paper will be the basis for a running example that illustrates alternative models of the length of stay of hospital pentients. A total of 1189 episodes, which contains patient records, were analyzed by using some parametric and nonparametric statistical methods. In this study, several factors are first considered and investigated, including date of admission, medical admission...
Predicting the length of stay of patients admitted for intensive care using a first step analysis
Health Services and Outcomes Research Methodology, 2006
For patients admitted to intensive care units (ICU), the length of stay in different destinations after the first day of ICU admission, has not been systematically studied. We aimed to estimate the average length of stay (LOS) of such patients in Colombia, using a discrete time Markov process. We used the maximum likelihood method and Markov chain modeling to estimate the average LOS in the ICU and at each destination after discharge from intensive care. Six Markov models were estimated, describing the LOS in each one of the Cardiovascular, Neurological, Respiratory, Gastrointestinal, Trauma and Other diagnostic groups from the ultimate primary reason for admission to ICU. Possible destinations were: the intensive care unit, ward in the same hospital, the high dependency unit/intermediate care area in the same hospital, ward in other hospital, intensive care unit in other hospital, other hospital, other location same hospital, discharge from same hospital and death. The stationary property was tested and using a split-sample analysis, we provide indirect evidence about the appropriateness of the Markov property. It is not possible to use a unique Markov chain model for each diagnostic group. The length of stay varies across the ultimate primary reason for admission to intensive care. Although our Markov models shown to be predictive, the fact that current available statistical methods do not allow us to verify the Markov property test is a limitation. Clinicians may be able to provide information about the hospital LOS by diagnostic groups for different hospital destinations.
A Descriptive Study of Length of Stay at an Intensive Care Unit
International Journal of Research Foundation of Hospital and Healthcare Administration
Background and aims As intensive care units (ICUs) are very resource intensive, length of stay (LOS) is of prime importance. This study was done to analyze the LOS in different ICUs and analyze it against a set benchmark. Materials and methods This retrospective study was conducted from April to June 2013 on patients admitted during January to March 2013 in the neurosurgery ICU (NICU), medical ICU (MICU), high dependency unit (HDU) and isolation ICU of a large multispecialty hospital in Pune (India). As per the quality manual of the hospital, benchmark LOS was considered as 3.08 days for ICU. Mean and median LOS was analyzed through Student's t and Chi-square test; proportion of short (<2 days) and long stay (>4 days) patients was also computed. Results Out of 835 patients admitted to the NICU, MICU, HDU and Isolation ICU, the overall mean LOS was 3.37 ± 5.54 days which was statistically significant at a p-value <0.001 (t = 17.58, 95% CI 3-3.75). The overall mean LOS wa...
Length of stay in pediatric intensive care unit: prediction model
einstein (São Paulo), 2020
Objective: To propose a predictive model for the length of stay risk among children admitted to a pediatric intensive care unit based on demographic and clinical characteristics upon admission. Methods: This was a retrospective cohort study conducted at a private and general hospital located in the municipality of Sao Paulo, Brazil. We used internal validation procedures and obtained an area under ROC curve for the to build of the predictive model. Results: The mean hospital stay was 2 days. Predictive model resulted in a score that enabled the segmentation of hospital stay from 1 to 2 days, 3 to 4 days, and more than 4 days. The accuracy model from 3 to 4 days was 0.71 and model greater than 4 days was 0.69. The accuracy found for 3 to 4 days (65%) and greater than 4 days (66%) of hospital stay showed a chance of correctness, which was considering modest. Conclusion: Our results showed that low accuracy found in the predictive model did not enable the model to be exclusively adopted for decision-making or discharge planning. Predictive models of length of stay risk that consider variables of patients obtained only upon admission are limit, because they do not consider other characteristics present during hospitalization such as possible complications and adverse events, features that could impact negatively the accuracy of the proposed model.
Optimizing intensive care capacity using individual length-of-stay prediction models
2007
Introduction Effective planning of elective surgical procedures requiring postoperative intensive care is important in preventing cancellations and empty intensive care unit (ICU) beds. To improve planning, we constructed, validated and tested three models designed to predict length of stay (LOS) in the ICU in individual patients.
OPSEARCH
Intensive care unit (ICU) is a critical resource in a hospital, especially in developing countries such as India. The length of ICU stay after a cardiac surgery is an important variable for effective use of this critical resource. In this context, a predictive model can help a hospital to make optimum use of its ICU occupancy. A study was thus conducted on ICU patients and data gather over a 1-year period in a hospital in India. The critical factors for prolonged ICU stay (more than 72 h) were identified using univariate and multivariate logistic regression and a predictive index was built based on model development set. The predictive index was tested on a validation set and the mean length of ICU stay appeared to increase with an increase in the risk score. In addition, the risk score was tested in case of mortality. Efficient use of the ICU facility is possible with the help of this predictive index.
A new model for the length of stay of hospital patients
Health Care Management Science, 2014
Hospital Length of Stay (LoS) is a valid proxy to estimate the consumption of hospital resources. Average LoS, however, albeit easy to quantify and calculate, can be misleading if the underlying distribution is not symmetric. Therefore the average does not reflect the nature of such underlying distribution and may mask different effects. This paper uses routinely collected data of an Italian hospital patients from different departments over a period of 5 years. This will be the basis for a running example illustrating the alternative models of patients length of stay. The models includes a new density model called Hypergamma. The paper concludes by summarizing these various modelling techniques and highlighting the use of a risk measure in bed planning.
Factors Affecting the Length of Stay in the Intensive Care Unit: Our Clinical Experience
BioMed research international, 2018
Long hospital days in intensive care unit (ICU) due to life-threatening diseases are increasing in the world. The primary goal in ICU is to decrease length of stay in order to improve the quality of medical care and reduce cost. The aim of our study is to identify and categorize the factors associated with prolonged stays in ICU. We retrospectively analyzed 3925 patients. We obtained the patients' demographic, clinical, diagnostic, and physiologic variables; mortality; lengths of stay by examining the intensive care unit database records. The mean age of the study was 61.6 ± 18.9 years. The average length of stay in intensive care unit was 10.2 ± 25.2 days. The most common cause of hospitalization was because of multiple diseases (19.5%). The length of stay was positively correlated with urea, creatinine, and sodium. It was negatively correlated with uric acid and hematocrit levels. Length of stay was significantly higher in patients not operated on than in patients operated on ...
To verify four 5-year-old mathematical models to predict the outcome of ICU patients
Minerva anestesiologica, 2003
The aim of this study is to verify calibration and discrimination after 5 years in the case mix of patients admitted to the Intensive Care Unit (ICU) during the year 2000. In this way we want to perform a quality control of our ICU in order to justify the increased amount of money spent for intensive care. A prospective study has been made on the 357 patients admitted to the ICU during the year 2000. The Apache II score was calculated within the first 24 hours and, depending on the length of stay in the ICU, on the 5(th), 10(th) and 15(th) day after ICU admission. On the basis of the 4 mathematical models death risk has been calculated for each of the 4 times. The Hosmer-Lemeshow test was performed for calibration and ROC curves for discrimination, always for each of the 4 mathematical models. The 1(st) model, at 24 hours from ICU admission, showed a bad calibration (p=0.000088), while the ROC curve was 0.744+/-0.32. Also the 2(nd) model, at the 5(th) day from admission, showed a ba...