Dataset Information

Dealing with highly skewed hospital length of stay distributions: The use of Gamma mixture models to study delivery hospitalizations.

ABSTRACT: The increased focus on addressing severe maternal morbidity and maternal mortality has led to studies investigating patient and hospital characteristics associated with longer hospital stays. Length of stay (LOS) for delivery hospitalizations has a strongly skewed distribution with the vast majority of LOS lasting two to three days in the United States. Prior studies typically focused on common LOSs and dealt with the long LOS distribution tail in ways to fit conventional statistical analyses (e.g., log transformation, trimming). This study demonstrates the use of Gamma mixture models to analyze the skewed LOS distribution. Gamma mixture models are flexible and, do not require data transformation or removal of outliers to accommodate many outcome distribution shapes, these models allow for the analysis of patients staying in the hospital for a longer time, which often includes those women experiencing worse outcomes. Random effects are included in the model to account for patients being treated within the same hospitals. Further, the role and influence of differing placements of covariates on the results is discussed in the context of distinct model specifications of the Gamma mixture regression model. The application of these models shows that they are robust to the placement of covariates and random effects. Using New York State data, the models showed that longer LOS for childbirth hospitalizations were more common in hospitals designated to accept more complicated deliveries, across hospital types, and among Black women. Primary insurance also was associated with LOS. Substantial variation between hospitals suggests the need to investigate protocols to standardize evidence-based medical care.

SUBMITTER: Williford E

PROVIDER: S-EPMC7170466 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Dealing with highly skewed hospital length of stay distributions: The use of Gamma mixture models to study delivery hospitalizations.

Williford Eva E Haley Valerie V McNutt Louise-Anne LA Lazariu Victoria V

PloS one 20200420 4

The increased focus on addressing severe maternal morbidity and maternal mortality has led to studies investigating patient and hospital characteristics associated with longer hospital stays. Length of stay (LOS) for delivery hospitalizations has a strongly skewed distribution with the vast majority of LOS lasting two to three days in the United States. Prior studies typically focused on common LOSs and dealt with the long LOS distribution tail in ways to fit conventional statistical analyses (e ...[more]

PMID: 32310963

Similar Datasets

Project description:BACKGROUND:Hospital length-of-Stay has been traditionally used as a surrogate to evaluate healthcare efficiency, as well as hospital resource utilization. Prolonged Length-of-stay (PLOS) is associated with increased mortality and other poor outcomes. Additionally, these patients represent a significant economic problem on public health systems and their families. We sought to describe and compare characteristics of patients with Normal hospital Length-of-Stay (NLOS) and PLOS to identify sociodemographic and disease-specific factors associated with PLOS in a tertiary care institution that attends adults with complicated diseases from all over Mexico. MATERIALS AND METHODS:We conducted a retrospective analysis of hospital discharges from January 2000-December 2017 using institutional databases of medical records. We compared NLOS and PLOS using descriptive and inferential statistics. PLOS were defined as those above the 95th percentile of length of hospitalization. RESULTS:We analyzed 85,904 hospitalizations (1,069,875 bed-days), of which 4,427 (5.1%) were PLOS (247,428 bed-days, 23.1% of total bed-days). Hematological neoplasms were the most common discharge diagnosis and surgery of the small bowel was the most common type of surgery. Younger age, male gender, a lower physician-to-patient ratio, emergency and weekend admissions, surgery, the number of comorbidities, residence outside Mexico City and lower socioeconomic status were associated with PLOS. Bone marrow transplant (OR 18.39 [95% CI 12.50-27.05, p<0.001), complex infectious diseases such as systemic mycoses and parasitoses (OR 4.65 [95% CI 3.40-6.63, p<0.001), and complex abdominal diseases such as intestinal fistula (OR 2.57 [95% CI 1.98-3.32) had the greatest risk for PLOS. Risk of mortality in patients with PLOS increased more than threefold (3.7% vs 13.3%, p<0.001). CONCLUSIONS:We report some key sociodemographic and disease-specific differences in patients with PLOS. These could serve to develop a specific model of directed hospital healthcare for patients identified as in risk of PLOS.

Dataset Information

Dealing with highly skewed hospital length of stay distributions: The use of Gamma mixture models to study delivery hospitalizations.

Publications

Dealing with highly skewed hospital length of stay distributions: The use of Gamma mixture models to study delivery hospitalizations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets