Predicting Length of Hospice Stay: An Application of Quantile Regression

Clinically informed machine learning elucidates the shape of hospice racial disparities within hospitals

Racial disparities in hospice care are well documented for patients with cancer, but the existence, direction, and extent of disparity findings are contradictory across the literature. Current methods to identify racial disparities aggregate data to produce single-value quality measures that exclude important patient quality elements and, consequently, lack information to identify actionable equity improvement insights. Our goal was to develop an explainable machine learning approach that elucidates healthcare disparities and provides more actionable quality improvement information. We infused clinical information with engineering systems modeling and data science to develop a time-by-utilization profile per patient group at each hospital using US Medicare hospice utilization data for a cohort of patients with advanced (poor-prognosis) cancer that died April-December 2016. We calculated the difference between group profiles for people of color and white people to identify racial disparity signatures. Using machine learning, we clustered racial disparity signatures across hospitals and compared these clusters to classic quality measures and hospital characteristics. With 45,125 patients across 362 hospitals, we identified 7 clusters; 4 clusters (n = 190 hospitals) showed more hospice utilization by people of color than white people, 2 clusters (n = 106) showed more hospice utilization by white people than people of color, and 1 cluster (n = 66) showed no difference. Within-hospital racial disparity behaviors cannot be predicted from quality measures, showing how the true shape of disparities can be distorted through the lens of quality measures. This approach elucidates the shape of hospice racial disparities algorithmically from the same data used to calculate quality measures.

Characterizing end-of-life communication in families

Background

The chronic disease course can be uncertain, contributing to delayed end-of-life discussion within families resulting in missed opportunity to articulate wishes, increased decisional uncertainty, and delayed hospice care. Consistent with the Family Communication Patterns Theory (FCPT), family communication patterns may affect the quality and timing of end-of-life discussion, hospice utilization, and the experience of 'a good death.'

Objective

To assess how families' conversation and conformity orientation (spontaneity of conversation and hierarchical rigidity) form four family communication patterns (consensual, pluralistic, protective, and laissez-faire) and may be associated with the number and timing of end-of-life discussions.

Design

A cross-sectional study.

Methods

Family members of loved ones who died from chronic illnesses while in hospice (n = 56) completed online surveys including a modified Revised Family Communication Pattern instrument (RFCP) and the Chronic Illness Rating Scale (CIRS). Additional survey questions assessed the number and timing of end-of-life discussions and timing of hospice enrollment. IBM SPSS version 26 was used for descriptive analysis.

Results

Most families (42.9%) were pluralistic, reporting communication styles with high conversation and low conformity orientation; (39.29%) were protective, reporting low conversation and high conformity orientation. Pluralistic families had more end-of-life conversations than did protective families.

Conclusion

Study findings suggest that there may be a relationship between family communication pattern type and inclination toward end-of-life discussion. This first step supports future research regarding whether the FCPT can be used to predict which families may be at increased risk for ineffective or delayed end-of-life discussion. Additional variables to consider include the timing of hospice enrollment and the quality of the dying experience. Clinicians may ultimately use findings to facilitate earlier identification of and intervention for families who are at risk for poor end-of-life communication and outcomes.

Length of Stay Analysis of COVID-19 Hospitalizations Using a Count Regression Model and Quantile Regression: A Study in Bologna, Italy

This study aimed to identify and explore the hospital admission risk factors associated with the length of stay (LoS) by applying a relatively novel statistical method for count data using predictors among COVID-19 patients in Bologna, Italy. The second goal of this study was to model the LoS of COVID patients to understand which covariates significantly influenced it and identify the potential risk factors associated with LoS in Bolognese hospitals from 1 February 2020 to 10 May 2021. The clinical settings we focused on were the Intensive Care Unit (ICU) and ordinary hospitalization, including low-intensity stays. We used Poisson, negative binomial (NB), Hurdle–Poisson, and Hurdle–NB regression models to model the LoS. The fitted models were compared using the Akaike information criterion (AIC), Vuong’s test criteria, and Rootograms. We also used quantile regression to model the effects of covariates on the quantile values of the response variable (LoS) using a Poisson distribution, and to explore a range of conditional quantile functions, thereby exposing various forms of conditional heterogeneity and controlling for unobserved individual characteristics. Based on the chosen performance criteria, Hurdle–NB provided the best fit. As an output from the model, we found significant changes in average LoS for each predictor. Compared with ordinary hospitalization and low-intensity stays, the ICU setting increased the average LoS by 1.84-fold. Being hospitalized in long-term hospitals was another contributing factor for LoS, increasing the average LoS by 1.58 compared with regular hospitals. When compared with the age group [50, 60) chosen as the reference, the average LoS decreased in the age groups [0, 10), [30, 40), and [40, 50), and increased in the oldest age group [80, 102). Compared with the second wave, which was chosen as the reference, the third wave did not significantly affect the average LoS, whereas it increased by 1.11-fold during the first wave and decreased by 0.77-fold during out-wave periods. The results of the quantile regression showed that covariates related to the ICU setting, hospitals with longer hospitalization, the first wave, and the out-waves were statistically significant for all the modeled quantiles. The results obtained from our study can help us to focus on the risk factors that lead to an increased LoS among COVID-19 patients and benchmark different models that can be adopted for these analyses.

Duration of palliative care before death in international routine practice: a systematic review and meta-analysis

BACKGROUND

Early provision of palliative care, at least 3-4 months before death, can improve patient quality of life and reduce burdensome treatments and financial costs. However, there is wide variation in the duration of palliative care received before death reported across the research literature. This study aims to determine the duration of time from initiation of palliative care to death for adults receiving palliative care across the international literature.

METHODS

We conducted a systematic review and meta-analysis that was registered with PROSPERO (CRD42018094718). Six databases were searched for articles published between Jan 1, 2013, and Dec 31, 2018: MEDLINE, Embase, CINAHL, Global Health, Web of Science and The Cochrane Library, as well undertaking citation list searches. Following PRISMA guidelines, articles were screened using inclusion (any study design reporting duration from initiation to death in adults palliative care services) and exclusion (paediatric/non-English language studies, trials influencing the timing of palliative care) criteria. Quality appraisal was completed using Hawker's criteria and the main outcome was the duration of palliative care (median/mean days from initiation to death).

RESULTS

One hundred sixty-nine studies from 23 countries were included, involving 11,996,479 patients. Prior to death, the median duration from initiation of palliative care to death was 18.9 days (IQR 0.1), weighted by the number of participants. Significant differences between duration were found by disease type (15 days for cancer vs 6 days for non-cancer conditions), service type (19 days for specialist palliative care unit, 20 days for community/home care, and 6 days for general hospital ward) and development index of countries (18.91 days for very high development vs 34 days for all other levels of development). Forty-three per cent of studies were rated as 'good' quality. Limitations include a preponderance of data from high-income countries, with unclear implications for low- and middle-income countries.

CONCLUSIONS

Duration of palliative care is much shorter than the 3-4 months of input by a multidisciplinary team necessary in order for the full benefits of palliative care to be realised. Furthermore, the findings highlight inequity in access across patient, service and country characteristics. We welcome more consistent terminology and methodology in the assessment of duration of palliative care from all countries, alongside increased reporting from less-developed settings, to inform benchmarking, service evaluation and quality improvement.