Applications for Quantile Regression in Epidemiology

Wei, Ying; Kehm, Rebecca D.; Goldberg, Mandy; Terry, Mary Beth

doi:10.1007/s40471-019-00204-6

Cited by 33 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The skewness measure is 1.67, indicating the expenditure distribution is highly skewed. Quantile regression (QR) methods are well suited to estimate how specified quantiles, or percentiles of the distribution of the outcome variable vary with covariates, and is robust against outliers and is more informative for a skewed distribution than mean-based regression [ 15 ]. We demonstrate the value of a highly flexible machine learning based quantile regression method in studying healthcare expenditures.…”

Section: Introductionmentioning

confidence: 99%

Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach

Sanderson

2020

BMC Health Serv Res

View full text Add to dashboard Cite

Background To identify and rank the importance of key determinants of high medical expenses among breast cancer patients and to understand the underlying effects of these determinants. Methods The Oncology Care Model (OCM) developed by the Center for Medicare & Medicaid Innovation were used. The OCM data provided to Mount Sinai on 2938 breast-cancer episodes included both baseline periods and three performance periods between Jan 1, 2012 and Jan 1, 2018. We included 11 variables representing information on treatment, demography and socio-economics status, in addition to episode expenditures. OCM data were collected from participating practices and payers. We applied a principled variable selection algorithm using a flexible tree-based machine learning technique, Quantile Regression Forests. Results We found that the use of chemotherapy drugs (versus hormonal therapy) and interval of days without chemotherapy predominantly affected medical expenses among high-cost breast cancer patients. The second-tier major determinants were comorbidities and age. Receipt of surgery or radiation, geographically adjusted relative cost and insurance type were also identified as important high-cost drivers. These factors had disproportionally larger effects upon the high-cost patients. Conclusions Data-driven machine learning methods provide insights into the underlying web of factors driving up the costs for breast cancer care management. Results from our study may help inform population health management initiatives and allow policymakers to develop tailored interventions to meet the needs of those high-cost patients and to avoid waste of scarce resource.

show abstract

Section: Introductionmentioning

confidence: 99%

Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach

Sanderson

2020

BMC Health Serv Res

View full text Add to dashboard Cite

show abstract

“…We remark that the number of surviving mice (equivalently, the higher quantiles of the survival time) is more sensitive to differences in strategy than is the median survival time. This is typical in biomedical studies where only a subpopulation of patients benefit from the intervention (for a review, see [ 70 ]).…”

Section: Resultsmentioning

confidence: 99%

Standing Variations Modeling Captures Inter-Individual Heterogeneity in a Deterministic Model of Prostate Cancer Response to Combination Therapy

Jain

Sorribes

Handelman

et al. 2021

Cancers

View full text Add to dashboard Cite

Sipuleucel-T (Provenge) is the first live cell vaccine approved for advanced, hormonally refractive prostate cancer. However, survival benefit is modest and the optimal combination or schedule of sipuleucel-T with androgen depletion remains unknown. We employ a nonlinear dynamical systems approach to modeling the response of hormonally refractive prostate cancer to sipuleucel-T. Our mechanistic model incorporates the immune response to the cancer elicited by vaccination, and the effect of androgen depletion therapy. Because only a fraction of patients benefit from sipuleucel-T treatment, inter-individual heterogeneity is clearly crucial. Therefore, we introduce our novel approach, Standing Variations Modeling, which exploits inestimability of model parameters to capture heterogeneity in a deterministic model. We use data from mouse xenograft experiments to infer distributions on parameters critical to tumor growth and to the resultant immune response. Sampling model parameters from these distributions allows us to represent heterogeneity, both at the level of the tumor cells and the individual (mouse) being treated. Our model simulations explain the limited success of sipuleucel-T observed in practice, and predict an optimal combination regime that maximizes predicted efficacy. This approach will generalize to a range of emerging cancer immunotherapies.

show abstract

“…To this end, we used the sqreg STATA command to estimate β coefficients and their bootstrap 95% confidence intervals while adjusting for the covariates shown in S3 Fig. Quantile regression provides a way of estimating the association between exposures and continuous health outcomes that are not normally distributed [36]; this is the case of hemoglobin concentrations in our study children (Shapiro-Wilk test for normality, P < 0.001).…”

Section: Discussionmentioning

confidence: 99%

Low-level Plasmodium vivax exposure, maternal antibodies, and anemia in early childhood: Population-based birth cohort study in Amazonian Brazil

et al. 2021

View full text Add to dashboard Cite

Background Malaria causes significant morbidity and mortality in children under 5 years of age in sub-Saharan Africa and the Asia-Pacific region. Neonates and young infants remain relatively protected from clinical disease and the transplacental transfer of maternal antibodies is hypothesized as one of the protective factors. The adverse health effects of Plasmodium vivax malaria in early childhood–traditionally viewed as a benign infection–remain largely neglected in relatively low-endemicity settings across the Amazon. Methodology/Principal findings Overall, 1,539 children participating in a birth cohort study in the main transmission hotspot of Amazonian Brazil had a questionnaire administered, and blood sampled at the two-year follow-up visit. Only 7.1% of them experienced malaria confirmed by microscopy during their first 2 years of life– 89.1% of the infections were caused by P. vivax. Young infants appear to be little exposed to, or largely protected from infection, but children >12 months of age become as vulnerable to vivax malaria as their mothers. Few (1.4%) children experienced ≥4 infections during the 2-year follow-up, accounting for 43.4% of the overall malaria burden among study participants. Antenatal malaria diagnosed by microscopy during pregnancy or by PCR at delivery emerged as a significant correlate of subsequent risk of P. vivax infection in the offspring (incidence rate ratio, 2.58; P = 0.002), after adjusting for local transmission intensity. Anti-P. vivax antibodies measured at delivery do not protect mothers from subsequent malaria; whether maternal antibodies transferred to the fetus reduce early malaria risk in children remains undetermined. Finally, recent and repeated vivax malaria episodes in early childhood are associated with increased risk of anemia at the age of 2 years in this relatively low-endemicity setting. Conclusions/Significance Antenatal infection increases the risk of vivax malaria in the offspring and repeated childhood P. vivax infections are associated with anemia at the age of 2 years.

show abstract

Applications for Quantile Regression in Epidemiology

Cited by 33 publications

References 21 publications

Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach

Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach

Standing Variations Modeling Captures Inter-Individual Heterogeneity in a Deterministic Model of Prostate Cancer Response to Combination Therapy

Low-level Plasmodium vivax exposure, maternal antibodies, and anemia in early childhood: Population-based birth cohort study in Amazonian Brazil

Contact Info

Product

Resources

About