Techniques for estimating health care costs with censored data: An overview for the health services researcher

Division of Cardiology, Schulich Heart Centre and Department of Medicine, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada.
ClinicoEconomics and Outcomes Research 06/2012; 4(1):145-55. DOI: 10.2147/CEOR.S31552
Source: PubMed


The aim of this study was to review statistical techniques for estimating the mean population cost using health care cost data that, because of the inability to achieve complete follow-up until death, are right censored. The target audience is health service researchers without an advanced statistical background.
Data were sourced from longitudinal heart failure costs from Ontario, Canada, and administrative databases were used for estimating costs. The dataset consisted of 43,888 patients, with follow-up periods ranging from 1 to 1538 days (mean 576 days). The study was designed so that mean health care costs over 1080 days of follow-up were calculated using naïve estimators such as full-sample and uncensored case estimators. Reweighted estimators - specifically, the inverse probability weighted estimator - were calculated, as was phase-based costing. Costs were adjusted to 2008 Canadian dollars using the Bank of Canada consumer price index (
Over the restricted follow-up of 1080 days, 32% of patients were censored. The full-sample estimator was found to underestimate mean cost ($30,420) compared with the reweighted estimators ($36,490). The phase-based costing estimate of $37,237 was similar to that of the simple reweighted estimator.
The authors recommend against the use of full-sample or uncensored case estimators when censored data are present. In the presence of heavy censoring, phase-based costing is an attractive alternative approach.

Download full-text


Available from: Harindra C Wijeysundera,
  • [Show abstract] [Hide abstract]
    ABSTRACT: Although multidisciplinary heart failure (HF) clinics are efficacious, it is not known how patient factors or HF clinic structural indicators and process measures have an impact on the cumulative health care costs. In this retrospective cohort study using administrative databases in Ontario, Canada, we identified 1216 HF patients discharged alive after an acute care hospitalization in 2006 and treated at a HF clinic. The primary outcome was the cumulative 1-year health care costs. A hierarchical generalized linear model with a logarithmic link and gamma distribution was developed to determine patient-level and clinic-level predictors of cost. The mean 1-year cost was $27,809 (range, $69 to $343,743). There was a 7-fold variation in the mean costs by clinic, from $14,670 to $96,524. Delays in being seen at a HF clinic were a significant patient-level predictor of costs (rate ratio 1.0015 per day; P<0.001). Being treated at a clinic with >3 physicians was associated with lower costs (rate ratio 0.78; P=0.035). Unmeasured patient-level differences accounted for 97.4% of the between-patient variations in cost. The between-clinic variation in costs decreased by 16.3% when patient-level factors were accounted for; it decreased by a further 49.8% when clinic-level factors were added. From a policy perspective, the wide spectrum of HF clinic structure translates to inefficient care. Greater guidance as to the type of patient seen at a HF clinic, the timeliness of the initial visit, and the most appropriate structure of the HF clinics may potentially result in more cost-effective care.
    Medical care 03/2014; 52(3):272-9. DOI:10.1097/MLR.0000000000000071 · 3.23 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The use of neoadjuvant chemotherapy (NAC) in the treatment of advanced ovarian cancer has increased in recent years. There is uncertainty about NAC's effectiveness and no study of its cost-effectiveness compared with that of standard primary debulking surgery (PDS). To seek answers to three important questions: 1) What is the lifetime cost of treating elderly patients with advanced ovarian cancer, based on the primary treatment received? 2) Are the extra costs expended by the NAC group worth any extra survival advantage? 3) Would NAC potentially benefit a particular subgroup and serve as a cost-effective first-line treatment approach? A cohort of elderly women (≥65 years) with stage III/IV ovarian cancer was identified from the Surveillance, Epidemiology and End Results-Medicare linked database from January 1, 2000, to December 31, 2009. Cost analysis was conducted from a payer perspective, and direct medical costs incurred by Medicare were integrated for each patient. Cumulative treatment costs were estimated with a phase-of-care approach, and effectiveness was measured as years of survival. Incremental cost-effectiveness ratio (ICER) and propensity-score-adjusted net monetary benefit regression was used to estimate the cost-effectiveness of NAC per life-year gained. Analyses were further stratified by risk group categorization on the basis of tumor stage, patient age, and comorbidity score. Average lifetime cost for treatment with NAC was $17,417 more than with PDS. With only 0.1 incremental life-year gained, the ICER estimate was $174,173. Stratification, however, helped to delineate the treatment effect. Patients in the high-risk subgroup incurred $34,390 and 0.8 life-years more than did patients in the PDS subgroup, with a corresponding ICER of $42,987. In the non-high-risk subgroup, NAC use was dominated by PDS (more costly, less effective). Administering NAC before surgery to patients in the high-risk subgroup was cost-effective at "normal" levels of willingness to pay, but not for the overall sample or for patients in the non-high-risk subgroup. Copyright © 2015 International Society for Pharmacoeconomics and Outcomes Research (ISPOR). Published by Elsevier Inc. All rights reserved.
    Value in Health 03/2015; 18(4). DOI:10.1016/j.jval.2015.01.005 · 3.28 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In the United States, nearly 8400 patients die each year from oral cavity and pharynx cancers, most of whom are 65 years and older; however, the costs attributable to these cancers are not well described. To identify the primary determinants of cost in patients with oral and pharyngeal cancer. In this retrospective cohort analysis of data from Medicare and Surveillance, Epidemiology, and End Results hospitals (January 1, 1995, through December 31, 2005), we studied patients 66 years and older with newly diagnosed oral cavity (n = 6724) and pharyngeal (n = 3987) cancers. Five-year cumulative costs, defined as Medicare Parts A and B payments, were estimated using inverse probability weighting. Linear regression analysis with inverse probability weighting was used in multivariate analyses of costs to estimate the effects of covariates on cumulative costs. In multivariate analyses, costs were significantly increased by demographics, comorbidities, and treatment selection. Compared with white patients, African Americans accumulated $11 450 (95% CI, $1320-$22 299) and $25 093 (95% CI, $14 917-$34 985) more in costs for oral cavity and pharyngeal cancers, respectively. The presence of 1 or 2 comorbidities increased the mean 5-year cumulative costs by $13 342 (95% CI, $6248-$19 186) and $14 139 (95% CI, $6009-$22 217) for patients with oral cavity and pharyngeal cancers, respectively. For 3 or more comorbidities, the mean 5-year cumulative costs increased by $22 196 (95% CI, $15 319-$28 614) and $27 799 (95% CI, $19 139-$36 702) for patients with oral cavity and pharyngeal cancers, respectively. Patients who received chemotherapy accumulated a mean of $26 919 (95% CI, $18 309-$35 056) and $37 407 (95% CI, $29 971-$44 644) more in costs by 5 years for oral cavity and pharyngeal cancers, respectively. Oral and pharyngeal cancer is burdensome to elderly patients from a Medicare cost perspective. Several factors were associated with 5-year costs, including some modifiable factors that may be potential targets for interventions to reduce overall costs.
    JAMA Otolaryngology - Head and Neck Surgery 06/2015; 141(7). DOI:10.1001/jamaoto.2015.0940 · 1.79 Impact Factor