Wait times for breast cancer care

Abstract

Measurement of care time intervals is complex, being influenced by many factors. The definition of the care interval monitored can also bias the detection of changes in waits. The implications of using different care interval definitions to report wait times and identify delays in care provision were examined using a retrospective chart review of 637 women with surgically treated breast cancer who were referred to a cancer centre between September 1999 and 2000 or September 2003 and 2004. Overall waits between detection and adjuvant treatment increased by 12 days over the two periods, but their exact location and cause(s) could not be determined at such a low-resolution interval. At higher resolutions of care intervals, reporting the comprehensive sequence of care events, the prolongation was mainly associated with delayed access to surgery (4 days) and delivery of adjuvant chemotherapy (4 days). The latter went unnoticed when waits were reported at intermediate (referral to adjuvant treatment) and low (detection to adjuvant treatment) resolutions. Disease stage and type of first adjuvant treatment consistently and significantly influenced the length of waits. Comprehensive monitoring of the entire care path is essential to effectively prioritize interventions, assess their outcomes and optimise access to cancer care.

Figure 1

Case selection and exclusion criteria for two patient cohorts: cohort 1 (1999–2000) and cohort 2 (2003–2004). Some cases may be excluded for more than one reason.

Figure 2

Selected levels of resolution of care intervals for breast cancer care: (1) low-resolution (long composite/overall interval embracing all events – Detection–First Adjuvant); (2) intermediate-resolution (mid-size composite intervals embracing some, but not all care events – Detection–Referral; Referral–First Adjuvant); and (3) high-resolution (small intervals embracing single/isolated care events – Detection–Biospy; Biopsy–Surgery; Surgery–Referral; Referral–Patient Contact; Patient Contact–Oncology Consultation; Oncology Consultation–First Adjuvant).

Figure 3

Wait times at low resolution. Shown in circles between intervals, are unadjusted geometric mean number of elapsed days. Below each interval are shown the covariates found to have a significant effect. Adjusted geometric mean number of days with 95% confidence intervals are shown in parenthesis and the sample size appears in square brackets. Period main effects are shown for every interval and interaction terms are represented by a colon. Period 2000 refers to cohort 1; Period 2004 refers to cohort 2.

Figure 4

Wait times at intermediate resolution. Shown in circles between intervals are unadjusted geometric mean number of elapsed days. Below each interval are shown the covariates found to have a significant effect. Adjusted geometric mean number of days with 95% confidence intervals are shown in parenthesis and the sample size appears in square brackets. Period main effects are shown for every interval and interaction terms are represented by a colon. Period 2000 refers to cohort 1; Period 2004 refers to cohort 2.

Figure 5

Wait times at high resolution. Shown in circles between intervals, are unadjusted geometric mean number of elapsed days. Below each interval are shown the covariates found to have a significant effect. Adjusted geometric mean number of days with 95% confidence intervals are shown in parenthesis and the sample size appears in square brackets. Period main effects are shown for every interval and interaction terms are represented by a colon. Period 2000 refers to cohort 1; Period 2004 refers to cohort 2.

Figure 6

Ordination showing the inter-relationships between wait times (←) and their cofactors (). Longer arrows indicate stronger influences. Arrows pointing in the same directions indicate strong co-associations. Arrows of care intervals point in the direction of increasing wait times. Arrows for categorical cofactors point in the direction of the highest classification order as described in Table 1. PC1 and PC2 accounted for 18 and 14% of the total variance in the data, respectively. Patients (cases) appear as points. Patients clustering in the second quadrant were generally from Cape Breton, living further from a cancer centre, with lower education and income levels, undergoing lumpectomy and receiving radiation therapy as first adjuvant treatment and experiencing prolonged elapsed times in most care intervals with the exception of Referral–Patient Contact. Most wait times were oriented (increasing) in the same direction as the period effect, highlighting the general (although not necessarily statistically significant) prolongation of wait times in most care intervals.