Search

This manuscript describes an approach for analyzing large amounts of disparate clinical data to elucidate the most impactful factor(s) that relate to a meaningful clinical outcome, in this case, the quality of life of cancer patients. The relationships between clinical and quality of life variables were evaluated using the EORTC QLQ-C30 global health domain--a validated surrogate variable for overall cancer patient well-being.A cross-sectional study design was used to evaluate the determinants of global health in cancer patients who initiated treatment at two regional medical centers between January 2001 and December 2009. Variables analyzed included 15 EORTC QLQ-C30 scales, age at diagnosis, gender, newly diagnosed/ recurrent disease status, and stage. The decision tree algorithm, perhaps unfamiliar to practicing clinicians, evaluates the relative contribution of individual parameters in classifying a clinically meaningful functional endpoint, such as the global health of a patient.Multiple patient characteristics were identified as important contributors. Fatigue, in particular, emerged as the most prevalent indicator of cancer patients' quality of life in 16/23 clinically relevant subsets. This analysis allowed results to be stated in a clinically-intuitive, rule set format using the language and quantities of the Quality of Life (QoL) tool itself.By applying the classification algorithms to a large data set, identification of fatigue as a root factor in driving global health and overall QoL was revealed. The ability to practice mining of clinical data sets to uncover critical clinical insights that are immediately applicable to patient care practices is illustrated.

PURPOSE: This research conducted a face validation study of patient responses to the application of an HRQOL assessment research tool in a comprehensive community cancer program setting across a heterogeneous cohort of cancer patients throughout the natural history of diagnosed malignant disease, many of whom would not be considered candidates for clinical research trial participation. METHODS: Cancer registries at two regional cancer treatment centers identified 11072 cancer patients over a period of nine years. The EORTC QLQ-C30 was administered to patients at the time of their initial clinical presentation to these centers. To determine the significance of differences between patient subgroups, two analytic criteria were used. The Mann-Whitney test was used to determine statistical significance; clinical relevance defined a range of point differences that could be perceived by patients with different health states. RESULTS: Univariate analyses were conducted across stratification variables for population, disease severity and demographic characteristics. The largest differences were associated with cancer diagnosis and recurrence of disease. Large differences were also found for site of origin, mortality and stage; minimal differences were observed for gender and age. Consistently sensitive QoL scales were appetite loss, fatigue and pain symptoms, and role (work-related), social and physical functions. CONCLUSIONS: 1) The EORTC QLQ-C30 collected meaningful patient health assessments in the context of non-research based clinical care, 2) patient assessment differences are manifested disparately across 15 QoL domains, and 3) in addition to indicating how a patient may feel at a point in time, QoL indicators may also reveal information about underlying biological responses to disease progression, treatments, and prospective survival.