JMIR Publications

ABSTRACT

Background:

A steady increase in colorectal and prostate cancer patients and survivors is expected in the upcoming years. Due to primary cancer treatments, patients suffer from numerous additional complaints, which also increases the need for cancer aftercare. However, referrals to appropriate cancer aftercare remain inadequate, despite a wide range of aftercare options. Caregivers and patients often do not know which aftercare is the most appropriate for the individual patient. Since characteristics and complaints of patients within a diagnosis group can be different, predefined patient clusters could provide substantive and efficient support for professionals in the conversation about aftercare. By using advanced data analysis methods, clusters of patients who are different from one another within one diagnosis group can be identified.

Objective:

The objective of this study was twofold: first, to identify, visualize, and describe potential patient clusters within colorectal and prostate cancer populations and, second, to explore the potential usability of these clusters in clinical practice.

Methods:

First, we used cross-sectional data from colorectal and prostate cancer patients provided by the population-based Patient Reported Outcomes Following Initial Treatment and Long Term Evaluation of Survivorship registry, which was originally collected between 2008 and 2012. To identify and visualize different clusters among the two patient populations, we conducted cluster analyses by applying the K-means algorithm and multiple-factor analyses. Second, in a qualitative study, we presented the patient clusters to prostate and colorectal cancer patients and oncology professionals. To assess the usability of these clusters, we held expert panel group interviews. The interviews were videorecorded and transcribed. Three researchers independently performed content-directed data analysis to understand and describe the qualitative data. Quotes illustrate the most important results.

Results:

We identified 3 patient clusters among colorectal cancer cases (N=3989) and 5 patient clusters among the prostate cancer cases (N=696), which were described in tabular form. Patient-experts (N=6) and professional-experts (N=17) recognized the patient clustering based on distinguishing variables. However, the tabular form was evaluated as less applicable in clinical practice. Instead, the experts suggested the development of a conversation tool (eg, decision tree) to guide professionals through the hierarchy of variables. In addition, participants suggested that information about possible aftercare initiatives should be offered and integrated. This would also ensure a good overview and seemed to be a precondition for finding suitable aftercare.

Conclusions:

This study demonstrates that a fully data-driven approach can be used to identify distinguishable and in-routine care recognizable patient clusters in large datasets within cancer populations. Challenges for the future include the identification of more distinguishing key variables, the development of a smart digital conversation and referral tool, and the further development of new data analysis techniques to detect normal and abnormal recovery patterns among cancer patients. Clinical Trial: Trial ID NL9226 (Trial Register, The Netherlands)