OBJECTIVES: The heterogeneity of prostate cancer (PC) patient journeys for a same stage makes their evaluation complex using descriptive statistics. Unsupervised machine learning has the potential to reveal patterns within heterogeneous data. However, impact of such methods in real-world studies is not yet clear.

METHODS: Patients with PC in 2014 were identified in SNDS and their data were extracted with up to 5-year history and 4-year follow-up. Fifty-one specific healthcare encounters constitutive of PC management were synthetized into 4 macro-variables using clustering of variables approach. Values of these macro-variables over patient follow-ups constituted healthcare pathways. Optimal matching using TRATE substitution method was applied to calculate distances between pathways. Partitioning around medoids algorithm was then used to define groups of similar pathways across four incident cohorts: hormone-sensitive (HSPC), metastatic hormone-sensitive (mHSPC), castration-resistant (CRPC), and metastatic castration-resistant (mCRPC). Index plots were used to represent pathway clusters.

RESULTS: The repartition of macro-variables values – surveillance, local treatment, androgenic deprivation, and advanced treatment – appeared to be consistent with PC status. Two to five clusters of healthcare pathways were observed in each of the different cohorts, corresponding for most of them to relevant clinical patterns. Clustering allowed to distinguish patients undergoing active surveillance, or treated according to cancer progression risk in HSPC; patients with rapid and slow disease progression in CRPC; patients receiving treatment for potentially curative or palliative purposes in mHSPC and mCRPC.

CONCLUSIONS: Visualization methods combined to clustering approach enabled the identification of clinically relevant patterns of PC management. This experience also highlighted potential improvement to leverage the impact of results. Characterization of these care pathways is an essential element for the robust assessment of healthcare technologies in health outcome research.