As shown in other studies Dynamic Time Warping (DTW) can be used to cluster patients by their Trajectories. Our study analyzed a comprehensive dataset of cancer patient records, structuring each patient’s medical events into ordered sequences categorized into inpatient admissions, outpatient visits, and ambulatory care attendances. We identified time gaps, inserting ’pause’ events for gaps of 21 days or more and substituted common diagnosis events with ICD-10 codes for clarity. We applied Dynamic Time Warping (DTW) to calculate sequence distances, using ICD-10 code co-occurrence rates, and the Kronecker delta for distance measurement excludes the longest and shortest 10% of sequences. Hierarchical clustering of these distances led to nine nontrivial clusters, subsequently analyzed via regression to assess their impact on patient outcomes, thus unveiling patterns and implications in cancer patients’ medical event sequences. We were able to find a significant impact of using clusters in regression models with mortality, depression score, and anxiety scores.