Temporal phenotyping by mining healthcare data to derive lines of therapy for cancer.

•An innovative algorithm pipeline to identify patient temporal phenotype subgroups.•Temporal phenotype subgroups of mNSCLC and metastatic melanoma were reported.•Innovative visualization of cluster memberships for treatment sequences.•Our method extracted and characterized patient-level LOT from a large claims database.•The algorithm is adjustable and can be applied for different cancer indications.