Cancer of unknown primary: Registered procedures compared with national integrated cancer pathway for illuminating external validity

Abstract

Cancer of unknown primary (CUP) ranges within top 10 cancers in both incidence and mortality. As primary identification is crucial to choosing treatment, guidelines on CUP emphasize the diagnostic strategy. Whether guidelines are complied with, or if they are indeed helpful, is however unclear. We compared procedures performed in suspected CUP patients with recommendations of national guidelines to assess external validity of guidelines.The Danish National Patient Registry (NPR) comprising population data was utilized to identify the suspected CUP patients during 2009 to 2010 and explore exposure to procedures and patient survival. The cohort was investigated in terms of validity of diagnosis through cross-referencing with the Cancer Registry (CR), which served as gold standard for cancer diagnoses and patients' cancer histories.The NPR cohort consisted of 542 patients (275 males, 264 females) of whom 210 (38.7%) had a CUP diagnosis confirmed. Within the cohort, 347 patients (64.0%) had a registration in CR matching with the NPR registration. Exposure to diagnostic procedures included biopsy (n = 439, 81.0%) and image modalities (n = 532, 98.2%). Survival was poor with 67 (12.4%) individuals alive after 4 years.The validity of a CUP diagnosis in NPR was low when using data from CR as reference. More than half the suspected CUP patients had a previous cancer diagnosis with CUP being the most frequent. Patients were diagnosed in compliance with guidelines indicating high external validity, but less than 1 quarter had their primary identified and the 1-year survival was approximately 20%. Research is needed to develop efficacious methods for primary detection.

Figure 1

Flowchart of patients. A total of 184,835 patients had any kind of CUP registration in the National Patient Registry (NPR). Restricting the population to relevant registrations decreased the population size to 542 of whom 347 had a hit in Cancer Registry (CR). CUP = cancer of unknown primary.

Figure 2

Kaplan–Meier plot of survival. Note: only 458 subjects were considered at risk in the Kaplan–Meier survival estimate at T = 0 because 84 subjects’ date of death was identical to their registered date of discharge.

Figure 3

PET/CT in CUP patients. Left: man aged 57 with a biopsy-verified adenocarcinoma metastasis in the liver from a hitherto undetected origin. PET/CT revealed a primary in the sigmoideum (arrow). Right: woman aged 50 with a tumor on her back, diagnosed 4 months later as a metastasis from an unknown primary. PET/CT performed 2 months later revealed multiple metastases precluding identification of the primary. Courtesy: Henrik Petersen, Department of Nuclear Medicine, Odense University Hospital, Denmark.