Influence of integrated molecular pathology test results on real-world management decisions for patients with pancreatic cysts: analysis of data from a national registry cohort

Abstract

Background: Integrated molecular pathology (IMP) approaches based on DNA mutational profiling accurately determine pancreatic cyst malignancy risk in patients lacking definitive diagnoses following endoscopic ultrasound imaging with fine-needle aspiration of fluid for cytology. In such cases, IMP 'low-risk' and 'high-risk' diagnoses reliably predict benign and malignant disease, respectively, and provide improved risk stratification for malignancy than a model of the 2012 International Consensus Guideline (ICG) recommendations. Our objective was to determine if initial adjunctive IMP testing influenced future real-world pancreatic cyst management decisions for intervention or surveillance relative to ICG recommendations, and if this benefitted patient outcomes.

Methods: Analysis of data from the previously described National Pancreatic Cyst Registry. Associations between real-world decisions (intervention vs. surveillance), ICG model recommendations (surgery vs. surveillance) and IMP diagnoses (high-risk vs. low-risk) were evaluated using 2 × 2 tables. Kaplan Meier and hazard ratio analyses were used to assess time to malignancy. Odds ratios (OR) for surgery decision were determined using logistic regression.

Results: Of 491 patients, 206 received clinical intervention at follow-up (183 surgery, 4 chemotherapy, 19 presumed by malignant cytology). Overall, 13 % (66/491) of patients had a malignant outcome and 87 % (425/491) had a benign outcome at 2.9 years' follow-up. When ICG and IMP were concordant for surveillance/surgery recommendations, 83 % and 88 % actually underwent surveillance or surgery, respectively. However, when discordant, IMP diagnoses were predictive of real-world decisions, with 88 % of patients having an intervention when ICG recommended surveillance but IMP indicated high risk, and 55 % undergoing surveillance when ICG recommended surgery but IMP indicated low risk. These IMP-associated management decisions benefitted patient outcomes in these subgroups, as 57 % had malignant and 99 % had benign outcomes at a median 2.9 years' follow-up. IMP was also more predictive of real-world decisions than ICG by multivariate analysis: OR 11.4 (95 % CI 6.0 - 23.7) versus 3.7 (2.4 - 5.8), respectively.

Conclusions: DNA-based IMP diagnoses were predictive of real-world management decisions. Importantly, when ICG and IMP were discordant, IMP influence benefitted patients by increasing confidence in surveillance and surgery decisions and reducing the number of unnecessary surgeries in patients with benign disease.

Fig. 1

Kaplan-Meier analysis of time-to-malignancy in a multivariate model as predicted by IMP and ICG. Y-axis represents probability of benign outcome in patients after initial IMP test. X-axis represents time post initial EUS-FNA that patient outcomes were determined based on review of follow-up medical records