IPMN-LEARN: A linear support vector machine learning model for predicting low-grade intraductal papillary mucinous neoplasms.

Backgrounds/Aims: We aimed to build a machine learning tool to help predict low-grade intraductal papillary mucinous neoplasms (IPMNs) in order to avoid unnecessary surgical resection. IPMNs are precursors to pancreatic cancer. Surgical resection remains the only recognized treatment for IPMNs yet carries some risks of morbidity and potential mortality. Existing clinical guidelines are imperfect in distinguishing low-risk cysts from high-risk cysts that warrant resection. Methods: We built a linear support vector machine (SVM) learning model using a prospectively maintained surgical database of patients with resected IPMNs. Input variables included 18 demographic, clinical, and imaging characteristics. The outcome variable was the presence of low-grade or high-grade IPMN based on post-operative pathology results. Data were divided into a training/validation set and a testing set at a ratio of 4:1. Receiver operating characteristics analysis was used to assess classification performance. Results: A total of 575 patients with resected IPMNs were identified. Of them, 53.4% had low-grade disease on final pathology. After classifier training and testing, a linear SVM-based model (IPMN-LEARN) was applied on the validation set. It achieved an accuracy of 77.4%, with a positive predictive value of 83%, a specificity of 72%, and a sensitivity of 83% in predicting low-grade disease in patients with IPMN. The model predicted low-grade lesions with an area under the curve of 0.82. Conclusions: A linear SVM learning model can identify low-grade IPMNs with good sensitivity and specificity. It may be used as a complement to existing guidelines to identify patients who could avoid unnecessary surgical resection.

Uncinate Duct Dilatation Predicts Additional Risk for High-Grade Dysplasia or Invasive Carcinoma Among Fukuoka-Positive Intraductal Papillary Mucinous Neoplasms.

OBJECTIVE: To determine whether uncinate duct dilatation (UDD) increases the risk of high-grade dysplasia or invasive carcinoma (HGD/IC) in Fukuoka-positive intraductal papillary mucinous neoplasms (IPMNs). BACKGROUND: Though classified as a branch duct, the uncinate duct is the primary duct of the pancreatic ventral anlage. We hypothesized that UDD, like main duct dilatation, confers additional risk for HGD/IC. METHODS: A total of 467 patients met inclusion criteria in a retrospective cohort study of surgically resected IPMNs at the Massachusetts General Hospital. We used multivariable logistic regression to analyze the association between UDD (defined as ≥4 mm) and HGD/IC, controlling for Fukuoka risk criteria. In a secondary analysis, the modeling was repeated in the 194 patients with dorsal branch duct IPMNs (BD-IPMNs) in the pancreatic neck, body, or tail. RESULTS: Mean age at surgery was 70, and 229 (49%) patients were female. In total, 267 (57%) patients had only worrisome features and 200 (43%) had at least 1 high-risk feature. UDD was present in 164 (35%) patients, of whom 118 (73%) had HGD/IC. On multivariable analysis, UDD increased the odds of HGD/IC by 2.8-fold, even while controlling for Fukuoka risk factors (95% CI: 1.8-4.4, P <0.001). Prevalence of HGD/IC in all patients with UDD was 73%, compared with 74% in patients with high-risk stigmata and 73% in patients with main duct IPMNs. In the secondary analysis, UDD increased the odds of HGD/IC by 3.2-fold in patients with dorsal BD-IPMNs (95% CI: 1.3-7.7, P =0.010). CONCLUSIONS: UDD confers additional risk for HGD/IC unaccounted for by current Fukuoka criteria. Further research can extend this study to Fukuoka-negative patients, including unresected patients.

Branch duct intraductal papillary mucinous neoplasms: does cyst size change the tip of the scale? A critical analysis of the revised international consensus guidelines in a large single-institutional series.

OBJECTIVE: The aim of this study was to critically analyze the safety of the revised guidelines, with focus on cyst size and worrisome features in the management of BD-IPMN. BACKGROUND: The Sendai guidelines for management of branch duct (BD) intraductal papillary mucinous neoplasm (IPMN) espouse safety of observation of asymptomatic cysts smaller than 3 cm without nodules (Sendai negative). Revised international consensus guidelines published in 2012 suggest a still more conservative approach, even for lesions of 3 cm or larger. By contrast, 2 recent studies have challenged the safety of both guidelines, describing invasive carcinoma or carcinoma in situ in 67% of BD-IPMN smaller than 3 cm and in 25% of "Sendai-negative" BD-IPMN. METHODS AND RESULTS: Review of a prospective database identified 563 patients with BD-IPMN. A total of 240 patients underwent surgical resection (152 at the time of diagnosis and 88 after being initially followed); the remaining 323 have been managed by observation with median follow-up of 60 months. No patient developed unresectable BD-IPMN carcinoma during follow-up. Invasive cancer arising in BD-IPMN was found in 23 patients of the entire cohort (4%), and an additional 21 patients (3.7%) had or developed concurrent pancreatic ductal adenocarcinoma. According to the revised guidelines, 76% of resected BD-IPMN with carcinoma in situ and 95% of resected BD-IPMN with invasive cancer had high-risk stigmata or worrisome features. The risk of high-grade dysplasia in nonworrisome lesions smaller than 3 cm was 6.5%, but when the threshold was raised to greater than 3 cm, it was 8.8%, and 1 case of invasive carcinoma was found. CONCLUSIONS: Expectant management of BD-IPMN following the old guidelines is safe, whereas caution is advised for larger lesions, even in the absence of worrisome features.