Prediction Of Postoperative Pancreatic Fistula Research Articles

Optimizing prediction models for pancreatic fistula after pancreatectomy: Current status and future perspectives

Postoperative pancreatic fistula (POPF) is a frequent complication after pancreatectomy, leading to increased morbidity and mortality. Optimizing prediction models for POPF has emerged as a critical focus in surgical research. Although over sixty models following pancreaticoduodenectomy, predominantly reliant on a variety of clinical, surgical, and radiological parameters, have been documented, their predictive accuracy remains suboptimal in external validation and across diverse populations. As models after distal pancreatectomy continue to be progressively reported, their external validation is eagerly anticipated. Conversely, POPF prediction after central pancreatectomy is in its nascent stage, warranting urgent need for further development and validation. The potential of machine learning and big data analytics offers promising prospects for enhancing the accuracy of prediction models by incorporating an extensive array of variables and optimizing algorithm performance. Moreover, there is potential for the development of personalized prediction models based on patient- or pancreas-specific factors and postoperative serum or drain fluid biomarkers to improve accuracy in identifying individuals at risk of POPF. In the future, prospective multicenter studies and the integration of novel imaging technologies, such as artificial intelligence-based radiomics, may further refine predictive models. Addressing these issues is anticipated to revolutionize risk stratification, clinical decision-making, and postoperative management in patients undergoing pancreatectomy.

Preoperative Prediction of Postoperative Pancreatic Fistula After Pancreatic Head Resection Using Radiomics and Machine Learning Based on Computed Tomographic Diagnostics

Preoperative Prediction of Postoperative Pancreatic Fistula After Pancreatic Head Resection Using Radiomics and Machine Learning Based on Computed Tomographic Diagnostics

Combined pre-operative risk score predicts pancreatic leak after pancreatic resection.

Post-operative pancreatic fistula (POPF) is a major complication following pancreatectomy and is currently difficult to predict pre-operatively. This study aims to validate pre-operative risk factors and develop a novel combined score for the prediction of POPF in the pre-operative setting. Data were collected from 2016 to 2021 for radiologic main pancreatic duct diameter (MPD), body mass index (BMI), physical status classified by American Society of Anesthesiologists (ASA), polypharmacy, mean platelet ratio (MPR), comorbidity-polypharmacy score (CPS), and a novel Combined Pancreatic Leak Prediction Score (CPLPS) (derived from MPD diameter, BMI, and CPS) were obtained from pre-operative data and analyzed for their independent association with POPF occurrence. In total, 166 patients who underwent pancreatectomy with pancreatic leak (Grade A, B, and C) occurring in 51(30.7%) of patients. Pre-operative radiologic MPD diameter < 4 mm (p < 0.001), < 5 mm (p < 0.001), < 6 mm (p = 0.001), BMI ≥ 25 (p = 0.009), and ≥ 30 (p = 0.017) were independently associated with the occurrence of pancreatic leak. CPLPS was also predictive of pancreatic leak following pancreatectomy on univariate (p = 0.005) and multivariate analysis (p = 0.036). MPD and BMI were independent risk factors predictive for the development of pancreatic leak. CPLPS, was an independent predictor of pancreatic leak following pancreatectomy and could be used to help guide surgical decision making and patient counseling.

Machine Learning Based Prediction of Postoperative Pancreatic Fistula Following Pancreaticoduodenectomy.

To develop a novel machine learning (ML) model to predict clinically relevant postoperative pancreatic fistula (CR-POPF) following pancreaticoduodenectomy (PD). Accurate prognostication of CR-POPF may allow for risk stratification and adaptive treatment strategies for potential PD candidates. However, antecedent models, such as the modified Fistula Risk Score (mFRS), are limited by poor discrimination and calibration. All records entailing PD within the 2014-2018 ACS NSQIP were identified. Additionally, patients undergoing PD at our institution between 2013 and 2021 were queried from our local data repository. An eXtreme Gradient Boosting (XGBoost) model was developed to estimate the risk of CR-POPF using data from the ACS NSQIP and evaluated using institutional data. Model discrimination was estimated using the area under the receiver operating characteristic (AUROC) and precision recall curve (AUPRC). Overall, 12,281 and 445 patients undergoing PD were identified within the 2014-2018 ACS NSQIP and our institutional registry, respectively. Application of the XGBoost and mFRS scores to the internal validation dataset revealed that the former model had significantly greater AUROC (0.72 vs. 0.68, P<0.001) and AUPRC (0.22 vs. 0.18, P<0.001). Within the external validation dataset, the XGBoost model remained superior to the mFRS with an AUROC of 0.79 (95% CI 0.74-0.84) versus 0.75 (95% CI 0.70-0.80, P<0.001). In addition, AUPRC was higher for the XGBoost model, compared to the mFRS. Our novel ML model consistently outperformed the previously validated mFRS within internal and external validation cohorts, thereby demonstrating its generalizability and utility for enhancing prediction of CR-POPF.

Quantitative edge analysis of pancreatic margins in patients with head pancreatic tumors: correlations between pancreatic margins and the onset of postoperative pancreatic fistula.

To assess the correlation between pancreatic quantitative edge analysis as a surrogate of parenchymal stiffness and the incidence of postoperative pancreatic fistula (POPF), in patients undergoing pancreaticoduodenectomy (PD). All consecutive patients who underwent PD at our Institution between March 2018 and November 2019 with an available preoperative CT were included. Pancreatic margin score (PMS) was calculated through computer-assisted quantitative edge analysis on the margins of the pancreatic body and tail (the expected pancreatic remnant) on non-contrast scans with in-house software. Intraoperative assessment of pancreatic stiffness by manual palpation was also performed, classifying pancreatic texture into soft and non-soft. PMS values were compared between groups using an unpaired T-test and correlated with the intraoperative evaluation of stiffness and with the grading of postoperative pancreatic fistula according to the International Study Group on Pancreatic Surgery (ISGPS). Patient population included 200 patients (mean age 64.6years), 146 without onset of POPF (73%, non-POPF group), and 54 with POPF (27%, POPF group). A significant difference in PMS values was observed between POPF and non-POPF (respectively 1.88 ± 0.05 vs 0.69 ± 0.01; p < 0.0001). PMS values of pancreatic parenchymas intraoperatively considered "soft" were significantly higher than those evaluated as "non-soft" (1.21 ± 0.04 vs 0.73 ± 0.02; p < 0.0001). A significant correlation between PMS values and POPF grade was observed (r = 0.8316), even in subgroups of patients with soft (r = 0.8016) and non-soft (r = 0.7602) pancreas (all p < 0.0001). Quantitative edge analysis with dedicated software may stratify patients with different pancreatic stiffness, thus potentially improving preoperative risk assessment and strategies for POPF mitigation. This study proposes quantitative pancreas edge analysis as a predictor for postoperative pancreatic fistula. The test has high accuracy and correlation with fistula grade according to the International Study Group on Pancreatic Surgery. • Prediction of postoperative pancreatic fistula (POPF) onset risk after pancreaticoduodenectomy is based only on intraoperative evaluation. • Quantitative edge analysis may preoperatively identify patients with higher risk of POPF. • Quantification of pancreatic stiffness through the analysis of pancreatic margins could be done on preoperative CT.

Prediction of postoperative pancreatic fistula and pancreatitis after pancreatoduodenectomy or distal pancreatectomy: A review.

Postoperative pancreatic fistula (POPF) is the leading cause of morbidity and early mortality in patients undergoing pancreatic resection. In addition, recent studies have identified postoperative acute pancreatitis (POAP) as an independent contributor to morbidity. Most perioperative mitigation strategies experimented for POPF have been shown to be in vain with no consensus on the best perioperative management. Clinical prediction models have been developed with the hope of identifying high POPF risk patients with the leading idea of finding subpopulations possibly benefiting from pre-existing or novel mitigation strategies. The aim of this review was to map out the existing prediction modeling studies to better understand the current stage of POPF prediction modeling, and the methodology behind them. A narrative review of the existing POPF prediction model studies was performed. Studies published before September 2022 were included. While the number of POPF prediction models for pancreatoduodenectomy has increased, none of the currently existing models stand out from the crowd. For distal pancreatectomy, two unique POPF prediction models exist, but due to their freshness, no further external validation or adoption in clinics or research has been reported. There seems to be a lack of adherence to correct methodology or reporting guidelines in most of the studies, which has rendered external validity-if assessed-low. Few of the most recent studies have demonstrated preoperative assessment of pancreatic aspects from computed tomography (CT) scans to provide relatively strong predictors of POPF. Main goal for the future would be to reach a consensus on the most important POPF predictors and prediction model. At their current state, few models have demonstrated adequate transportability and generalizability to be up to the task. Better understanding of POPF pathophysiology and the possible driving force of acute inflammation and POAP might be required before such a prediction model can be accessed.

Development of a Pancreatic Fistula Prediction Model After Pancreaticoduodenectomy Based on a Decision Tree and Random Forest Algorithm.

The incidence of postoperative pancreatic fistula (POPF) after pancreaticoduodenectomy (PD) is high. We sought to develop a POPF prediction model based on a decision tree (DT) and random forest (RF) algorithm after PD and to explore its clinical value. The case data of 257 patients who underwent PD in a tertiary general hospital from 2013 to 2021 were retrospectively collected in China. The RF model was used to select features by ranking the importance of variables, and both algorithms were used to build the prediction model after automatic adjustment of parameters by setting the respective hyperparameter intervals and resampling as a 10-fold cross-validation method, etc. The prediction model's performance was assessed by the receiver operating characteristic curve (ROC) and the area under curve (AUC). Postoperative pancreatic fistula occurred in 56 cases (56/257, 21.8%). The DT model had an AUC of .743 and an accuracy of .840, while the RF model had an AUC of .977 and an accuracy of .883. The DT plot visualized the process of inferring the risk of pancreatic fistula from the DT model on independent individuals. The top 10 important variables were selected for ranking in the RF variable importance ranking. This study successfully developed a DT and RF algorithm for the POPF prediction model, which can be used as a reference for clinical health care professionals to optimize treatment strategies to reduce the incidence of POPF.

Combined pre-operative risk score predicts pancreatic leak following pancreatectomy

Background: Post-operative pancreatic fistula (POPF) is a major complication following pancreatectomy and is difficult to predict pre-operatively. The burden of polypharmacy is increasing with the age of society and thus could prove predictive of post-operative complications including POPF. This study aims to validate pre-operative risk factors, including radiologic main pancreatic duct diameter (MPD), body mass index (BMI), and the Co-morbidity Polypharmacy Score (CPS), and develop a novel combined pancreatic leak prediction score (CPLPS) for the prediction of POPF.

Impact of Osteopenia on Pancreatic Fistula in Patients Undergoing Pancreaticoduodenectomy

This study aimed to identify the potential risk for postoperative pancreatic fistula (POPF), a major complication of pancreaticoduodenectomy. This retrospective study included 124 patients with biliary and pancreatic disorders who underwent pancreaticoduodenectomy between 2015 and 2020. Bone marrow density (BMD) was determined in the 11th thoracic vertebra using preoperative computed tomographic images. Delta BMD (dBMD=measured BMD - standard BMD) was calculated using standard BMD determined on the basis of age and sex, and dBMD <0 was defined as osteopenia. The relationship between clinicopathological factors and dBMD was investigated. The average BMD level was 140 Hounsfield units. BMD was significantly lower in women than in men (p<0.01) and in older patients than in younger patients (p<0.01). POPF was significantly correlated with low dBMD (p=0.032). Osteopenia was a risk factor for POPF in patients with soft pancreas (p=0.016). Osteopenia was an independent risk factor for POPF after pancreaticoduodenectomy in patients with soft pancreas. Preoperative osteopenia assessment may be useful for the prediction of POPF, and preoperative vitamin D supplementation might be considered in patients with osteopenia.

Dual-Energy CT Iodine Concentration to Evaluate Postoperative Pancreatic Fistula after Pancreatoduodenectomy.

Background Pancreatic fibrosis and fatty infiltration are associated with postoperative pancreatic fistula (POPF), but accurate preoperative assessment remains a challenge. Iodine concentration (IC) and fat fraction derived from dual-energy CT (DECT) may reflect the amount of fibrosis and steatosis, potentially enabling the preoperative prediction of POPF. Purpose To identify multiphasic DECT-derived IC and fat fraction that improve the prediction of POPF risks compared with contrast-enhanced CT attenuation values and to evaluate the underlying histopathologic changes. Materials and Methods This retrospective study included patients who underwent pancreatoduodenectomy and DECT (including pancreatic parenchymal, portal venous, and delayed phase scanning) between January 2020 and December 2020. The relationships of the quantitative DECT-derived IC and fat fraction, along with CT attenuation values from enhanced images with POPF risk, were analyzed with logistic regression analysis. The predictive performance of the IC was compared with that of the CT values. The histopathologic underpinnings of IC were evaluated with multivariable linear regression analysis. Results A total of 107 patients (median age, 65 years; interquartile range, 57-70 years; 56 men) were included. Of these, 23 (21%) had POPF. The pancreatic parenchymal-to-portal venous phase IC ratio (adjusted odds ratio [OR], 13; 95% CI: 2, 162; P < .001) was an independent predictor of POPF occurrence. The accuracy of the pancreatic parenchymal-to-portal venous phase IC ratio in predicting POPF was higher than that of the CT value ratio in the same phases (78% vs 65%, P < .001). The pancreatic parenchymal-to-portal venous phase IC ratio was independently associated with pancreatic fibrosis (β = -1.04; 95% CI: -0.44, -1.64; P = .001). Conclusion A higher pancreatic parenchymal-to-portal venous phase IC ratio was associated with less histologic fibrosis and greater risk of POPF. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Lee and Yoon in this issue.

Development and validation of risk prediction nomogram for pancreatic fistula and risk-stratified strategy for drainage management after pancreaticoduodenectomy.

Postoperative pancreatic fistula (POPF) is the major complication following pancreaticoduodenectomy (PD). We sought to develop and validate a risk prediction model for POPF after PD with the aim of determining personal risk probability and proposing a novel strategy for intraoperative placement and/or early-removal of prophylactic drainage. Data from 993 patients undergoing PD from January 2012 to December 2016 were retrospectively analyzed. Patients were randomly assigned to either training cohort or validation cohort. A nomogram was formulated based on the results from multivariable regression model for prediction of POPF. Internal and external validation were carried out with calibration plot respectively. POPF occurred in 162 (16.3%) patients. The final pre-/intra-operative prediction model included alanine transaminase level [odds ratio (OR) 1.00, 95% confidence interval (CI): 1.00-1.00, P=0.023], combined portal-superior mesenteric vein resection (OR 0.22, 95% CI: 0.05-0.95, P=0.043), pancreatic duct diameter (OR 1.48, 95% CI: 1.11-1.96, P=0.007), intraoperative colloid infusion (OR 1.00, 95% CI: 1.00-1.00, P=0.001), pathology (OR 1.71, 95% CI: 1.09-2.66, P=0.018). The area under the curve (AUC) was 0.667 in the training cohort and 0.621 in the validation cohort. The final postoperative prediction model included pancreatic duct diameter (OR 1.58, 95% CI: 1.14-2.19, P=0.006), intraoperative colloid infusion (OR 2.52, 95% CI: 1.26-5.06, P=0.009), drainage fluid amylase on postoperative day 3 (POD3) (OR 4.70, 95% CI: 3.30-6.70, P<0.001), and neutrophil count on POD3 (OR 2.83, 95% CI: 1.63-4.93, P<0.001). The AUC was 0.809 in the training cohort and 0.797 in the validation cohort. Based on these variables, two nomogram prediction models were developed respectively. The calibration plot of the two models showed a good correlation between the expected risk and the actual risk in the low-risk range. Our risk-stratified strategy for drain management according to nomograms may be beneficial for 34.5% of patients. Our study formulated and validated two nomogram models for predicting POPF that performed particularly well in the low-risk range. This tool may allow surgeons to propose a risk stratified strategy for intraoperative drain placement and early drain removal, which may be beneficial for a substantial proportion of patients.

Prediction of pancreatic fistula after pancreatectomy by virtual touch tissue imaging and quantification (VTIQ) technology

ObjectivesThe aim of this study was to quantitatively evaluate the stiffness of pancreatic parenchyma and solid focal pancreatic lesions (FPLs) by virtual touch tissue imaging and quantification (VTIQ) technique and to investigate the potential usefulness of VTIQ method in the prediction of post-operative pancreatic fistula (POPF) after pancreatectomy. MethodsIn this prospective study, patients who scheduled to undergo pancreatectomy were initially enrolled and received VTIQ assessment within one week before surgery. VTIQ elastography (Siemens ACUSON Sequoia, 5C-1 transducer) was used to measure the shear wave velocity (SWV) value of FPLs and the body part pancreatic parenchyma. The palpation stiffness of pancreas was qualitatively evaluated during operation by surgeons. POPF was finally diagnosed and graded through a three-weeks post-operative follow-up according to international study group of pancreatic fistula (ISGPF). SWV values were compared between POPF positive and negative group. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic efficacy of SWV value in predicting POPF. ResultsFrom December 2020 to June 2021, 44 patients were finally enrolled in this study, among which, 26 patients were identified to develop POPF after pancreatectomy. The SWV value of pancreatic parenchyma in POPF positive group was significantly lower than that in POPF negative group (P = 0.001). However, there was no significant difference in palpation stiffness between the two groups (P = 0.124). Besides, neither the SWV value of FPL nor the SWV ratio between FPL to surrounding pancreatic parenchyma differ significantly between POPF positive and negative group (P > 0.05). Taking SWV value of pancreatic parenchyma >1.10 m/s as a cut-off value for predicting POPF, area under the receiver operating characteristic curve (AUROC) was 0.864 with 72.2% sensitivity, 92.3% specificity, 86.7% positive predictive value (PPV) and 82.8% negative predictive value (NPV), respectively. ConclusionsVTIQ technique might be a potential non-invasive imaging method to predict POPF before pancreatectomy in future clinical practice.

Research status of risk prediction and management of postoperative pancreatic fistula

Pancreatic fistula is a common complication of pancreatic surgery and also a leading cause of postoperative death. The 2016 International Study Group on Pancreatic Surgery definition and grading criterion of postoperative pancreatic fistula (POPF) is instructive to clinical practice and scientific research. Although the criterion is widely applied, further optimization is required. It has established a variety of risk prediction models, which forwards the early diagnosis of POPF. However, the inconsistency of the criteria and the potential mutual influence of multiple factors hindered the model extrapolation. Moreover, it remains controversial in specific strategies of perioperative nutritional support, surgical methods, postoperative drainage, and somatostatin application in the prevention and treatment of POPF. Thus, more prospective studies are needed to explore safer, more effective and economical POPF prediction and intervention methods.

Perioperative acinar cell count method works well in the prediction of postoperative pancreatic fistula and other postoperative complications after pancreaticoduodenectomy

BackgroundEarlier we have shown that high frequency of acinar cells in the pancreatic transsection line predicts postoperative pancreatic fistula after pancreaticoduodenectomy (PD). Acinar cell count method (ACM) is fast to perform during operation. In this study our aim was to validate the accuracy of ACM to compare it with other published risk prediction methods. Methods87 patients who underwent PD without any trial including perioperative medications were collected from a single hospital. Data on demographics, surgical details, postoperative complications clinically relevant pancreatic fistulae (CR-POPF) and clinically relevant Clavien-Dindo complications (CR-CDC) were registered. Thirteen previously published risk prediction methods were included in the comparison, such as pancreatic duct diameter, palpable texture of pancreas, Braga score (BC), Fistula Risk Score, Modified Fistula Risk Score, Alternative Fistula Risk Score and multiple radiological parameters. ROC-curves were calculated to compare sensitivity and specificity for identifying high risk patients for CR-POPF and CR-CDC. ResultsThe three most accurate risk prediction methods for CR-POPF were ACM (sensitivity 88.9%, specificity 52.6%; p = 0.043), BC (87.5%, 56.6%; p = 0.039) and visceral fat area to subcutaneous fat area ratio (75.5%, 80.0%; p = 0.032). In predicting CR-CDC the three most accurate methods were ACM (73.9%, 56.2%; p = 0.033), BC (68.4%, 59.5%; p = 0.036) and TPAI (78.3%, 41.7%; p = 0.012). ConclusionACM was shown to be as good as the more complicated risk scoring methods in the prediction of CR-POPF. It was good also in predicting all clinically relevant complications. ACM is easy to use during operation and can be recommended as a routine risk prediction method.

Scoring systems to predict pancreatic fistula after Whipple procedure

Specific complications is an «Achilles heel» of pancreaticoduodenectomy. Postoperative pancreatic fistula (POPF) is the most common specific complication. POPF prediction is an actual problem in pancreatic surgery. Analysis of statistically significant scoring systems to predict POPF is a modern trend in perioperative planning. Several prognostic scales (FRS, a-FRS, ua-FRS, Modified Fistula Risk Score) are recommended for clinical practice.

Postoperative C-reactive protein as a predictor of postoperative pancreatic fistula and hospital readmission following pancreaticoduodenectomy

Introduction: Postoperative pancreatic fistula (POPF) is the Achilles heel following Pancreaticoduodenectomy (PD).Early prediction of POPF has direct influence on patient management and outcome. This study aimed at identifying role of C-reactive protein (CRP) on first postoperative day (POD1) as predictor of clinically relevant pancreatic fistula (CR-POPF) and at discharge as a predictor of hospital readmission. Methods: A prospective observational quantitative study was performed on 49 patients over one year who underwent PD. Clinical, biochemical, intraoperative and pathological characteristics were recorded. Quantitative serum CRP was sent on POD1 and at discharge. POPF was graded according to International Study Group in Pancreatic Surgery 2016.Diagnostic accuracy of CRP on POD1 to predict CR-POPF and at discharge to predict 90 day readmission were assessed by Receiver Operating Characteristics (ROC) curve analysis and cut-off value of CRP was calculated. Results: Overall morbidity was 57.1% with mortality of 4.1%.Bile leak occurred in 38.8%.CR-POPF developed in 26.5% and cholangitis was independent risk factor(p< 0.05). Readmission rate was 14.3%. ROC curve analysis showed POD1 CRP level >100mg/l as a predictor of CR-POPF (AUC: 0.687; 95%CI [0.522-0.852] and CRP>50mg/L at discharge as a significant predictor of hospital readmission (AUC: 0.807 (95%CI [0.607-0.100], p< 0.05). Conclusion: CRP is a reliable predictor of CR-POPF and hospital readmission, thus should be utilized in patient management. Keywords: C-reactive protein; Pancreaticoduodenectomy, Postoperative pancreatic fistula; Readmission

Perioperative Acinar Cell Count Method Works Well in the Prediction of Postoperative Pancreatic Fistula and Other Postoperative Complications After Pancreaticoduodenectomy

Earlier we have shown that high frequency of acinar cells in the pancreatic transsection line predicts postoperative pancreatic fistula after pancreaticoduodenectomy (PD). Acinar cell count method (ACM) is fast to perform during operation. In this study our aim was to validate the accuracy of ACM to compare it with other published risk prediction methods. 87 patients who underwent PD without any trial including perioperative medications were collected from a single hospital. Data on demographics, surgical details, postoperative complications clinically relevant pancreatic fistulae (CR-POPF) and clinically relevant Clavien-Dindo complications (CR-CDC) were registered. Thirteen previously published risk prediction methods were included in the comparison, such as pancreatic duct diameter, palpable texture of pancreas, Braga score (BC), Fistula Risk Score, Modified Fistula Risk Score, Alternative Fistula Risk Score and multiple radiological parameters. ROC-curves were calculated to compare sensitivity and specificity for identifying high risk patients for CR-POPF and CR-CDC. The three most accurate risk prediction methods for CR-POPF were ACM (sensitivity 88.9%, specificity 52.6%; p=0.043), BC (87.5%, 56.6%; p=0.039) and visceral fat area to subcutaneous fat area ratio (75.5%, 80.0%; p=0.032). In predicting CR-CDC the three most accurate methods were ACM (73.9%, 56.2%; p=0.033), BC (68.4%, 59.5%; p=0.036) and TPAI (78.3%, 41.7%; p=0.012). ACM was shown to be as good as the more complicated risk scoring methods in the prediction of CR-POPF. It was good also in predicting all clinically relevant complications. ACM is easy to use during operation and can be recommended as a routine risk prediction method.

What should we trust to define, predict and assess pancreatic fistula after pancreatectomy?

ObjectiveThe ISGPF postoperative pancreatic fistula (POPF) definition using amylase drain concentration is widely used. However, the interest of lipase drain concentration, daily drain output and absolute enzyme daily production (concentration x daily drain volume) have been poorly investigated. Material and methodsThese predictive on postoperative day (POD) 1, 3, 5 and 7 were analyzed in a development cohort, and subsequently tested in an independent validation cohort. ResultsOf the 227 patients of the development cohort, 17% developed a biochemical fistula and 34% a POPF (Grade B/C). Strong correlation was found between amylase/lipase drain concentration at all postoperative days (ρ = 0.90; p = 0.001). Amylase and lipase were both significantly higher in patients with a POPF (p < 0.001) presenting an equivalent under the ROC curve area (0.85 vs 0.84; p = 0.466). Combining POD1 and POD3 threefold enzyme cut-off value increased significantly POPF prediction sensibility (97.4% vs 77.8%) and NPV (97.1% vs 86.3%). These results were also confirmed in the validation cohort of 554 patients. Finally, absolute enzyme daily production and daily drain output were significantly higher in patients with a POPF (p < 0.001) but did not add clinical value when compared to drain enzyme concentration. ConclusionLipase is as effective as amylase drain concentration to define POPF. Absolute enzyme daily production or daily drain output do not help to better predict clinically significant POPF occurrence and severity. Lipase and amylase should mainly be used for their negative predictive value to predict the absence of clinically significant POPF and could allow early drain removal and hospital discharge.

Risk prediction platform for pancreatic fistula after pancreatoduodenectomy using artificial intelligence.

BACKGROUNDDespite advancements in operative technique and improvements in postoperative managements, postoperative pancreatic fistula (POPF) is a life-threatening complication following pancreatoduodenectomy (PD). There are some reports to predict POPF preoperatively or intraoperatively, but the accuracy of those is questionable. Artificial intelligence (AI) technology is being actively used in the medical field, but few studies have reported applying it to outcomes after PD.AIMTo develop a risk prediction platform for POPF using an AI model.METHODSMedical records were reviewed from 1769 patients at Samsung Medical Center who underwent PD from 2007 to 2016. A total of 38 variables were inserted into AI-driven algorithms. The algorithms tested to make the risk prediction platform were random forest (RF) and a neural network (NN) with or without recursive feature elimination (RFE). The median imputation method was used for missing values. The area under the curve (AUC) was calculated to examine the discriminative power of algorithm for POPF prediction.RESULTSThe number of POPFs was 221 (12.5%) according to the International Study Group of Pancreatic Fistula definition 2016. After median imputation, AUCs using 38 variables were 0.68 ± 0.02 with RF and 0.71 ± 0.02 with NN. The maximal AUC using NN with RFE was 0.74. Sixteen risk factors for POPF were identified by AI algorithm: Pancreatic duct diameter, body mass index, preoperative serum albumin, lipase level, amount of intraoperative fluid infusion, age, platelet count, extrapancreatic location of tumor, combined venous resection, co-existing pancreatitis, neoadjuvant radiotherapy, American Society of Anesthesiologists’ score, sex, soft texture of the pancreas, underlying heart disease, and preoperative endoscopic biliary decompression. We developed a web-based POPF prediction platform, and this application is freely available at http://popfrisk.smchbp.org.CONCLUSIONThis study is the first to predict POPF with multiple risk factors using AI. This platform is reliable (AUC 0.74), so it could be used to select patients who need especially intense therapy and to preoperatively establish an effective treatment strategy.

External validation and comparison of the original, alternative and updated-alternative fistula risk scores for the prediction of postoperative pancreatic fistula after pancreatoduodenectomy

BackgroundMany postoperative pancreatic fistula (POPF) predictions models were developed and validated in western populations. Direct use of these models in the large Indian/Asian population, however, requires proper validation. ObjectiveTo validate the original, alternative and updated alternative fistula risk score (FRS) models. MethodsA validation study was performed in consecutive patients undergoing pancreatoduodenectomy (PD) from January 2011 to March 2018. The area under the receiver operating curve (ROC) and calibration plots were used to assess the performance of original-FRS (o-FRS), alternative FRS (a-FRS) and updated alternative FRS (ua-FRS) models. ResultsThis cohort consisted of 825 patients of which 66% were males with a median age of 55 years and mean body mass index of 22.6. The majority of tumors (61.8%) were of periampullary origin. Clinically relevant POPF was observed in 16.8% patients. Area under curve (AUC) of ROC for the o-FRS was 0.65, 0.69 for a-FRS and 0.70 for ua-FRS, respectively (p = 0.006). ConclusionsIn this large Indian cohort of predominantly periampullary tumors, the ua-FRS performed better than the a-FRS and o-FRS, although differences were small. Since the AUC value of the ua-FRS is at the accepted threshold there might be room for improvement for a FRS.