Machine learning models in predicting graft survival in kidney transplantation: meta-analysis.

BACKGROUND: The variations in outcome and frequent occurrence of kidney allograft failure continue to pose important clinical and research challenges despite recent advances in kidney transplantation. The aim of this systematic review was to examine the current application of machine learning models in kidney transplantation and perform a meta-analysis of these models in the prediction of graft survival. METHODS: This review was registered with the PROSPERO database (CRD42021247469) and all peer-reviewed original articles that reported machine learning model-based prediction of graft survival were included. Quality assessment was performed by the criteria defined by Qiao and risk-of-bias assessment was performed using the PROBAST tool. The diagnostic performance of the meta-analysis was assessed by a meta-analysis of the area under the receiver operating characteristic curve and a hierarchical summary receiver operating characteristic plot. RESULTS: A total of 31 studies met the inclusion criteria for the review and 27 studies were included in the meta-analysis. Twenty-nine different machine learning models were used to predict graft survival in the included studies. Nine studies compared the predictive performance of machine learning models with traditional regression methods. Five studies had a high risk of bias and three studies had an unclear risk of bias. The area under the hierarchical summary receiver operating characteristic curve was 0.82 and the summary sensitivity and specificity of machine learning-based models were 0.81 (95 per cent c.i. 0.76 to 0.86) and 0.81 (95 per cent c.i. 0.74 to 0.86) respectively for the overall model. The diagnostic odds ratio for the overall model was 18.24 (95 per cent c.i. 11.00 to 30.16) and 29.27 (95 per cent c.i. 13.22 to 44.46) based on the sensitivity analyses. CONCLUSION: Prediction models using machine learning methods may improve the prediction of outcomes after kidney transplantation by the integration of the vast amounts of non-linear data.

Patterns of peritoneal dissemination and response to systemic chemotherapy in common and rare peritoneal tumours treated by cytoreductive surgery: study protocol of a prospective, multicentre, observational study.

INTRODUCTION: Despite optimal patient selection and surgical effort, recurrence is seen in over 70% of patients undergoing cytoreductive surgery (CRS) for peritoneal metastases (PM). Apart from the Peritoneal Cancer Index (PCI), completeness of cytoreduction and tumour grade, there are other factors like disease distribution in the peritoneal cavity, pathological response to systemic chemotherapy (SC), lymph node metastases and morphology of PM which may have prognostic value. One reason for the underutilisation of these factors is that they are known only after surgery. Identifying clinical predictors, specifically radiological predictors, could lead to better utilisation of these factors in clinical decision making and the extent of peritoneal resection performed for different tumours. This study aims to study these factors, their impact on survival and identify clinical and radiological predictors. METHODS AND ANALYSIS: There is no therapeutic intervention in the study. All patients with biopsy-proven PM from colorectal, appendiceal, gastric and ovarian cancer and peritoneal mesothelioma undergoing CRS will be included. The demographic, clinical, radiological, surgical and pathological details will be collected according to a prespecified format that includes details regarding distribution of disease, morphology of PM, regional node involvement and pathological response to SC. In addition to the absolute value of PCI, the structures bearing the largest tumour nodules and a description of the morphology in each region will be recorded. A correlation between the surgical, radiological and pathological findings will be performed and the impact of these potential prognostic factors on progression-free and overall survival determined. The practices pertaining to radiological and pathological reporting at different centres will be studied. ETHICS AND DISSEMINATION: The study protocol has been approved by the Zydus Hospital ethics committee (27 July, 2020) and Lyon-Sud ethics committee (A15-128). TRIAL REGISTRATION NUMBER: CTRI/2020/09/027709; Pre-results.

Margin ACcentuation for resectable Pancreatic cancer using Irreversible Electroporation - Results from the MACPIE-I study.

INTRODUCTION: Margin accentuation (MA) using Irreversible electroporation (IRE) offers an unique opportunity to reduce the R1 resections in resectable pancreatic cancer (RPC). This study aims to assess the rate of margin positivity using IRE for MA during pancreaticoduodenectomy (PD) for resectable pancreatic head tumours. MATERIALS AND METHODS: Following ethical approval, MA using IRE was carried out in 20 consecutive patients to posterior and superior mesenteric vein (SMV) margin, and the pancreatic neck, prior to the PD resection. The control group (non-IRE; n = 91) underwent PD without MA over the study period, March 2018 to March 2020. RESULTS: There was no difference between the two groups in terms of patients' age, gender, pre-op biliary drainage, site of malignancy or pre-operative TNM stage. The overall margin positive rate for IRE group was lesser (35.0%) when compared to non-IRE group (51.6%; p = 0.177), with significantly less posterior pancreatic margin positivity (5.0% vs. 25.3%; p = 0.046). When only treated margins (SMA margin excluded) were compared, the IRE group had significantly lower margin positive rates (20.0% vs. 51.6%; p = 0.013). There was no difference between the two groups in terms of intra- or post-operative complications. With a median follow-up of 15.6 months, the median DFS and OS for IRE and non-IRE groups were 17 and 18 months (p = 0.306) and 19 and 22 months (p = 0.227) respectively. CONCLUSION: Our pilot study confirms the safety of MA using IRE for RPC, with reduction in margin positivity. These results as a proof of concept are promising and need further validation with a randomised controlled trial.