IPOscore: An interactive web-based platform for postoperative surgical complications analysis and prediction in the oncology domain.

BACKGROUND: The performance of traditional risk score systems to predict (post)-operative outcomes is limited. This weakness reduces confidence in its use to support clinical risk mitigation decisions. However, the rapid growth of health data in the last years offers principles to deal with some of these limitations. In this regard, the data allows the extraction of relevant information for both patients stratification and the rigorous identification of associated risk factors. The patients can then be targeted to specific preoperative optimization programs, thus contributing to the reduction of associated morbidity and mortality. OBJECTIVES: The main goal of this work is, therefore, to provide a clinical decision support system (CDSS) based on data-driven modeling methods for surgical risk prediction specific for cancer patients in Portugal. RESULTS: The result is IPOscore, a single web-based platform aimed at being an innovative approach to assist clinical decision-making in the surgical oncology domain. This system includes a database to store/manage the clinical data collected in a structured format, data visualization and analysis tools, and predictive machine learning models to predict postoperative outcomes in cancer patients. IPOscore also includes a pattern mining module based on biclustering to assess the discriminative power of a pattern towards postsurgical outcomes. Additionally, a mobile application is provided to this end. CONCLUSIONS: The IPOscore platform is a valuable tool for surgical oncologists not only for clinical data management but also as a preventative and predictive healthcare system. Currently, this clinical support tool is being tested at the Portuguese Institute of Oncology (IPO-Porto), and can be accessed online at https://iposcore.org.

Incidence and Grading of Complications After Gastrectomy for Cancer Using the GASTRODATA Registry: A European Retrospective Observational Study.

OBJECTIVE: Utilizing a standardized dataset based on a newly developed list of 27 univocally defined complications, this study analyzed data to assess the incidence and grading of complications and evaluate outcomes associated with gastrectomy for cancer in Europe. SUMMARY BACKGROUND DATA: The absence of a standardized system for recording gastrectomy-associated complications makes it difficult to compare results from different hospitals and countries. METHODS: Using a secure online platform (www.gastrodata.org), referral centers for gastric cancer in 11 European countries belonging to the Gastrectomy Complications Consensus Group recorded clinical, oncological, and surgical data, and outcome measures at hospital discharge and at 30 and 90 days postoperatively. This retrospective observational study included all consecutive resections over a 2-year period. RESULTS: A total of 1349 gastrectomies performed between January 2017 and December 2018 were entered into the database. Neoadjuvant chemotherapy was administered to 577 patients (42.8%). Total (46.1%) and subtotal (46.4%) gastrectomy were the predominant resections. D2 or D2+ lymphadenectomy was performed in almost 80% of operations. The overall complications' incidence was 29.8%; 402 patients developed 625 complications, with the most frequent being nonsurgical infections (23%), anastomotic leak (9.8%), other postoperative abnormal fluid from drainage and/or abdominal collections (9.3%), pleural effusion (8.3%), postoperative bleeding (5.6%), and other major complications requiring invasive treatment (5.6%). The median Clavien-Dindo score and Comprehensive Complications Index were IIIa and 26.2, respectively. In-hospital, 30-day, and 90-day mortality were 3.2%, 3.6%, and 4.5%, respectively. CONCLUSIONS: The use of a standardized platform to collect European data on perioperative complications revealed that gastrectomy for gastric cancer is still associated with heavy morbidity and mortality. Actions are needed to limit the incidence of, and to effectively treat, the most frequent and most lethal complications.