Pancreaticoduodenectomy (PD) is burdened by a treacherous postoperative complication, the pancreatic fistula (PF). Pancreas morphology, clinical features and sarcopenic obesity (SO) are related to the development of a PF. 
Create an artificial intelligence (AI) risk model able to predict PF by combining radiomic features extracted by preoperative CT images.100 patients undergoing PD from 2010 through 2020 were included. 
Two radiologists annotated pancreatic parenchyma and muscle/fatty tissue on CT. Clinical data, radiomic features defining pancreas morphology and SO were fed to a machine learning pipeline with the optimal hyper-parameter configuration based on a cross-validation phase. Clinically relevant PF was the primary outcome.
A logistic regression model with principal component analysis demonstrated a specificity of 0.690 and a sensibility of 0.751 a true-positive predictive value of 0.422, a negative of 0.902 and an AUC of 0.790. Clinical, morphological and SO features were relevant in this model. Then we applied a random forest model, we found similar consistent metrics but, in this case, clinical features were not relevant to build the model.
Our multimodal AI risk model for clinically relevant PF is consistent and showed a strong negative predictive value. The possibility to identify preoperatively patients that will not develop a PF could greatly improve the clinical management.

Artificial intelligence in pancreatic surgery: development of a multimodal risk score to predict short-terms outcomes through radiomic analysis

The new EuSoMII Annual Meeting 2020 is a very nice live format with hosts and moderators in live video streaming  plus speakers connected remotely from Europe and US. The Program includes a morning session with Didactic Lectures and the possibility to do an examination at the end. A great afternoon session will follow: 2 great European speakers  and a Joint Session with our US partner  SIIM (Society for Imaging Informatics in Medicine). [Visit the Event Page](https://www.eusomii.org/events/eusomii-annual-meeting-2020/https://www.eusomii.org/events/eusomii-annual-meeting-2020/#:~:text=The%20new%20EuSoMII%20Annual%20Meeting,an%20examination%20at%20the%20end.)

[Introduction of the speakers](https://drive.google.com/file/d/12c7ObMM72HgA6TYZ1j8NWTqCcHumXurG/view?usp=sharing)

Sponsors:
[SECTRA PLATINUM EXCLUSIVE](https://medical.sectra.com/solutionarea/ai-medical-imaging/) | [QUIBIM Platinum](https://quibim.com/) | [PHILIPS Platinum](https://www.philips.com/global) | [ROBOVISION Platinum](https://robovision.ai/) | [BRACCO Imaging GOLD](https://www.braccoimaging.com/) | [Contextflow Silver](https://contextflow.com/) | [TeraRecon Silver](https://www.terarecon.com/) | [InferVISION](https://global.infervision.com/)