Performance metrics measures as Receiver Operator Characteristics Area Under the Curve (ROC AUC) of the four different modelling approaches benchmarked against each other for predicting the mortality and the 18 different complications included in the National Surgical Quality Improvement Program (NSQIP) dataset.

<p>SSSI: Superficial Surgical site infection, DSSI: Deep surgical site infection, OSSI: Organ/space surgical site infection, WOUND: Wound disruption, PNEUMONIA: Postoperative pneumonia, UNPINT: Unplanned intubation, PE: Pulmonary embolism, VENT48: Ventilator dependence >48 hours, PRI: Progr...

Full description

Saved in:

Bibliographic Details
Main Author:	Mikkel Bonde (17322967) (author)
Other Authors:	Alexander Bonde (11655949) (author), Haytham Kaafarani (12137067) (author), Andreas Millarch (20485197) (author), Martin Sillesen (697747) (author)
Published:	2024
Subjects:	Medicine Genetics Marine Biology Cancer Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified specific patient cohort pancreatic ductal adenocarcinoma optimal treatment planning deep neural networks 2002 &# 8211 transfer learning may surgical risk calculator pd specific cohort pd patient cohort modelling approaches comprised xlink "> pancreaticoduodenectomy xlink "> data general surgery patients general model achieving general model ), postoperative complication prediction poc risk prediction rf model ). direct model ), 728 pd patients 19 prediction tasks 881 million patients src regarding mortality xlink "> general model risk prediction rf model direct model 19 tasks morbidity prediction subsequent transfer src regarding predicting mortality postoperative complications model trained legacy approaches high risk therefore critical subsequently compared including 31 american college 668 compared
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Similar Items