Dr. Bas van Niftrik from the MICN Lab has come 1st place in the 2020 clinical research prize of the Clinical Neuroscience Center of the University Hospital Zurich. His paper, entitled “Machine Learning Algorithm Identifies Patients at High Risk for Early Complications After Intracranial Tumor Surgery: Registry-Based Cohort Study” and published in Neurosurgery, elucidates the use of clinical prediction models to forecast early complications after cranial tumor surgery. The authors were able to predict such complications with an area under the curve of 0.73 and a sensitivity and specificity of 0.80 and 0.67, respectively. Early prediction of adverse events allows enhanced healthcare resource allocation, in this case most importantly to already preoperatively identify those patients who most necessitate postoperative surveillance in the neurointensive care unit (ICU). Currently, virtually all patients undergoing brain tumor surgery are admitted to the ICU postoperatively. Another finding of the study was that anatomical location of brain tumors exhibited the greatest variable importance in the clinical prediction model.
Dr. van Niftrik will present the paper at the award ceremony on November 26th 2020 at 17:55.
van Niftrik CHB, van der Wouden F, Staartjes VE, Fierstra J, Stienen MN, Akeret K, Sebök M, Fedele T, Sarnthein J, Bozinov O, Krayenbühl N, Regli L, Serra C (2019) Machine Learning Algorithm Identifies Patients at High Risk for Early Complications After Intracranial Tumor Surgery: Registry-Based Cohort Study. Neurosurgery