• Whitney E Muhlestein, Meredith A Monsour, Gabriel N Friedman, Aniket Zinzuwadia, Marcus A Zachariah, Jean-Valery Coumans, Bob S Carter, and Lola B Chambless.
• Department of Neurosurgery, University of Michigan Medical Center, Ann Arbor, Michigan.
• Neurosurgery. 2021 Mar 15; 88 (4): 838-845.

BackgroundMachine learning (ML)-based predictive models are increasingly common in neurosurgery, but typically require large databases of discrete variables for training. Natural language processing (NLP) can extract meaningful data from unstructured text.ObjectiveTo present an NLP model that predicts nonhome discharge and a point-of-care implementation.MethodsWe retrospectively collected age, preoperative notes, and radiology reports from 595 adults who underwent meningioma resection in an academic center from 1995 to 2015. A total of 32 algorithms were trained with the data; the 3 best performing algorithms were combined to form an ensemble. Predictive ability, assessed by area under the receiver operating characteristic curve (AUC) and calibration, was compared to a previously published model utilizing 52 neurosurgeon-selected variables. We then built a multi-institutional model by incorporating notes from 693 patients at another center into algorithm training. Permutation importance was used to analyze the relative importance of each input to model performance. Word clouds and non-negative matrix factorization were used to analyze predictive features of text.ResultsThe single-institution NLP model predicted nonhome discharge with AUC of 0.80 (95% CI = 0.74-0.86) on internal and 0.76 on holdout validation compared to AUC of 0.77 (95% CI = 0.73-0.81) and 0.74 for the 52-variable ensemble. The multi-institutional model performed similarly well with AUC = 0.78 (95% CI = 0.74-0.81) on internal and 0.76 on holdout validation. Preoperative notes most influenced predictions. The model is available at http://nlp-home.insds.org.ConclusionML and NLP are underutilized in neurosurgery. Here, we construct a multi-institutional NLP model that predicts nonhome discharge.© Congress of Neurological Surgeons 2021.

25 keywords...

hide…