|
Abstract
|
OBJECTIVE: To use machine learning to predict AIS scores for newly injured SCI patients at hospital discharge time from hospital admission data. Additionally, to analyze the best model for feature importance in order to validate the criticality of AIS score and highlight relevant demographic details.
DESIGN: Data used for training machine learning models was from the NSCISC database of United States SCI patient details. 18 real features were used from 417 provided ones, which mapped to 53 machine learning features after processing. 8 models were tuned on the dataset to predict AIS scores and Shapely analysis was performed to extract the most important of the 53 features.
PARTICIPANTS: Patients within the NSCISC database who sustained injuries between 1972 and 2016 after data cleaning (n = 20,790).
OUTCOME MEASURES: Test set multi-class and aggregated Shapely score magnitudes.
RESULTS: Ridge Classifier was the best performer with 73.6% test set accuracy. AIS scores and neurologic category at admission time were the best predictors of recovery. Demographically, features were less important but age, sex, marital status, and race stood out. AIS scores on admission are highly predictive of patient outcomes when combined with patient demographic data.
CONCLUSION: Promising results in terms of predicting recovery were seen and Shapely analysis allowed for the machine learning model to be probed as whole, giving insight into overall feature trends.SignificanceThe research is intended to introduce the use of machine learning to enhance predictive capabilities of spinal cord injury recovery, to validate previous motor-sensory classification work, and to extract important deciders of recovery from constructed models.
Language: en |