Predicting falls using electronic health records: a time series approach

Abstract

Objective: To develop a more accurate fall prediction model within the Veterans Health Administration.

Materials and methods: The cohort included Veterans admitted to a Veterans Health Administration acute care setting from July 1, 2020, to June 30, 2022, with a length of stay between 1 and 7 days. Demographic and clinical data were obtained through electronic health records. Veterans were identified as having a documented fall through clinical progress notes. A transformer model was used to obtain features of this data, which was then used to train a Light Gradient-Boosting Machine for classification and prediction. Area under the precision-recall curve assisted in model tuning, with geometric mean used to define an optimal classification threshold.

Results: Among 242,844 Veterans assessed, 5965 (2.5%) were documented as having a fall during their clinical stay. Employing a transformer model with a Light Gradient-Boosting Machine resulted in an area under the curve of .851 and an area under the precision-recall curve of .285. With an accuracy of 76.3%, the model resulted in a specificity of 76.2% and a sensitivity of 77.3%.

Discussion: Prior evaluations have highlighted limitations of the Morse Fall Scale (MFS) in accurately assessing fall risk. Developing a time series classification model using existing electronic health record data, our model outperformed traditional MFS-based evaluations and other fall-risk models. Future work is necessary to address limitations, including class imbalance and the need for prospective validation.

Conclusion: An improvement over the MFS, this model, automatically calculated from existing data, can provide a more efficient and accurate means for identifying patients at risk of fall.

Keywords: Veterans; electronic health records; fall prediction; fall-risk assessment; time series classification.

Figure 1.

Schematic detailing the processing of data into a multi-index data frame, transformation of EHR data, as well as the analysis methods. Note: VHA: Veterans Health Administration; EHR: electronic health records.

Figure 2.

Precision-recall curve and receiver operating characteristic curve representing performance of the final model. Note: ROC, Receiver operating characteristic; PR, precision; AUC, area under curve.

Figure 3.

Confusion matrix representing how the model classified patients against their true classifications.

Figure 4.

Probability calibration curve portraying the true probability against the predictive probability to assess model performance on the reserved test dataset.