Comparing "people-like-me" and linear mixed model predictions of functional recovery following knee arthroplasty

Abstract

Objective: Prediction models can be useful tools for monitoring patient status and personalizing treatment in health care. The goal of this study was to compare the relative strengths and weaknesses of 2 different approaches for predicting functional recovery after knee arthroplasty: a neighbors-based "people-like-me" (PLM) approach and a linear mixed model (LMM) approach.

Materials and methods: We used 2 distinct datasets to train and then test PLM and LMM prediction approaches for functional recovery following knee arthroplasty. We used the Timed Up and Go (TUG)-a common test of mobility-to operationalize physical function. Both approaches used patient characteristics and baseline postoperative TUG values to predict TUG recovery from days 1-425 following surgery. We then compared the accuracy and precision of PLM and LMM predictions.

Results: A total of 317 patient records with 1379 TUG observations were used to train PLM and LMM approaches, and 456 patient records with 1244 TUG observations were used to test the predictions. The approaches performed similarly in terms of mean squared error and bias, but the PLM approach provided more accurate and precise estimates of prediction uncertainty.

Discussion and conclusion: Overall, the PLM approach more accurately and precisely predicted TUG recovery following knee arthroplasty. These results suggest PLM predictions may be more clinically useful for monitoring recovery and personalizing care following knee arthroplasty. However, clinicians and organizations seeking to use predictions in practice should consider additional factors (eg, resource requirements) when selecting a prediction approach.

Keywords: patient-centered care; patient-specific modeling; precision medicine; prognosis; recovery of function; total knee arthroplasty.

Figure 1.

Data flow diagram for training and testing dataset.

Figure 2.

Calibration plots for PLM and LMM models in both the training and testing datasets. PLM calibration is displayed in the left column for the training dataset (A) and the testing dataset (C). LMM calibration is displayed in the right column for the training dataset (B) and the testing dataset (D). Observations were binned into deciles according to predicted TUG value. The mean observed TUG value (y axis) is plotted against the mean predicted TUG value (x axis) for each decile. The error bars indicate the confidence interval around the mean observed TUG value for each decile. LMM: linear mixed model; PLM: “people-like-me”; TUG: Timed Up and Go.

Figure 3.

Plotting PLM (left) versus LMM (right) prediction trajectories for individual records. Patient records were divided into tertiles according to the difference in precision between the approaches. Two records were randomly selected from each tertile for plotting. Baseline and follow-up measurements for each record are plotted against the predicted trajectory and prediction intervals. Patient 503’s baseline observation is not depicted because it fell above the y-axis scale. LMM: linear mixed model; PLM: “people-like-me”; TUG: Timed Up and Go.