Using Early Gait Data From a Smart-Enabled Total Knee Arthroplasty to Identify Patient Function and Activity at 90...

Area of Science:

• Orthopedic Surgery
• Biomedical Engineering
• Rehabilitation Medicine

Background:

• A significant portion of total knee arthroplasty (TKA) patients experience suboptimal recovery, characterized by decreased function or activity levels.
• Smart implantable devices (SIDs) offer continuous, adherence-independent kinematic monitoring for early identification of patients at risk for poor outcomes.
• This study investigates the predictive capability of early gait data from SIDs for 90-day TKA recovery outcomes.

Purpose of the Study:

• To determine if early gait data collected by smart implants can predict three-class recovery outcomes (green, yellow, red) at 90 days post-TKA.
• To assess the accuracy and reliability of kinematic modeling in identifying patients with suboptimal recovery trajectories.
• To explore the potential of implant-based data for enabling targeted, early interventions.

Main Methods:

• Kinematic data from 4,281 TKA patients with SIDs were analyzed; 2,809 for training and 1,472 for validation.
• Seven daily gait parameters from postoperative days 8-90 were reduced to composite function and activity scores using principal component analysis.
• Multivariate logistic regression models utilized 'starting' ellipse parameters (days 8-21) to predict 'outcome' ellipses (days 77-90) and assign a three-class recovery measure.

Main Results:

• The predictive model demonstrated a 70.4% overall accuracy in the validation cohort, with a sensitivity of 0.780 and specificity of 0.612.
• The distribution of recovery outcomes (green, yellow, red) was consistent between training and validation datasets.
• Predictive sensitivity was notably higher in women under 65 years (0.801).

Conclusions:

• Passively collected, implant-based gait data within the first three postoperative weeks can reliably predict 90-day recovery class after TKA.
• Early kinematic modeling using SIDs shows promise for identifying patients needing timely, targeted interventions.
• This approach may lead to improved functional recovery and patient satisfaction following total knee arthroplasty.