Developing a Prediction Model for Identification of Distinct Perioperative Clinical Stages in Spine Surgery With Smartphone-Based Mobility Data

Authors

Hasan S. Ahmad, Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Andrew I. Yang, Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Gregory W. Basil, Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, Florida, USA.
Disha Joshi, Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Michael Y. Wang, Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, Florida, USA.
William C. Welch, Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Jang W. Yoon, Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.

Document Type

Article

Abstract

BACKGROUND: Spine surgery outcomes assessment currently relies on patient-reported outcome measures, which satisfy established reliability and validity criteria, but are limited by the inherently subjective and discrete nature of data collection. Physical activity measured from smartphones offers a new data source to assess postoperative functional outcomes in a more objective and continuous manner. OBJECTIVE: To present a methodology to characterize preoperative mobility and gauge the impact of surgical intervention using objective activity data garnered from smartphone-based accelerometers. METHODS: Smartphone mobility data from 14 patients who underwent elective lumbar decompressive surgery were obtained. A time series analysis was conducted on the number of steps per day across a 2-year perioperative period. Five distinct clinical stages were identified using a data-driven approach and were validated with clinical documentation. RESULTS: Preoperative presentation was correctly classified as either a chronic or acute mobility decline in 92% of patients, with a mean onset of acute decline of 11.8 ± 2.9 weeks before surgery. Postoperative recovery duration demonstrated wide variability, ranging from 5.6 to 29.4 weeks (mean: 20.6 ± 4.9 weeks). Seventy-nine percentage of patients ultimately achieved a full recovery, associated with an 80% ± 33% improvement in daily steps compared with each patient's preoperative baseline (P = .002). Two patients subsequently experienced a secondary decline in mobility, which was consistent with clinical history. CONCLUSION: The perioperative clinical course of patients undergoing spine surgery was systematically classified using smartphone-based mobility data. Our findings highlight the potential utility of such data in a novel quantitative and longitudinal surgical outcome measure.

Medical Subject Headings

Exercise; Humans; Lumbosacral Region; Patient Reported Outcome Measures; Reproducibility of Results; Smartphone

Publication Date

5-1-2022

Publication Title

Neurosurgery

E-ISSN

1524-4040

Volume

90

Issue

5

First Page

588

Last Page

596

PubMed ID

35199652

Digital Object Identifier (DOI)

10.1227/neu.0000000000001885

Recommended Citation

Ahmad, Hasan S.; Yang, Andrew I.; Basil, Gregory W.; Joshi, Disha; Wang, Michael Y.; Welch, William C.; and Yoon, Jang W., "Developing a Prediction Model for Identification of Distinct Perioperative Clinical Stages in Spine Surgery With Smartphone-Based Mobility Data" (2022). Neurosurgery. 1892.
https://scholar.barrowneuro.org/neurosurgery/1892