Streamlining the KOOS Activities of Daily Living Subscale Using Machine Learning

Ashim Gupta; Ajish S R Potty; Deepak Ganta; R Justin Mistovich; Sreeram Penna; Craig Cady; Anish G Potty

doi:10.1177/2325967120910447

Streamlining the KOOS Activities of Daily Living Subscale Using Machine Learning

Orthop J Sports Med. 2020 Mar 24;8(3):2325967120910447. doi: 10.1177/2325967120910447. eCollection 2020 Mar.

Authors

Ashim Gupta^{1

2

3

4}, Ajish S R Potty¹, Deepak Ganta⁵, R Justin Mistovich⁶, Sreeram Penna⁷, Craig Cady⁸, Anish G Potty^{1

9}

Affiliations

¹ South Texas Orthopaedic Research Institute, Laredo, Texas, USA.
² Department of Psychology, Illinois Wesleyan University, Bloomington, Illinois, USA.
³ Future Biologics, Lawrenceville, Georgia, USA.
⁴ BioIntegrate, New York, New York, USA.
⁵ School of Engineering, Texas A&M International University, Laredo, Texas, USA.
⁶ Department of Orthopaedics, School of Medicine, Case Western Reserve University, Cleveland, Ohio, USA.
⁷ Rothman Orthopaedic Institute, Philadelphia, Pennsylvania, USA.
⁸ Department of Biology, Bradley University, Peoria, Illinois, USA.
⁹ Laredo Sports Medicine Clinic, Laredo, Texas, USA.

Abstract

Background: Functional outcome scores provide valuable data, yet they can be burdensome to patients and require significant resources to administer. The Knee injury and Osteoarthritis Outcome Score (KOOS) is a knee-specific patient-reported outcome measure (PROM) and is validated for anterior cruciate ligament (ACL) reconstruction outcomes. The KOOS requires 42 questions in 5 subscales. We utilized a machine learning (ML) algorithm to determine whether the number of questions and the resultant burden to complete the survey can be lowered in a subset (activities of daily living; ADL) of KOOS, yet still provide identical data.

Hypothesis: Fewer questions than the 17 currently provided are actually needed to predict KOOS ADL subscale scores with high accuracy.

Study design: Cohort study (diagnosis); Level of evidence, 2.

Methods: Pre- and postoperative patient-reported KOOS ADL scores were obtained from the Surgical Outcome System (SOS) data registry for patients who had ACL reconstruction. Categorical Boosting (CatBoost) ML models were built to analyze each question and its value in predicting the patient's actual functional outcome (ie, KOOS ADL score). A streamlined set of minimal essential questions were then identified.

Results: The SOS registry contained 6185 patients who underwent ACL reconstruction. A total of 2525 patients between the age of 16 and 50 years had completed KOOS ADL scores presurgically and 3 months postoperatively. The data set consisted of 51.84% male patients and 48.16% female patients, with a mean age of 29 years. The CatBoost model predicted KOOS ADL scores with high accuracy when only 6 questions were asked (R² = 0.95), similar to when all 17 questions of the subscale were asked (R² = 0.99).

Conclusion: ML algorithms successfully identified the essential questions in the KOOS ADL questionnaire. Only 35% (6/17) of KOOS ADL questions (descending stairs, ascending stairs, standing, walking on flat surface, putting on socks/stockings, and getting on/off toilet) are needed to predict KOOS ADL scores with high accuracy after ACL reconstruction. ML can be utilized successfully to streamline the burden of patient data collection. This, in turn, can potentially lead to improved patient reporting, increased compliance, and increased utilization of PROMs while still providing quality data.

Keywords: ADL; KOOS; Knee injury and Osteoarthritis Outcome Score; activities of daily living; anterior cruciate ligament; function of daily living; machine learning algorithm; CatBoost; patient-reported outcome measure.