Leveraging social supports for improving personal expertise on ACL reconstruction and rehabilitation

What Are Our Patients Really Telling Us? Psychological Constructs Associated With Patient-Reported Outcomes After Anterior Cruciate Ligament Reconstruction

CONTEXT

Depressed patient-reported outcomes (PROs) are directly related to suboptimal recovery after anterior cruciate ligament reconstruction (ACLR). Various PROs commonly used after ACLR can provide a gross estimation of function but do not fully elucidate the causes of self-perceived disability.

OBJECTIVE

To more fully characterize the factors driving responses on PROs.

DESIGN

Cross-sectional study. A mixed-methods approach was used, in which qualitative interviews were conducted alongside administration of PROs to uncover the themes behind a participant's PRO responses.

SETTING

Laboratory.

PATIENTS OR OTHER PARTICIPANTS

Twenty-one individuals with unilateral ACLR (age = 20.90 ± 2.86 years, height = 172.0 ± 11.03 cm; mass = 71.52 ± 13.59 kg, postsurgery = 3.66 ± 3.03 years).

MAIN OUTCOME MEASURE(S)

Patient-reported outcome measures were administered and qualitative interviews were conducted. The PROs consisted of the International Knee Documentation Committee form, Knee Injury and Osteoarthritis Outcomes Score (KOOS), ACL-Return to Sport after Injury (ACL-RSI) scale, and Tampa Scale of Kinesiophobia (TSK). A hierarchical cluster analysis was used to identify subgroups based on PRO responses. Qualitative interviews provided supplemental insight into perceived disability. Independent t tests examined cluster differences for themes. Spearman ρ correlations indicated associations between PRO responses and themes.

RESULTS

Two clusters (perceived high or low disability) emerged. Individuals with low perceived disability scored better on all PROs (P < .05) except for the KOOS-Activities of Daily Living. Internal and external facilitators or barrier subthemes emerged from the interviews. A significant difference was present between clusters and themes. Lower TSK andgreater ACL-RSI and KOOS-Quality of Life scores were associated with more perceived facilitators.

CONCLUSIONS

Participants with greater internal motivation and confidence and a support network had improved PROs. Those with avoidance tendencies, fear, lack of clear expectations, and less social support scored worse on PROs. The TSK, ACL-RSI, and KOOS-Quality of Life scales were best able to capture the constructs associated with perceived wellness, which reinforces their utility in recovery.

Hierarchical classification of large-scale patient records for automatic treatment stratification

In this paper, a hierarchical learning algorithm is developed for classifying large-scale patient records, e.g., categorizing large-scale patient records into large numbers of known patient categories (i.e., thousands of known patient categories) for automatic treatment stratification. Our hierarchical learning algorithm can leverage tree structure to train more discriminative max-margin classifiers for high-level nodes and control interlevel error propagation effectively. By ruling out unlikely groups of patient categories (i.e., irrelevant high-level nodes) at an early stage, our hierarchical approach can achieve log-linear computational complexity, which is very attractive for big data applications. Our experiments on one specific medical domain have demonstrated that our hierarchical approach can achieve very competitive results on both classification accuracy and computational efficiency as compared with other state-of-the-art techniques.