Using Presurgical Biopsychosocial Features to Develop an Advanced Clinical Decision-Making Support Tool for Predicting Recovery Trajectories in Patients Undergoing Total Knee Arthroplasty: Protocol for a Prospective Observational Study
Bibliographic record
Abstract
BACKGROUND: Following total knee arthroplasty (TKA), 10% to 20% of patients report dissatisfaction with procedural outcomes. There is growing recognition that postsurgical satisfaction is shaped not only by the quality of surgery but also by psychological and social factors. Surprisingly, information on the psychological and social determinants of surgical outcomes is rarely collected before surgery. A comprehensive collection of biopsychosocial information could assist clinicians in making recommendations in relation to rehabilitation, particularly if there is robust evidence to support the ability of presurgical constructs to predict postsurgical outcomes. Clinical decision support tools can help identify factors influencing patient outcomes and support the provision of interventions or services that can be tailored to meet individuals' needs. However, despite their potential clinical benefit, the application of such tools remains limited. OBJECTIVE: This study aims to develop a clinical decision tool that will assist with patient stratification and more precisely targeted clinical decision-making regarding prehabilitation and rehabilitation for TKA, based on the identified individual biopsychosocial needs. METHODS: In this prospective observational study, all participants provided written or electronic consent before study commencement. Patient-completed questionnaires captured information related to a broad range of biopsychosocial parameters during the month preceding TKA. These included demographic factors (sex, age, and rurality), psychological factors (mood status, pain catastrophizing, resilience, and committed action), quality of life, social support, lifestyle factors, and knee symptoms. Physical measures assessing mobility, balance, and functional lower body strength were performed via video calls with patients in their home. Information related to preexisting health issues and concomitant medications was derived from hospital medical records. Patient recovery outcomes were assessed 3 months after the surgical procedure and included quality of life, patient-reported knee symptoms, satisfaction with the surgical procedure, and mood status. Machine learning data analysis techniques will be applied to determine which presurgery parameters have the strongest power for predicting patient recovery following total knee replacement. On the basis of these analyses, a predictive model will be developed. Predictive models will undergo internal validation, and Bayesian analysis will be applied to provide additional metrics regarding prediction accuracy. RESULTS: Patient recruitment and data collection commenced in November 2019 and was completed in June 2022. A total of 1050 patients who underwent TKA were enrolled in this study. CONCLUSIONS: Our findings will facilitate the development of the first comprehensive biopsychosocial prediction tool, which has the potential to objectively predict a patient's individual recovery outcomes following TKA once selected by an orthopedic surgeon to undergo TKA. If successful, the tool could also inform the evolution rehabilitation services, such that factors in addition to physical performance can be addressed and have the potential to further enhance patient recovery and satisfaction. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48801.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.004 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.012 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".