Artificial Intelligence in developing realistic expectations following a Total Knee Arthroplasty
Bibliographic record
Abstract
The integration of artificial intelligence (AI) in clinical decision-making has the potential to enhance patient understanding and confidence in treatment choices. This study evaluates the impact of an AI-based online tool in assisting patients with knee osteoarthritis (OA) to develop realistic expectations following a total knee arthroplasty. A total of 109 patients were enrolled; 4 were excluded (3 due to navigation difficulties and 1 due to time constraints), leaving 105 patients. All patients underwent clinical and radiographic assessment, followed by a final diagnosis and a treatment plan involving either non-operative management or surgery. Participants were invited to use an AI-based decision-support tool, and their time to complete the program was recorded. Upon completion, results were documented, and patients completed a questionnaire assessing the AI tool's usefulness and ease of use. The AI tool altered the treatment decision in 10.6 % of patients. Most participants found the AI system beneficial, with 83.8 % rating it as helpful and 96.1 % reporting ease of navigation. Additionally, 83.4 % of patients experienced greater peace of mind regarding their decision, and 90 % would recommend the AI tool. The mean time to complete the AI program was 17.5 min (range: 6–36 min, SD: 6.65). Statistically significant correlations were found between the severity of OA and the likelihood of surgical booking (p = 0.0121, OR = 3.57), BMI and surgery booking (p = 0.0036, OR = 1.28), and patient's age and surgical booking (p = 0.022). There was no significant association between AI recommendations and patients' final treatment decisions. However, lower predicted improvement in pain by AI was significantly associated with a contradiction in the patient's decision (p = 0.031, OR = 1.03). Older patients took longer to complete the AI program (p = 0.00041). Increased age correlated with a lower predicted risk of mortality (p = 0.0001) but a higher risk of complications (p = 0.003). Higher BMI was associated with a lower predicted complication risk (p = 0.002). Higher Oxford scores correlated with a lower likelihood of surgery (p = 0.011, OR = 1.09), while higher KOOS scores increased surgical likelihood (p = 0.044, OR = 0.89). The AI-based decision tool was well-received, providing reassurance and guidance for patients. However, its influence on actual treatment decisions was limited. Factors such as OA severity, BMI, and age significantly impacted surgical decisions, whereas AI predictions did not alter final choices. Further refinement of AI algorithms may enhance their predictive value and impact on decision-making.
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 | 0.002 | 0.020 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".