To determine the impact of automated planning (AP) on the time required for preoperative planning in shoulder arthroplasty, specifically measuring planning duration and user actions.
Approach:
Key Findings:
Surgeons using AP had significantly reduced planning times compared to those using manual methods (p < 0.05).
The number of user actions required was also lower in the AP group (p < 0.05).
Surgeon experience with the software influenced planning efficiency, with expert users benefiting the most.
Interpretation:
Automated planning tools can streamline preoperative planning, reducing time and effort for surgeons, particularly beneficial for those with less experience by providing structured guidance.
Limitations:
The study focused only on glenoid-side implant planning, leaving humeral-side planning to the surgeon, which may affect overall planning efficiency.
Data was limited to a specific software version and may not generalize to other systems, potentially limiting the applicability of the findings.
Conclusion:
AP in preoperative planning for shoulder arthroplasty significantly decreases planning time and user actions, supporting its use in clinical practice.
In a UK cohort, patients with osteoarthritis who initiated centrally acting analgesics had a higher hazard of knee or hip replacement than those who initiated SSRIs, though residual confounding by pain severity remains a key limitation.
Machine-learning models distinguished healthy knees from those with osteoarthritis-related cartilage damage, but age and BMI performed as well as or better than the vibration-based models.
Researchers urge caution in interpreting joint replacement predictors, noting that surgery reflects access and decision-making as well as disease biology.