Patients Consistently Report Worse Outcomes Following Revision Total Knee Arthroplasty Compared to Primary Total Knee Arthroplasty.

BACKGROUND: Differences in patient-reported outcome measures (PROMs) between primary TKA (pTKA) and revision TKA (rTKA) have not been well-studied. Therefore, we compared pTKA and rTKA patients by the rates of achieving the Minimal Clinically Important Difference for Improvement (MCID-I) and Worsening (MCID-W). METHODS: A total of 2,448 patients (2,239 pTKAs/209 rTKAs) were retrospectively studied. Patients who completed the Knee Injury and Osteoarthritis Outcome Score-Physical Function Short Form (KOOS-PS), Patient-Reported Outcomes Measurement Information System (PROMIS) Physical Function Short Form 10a (PF10a), PROMIS Global-Mental, or PROMIS Global-Physical questionnaires were identified by Current Procedural Terminology (CPT) codes. Patient-reported outcome measures and MCID-I/MCID-W rates were compared. Multivariate logistic regression models measured relationships between surgery type and postoperative outcomes. RESULTS: Patients who underwent rTKA (all causes) had lower rates of improvement and higher rates of worsening compared to pTKA patients for KOOS-PS (MCID-I: 54 versus 68%, P < .001; MCID-W: 18 versus 8.6%, P < .001), PF10a (MCID-I: 44 versus 65%, P < .001; MCID-W: 22 versus 11%, P < .001), PROMIS Global-Mental (MCID-I: 34 versus 45%, P = .005), and PROMIS Global-Physical (MCID-I: 51 versus 60%, P = .014; MCID-W: 29 versus 14%, P < .001). Undergoing revision was predictive of worsening postoperatively for KOOS-PS, PF10a, and PROMIS Global-Physical compared to pTKA. Postoperative scores were significantly higher for all 4 PROMs following pTKA. CONCLUSION: Patients reported significantly less improvement and higher rates of worsening following rTKA, particularly for PROMs that assessed physical function. Although pTKA patients did better overall, the improvement rates may be considered relatively low and should prompt discussions on improving outcomes following pTKA and rTKA. LEVEL OF EVIDENCE: Level III, retrospective comparative study.

The Not-So-Distant Future or Just Hype? Utilizing Machine Learning to Predict 30-Day Post-Operative Complications in Laparoscopic Colectomy Patients.

BACKGROUND: Complex machine learning (ML) models have revolutionized predictions in clinical care. However, for laparoscopic colectomy (LC), prediction of morbidity by ML has not been adequately analyzed nor compared against traditional logistic regression (LR) models. METHODS: All LC patients, between 2017 and 2019, in the National Surgical Quality Improvement Program (NSQIP) were identified. A composite outcome of 17 variables defined any post-operative morbidity. Seven of the most common complications were additionally analyzed. Three ML models (Random Forests, XGBoost, and L1-L2-RFE) were compared with LR. RESULTS: Random Forests, XGBoost, and L1-L2-RFE predicted 30-day post-operative morbidity with average area under the curve (AUC): .709, .712, and .712, respectively. LR predicted morbidity with AUC = .712. Septic shock was predicted with AUC ≤ .9, by ML and LR. CONCLUSION: There was negligible difference in the predictive ability of ML and LR in post-LC morbidity prediction. Possibly, the computational power of ML cannot be realized in limited datasets.

Patient-Reported Mental Health Score Influences Physical Function After Primary Total Knee Arthroplasty.

BACKGROUND: Despite the effectiveness of total knee arthroplasty (TKA), patients often have lingering pain and dysfunction. Recent studies have raised concerns that preoperative mental health may negatively affect outcomes after TKA. The primary aim of this study investigates the relationship between patient-reported mental health and postoperative physical function following TKA. METHODS: A retrospective study of 1392 primary TKA patients was performed. Mental health and physical function scores were measured using the Patient-Reported Outcomes Measurement Information System (PROMIS) Global Health, and PROMIS Physical Function 10a and Knee injury and Osteoarthritis Outcome Score Physical Function (KOOS-PS) short forms. These assessments were completed preoperatively and up to 1-year postoperatively. Patients were stratified based on preoperative mental health scores into five distinct categories ranging from "Poor" to "Excellent." Locally estimated scatter plot smoothing curves (LOESS) were fit to the data examining physical function score trends over time. RESULTS: Patients with higher mental health scores before surgery demonstrated better preoperative and postoperative physical function scores. However, all patients experienced similar gains in physical function following surgery. Despite this early improvement, patients with the worst mental health scores experienced a sharp decline in physical function approximately a year after surgery and did not appear to recover. CONCLUSIONS: Poor mental health should not be a contraindication for performing TKA. For patients with the lowest mental health scores, physicians should account for the possibility that physical function scores may deteriorate a year after surgery. Tighter follow-up guidelines, more frequent physical therapy visits, or treatment for mental health issues may be considered to counter such deterioration.