Predicting Outcome after Total Hip Arthroplasty: The Role of Preoperative Patient-Reported Measures

Early Recovery Outcomes in Patients Undergoing Contemporary Posterior Approach Total Hip Arthroplasty: Each Week Shows Progress

Background: Little is known about patients' postoperative week-by-week progress after undergoing posterior approach total hip arthroplasty (THA) with regard to pain, function, return to work, and driving. Purpose: We sought to evaluate a large cohort of patients undergoing posterior approach THA with modified posterior hip precautions to better understand the trajectory of recovery. Methods: Patients at a single institution undergoing primary posterior approach THA by fellowship-trained arthroplasty surgeons were prospectively enrolled. Patient functional status and early rehabilitation recovery milestones were evaluated preoperatively and each week postoperatively for 6 weeks. Results: Of 312 patients who responded to weekly questionnaires, there were varying response rates per question. At 1 week after surgery, 15% (39/256) of respondents had returned to work, increasing to 57% (129/225) at week 6. At 6 weeks, 77% of patients (174/225) had returned to driving; 25% (56/225) were taking pain medication (including prescription opioids or nonsteroidal anti-inflammatory drugs); and 15% (34/225) were using assistive devices (down from 91%, 78%, 56%, 35%, and 27% at weeks 1, 2, 3, 4, and 5, respectively). Average postoperative Hip dysfunction and Osteoarthritis Outcome Score for Joint Replacement and Lower Extremity Functional Scale scores were significantly higher than preoperative scores. Respondents reported significantly less pain at each week postoperatively than the previous week. Conclusion: These findings suggest that there may be an expected pathway for recovery after posterior THA using perioperative pain protocols, modified postoperative precautions, and physical therapy protocols to improve patient outcomes after THA, with most patients returning to normal at 4 weeks. Defining the expected recovery timeline may help surgeons in counseling patients preoperatively and guiding their recovery.

Can minimal clinically important differences in patient reported outcome measures be predicted by machine learning in patients with total knee or hip arthroplasty? A systematic review

OBJECTIVES

To systematically review studies using machine learning (ML) algorithms to predict whether patients undergoing total knee or total hip arthroplasty achieve an improvement as high or higher than the minimal clinically important differences (MCID) in patient reported outcome measures (PROMs) (classification problem).

METHODS

Studies were eligible to be included in the review if they collected PROMs both pre- and postintervention, reported the method of MCID calculation and applied ML. ML was defined as a family of models which automatically learn from data when selecting features, identifying nonlinear relations or interactions. Predictive performance must have been assessed using common metrics. Studies were searched on MEDLINE, PubMed Central, Web of Science Core Collection, Google Scholar and Cochrane Library. Study selection and risk of bias assessment (ROB) was conducted by two independent researchers.

RESULTS

517 studies were eligible for title and abstract screening. After screening title and abstract, 18 studies qualified for full-text screening. Finally, six studies were included. The most commonly applied ML algorithms were random forest and gradient boosting. Overall, eleven different ML algorithms have been applied in all papers. All studies reported at least fair predictive performance, with two reporting excellent performance. Sample size varied widely across studies, with 587 to 34,110 individuals observed. PROMs also varied widely across studies, with sixteen applied to TKA and six applied to THA. There was no single PROM utilized commonly in all studies. All studies calculated MCIDs for PROMs based on anchor-based or distribution-based methods or referred to literature which did so. Five studies reported variable importance for their models. Two studies were at high risk of bias.

DISCUSSION

No ML model was identified to perform best at the problem stated, nor can any PROM said to be best predictable. Reporting standards must be improved to reduce risk of bias and improve comparability to other studies.

Machine Learning Predicts the Fall Risk of Total Hip Arthroplasty Patients Based on Wearable Sensor Instrumented Performance Tests

BACKGROUND

The prevalence of falls affects the wellbeing of aging adults and places an economic burden on the healthcare system. Integration of wearable sensors into existing fall risk assessment tools enables objective data collection that describes the functional ability of patients. In this study, supervised machine learning was applied to sensor-derived metrics to predict the fall risk of patients following total hip arthroplasty.

METHODS

At preoperative, 2-week, and 6-week postoperative appointments, patients (n = 72) were instrumented with sensors while they performed the timed-up-and-go walking test. Preoperative and 2-week postoperative data were used to form the feature sets and 6-week total times were used as labels. Support vector machine and linear discriminant analysis classifier models were developed and tested on various combinations of feature sets and feature reduction schemes. Using a 10-fold leave-some-subjects-out testing scheme, the accuracy, sensitivity, specificity, and area under the receiver-operator curve (AUC) were evaluated for all models.

RESULTS

A high performance model (accuracy = 0.87, sensitivity = 0.97, specificity = 0.46, AUC = 0.82) was obtained with a support vector machine classifier using sensor-derived metrics from only the preoperative appointment. An overall improved performance (accuracy = 0.90, sensitivity = 0.93, specificity = 0.59, AUC = 0.88) was achieved with a linear discriminant analysis classifier when 2-week postoperative data were added to the preoperative data.

CONCLUSION

The high accuracy of the fall risk prediction models is valuable for patients, clinicians, and the healthcare system. High-risk patients can implement preventative measures and low-risk patients can be directed to enhanced recovery care programs.

Why Do People Undergo THR and What Do They Expect to Gain-A Comparison of the Views of Patients and Health Care Professionals

Little concerted effort has been made to understand why individuals undergo total hip replacement (THR) surgery and their rehabilitation goals. Similarly, insight of views and perspective of health care professionals’ (HCPs) regarding surgery and what objective measures help them with decision-making is lacking. This patient and public involvement report aimed to explore both patients’ and HCPs’ perspectives of THR surgery. Twenty patients, 10 pre-THR, 10 post-THR, 9 physiotherapists, and 6 surgeons took part. Results suggest a consensus among patients and HCPs on pain reduction being the main reason for undergoing THR. The inability to carry out simple daily activities such as dog walking and sleep deprivation had a significant effect on patients’ mental and physical well-being. This article is the first to explore the views of THR patients and HCPs on reasons behind THR surgery amalgamated into a single report. As walking is important, wearable activity monitors are suggested as a possible motivator to enhance patient compliance to self-care rehabilitation and increase quality of life. A future research project on the use of such wearable activity monitors in enhancing mobility post-THR is therefore planned.

Are Oxford Hip Score and Western Ontario and McMaster Universities Osteoarthritis Index Useful Predictors of Clinical Meaningful Improvement and Satisfaction After Total Hip Arthroplasty?

BACKGROUND

Up to 15% of patients express dissatisfaction after total hip arthroplasty (THA). Preoperative patient-report outcome measures (PROMs) scores can potentially mitigate this by predicting postoperative satisfaction, identifying patients that will benefit most from surgery. The aim of this study was to (1) calculate the minimal clinically important difference (MCID) thresholds for Oxford Hip Score (OHS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and the Short Form-36 (SF-36) mental component summary (MCS) and physical component summary (PCS) scores and (2) identify the threshold values of these PROMs that could be used to predict patient satisfaction and expectation fulfilment.

METHODS

Prospectively collected registry data of 1334 primary THA patients who returned for 2-year follow-up from 1998 to 2016 were reviewed. All patients were assessed preoperatively and postoperatively at 2 years using the OHS, WOMAC, and SF-36 PCS/MCS scores. The MCID for each PROMs was calculated, and the proportion of patients that attained MCID was recorded. The relationship between satisfaction, expectation fulfilment, and MCID attainment was analyzed using Spearman rank correlation. Optimal threshold scores for each PROM that predicted MCID attainment and satisfaction/expectation fulfilment at 2 years were calculated using receiver operating curve analysis.

RESULTS

The calculated MCID for OHS, WOMAC, SF-36 PCS, and SF-36 MCS were 5.2, 10.8, 6.7, and 6.2, respectively. A threshold value of 24.5 for the preoperative OHS was predictive of achieving WOMAC MCID at 2 years after THA (area under the curve 0.80, P < .001). 93.1% of patients were satisfied, and 95.5% had expectations fulfilled at 2 years. None of the PROMs were able to predict satisfaction.

CONCLUSION

OHS and WOMAC scores can be used to determine clinical meaningful improvement but are limited in their ability to predict patient satisfaction after THA.

Early improvement in physical activity and function after total hip arthroplasty: Predictors of outcomes

Objectives

This study aims to assess early changes in physical activity and function after total hip arthroplasty (THA) using both subjective and objective methods, and to identify predictors of outcomes of THA.

Patients and methods

Between October 2014 and October 2015, a total of 50 patients (14 males, 36 females; mean age 57.1±13.0 years; range, 31 to 75 years) with end-stage primary hip osteoarthritis who were scheduled for THA and 50 age- and sex-matched controls (10 males, 40 females; mean age 52.9±9.3 years; range, 36 to 75 years) were included in the study. Pain was evaluated using the Numeric Rating Scale (NRS), physical function using the Lequesne Index, physical capacity using the Six-Minute Walking Test (6MWT), and physical activity using both International Physical Activity Impact Questionnaire Short Form (IPAQ-SF) and step count monitor. Data at baseline and six weeks and six months were recorded.

Results

Pain severity was significantly lower after THA at six weeks and six months (NRS scores: 2.83 and 0.82, respectively; p<0.001), compared to baseline. Physical function, capacity, and activity significantly improved after THA at six weeks and six months with a mean Lequesne Index score of 2.62 and 1.02, respectively. The mean 6MWT distance was 272.62 at six weeks and 326.16 at six months. The mean IPAQ and 6MWT results were similar between the patient and control groups at six weeks and six months. Age, presence of comorbidities, and baseline Lequesne Index score were found to be effective on functional outcomes of THA. Age and baseline 6MWT scores were correlated with physical capacity after THA.

Conclusion

Our study showed a significant early improvement in pain severity and physical activity and function at six weeks and six months after THA, compared to baseline values. Baseline values and age were the positive predictors of improved postoperative function and physical capacity.