A Qualitative Study of Patient Themes for the Quality of the Total Joint Arthroplasty Experience.

Patients have limited involvement in the development of quality measures that address the experience of undergoing total joint arthroplasty (TJA). Current quality measures may not fully assess the aspects of care that are important to patients. The goal of this study was to understand quality of care in TJA from the patient perspective by exploring patients' knowledge gaps, experiences, and goals. The authors completed a prospective qualitative analysis of patients who had undergone hip or knee TJA. Patients completed an open-ended, structured questionnaire about the surgical and recovery process as it relates to quality of care. The authors used a phenomenologic approach and purposeful sampling to enroll 74 patients 6 to 8 weeks after TJA. Responses underwent thematic analysis. Codes were used to identify themes that were important to patients in quality of care in TJA. The authors identified 3 themes: (1) returning to activity without pain or complication, which included psychological, functional, and complication-related goals; (2) negotiating the physical and psychological challenges of recovery, which encompassed the need for assistance from the caregiver as well as psychological and physical barriers to recovery; and (3) being prepared and informed for the process of surgery, including physical, logistical, and psychological preparation. Both patients and health systems may benefit from efforts to address these patient-centered themes of quality care through quality measures for TJA (eg, improving the psychological challenges of recovery). Future quality measures, such as assessment of patient experience, may be made more patient centered if they measure and improve aspects of care that matter to patients. [Orthopedics. 2021;44(2):117-122.].

The Importance of Concordance Between Patients and Their Subspecialists.

Concordance, the concept of patients having shared demographic/socioeconomic characteristics with their physicians, has been associated with improved patient satisfaction and outcomes in primary care but has not been studied in subspecialty care. The objective of this study was to investigate whether patients value concordance with their specialty physicians. The authors assessed the importance of concordance in subspecialist care in 2 cohorts of participants. The first cohort consisted of patients seeking care at a multispecialty orthopedic clinic. The second cohort consisted of volunteer participants recruited from an online platform. Each participant completed a survey scored on an ordinal scale which characteristics of their physicians they find important for their primary care physician (PCP) and a specialist. The characteristics included age, sex, ethnicity, sexual orientation, primary language spoken, and religion. The difference in concordance scores for PCPs and specialists were compared with paired t tests with a Bonferroni correction. A total of 118 patients were recruited in clinic, and a total of 982 volunteers were recruited online. In the clinic cohort, the level of importance for patient-physician concordance of age, ethnicity, language, and religion was not significantly different between PCPs and specialists. In the volunteer cohort, the level of importance for concordance of age, sex, national origin, language, and religion was not significantly different between PCPs and specialists. The volunteers recruited online had significantly higher concordance scores than the patients recruited in clinic for most variables. Patients find patient-physician concordance as important in specialty care as they do in primary care. This may have similar effects on patient outcomes in specialty care. [Orthopedics. 2020;43(5):315-319.].

A Simple Goal Elicitation Tool Improves Shared Decision Making in Outpatient Orthopedic Surgery: A Randomized Controlled Trial.

Introduction. Shared decision making involves educating the patient, eliciting their goals, and collaborating on a decision for treatment. Goal elicitation is challenging for physicians as previous research has shown that patients do not bring up their goals on their own. Failure to properly elicit patient goals leads to increased patient misconceptions and decisional conflict. We performed a randomized controlled trial to test the efficacy of a simple goal elicitation tool in improving patient involvement in decision making. Methods. We conducted a randomized, single-blind study of new patients presenting to a single, outpatient surgical center. Prior to their consultation, the intervention group received a demographics questionnaire and a goal elicitation worksheet. The control group received a demographics questionnaire only. After the consultation, both groups were asked to complete the Perceived Involvement in Care Scale (PICS) survey. We compared the mean PICS scores for the intervention and control groups using a nonparametric Mann-Whitney Wilcoxon test. Secondary analysis included a qualitative content analysis of the patient goals. Results. Our final cohort consisted of 96 patients (46 intervention, 50 control). Both groups were similar in terms of demographic composition. The intervention group had a significantly higher mean (SD) PICS score compared to the control group (9.04 [2.15] v. 7.54 [2.27], P < 0.01). Thirty-nine percent of patient goals were focused on receiving a diagnosis or treatment, while 21% of patients wanted to receive education regarding their illness or their treatment options. Discussion. A single-step goal elicitation tool was effective in improving patient-perceived involvement in their care. This tool can be efficiently implemented in both academic and nonacademic settings.

Data for registry and quality review can be retrospectively collected using natural language processing from unstructured charts of arthroplasty patients.

AIMS: Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction. METHODS: A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. A NLP algorithm was created to automatically extract these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Performance of the NLP algorithm was measured in Statistical Analysis System (SAS) by calculating the accuracy of the variables collected, the ability of the algorithm to collect the correct information when it was indeed in the note (sensitivity), and the ability of the algorithm to not collect a certain data element when it was not in the note (specificity). RESULTS: The NLP algorithm performed well at extracting variables from unstructured data in our random test dataset (accuracy = 96.3%, sensitivity = 95.2%, and specificity = 97.4%). It performed better at extracting data that were in a structured, templated format such as range of movement (ROM) (accuracy = 98%) and implant brand (accuracy = 98%) than data that were entered with variation depending on the author of the note such as the presence of deep-vein thrombosis (DVT) (accuracy = 90%). CONCLUSION: The NLP algorithm used in this study was able to identify a subset of variables from randomly selected unstructured notes in arthroplasty with an accuracy above 90%. For some variables, such as objective exam data, the accuracy was very high. Our findings suggest that automated algorithms using NLP can help orthopaedic practices retrospectively collect information for registries and quality improvement (QI) efforts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):99-104.

Incremental inputs improve the automated detection of implant loosening using machine-learning algorithms.

AIMS: The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. METHODS: A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset. RESULTS: The convolutional neural network we built performed well when detecting loosening from radiographs alone. The first model built de novo with only the radiological image as input had an accuracy of 70%. The final model, which was built by fine-tuning a publicly available model named DenseNet, combining the AP and lateral radiographs, and incorporating information from the patient's history, had an accuracy, sensitivity, and specificity of 88.3%, 70.2%, and 95.6% on the independent test dataset. It performed better for cases of revision THA with an accuracy of 90.1%, than for cases of revision TKA with an accuracy of 85.8%. CONCLUSION: This study showed that machine learning can detect prosthetic loosening from radiographs. Its accuracy is enhanced when using highly trained public algorithms, and when adding clinical data to the algorithm. While this algorithm may not be sufficient in its present state of development as a standalone metric of loosening, it is currently a useful augment for clinical decision making. Cite this article: Bone Joint J 2020;102-B(6 Supple A):101-106.

Do Hospital Rankings Mislead Patients? Variability Among National Rating Systems for Orthopaedic Surgery.

INTRODUCTION: A growing number of online hospital rating systems for orthopaedic surgery are found. Although the accuracy and consistency of these systems have been questioned in other fields of medicine, no formal analysis of these systems in orthopaedics has been found. METHODS: Five hospital rating systems (US News, HealthGrades, CareChex, Women's Choice, and Hospital Compare) were examined which designate "high-performing" and "low-performing" hospitals for orthopaedic surgery. Descriptive analysis was conducted for all hospitals defined as high- or low-performing in any of the five rating systems, and assessment for agreement/disagreement between ratings was done. A subsample of hospitals ranked by all systems was then created, and agreement between rating systems was investigated using a Cohen's kappa. Each hospital was included in a multinomial logistic regression model investigating which hospital characteristics increased the odds of being favorably/unfavorably rated by each system. RESULTS: One thousand six hundred forty hospitals were evaluated by every rating system. Six hundred thirty-eight unique hospitals were identified as high-performing by at least 1 rating system; however, no hospital was ranked as high-performing by all five rating systems. Four hundred fifty-two unique hospitals were identified as low-performing; however, no hospital was ranked as low-performing by all the three rating systems which define low-performing hospitals. Within the study subsample of hospitals evaluated by each system, little agreement between any combination of rating systems (κ < 0.10) regarding top-tier or bottom-tier performance was found. It was more likely for a hospital to be considered high-performing by one system and low-performing by another (10.66%) than for the majority of the five rating systems to consider a hospital high-performing (3.76%). CONCLUSION: Little agreement between hospital quality rating systems for orthopaedic surgery is found. Publicly available hospital ratings for performance in orthopaedic surgery offer conflicting results and provide little guidance to patients, providers, or payers when selecting a hospital for orthopaedic surgery. LEVEL OF EVIDENCE: Level 1 economic study.

Machine Learning Algorithms Can Use Wearable Sensor Data to Accurately Predict Six-Week Patient-Reported Outcome Scores Following Joint Replacement in a Prospective Trial.

BACKGROUND: Tracking patient-generated health data (PGHD) following total joint arthroplasty (TJA) may enable data-driven early intervention to improve clinical results. We aim to demonstrate the feasibility of combining machine learning (ML) with PGHD in TJA to predict patient-reported outcome measures (PROMs). METHODS: Twenty-two TJA patients were recruited for this pilot study. Three activity trackers collected 35 features from 4 weeks before to 6 weeks following surgery. PROMs were collected at both endpoints (Hip and Knee Disability and Osteoarthritis Outcome Score, Knee Osteoarthritis Outcome Score, and Veterans RAND 12-Item Health Survey Physical Component Score). We used ML to identify features with the highest correlation with PROMs. The algorithm trained on a subset of patients and used 3 feature sets (A, B, and C) to group the rest into one of the 3 PROM clusters. RESULTS: Fifteen patients completed the study and collected 3 million data points. Three sets of features with the highest R2 values relative to PROMs were selected (A, B and C). Data collected through the 11th day had the highest predictive value. The ML algorithm grouped patients into 3 clusters predictive of 6-week PROM results, yielding total sum of squares values ranging from 3.86 (A) to 1.86 (C). CONCLUSION: This small but critical proof-of-concept study demonstrates that ML can be used in combination with PGHD to predict 6-week PROM data as early as 11 days following TJA surgery. Further study is needed to confirm these findings and their clinical value.

Optimal Sampling Frequency for Wearable Sensor Data in Arthroplasty Outcomes Research. A Prospective Observational Cohort Trial.

BACKGROUND: Wearable sensors can track patient activity after surgery. The optimal data sampling frequency to identify an association between patient-reported outcome measures (PROMs) and sensor data is unknown. Most commercial grade sensors report 24-hour average data. We hypothesize that increasing the frequency of data collection may improve the correlation with PROM data. METHODS: Twenty-two total joint arthroplasty (TJA) patients were prospectively recruited and provided wearable sensors. Second-by-second (Raw) and 24-hour average data (24Hr) were collected on 7 gait metrics on the 1st, 7th, 14th, 21st, and 42nd days postoperatively. The average for each metric as well as the slope of a linear regression for 24Hr data (24HrLR) was calculated. The R2 associations were calculated using machine learning algorithms against individual PROM results at 6 weeks. The resulting R2 values were defined having a mild, moderate, or strong fit (R2 ≥ 0.2, ≥0.3, and ≥0.6, respectively) with PROM results. The difference in frequency of fit was analyzed with the McNemar's test. RESULTS: The frequency of at least a mild fit (R2 ≥ 0.2) for any data point at any time frame relative to either of the PROMs measured was higher for Raw data (42%) than 24Hr data (32%; P = .041). There was no difference in frequency of fit for 24hrLR data (32%) and 24Hr data values (32%; P > .05). Longer data collection improved frequency of fit. CONCLUSION: In this prospective trial, increasing sampling frequency above the standard 24Hr average provided by consumer grade activity sensors improves the ability of machine learning algorithms to predict 6-week PROMs in our total joint arthroplasty cohort.

Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images.

BACKGROUND: The variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results. METHODS: Patients recruited into the Osteoarthritis Initiative with a radiographic Kellgren-Lawrence grade of 0 or 1 with 3D double-echo steady-state MRIs were included and their gender, age, and body mass index were collected. Using a validated ML algorithm, 2 orthogonal points on each femoral condyle were identified (distal and posterior) and ACT was measured on each MRI. Site-specific ACT was compared using paired t-tests, and multivariate regression was used to investigate the risk-adjusted effect of each demographic variable on ACT. RESULTS: A total of 3910 MRI were included. The average femoral ACT was 2.34 mm (standard deviation, 0.71; 95% confidence interval, 0.95-3.73). In multivariate analysis, distal-medial (-0.17 mm) and distal-lateral cartilage (-0.32 mm) were found to be thinner than posterior-lateral cartilage, while posterior-medial cartilage was found to be thicker (0.21 mm). In addition, female sex was found to negatively impact cartilage thickness (OR, -0.36; all values: P < .001). CONCLUSION: ML was effectively used to automate the segmentation and measurement of cartilage thickness on a large number of MRIs of healthy knees to provide normative data on the variation in ACT in this population. We further report patient variables that can influence ACT. Further validation will determine whether this technique represents a powerful new tool for tracking the impact of medical intervention on the progression of articular cartilage degeneration.

Video instruction is more effective than written instruction in improving inhaler technique.

INTRODUCTION: Many patients with asthma use inhalers incorrectly. Better inhaler technique is associated with better asthma control. We tested the effectiveness of a computer-based video training solution versus traditional written instructions, both which may be used in a resource-limited setting, for teaching inhaler technique. We hypothesized that computer based training will provide a higher quality of instruction which will improve technique more effectively than written training. METHODS: 50 asthma patients were recruited from pulmonary clinic at the Junta De Beneficencia Hospital, Ecuador (average age 48.2 years, 58% female). Inhaler technique was taught using written instructions in 20 and video in 30 patients. Inhaler technique was analyzed by video recording pre and post training inhaler use. Inhaler technique score was calculated for each video recording. RESULTS: Baseline performance was equivalent in each group, achieving an average of around 5 of 11 of the inhaler steps. Video training was significantly more effective than written instructions (change of 3.6 points vs. change of 0.4 points, p < 0.001), and improved inhaler technique by 70% (8.6 vs 5.03, p < 0.001); written training did not result in a significant increase in inhaler competency (5.9 vs. 5.5, p = 0.11). CONCLUSIONS: We conclude that written instruction appears to be inadequate to achieve safe and effective administration of inhaled medicine. In contrast, video-based education can effectively create adequate inhaler technique without additional provider time. REGISTRATION NUMBER (CLINICALTRIALS.GOV IDENTIFIER): NCT02660879.