Operative or Nonoperative Treatment is Predicted Accurately for Patients Who Have Hip Complaints Consulting an Orthopedic Surgeon Using Machine Learning Algorithms Trained With Prehospital Acquired History-Taking Data.

BACKGROUND: Increasing numbers of patients suffering from hip osteoartritis will lead to increased orthopaedic health care consumption. Artificial intelligence might alleviate this problem, using Machine learning (ML) to optimize orthopaedic consultation workflow by predicting treatment strategy (non-operative or operative) prior to consultation. The purpose of this study was to assess ML accuracy in clinical practice, by comparing ML predictions to the outcome of clinical consultations. METHODS: In this prospective clinical cohort study, adult patients referred for hip complaints between January 20th to February 20th 2023 were included. Patients completed a computer-assisted history taking (CAHT) form and using these CAHT answers, a ML-algorithm predicted non-operative or operative treatment outcome prior to in-hospital consultation. During consultation, orthopaedic surgeons and physician assistants were blinded to the prediction in 90 and unblinded in 29 cases. Consultation outcome (non-operative or operative) was compared to ML treatment prediction for all cases, and for blinded and unblinded conditions separately. Analysis was done on 119 consultations. RESULTS: Overall treatment strategy prediction was correct in 101 cases (accuracy 85%, P < .0001). Non-operative treatment prediction (n = 71) was 97% correct versus 67% for operative treatment prediction (n = 48). Results from unblinded consultations (86.2% correct predictions,) were not statistically different from blinded consultations (84.4% correct, P > .05). CONCLUSIONS: Machine Learning algorithms can predict non-operative or operative treatment for patients with hip complaints with high accuracy. This could facilitate scheduling of non-operative patients with physician assistants, and operative patients with orthopaedic surgeons including direct access to pre-operative screening, thereby optimizing usage of health care resources.

Only Low Patients' Expectations Are Prognostic for Dissatisfaction With Performing Work-Related Knee-Straining Activities After Total Knee Arthroplasty: A Prospective Multicenter Cohort Study.

OBJECTIVE: To investigate whether preoperative expectations regarding performing work-related knee-straining activities were associated with being dissatisfied 6 months after total knee arthroplasty (TKA) among working patients, and, to identify prognostic factors for being dissatisfied with performing these work-related knee-straining activities. DESIGN: Multicenter prospective cohort study. SETTING: Orthopedic surgery departments of 7 hospitals in the Netherlands. PARTICIPANTS: A consecutive sample of 175 working patients who were on the waiting list for TKA (median age 59 years, 53% women) and intended to return to work (N=175). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURE(S): Dissatisfaction with performing work-related knee-straining activities 6 months postoperative was measured using the Work Osteoarthritis or joint-Replacement Questionnaire (score range 0-100). The clinically relevant cut-off points for being satisfied and dissatisfied were ≥71 and ≤50, respectively. RESULTS: Thirty-three patients (19%) were dissatisfied with performing work-related knee-straining activities 6 months after TKA. Patients who expected to be dissatisfied preoperative had a 5.1 times higher odds (95% CI 1.7-15.5) of being dissatisfied 6 months postoperatively compared with patients who expected to be satisfied preoperative. Regression analyses revealed that only patients' expectations were prognostic for being dissatisfied 6 months postoperatively rather than age, pain level, or having a knee-straining job. CONCLUSIONS: Two in 10 working patients are dissatisfied with performing work-related knee-straining activities 6 months after TKA. Only preoperative patients' expectations appeared prognostic. Therefore, we should better prepare working patients with low expectations by managing their preoperative expectations and improving their performance of work-related knee-straining activities in rehabilitation.

Machine learning algorithms trained with pre-hospital acquired history-taking data can accurately differentiate diagnoses in patients with hip complaints.

Background and purpose - Machine learning (ML) techniques are a form of artificial intelligence able to analyze big data. Analyzing the outcome of (digital) questionnaires, ML might recognize different patterns in answers that might relate to different types of pathology. With this study, we investigated the proof-of-principle of ML-based diagnosis in patients with hip complaints using a digital questionnaire and the Kellgren and Lawrence (KL) osteoarthritis score.Patients and methods - 548 patients (> 55 years old) scheduled for consultation of hip complaints were asked to participate in this study and fill in an online questionnaire. Our questionnaire consists of 27 questions related to general history-taking and validated patient-related outcome measures (Oxford Hip Score and a Numeric Rating Scale for pain). 336 fully completed questionnaires were related to their classified diagnosis (either hip osteoarthritis, bursitis or tendinitis, or other pathology). Different AI techniques were used to relate questionnaire outcome and hip diagnoses. Resulting area under the curve (AUC) and classification accuracy (CA) are reported to identify the best scoring AI model. The accuracy of different ML models was compared using questionnaire outcome with and without radiologic KL scores for degree of osteoarthritis.Results - The most accurate ML model for diagnosis of patients with hip complaints was the Random Forest model (AUC 82%, 95% CI 0.78-0.86; CA 69%, CI 0.64-0.74) and most accurate analysis with addition of KL scores was with a Support Vector Machine model (AUC 89%, CI 0.86-0.92; CA 83%, CI 0.79-0.87).Interpretation - Analysis of self-reported online questionnaires related to hip complaints can differentiate between basic hip pathologies. The addition of radiological scores for osteoarthritis further improves these outcomes.

Three Out of Ten Working Patients Expect No Clinical Improvement of Their Ability to Perform Work-Related Knee-Demanding Activities After Total Knee Arthroplasty: A Multicenter Study.

Purpose Three out of ten patients do not return to work after total knee arthroplasty (TKA). Patient expectations are suggested to play a key role. What are patients' expectations regarding the ability to perform work-related knee-demanding activities 6 months after TKA compared to their preoperative status? Methods A multi-center cross-sectional study was performed among 292 working patients listed for TKA. The Work Osteoarthritis or joint-Replacement Questionnaire (WORQ, range 0-100, minimal important difference 13) was used to assess the preoperatively experienced and expected ability to perform work-related knee-demanding activities 6 months postoperatively. Differences between the preoperative and expected WORQ scores were tested and the most difficult knee-demanding work-related activities were described. Results Two hundred thirty-six working patients (81%) completed the questionnaire. Patients' expected WORQ score (Median = 75, IQR 60-86) was significantly (p < 0.01) higher than their preoperative WORQ score (Median = 44, IQR 35-56). A clinical improvement in ability to perform work-related knee-demanding activities was expected by 72% of the patients, while 28% of the patients expected no clinical improvement or even worse ability to perform work-related knee-demanding activities 6 months after TKA. Of the patients, 34% expected severe difficulty in kneeling, 30% in crouching and 17% in clambering 6 months after TKA. Conclusions Most patients have high expectations, especially regarding activities involving deep knee flexion. Remarkably, three out of ten patients expect no clinical improvement or even a worse ability to perform work-related knee-demanding activities 6 months postoperatively compared to their preoperative status. Therefore, addressing patients expectations seems useful in order to assure realistic expectations regarding work activities.

Do lifestyle restrictions and precautions prevent dislocation after total hip arthroplasty? A systematic review and meta-analysis of the literature.

OBJECTIVE: A systematic literature review and meta-analysis on the effectiveness of lifestyle restrictions and precautions to prevent dislocation after total hip arthroplasty. DATA SOURCES: MEDLINE and the Cochrane Library were searched in February 2015, with additional hand searching of systematic reviews and reference lists. REVIEW METHODS: This review was conducted in accordance with the PRISMA statement for reporting systematic reviews and meta-analysis. PubMed and the Cochrane Library were searched from their start date through to February 2015. Randomized controlled trials and comparative case series in English, Dutch or German language were included. Only primary total hip arthroplasty procedures managed with different postoperative restrictions and precautions protocols were included. Primary outcome was the total hip arthroplasty dislocation rate, secondary outcomes were patient functioning, return to activities of daily living and patient satisfaction. RESULTS: A total of 119 eligible articles were identified, six were included: three randomized controlled trials, one retrospective matched cohort study, one retrospective and one prospective cohort study, describing 1122 procedures (restrictions group: n = 528; no restrictions group: n = 594). Both the standard posterior and anterolateral surgical approaches were included. There were eight dislocations (1.5%) in the restricted group, vs. six dislocations (1.0%) in the unrestricted group. Patients in the unrestricted group resumed activities significantly faster and were more satisfied with their pace of recovery. CONCLUSION: A more liberal lifestyle restrictions and precautions protocol will not lead to worse dislocation rates after total hip arthroplasty, but will lead to earlier and better resumption of activities and higher patient satisfaction. These results appear to hold up for various surgical approaches.

A 20 mg dose of dexamethasone does not reduce the proportion of joint replacement patients needing rescue analgesia: a matched cohort study.

Background: Consistent pain control after total joint replacement (TJR) has not yet been reached in all patients managed with a multimodal analgesia regime. Questions remain on dosage and timing of analgesics. Glucocorticoids such as dexamethasone are considered most powerful in reducing the surgery-induced inflammatory response with most pain studies using a 6-12 mg dose. Reviews agree that additional glucocorticoids may provide more analgesia, but a dose-finding analysis is limited. The primary aim of this study was to determine if a high, single preoperative dose of dexamethasone resulted in a reduced need for rescue analgesics during the first 24 hours after TJR when compared to a standard 8 mg dose of dexamethasone. Methods: A cohort study in which 59 patients who received 20 mg dexamethasone intravenously just prior to incision were matched 1:1 to patients who received a standard 8 mg dose. Consecutive elective hip and knee replacement patients managed by one anaesthesiologist were included in the high dose group between June 2019 and March 2020. Patients were matched for arthroplasty type, gender, age, anaesthesia type and pre-operative pain. Patients with opioid use before surgery or with diabetes mellitus were excluded. Oxynorm rescues analgesics (number of times given and dosage) usage during hospitalization was retrieved from the electronic nursing files. Results: There were no significant differences between groups in gender distribution, mean age and body mass index (BMI), in American Society of Anesthesiologists (ASA), type of arthroplasty, anaesthesia type and pre-operative pain score. In the 20 mg group 54 patients (91.5%) needed oxynorm during hospitalization versus 58 (98.3%) in the 8 mg group (P=0.09). High dose group patients received a median of 5 mg [interquartile range (IQR): 0] oxynorm versus 5 mg (IQR: 0) in the standard dose group (P=0.70). Conclusions: In this matched cohort study there was no difference in the proportion of patients needing rescue analgesics during hospitalization between the group of patients who preoperatively received 20 mg dexamethasone and the group of patients who received 8 mg. Future blinded randomized controlled trials are needed to further investigate the effect of different glucocorticoids dosages on pain after joint replacement surgery.

It is safe to use minimal restrictions following posterior approach total hip arthroplasty: results from a large cohort study.

BACKGROUND: To prevent early postoperative dislocation following a total hip arthroplasty (THA) procedure, patients must adhere to restrictions. Restrictive protocols are common if THA surgery is performed using the posterior approach, but scientific evidence form larger studies that supports these restrictions are scarce. In this large cohort study we compare the <90-days dislocation rate between patients receiving posterior approach THA managed with minimal versus extensive restrictions. METHODS: Prospective cohort (n = 1049) of consecutive elective primary hip replacement surgery procedures (September 2014-July 2017) managed with minimal postoperative restrictions. Hospital charts were prospectively reviewed for patient demographics, risk factors and any hip dislocation. Control (n = 1102) consecutive primary elective THAs (January 2011-August 2014) managed with a traditional restrictive protocol. A posterior surgical approach was used in all procedures. RESULTS: Minimal restrictions group: 17 dislocations <90 days (1.6%); Restricted group: 28 (2.5%), chi-square p = 0.1. Testing the hypothesis of inferiority by a minimum of 1% increase in ⩽90 days dislocation risk: p = 0.14 (test for difference) and p < 0.001 (non-inferiority test), allowing us to discard the null hypothesis (absolute increase in risk of ⩾1% with minimal restrictions). The proportion of surgeries performed with a femoral head size ⩾32 mm was higher in the minimal restrictions group. CONCLUSIONS: Patients can be managed safely with minimal restrictions following posterior approach THA if combined with frequent use of larger femoral heads.

The Effect of an App for Day-to-Day Postoperative Care Education on Patients With Total Knee Replacement: Randomized Controlled Trial.

BACKGROUND: Patients who undergo primary Total Knee Replacement surgery (TKR) are often discharged within 1-3 days after surgery. With this relatively short length of hospital stay, a patient's self-management is a crucial factor in optimizing the outcome of their treatment. In the case of TKR, self-management primarily involves adequate pain management, followed by physiotherapy exercises and daily self-care activities. Patients are educated on all these topics by hospital staff upon discharge from the hospital but often struggle to comprehend this information due to its quantity, complexity, and the passive mode of communication used to convey it. OBJECTIVE: This study primarily aims to determine whether actively educating TKR patients with timely, day-to-day postoperative care information through an app could lead to a decrease in their level of pain compared to those who only receive standard information about their recovery through the app. In addition, physical functioning, quality of life, ability to perform physiotherapy exercises and daily self-care activities, satisfaction with information, perceived involvement by the hospital, and health care consumption were also assessed. METHODS: A multicenter randomized controlled trial was performed in five Dutch hospitals. In total, 213 patients who had undergone elective, primary, unilateral TKR participated. All patients had access to an app for their smartphone and tablet to guide them after discharge. The intervention group could unlock day-to-day information by entering a personal code. The control group only received weekly, basic information. Primary (level of pain) and secondary outcomes (physical functioning, quality of life, ability to perform physiotherapy exercises and activities of daily self-care, satisfaction with information, perceived involvement by the hospital, and health care consumption) were measured using self-reported online questionnaires. All outcomes were measured weekly in the four weeks after discharge, except for physical functioning and quality of life, which were measured at baseline and at four weeks after discharge. Data was analyzed using Student t tests, chi-square tests, and linear mixed models for repeated measures. RESULTS: In total, 114 patients were enrolled in the intervention group (IG) and 99 in the control group (CG). Four weeks after discharge, patients in the IG performed significantly better than patients in the CG on all dimensions of pain: pain at rest (mean 3.45 vs mean 4.59; P=.001), pain during activity (mean 3.99 vs mean 5.08; P<.001) and pain at night (mean 4.18 vs mean 5.21; P=.003). Additionally, significant differences were demonstrated in favor of the intervention group for all secondary outcomes. CONCLUSIONS: In the four weeks following TKR, the active and day-to-day education of patients via the app significantly decreased their level of pain and improved their physical functioning, quality of life, ability to perform physiotherapy exercises and activities of daily self-care, satisfaction with information, perceived involvement by the hospital, and health care consumption compared to standard patient education. Given the rising number of TKR patients and the increased emphasis on self-management, we suggest using an app with timely postoperative care education as a standard part of care. TRIAL REGISTRATION: Netherlands Trial Register NTR7182; https://www.trialregister.nl/trial/6992.

Assessing the Efficacy of an Educational Smartphone or Tablet App With Subdivided and Interactive Content to Increase Patients' Medical Knowledge: Randomized Controlled Trial.

BACKGROUND: Modern health care focuses on shared decision making (SDM) because of its positive effects on patient satisfaction, therapy compliance, and outcomes. Patients' knowledge about their illness and available treatment options, gained through medical education, is one of the key drivers for SDM. Current patient education relies heavily on medical consultation and is known to be ineffective. OBJECTIVE: This study aimed to determine whether providing patients with information in a subdivided, categorized, and interactive manner via an educational app for smartphone or tablet might increase the knowledge of their illness. METHODS: A surgeon-blinded randomized controlled trial was conducted with 213 patients who were referred to 1 of the 6 Dutch hospitals by their general practitioner owing to knee complaints that were indicative of knee osteoarthritis. An interactive app that, in addition to standard care, actively sends informative and pertinent content to patients about their illness on a daily basis by means of push notifications in the week before their consultation. The primary outcome was the level of perceived and actual knowledge that patients had about their knee complaints and the relevant treatment options after the intervention. RESULTS: In total, 122 patients were enrolled in the control group and 91 in the intervention group. After the intervention, the level of actual knowledge (measured on a 0-36 scale) was 52% higher in the app group (26.4 vs 17.4, P<.001). Moreover, within the app group, the level of perceived knowledge (measured on a 0-25 scale) increased by 22% during the week within the app group (from 13.5 to 16.5, P<.001), compared with no gain in the control group. CONCLUSIONS: Actively offering patients information in a subdivided (per day), categorized (per theme), and interactive (video and quiz questions) manner significantly increases the level of perceived knowledge and demonstrates a higher level of actual knowledge, compared with standard care educational practices. TRIAL REGISTRATION: International Standard Randomized Controlled Trial Number ISRCTN98629372; http://www.isrctn.com/ISRCTN98629372 (Archived by WebCite at http://www.webcitation.org/73F5trZbb).

Periprosthetic pathology in 'at risk' ceramic-on-polyethylene total hip arthroplasty: a clinical study using MARS-MRI in 50 patients.

PURPOSE: Recent studies of metal-on-metal (MoM) total hip arthroplasty (THA) using metal-artefact-reducing-sequence software for magnetic resonance Imaging (MARS-MRI) have revealed remarkable soft tissue pathology around the hip, usually referred to as pseudotumours. Case reports describe identical pathology in non-MoM THA, but descriptive overviews of MRI abnormalities in patients with non-MoM prosthesis are scarce. METHODS: A clinical study in a cohort of 50 ceramic-on-polyethylene (CoP) THA selected for high risk of peri-prosthetic pathology including 2 subgroups: (i) 40 patients with a high polyethylene (PE) wear rate (>0.2 mm per year) and 5-12 years follow-up; (ii) 10 patients with a 2 to 5 years follow-up and a documented history of persistent complaints. All patients were clinically evaluated, MARS-MRIs were completed and chrome and cobalt serum samples were taken. RESULTS: 17 scans were normal (34%). Periprosthetic fluid collections were seen as a bursae iliopsoas (n = 12, 24%), in the trochanter bursae (n = 4, 8%) and in the surgical tract (n = 9, 18%). 1 case demonstrated a cyst on MARS-MRI resembling a pseudotumour as seen with MoM THA (2%). Intraosseous acetabular cysts were seen in 12 cases (24%), intraosseous trochanteric cysts in 10 cases (20%). CONCLUSIONS: Soft tissue abnormalities after non-MoM THA are common in selected patients and can be clearly visualised with MARS-MRI. Pseudotumours as seen on MARS-MRI do occur in non-MoM hip arthroplasty but with low prevalence.