Artificial intelligence can be used in the identification and classification of shoulder osteoarthritis and avascular necrosis on plain radiographs: a training study of 7,139 radiograph sets.

BACKGROUND AND PURPOSE: Knowledge concerning the use AI models for the classification of glenohumeral osteoarthritis (GHOA) and avascular necrosis (AVN) of the humeral head is lacking. We aimed to analyze how a deep learning (DL) model trained to identify and grade GHOA on plain radiographs performs. Our secondary aim was to train a DL model to identify and grade AVN on plain radiographs. PATIENTS AND METHODS: A modified ResNet-type network was trained on a dataset of radiographic shoulder examinations from a large tertiary hospital. A total of 7,139 radiographs were included. The dataset included various projections of the shoulder, and the network was trained using stochastic gradient descent. Performance evaluation metrics, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to assess the network's performance for each outcome. RESULTS: The network demonstrated AUC values ranging from 0.73 to 0.93 for GHOA classification and > 0.90 for all AVN classification classes. The network exhibited lower AUC for mild cases compared with definitive cases of GHOA. When none and mild grades were combined, the AUC increased, suggesting difficulties in distinguishing between these 2 grades. CONCLUSION: We found that a DL model can be trained to identify and grade GHOA on plain radiographs. Furthermore, we show that a DL model can identify and grade AVN on plain radiographs. The network performed well, particularly for definitive cases of GHOA and any level of AVN. However, challenges remain in distinguishing between none and mild GHOA grades.

Achilles tendon rupture healing is enhanced by intermittent pneumatic compression upregulating collagen type I synthesis.

PURPOSE AND HYPOTHESIS: Adjuvant intermittent pneumatic compression (IPC) during leg immobilization following Achilles tendon rupture (ATR) has been shown to reduce the risk of deep venous thrombosis. The purpose of this study was to investigate whether IPC can also promote tendon healing. METHODS: One hundred and fifty patients with surgical repair of acute ATR were post-operatively leg immobilized and prospectively randomized. Patients were allocated for 2 weeks of either adjuvant IPC treatment (n = 74) or treatment-as-usual (n = 74) in a plaster cast without IPC. The IPC group received 6 h daily bilateral calf IPC applied under an orthosis on the injured side. At 2 weeks post-operatively, tendon healing was assessed using microdialysis followed by enzymatic quantification of tendon callus production, procollagen type I (PINP) and type III (PIIINP) N-terminal propeptide, and total protein content. 14 IPC and 19 cast patients (control group) consented to undergo microdialysis. During weeks 3-6, all subjects were leg-immobilized in an orthosis without IPC. At 3 and 12 months, patient-reported outcome was assessed using reliable questionnaires (ATRS and EQ-5D). At 12 months, functional outcome was measured using the validated heel-rise test. RESULTS: At 2 weeks post-rupture, the IPC-treated patients exhibited 69% higher levels of PINP in the ruptured Achilles tendon (AT) compared to the control group (p = 0.001). Interestingly, the IPC-treated contralateral, intact AT also demonstrated 49% higher concentrations of PINP compared to the non-treated intact AT of the plaster cast group (p = 0.002). There were no adverse events observed associated with IPC. At 3 and 12 months, no significant (n.s.) differences between the two treatments were observed using patient-reported and functional outcome measures. CONCLUSIONS: Adjuvant IPC during limb immobilization in patients with ATR seems to effectively enhance the early healing response by upregulation of collagen type I synthesis, without any adverse effects. Whether prolonged IPC application during the whole immobilization period can also lead to improved long-term clinical healing response should be further investigated. The healing process during leg immobilization in patients with Achilles tendon rupture can be improved through adjuvant IPC therapy, which additionally prevents deep venous thrombosis. LEVEL OF EVIDENCE: Randomized controlled trial, Level I.

Deep Venous Thrombosis and Tendon Healing.

Tendon metabolism after acute Achilles tendon rupture (ATR) is associated with major complications related to immobilization, which results in reduced circulation, high risk of deep venous thrombosis (DVT), impaired healing and functional deficits.DVT has been demonstrated to occur in up to 50 % of the patients with ATR. Suffering from a DVT during tendon healing has been demonstrated as an independent predictive factor for impaired patient outcome at 1 year after ATR, suggesting that specific interventions are warranted to prevent DVT. Since pharmacological DVT prophylaxis has low or no effect during lower leg immobilization it is speculated whether adjuvant treatment with intermittent pneumatic compression (IPC) applied during lower limb immobilization can reduce the incidence of DVT.IPC, which acts through mechanical, chemical and molecular mechanisms, has been demonstrated to enhance neuro-vascular ingrowth in a tendon repair model and stimulate collagen production leading to improved maximum force during healing.Recently, a prospective randomized trial compared adjuvant IPC applied under an orthosis versus plaster cast only in ATR patients. The study found at 2 weeks post-operatively 21 % DVTs in the IPC-group compared to 37 % in the control group. Patients that received no IPC treatment exhibited an almost threefold increased odds for DVT, independently of age. Furthermore, using microdialysis technique, adjuvant IPC treatment was shown to increase the metabolic healing activity at 2 weeks post-ATR.Tendon healing is impaired by reduced circulation and DVT. The demonstration that adjuvant IPC effectively reduced DVT incidence, and also is capable of enhancing the metabolic response suggests that IPC treatment may not only be a viable means of prophylaxis against DVT, but possibly also a method of promoting healing.

Meta-analysis and suggested guidelines for prevention of venous thromboembolism (VTE) in foot and ankle surgery.

PURPOSE: To perform a meta-analysis investigating venous thromboembolism (VTE) following isolated foot and ankle surgery and propose guidelines for VTE prevention in this group of patients. METHODS: Following a PRISMA compliant search, 372 papers were identified and meta-analysis performed on 22 papers using the Critical Appraisal Skills Programme and Centre for Evidence-Based Medicine level of evidence. RESULTS: 43,381 patients were clinically assessed for VTE and the incidence with and without chemoprophylaxis was 0.6% (95% CI 0.4-0.8%) and 1% (95% CI 0.2-1.7%), respectively. 1666 Patients were assessed radiologically and the incidence of VTE with and without chemoprophylaxis was 12.5% (95% CI 6.8-18.2%) and 10.5% (95% CI 5.0-15.9%), respectively. There was no significant difference in the rates of VTE with or without chemoprophylaxis whether assessed clinically or by radiological criteria. The risk of VTE in those patients with Achilles tendon rupture was greater with a clinical incidence of 7% (95% CI 5.5-8.5%) and radiological incidence of 35.3% (95% CI 26.4-44.3%). CONCLUSION: Isolated foot and ankle surgery has a lower incidence of clinically apparent VTE when compared to general lower limb procedures, and this rate is not significantly reduced using low molecular weight heparin. The incidence of VTE following Achilles tendon rupture is high whether treated surgically or conservatively. With the exception of those with Achilles tendon rupture, routine use of chemical VTE prophylaxis is not justified in those undergoing isolated foot and ankle surgery, but patient-specific risk factors for VTE should be used to assess patients individually. LEVEL OF EVIDENCE: II.

STOP leg clots-Swedish multicentre trial of outpatient prevention of leg clots: study protocol for a randomised controlled trial on the efficacy of intermittent pneumatic compression on venous thromboembolism in lower leg immobilised patients.

INTRODUCTION: Leg immobilisation in a cast or an orthosis after lower limb injuries is associated with a high risk of complications of venous thromboembolism (VTE) and hampered healing. Current pharmacoprophylaxes of VTE are inefficient and associated with adverse events. Intermittent pneumatic compression (IPC) could represent a novel, efficient and safe VTE-prophylactic alternative that may enhance injury healing. The aim of STOP leg clots is to assess the efficacy of adjuvant IPC-therapy on reduction of VTE incidence and improvement of healing in lower leg immobilised outpatients. METHODS AND ANALYSIS: STOP leg clots is a multicentre randomised controlled superiority trial. Eligible patients (700 patients/arm) with either an acute ankle fracture or Achilles tendon rupture will be randomised to either addition of IPC during lower-leg immobilisation or to treatment-as-usual. The primary outcome will be the total VTE incidence, that is, symptomatic and asymptomatic deep venous thrombosis (DVT) or symptomatic pulmonary embolism (PE), during the leg immobilisation period, approximately 6-8 weeks. DVT incidence will be assessed by screening whole leg compression duplex ultrasound at removal of leg immobilisation and/or clinically diagnosed within the time of immobilisation. Symptomatic PE will be verified by CT.Secondary outcomes will include patient-reported outcome using validated questionnaires, healing evaluated by measurements of tendon callus production and changes in VTE-prophylactic mechanisms assessed by blood flow and fibrinolysis. Data analyses will be blinded and based on the intention-to-treat. ETHICS AND DISSEMINATION: Ethical approval was obtained by the ethical review board in Stockholm, Sweden, Dnr 2016/1573-31. The study will be conducted in accordance with the Helsinki declaration. The results of the study will be disseminated in peer-reviewed international journals. TRIAL REGISTRATION: NCT03259204. TIME SCHEDULE: 1 September 2018 to 31 December 2022.