Sire, Alessandro de

AbstractPurposeWhile several artificial intelligence (AI)‐assisted medical imaging applications are reported in the recent orthopaedic literature, comparison of the clinical efficacy and utility of these applications is currently lacking. The aim of this systematic review is to evaluate the effectiveness and reliability of AI applications in orthopaedic imaging, focusing on their impact on diagnostic accuracy, image segmentation and operational efficiency across various imaging modalities.MethodsBased on the PRISMA guidelines, a comprehensive literature search of PubMed, Cochrane and Scopus databases was performed, using combinations of keywords and MeSH descriptors ('AI', 'ML', 'deep learning', 'orthopaedic surgery' and 'imaging') from inception to March 2024. Included were studies published between September 2018 and February 2024, which evaluated machine learning (ML) model effectiveness in improving orthopaedic imaging. Studies with insufficient data regarding the output variable used to assess the reliability of the ML model, those applying deterministic algorithms, unrelated topics, protocol studies, and other systematic reviews were excluded from the final synthesis. The Joanna Briggs Institute (JBI) Critical Appraisal tool and the Risk Of Bias In Non‐randomised Studies‐of Interventions (ROBINS‐I) tool were applied for the assessment of bias among the included studies.ResultsThe 53 included studies reported the use of 11.990.643 images from several diagnostic instruments. A total of 39 studies reported details in terms of the Dice Similarity Coefficient (DSC), while both accuracy and sensitivity were documented across 15 studies. Precision was reported by 14, specificity by nine, and the F1 score by four of the included studies. Three studies applied the area under the curve (AUC) method to evaluate ML model performance. Among the studies included in the final synthesis, Convolutional Neural Networks (CNN) emerged as the most frequently applied category of ML models, present in 17 studies (32%).ConclusionThe systematic review highlights the diverse application of AI in orthopaedic imaging, demonstrating the capability of various machine learning models in accurately segmenting and analysing orthopaedic images. The results indicate that AI models achieve high performance metrics across different imaging modalities. However, the current body of literature lacks comprehensive statistical analysis and randomized controlled trials, underscoring the need for further research to validate these findings in clinical settings.Level of evidenceSystematic Review; Level of evidence IV.

Background and Objectives: Diabetes mellitus type 2 (T2DM) is a chronic disease associated with fluid accumulation in the interstitial tissue. Manual lymphatic drainage (MLD) plays a role in reducing lymphoedema, like intermittent pneumatic compression (IPC). By the present pilot study, we aimed to evaluate the efficacy of a synergistic treatment with MLD and IPC in reducing lower limb lymphedema in T2DM patients. Materials and Methods: Adults with a clinical diagnosis of T2DM and lower limb lymphedema (stage II–IV) were recruited from July to December 2020. Study participants were randomized into two groups: experimental group, undergoing a 1-month rehabilitative program consisting of MLD and IPC (with a compression of 60 to 80 mmHg); control group, undergoing MLD and a sham IPC (with compression of <30 mmHg). The primary outcome was the lower limb lymphedema reduction, assessed by the circumferential method (CM). Secondary outcomes were: passive range of motion (pROM) of hip, knee, and ankle; quality of life; laboratory exams as fasting plasma glucose and HbA1c. At baseline (T0) and at the end of the 1-month rehabilitative treatment (T1), all the outcome measures were assessed, except for the Hb1Ac evaluated after three months. Results: Out of 66 T2DM patients recruited, only 30 respected the eligibility criteria and were randomly allocated into 2 groups: experimental group (n = 15; mean age: 54.2 ± 4.9 years) and control group (n = 15; mean age: 54.0 ± 5.5 years). At the intra-group analysis, the experimental group showed a statistically significant improvement of all outcome measures (p < 0.05). The between-group analysis showed a statistically significant improvement in pROM of the hip, knee, ankle, EQ-VAS, and EQ5D3L index at T1. Conclusions: A multimodal approach consisting of IPC and MLD showed to play a role in reducing lower limb lymphedema, with an increase of pROM and HRQoL. Since these are preliminary data, further studies are needed.