Can machine learning predict the accuracy of preoperative planning for total hip arthroplasty, basing on patient-related factors? An explorative investigation on Supervised machine learning classification models.

Background: The success of Total Hip Arthroplasty (THA) is influenced by preoperative planning, with traditional 2D approaches displaying varied reliability as well. The present study investigates the use of Supervised Machine Learning (SML) models with patient-related features to improve accuracy. Methods: Preoperative and perioperative data, as well as planning and final implant information, were obtained from 800 consecutive cementless primary THA, which was performed uniformly by a specialized surgical team. Six Supervised Machine Learning models were trained and validated using patient characteristics and implant data: Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (CART), Gaussian Naive Bayes (GN), and Support Vector Classifier (SVC). The models' ability to predict planning reliability and leg length disparity was evaluated. Results: KNN performed better on the cup model (97.9 %), femur model (96.7 %), and femur size (99.2 %). SVM emerged as the model with the highest accuracy for cup size (60.4 %) and head size (62.1 %). CART had the best accuracy (99 %) when determining leg length discrepancy. Conclusion: The study demonstrates the utility of Supervised Machine Learning models, specifically KNN, in predicting the accuracy of preoperative planning in THA. The accuracy of these models, which are driven by patient-related characteristics, provides useful information for optimizing patients' selection and improving surgical outcome.

Simultaneous vs staged bilateral hip arthroplasty: monocentric analysis of satisfaction rate and complications.

PURPOSE: Interest in bilateral total hip arthroplasty (THA) has been increasing over the past decade. This study aims to compare postoperative local and systemic complications, hospital readmissions, and satisfaction assessment in patients undergoing simultaneous versus staged bilateral THA. METHODS: A retrospective observational study was conducted among patients who underwent simultaneous or staged bilateral THA between 2017 and 2020. Data on perioperative parameters, local and systemic complications, and 30-day hospital readmissions were collected. Patient satisfaction was assessed using Forgotten Joint Score (FJS). The comparison of continuous variables with normal distribution of variance was performed by ANOVA; for variables with abnormal distribution, the nonparametric test Mann-Whitney U was adopted. The distribution of dichotomous variables was analyzed by chi-square test, and statistical significance was calculated by Fisher exact test. RESULTS: The study included 199 patients, of whom 156 underwent staged and 43 simultaneous bilateral THA. A total of 44 patients developed complications (21 systemics, 12 locals, and 20 postoperative anemia). There were no significant differences regarding local (simultaneous 5% vs. staged 6%; p = 0.999) or systemic complications (simultaneous 14% vs. staged 10%; p = 0.408). Only the incidence of postoperative anemia was significantly higher in simultaneous group compared with staged group (p = 0.003). There were no significant differences in FJS between the two groups (p = 0.258). CONCLUSION: No differences in local or systemic complications nor readmission rates were observed following simultaneous or staged bilateral THA. Simultaneous bilateral THA is non-inferior to staged implants in terms of safety and patient satisfaction.

Platelet-rich plasma injections for chronic plantar fasciopathy: a systematic review.

INTRODUCTION: There is an increasing interest in platelet-rich plasma (PRP) injection as a treatment for chronic plantar fasciopathy (PF). We wished to evaluate the evidence for the use of PRP in PF/fasciitis. SOURCES OF DATA: We performed a systematic review on the effects of PRP in PF. In June 2014, we searched Medline, Cochrane, CINAHL and Embase databases using various combinations of the commercial names of each PRP preparation and 'plantar' (with its associated terms). We only included prospectively designed studies in humans. AREAS OF AGREEMENT: Eight articles met the inclusion criteria, three of them were randomized. All studies yielded a significantly greater improvement in symptoms between baseline and last follow-up assessment. None of the papers recorded major complications. AREAS OF CONTROVERSY: Only three randomized studies were identified; none of them had a true controlled group treated with placebo and one of the three studies had a very short (6 week) follow-up. A non-randomized study evaluating PRP versus corticosteroids (CCS) injections, and a randomized controlled trial comparing PRP and dextrose prolotherapy reported no statistical significant differences at 6 months. Most studies did not have a control group and imaging evaluation. GROWING POINTS AND AREAS FOR RESEARCH: Evidence for the use of PRP in PF shows promising results, and this therapy appears safe. However, the number of studies available is limited and randomized placebo-controlled studies are required. Characterizing the details of the intervention and standardizing the outcome scores would help to better document the responses and optimize the treatment.

[Adenoid cystic carcinoma of the larynx: review of the literature and caseload]. / Carcinoma adenoide quístico de laringe: revisión de la literatura y aportación casuística.

Two cases of laryngeal adenoid cystic carcinoma (1 supraglottic, 1 subglottic) are reported, particular attention being paid to diagnosis and treatment. The literature on this topic has been reviewed, in order to describe the natural course and the different treatments of this tumour. The authors underline the difficulty in evaluating the effectiveness of treatment, due to the insufficient follow-up in most published cases.