RESUMO
Objective To identify key variables predictive of patient responses to microfragmented adipose tissue (MFAT) treatment in knee osteoarthritis (KOA) and evaluate its potential to delay or mitigate the need for total knee replacement (TKR). Methods We utilised a dataset comprising 329 patients treated with MFAT for KOA, incorporating variables such as gender, age, BMI, arthritic aetiology, radiological grade, and Oxford Knee Scores (OKS) pre- and post-treatment. We employed random forest regressors for model training and testing, with gender bias mitigation and outlier detection to enhance prediction accuracy. Model performance was assessed through root mean squared error (RMSE) and mean absolute error (MAE), with further validation in a TKR-suitable patient subset. Results The model achieved a test RMSE of 6.72 and an MAE of 5.38, reflecting moderate predictive accuracy across the patient cohort. Stratification by gender revealed no statistically significant differences between actual and predicted OKS improvements (p-values: males = 0.93, females = 0.92). For the subset of patients suitable for TKR, the model presented an increased RMSE of 9.77 and MAE of 7.81, indicating reduced accuracy in this group. The decision tree analysis identified pre-operative OKS, radiological grade, and gender as significant predictors of post-treatment outcomes, with pre-operative OKS being the most critical determinant. Patients with lower pre-operative OKS showed varying responses based on radiological severity and gender, suggesting a nuanced interaction between these factors in determining treatment efficacy. Conclusion This study highlights the potential of MFAT as a non-surgical alternative for KOA treatment, emphasising the importance of personalised patient assessments. While promising, the predictive model warrants further refinement and validation with a larger, more diverse dataset to improve its utility in clinical decision-making for KOA management.
RESUMO
Background Quantum computing and quantum machine learning (QML) are promising experimental technologies that can improve precision medicine applications by reducing the computational complexity of algorithms driven by big, unstructured, real-world data. The clinical problem of knee osteoarthritis is that, although some novel therapies are safe and effective, the response is variable, and defining the characteristics of an individual who will respond remains a challenge. In this study, we tested a quantum neural network (QNN) application to support precision data-driven clinical decisions to select personalized treatments for advanced knee osteoarthritis. Methodology After obtaining patients' consent and Research Ethics Committee approval, we collected the clinicodemographic data before and after the treatment from 170 patients eligible for knee arthroplasty (Kellgren-Lawrence grade ≥3, Oxford Knee Score (OKS) ≤27, age ≥64 years, and idiopathic aetiology of arthritis) treated over a two-year period with a single injection of microfragmented fat. Gender classes were balanced (76 males and 94 females) to mitigate gender bias. A patient with an improvement ≥7 OKS was considered a responder. We trained our QNN classifier on a randomly selected training subset of 113 patients to classify responders from non-responders (73 responders and 40 non-responders) in pain and function at one year. Outliers were hidden from the training dataset but not from the validation set. Results We tested our QNN classifier on a randomly selected test subset of 57 patients (34 responders, 23 non-responders) including outliers. The no information rate was 0.59. Our application correctly classified 28 responders out of 34 and 6 non-responders out of 23 (sensitivity = 0.82, specificity = 0.26, F1 Statistic = 0.71). The positive and negative likelihood ratios were 1.11 and 0.68, respectively. The diagnostic odds ratio was 2. Conclusions Preliminary results on a small validation dataset showed that QML applied to data-driven clinical decisions for the personalized treatment of advanced knee osteoarthritis is a promising technology to reduce computational complexity and improve prognostic performance. Our results need further research validation with larger, real-world unstructured datasets, as well as clinical validation with an artificial intelligence clinical trial to test model efficacy, safety, clinical significance, and relevance at a public health level.
RESUMO
Hip osteoarthritis (OA) is a major contributor to reduced quality of life and concomitant disability associated with lost working life months. Intra-articular injection of various biological materials has shown promise in alleviating symptoms and potentially slowing down the degenerative process. Here, we compared the effects of treatment of a cohort of 147 patients suffering from grade 1-4 hip OA; with either micro-fragmented adipose tissue (MFAT), or a combination of MFAT with platelet-rich plasma (PRP). We found significant improvements in both the visual analogue score for pain (VAS) and Oxford hip score (OHS) that were similar for both treatments with over 60% having an improvement in the VAS score of 20 points or more. These results suggest a positive role for intra-articular injection of MFAT + PRP as a treatment for hip osteoarthritis which may be important particularly in low body mass index (BMI) patients where the difficulty in obtaining sufficient MFAT for treatment could be offset by using this combination of biologicals.
RESUMO
BACKGROUND: Knee osteoarthritis (KOA) is a significant cause of disability in a globally ageing population. Knee replacement surgery has been shown to improve function and quality of life. Access to this intervention can be limited for a number of reasons including rationing of care, lack of healthcare provision in austere environments, and more recently, due to the cessation of elective orthopaedic care as a result of the COVID pandemic. Referral for knee replacement surgery is often guided by the patient's Oxford Knee Score (OKS). Recent therapies including treatment with microfragmented adipose tissue (MFAT) have emerged as alternatives to relieve pain and improve function in such patients. METHOD: We identified all patients with KOA Kellgren-Lawrence grade 3 and 4 in our dataset of patients treated with a single injection of MFAT and applied published OKS thresholds for referral for TKR to separate them into 3 cohorts according to their functional impairment. 220 patients (95 females, 125 males) with KOA were given one MFAT injection. The function (OKS) and quality of life (EuroQol-5) prior to and 24 months after therapy were compared. RESULTS: MFAT injection provided a statistically significant improvement in the quality of life (EQ-5D) at 24 months in patients with a baseline OKS of 39 or less (p value: <0.001) as well as those with OKS of 27 or less who are deemed suitable for a knee replacement (p value: <0.001). CONCLUSION: MFAT injection improves quality of life in patients with KOA who are deemed suitable for the knee replacement. MFAT is a low-morbidity alternative biological treatment and can delay the need for total knee replacement in suitable patients.
RESUMO
Knee osteoarthritis is a major cause of disability worldwide. Newer modalities of treatment with less morbidity, such as intra-articular injection of microfragmented fat (MFAT), are showing promise. We report on our novel observation that women show a greater improvement in pain and function to MFAT than men. Traditionally, women have been underrepresented in studies and studies with both sexes regularly fail to analyze the results by sex. To mitigate for this bias and quantify it, we describe a technique using reproducible statistical analysis and replicable results with Open Access statistical software R to calculate the magnitude of this difference. Genetic, hormonal, environmental, and age factors play a role in our observed difference between the sexes. There is a need for further studies to identify the molecular basis for this difference and be able to utilize it to improve outcome for both women and men.
RESUMO
INTRODUCTION: Microfragmented adipose tissue (MFAT) has been shown to benefit osteoarthritic patients by reducing pain and supporting tissue regeneration through a mesenchymal stem cell (MSC)-related paracrine mechanism. This observational study of 110 knees assessed patient-centered outcomes of pain, functionality, and quality of life, analyzing their variation at twelve months following one ultrasound-guided intra-articular injection of autologous MFAT for the treatment of knee osteoarthritis (KOA). METHOD: Inclusion criteria were as follows: VAS >50, and the presence of KOA as diagnosed on X-ray and MRI. Exclusion criteria included the following: recent injury (<3 months) of the symptomatic knee, intra-articular steroid injections performed within the last three months, and hyaluronic acid injections prior to this treatment. Changes in VAS, OKS, and EQ-5D were scored at baseline and twelve months following a single intra-articular injection of autologous MFAT. Score variation was analyzed utilizing a nonparametric paired samples Wilcoxon test. The statistical analysis is reproducible with Open Access statistical software R (version 4.0.0 or higher). The study was carried out with full patient consent, in a private practice setting. RESULTS: Median VAS (pain) improved from 70 (IQR 20) to 30 (IQR 58) (p < 0.001); median OKS (function) improved from 25 (IQR 11) to 33.5 (IQR 16) (p < 0.001); and median EQ-5D (quality of life) improved from 0.62 (IQR 0.41) to 0.69 (IQR 0.28) (p < 0.001). No adverse events were reported during the intraoperative, recovery, or postoperative periods. CONCLUSIONS: For patients with all grades of knee osteoarthritis who were treated with intra-articular injections of MFAT, statistically significant improvements in pain, function, and quality of life were reported. Although further research is warranted, the results are encouraging and suggest a positive role for intra-articular injection of MFAT as a treatment for knee osteoarthritis.