术前影像与患者因素对膝关节骨软骨同种异体移植术后临床有意义结局的影响:机器学习分析
本研究采用机器学习方法分析185例膝关节骨软骨同种异体移植(OCA)患者,其中153例(83%)完成2年随访。结果显示术前MRI、基线患者报告结局指标(PROMs)和患者人口学特征可可靠预测2年时达到最小临床重要差异(MCID)和实质性临床获益(SCB)的功能结局,AUC为0.88-0.91;但MRI对心理和生理健康总分的MCID预测较差(AUC 0.60-0.68)。较高BMI、膝关节力线不良、无术前骨水肿、合并前交叉韧带或半月板损伤、较大缺损尺寸及植入>1个OCA移植物是预测未达到MCID或SCB的因素。
要点
- 术前MRI、基线PROMs和患者因素可预测OCA术后2年功能MCID/SCB,AUC达0.88-0.91。
- MRI对SF-36心理和生理总分的MCID预测能力较差,AUC仅0.60-0.68。
- 较高BMI、力线不良、无骨水肿、合并韧带/半月板损伤、大缺损和多移植物预测功能改善失败。
核心结论
- 机器学习模型显示术前MRI、基线PROMs和患者人口学特征可可靠预测膝关节OCA术后2年功能结局达到临床有意义阈值。
- 生活质量改善依赖于对患者心理和生理健康感知的全面术前评估。
- 无骨水肿、合并前交叉韧带或半月板损伤、MRI较大病变、膝关节力线不良和较高BMI预测OCA术后2年功能获益失败。
研究设计与样本
- 病例对照研究,证据等级3。
- 分析2018年5月1日前由2名高容量专科培训软骨外科医生行OCA的患者数据。
- 从机构软骨登记处纳入185例符合标准的膝关节OCA患者,153例(83%)完成2年随访。
- 使用7种独特架构创建42个预测模型,检测4种结局指标MCID及IKDC和KOS-ADL的SCB达成情况。
- 输入模型的数据包括性别、年龄、BMI、基线PROMs、病变大小、合并韧带或半月板撕裂、骨挫伤或骨水肿存在。
主要发现
- 术前MRI、基线PROMs和患者人口学特征最佳预测2年IKDC和KOS-ADL的MCID和SCB,顶级模型AUC范围从良好(0.88)到优秀(0.91)。
- MRI预测心理和生理总分MCID表现不佳,AUC为0.60-0.68。
- 较高BMI、膝关节力线不良、无术前骨水肿、合并前交叉韧带或半月板损伤、较大缺损尺寸和植入>1个OCA移植物是一致性预测未达到2年MCID或SCB的因素。
关键数值与推荐
- IKDC和KOS-ADL的MCID和SCB预测模型AUC为0.88-0.91。
- SF-36心理和生理总分MCID预测模型AUC为0.60-0.68。
临床怎么用
- 术前可使用MRI、基线PROMs和患者因素预测OCA术后2年功能改善可能性。
- 应综合评估患者心理和生理健康感知以预测生活质量改善。
- 对具有较高BMI、力线不良、无骨水肿、合并韧带/半月板损伤、大缺损或多移植物的患者应预期功能获益可能失败。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Fresh osteochondral allograft transplantation (OCA) is an effective method of treating symptomatic cartilage defects of the knee. This restoration technique involves the single-stage implantation of viable, mature hyaline cartilage into a chondral or osteochondral lesion. The extent to which preoperative imaging and patient factors predict achieving clinically meaningful outcomes among patients undergoing OCA for cartilage lesions of the knee remains unknown. PURPOSE: To determine the predictive relationship of preoperative imaging, preoperative patient-reported outcome measures (PROMs), and patient demographics with achievement of the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) for functional and quality-of-life PROMs at 2 years after OCA for symptomatic cartilage defects of the knee. STUDY DESIGN: Case-control study; Level of evidence, 3. METHODS: Data were analyzed for patients who underwent OCA before May 1, 2018, by 2 high-volume fellowship-trained cartilage surgeons. The International Knee Documentation Committee (IKDC) subjective form, Knee Outcome Survey-Activities of Daily Living (KOS-ADL), and mental and physical component summaries of the SF-36 were administered preoperatively and at 2 years postoperatively. A total of 42 predictive models were created using 7 unique architectures to detect achievement of the MCID for each of the 4 outcome measures and the SCB for the IKDC and KOS-ADL. Data inputted into the models included sex, age, body mass index, baseline PROMs, lesion size, concomitant ligamentous or meniscal tear, and presence of "bone bruise" or osseous edema. Shapley additive explanations plot analysis identified predictors of reaching the MCID and SCB. RESULTS: Of the 185 patients who underwent OCA for the knee and met eligibility criteria from an institutional cartilage registry, 153 (83%) had 2-year follow-up. Preoperative magnetic resonance imaging (MRI), baseline PROMs, and patient demographics best predicted reaching the 2-year MCID and SCB of the IKDC and KOS-ADL PROMs, with areas under the receiver operating characteristic curve of the top-performing models ranging from good (0.88) to excellent (0.91). MRI faired poorly (areas under the curve, 0.60-0.68) in predicting the MCID for the mental and physical component summaries. Higher body mass index, knee malalignment, absence of preoperative osseous edema, concomitant anterior cruciate ligament or meniscal injury, larger defect size, and the implantation of >1 OCA graft were consistent findings contributing to failure to achieve the MCID or SCB at 2 years postoperatively. CONCLUSION: Our machine learning models demonstrated that preoperative MRI, baseline PROMs, and patient demographics reliably predict the ability to reach clinically meaningful thresholds for functional knee outcomes 2 years after OCA for cartilage defects. Although clinical improvement in knee function can be reliably predicted, improvements in quality of life after OCA depend on a comprehensive preoperative assessment of the patient's perception of his or her mental and physical health. Absence of osseous edema, concomitant anterior cruciate ligament or meniscal injury, larger lesion size on MRI, knee malalignment, and elevated body mass index are predictive of failure to achieve 2-year functional benefits after OCA of the knee.
引用
- Ramkumar PN, Karnuta JM, Haeberle HS, et al. Effect of Preoperative Imaging and Patient Factors on Clinically Meaningful Outcomes and Quality of Life After Osteochondral Allograft Transplantation: A Machine Learning Analysis of Cartilage Defects of the Knee. Am J Sports Med. 2021. PMID: 34048288. doi:10.1177/03635465211015179
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。