机器学习衍生的临床决策算法用于诊断原发性甲状旁腺功能亢进症患者的高功能甲状旁腺
本回顾性研究纳入458例原发性甲状旁腺功能亢进症患者,基于16项术前变量用随机森林筛选出3项变量构建机器学习临床决策算法(MLCDA),以手术记录和病理四象限定位为参考标准。MLCDA在训练集(4D-CT+MIBI)正确分类准确率为0.91(95%CI: 0.89-0.92),验证集为0.90(95%CI: 0.86-0.94)。
要点
- MLCDA纳入联合4D-CT与MIBI的敏感读片、特异读片及血钙与甲状旁腺激素乘积3项变量。
- 算法输出五个概率类别用于判定高功能甲状旁腺,训练集正确分类准确率0.91。
- 验证集正确分类准确率0.90,作者认为可用于改进术前定位并写入放射报告。
核心结论
- 机器学习生成的临床决策算法通过概率分类能准确诊断高功能甲状旁腺,作者认为可实施以改进术前规划并传达诊断确定性。
研究设计与样本
- 回顾性研究,纳入2013年2月至2016年9月458例连续原发性甲状旁腺功能亢进症患者,均行联合4D-CT与司他比锝SPECT/CT(MIBI)后接受甲状旁腺切除术;前400例为训练集,其余58例为验证集;以手术记录和病理的四象限定位为参考标准。
诊断标准与关键数值
- 随机森林从16项变量中选出3项:联合4D-CT与MIBI的敏感读片、特异读片、血钙与甲状旁腺激素水平的乘积;MLCDA输出五个概率类别判定高功能腺体;训练集正确分类准确率0.91(95%CI: 0.89-0.92),验证集0.90(95%CI: 0.86-0.94)。
临床应用与阅片要点
- 作者认为该算法可利用标准术前变量改进术前甲状旁腺定位,并可纳入放射报告用于手术规划。
局限性
- 原文未报告局限性。
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)。
英文原文(摘要)· 点击展开
PURPOSE: To train and validate machine learning-derived clinical decision algorithm (MLCDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning.
METHODS: This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance (MLCDA). The MLCDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of MLCDA was prospectively validated.
RESULTS: Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an MLCDA using five probability categories for hyperfunctioning glands. The MLCDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94].
CONCLUSION: Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty.
KEY POINTS: Question Can an MLCDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed MLCDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an MLCDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.
引用
- Yeh R, Kuo JH, Huang B, et al. Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism. Eur Radiol. 2024. PMID: 39476058. doi:10.1007/s00330-024-11159-8
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。