人类离体肺灌注的机器学习方法可预测移植结果并促进器官利用,Nature Communications

当前位置： X-MOL 学术 › Nat. Commun. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

人类离体肺灌注的机器学习方法可预测移植结果并促进器官利用
Nature Communications ( IF 14.7 ) Pub Date : 2023-08-09 , DOI: 10.1038/s41467-023-40468-7
Andrew T Sage _{1,

2,

3,

4} , Laura L Donahoe _{2,

3} , Alaa A Shamandy _{5,

6} , S Hossein Mousavi _{1,

2} , Bonnie T Chao _{1,

2} , Xuanzi Zhou _{1,

2} , Jerome Valero _{1,

2} , Sharaniyaa Balachandran ₂ , Aadil Ali _{1,

2} , Tereza Martinu _{1,

2,

4} , George Tomlinson ₇ , Lorenzo Del Sorbo _{1,

8} , Jonathan C Yeung _{1,

2,

3} , Mingyao Liu _{1,

2,

3,

4} , Marcelo Cypel _{1,

2,

3,

4} , Bo Wang _{5,

6,

9,

10} , Shaf Keshavjee _{1,

2,

3,

4}

Affiliation

离体肺灌注（EVLP）是一个数据密集型平台，用于评估离体肺移植的情况；然而，整合人工智能来快速解释离体评估过程中产生的大量临床数据仍然是一个未得到满足的需求。我们开发了一种名为InsighTx的机器学习模型，使用 n = 725 个 EVLP 病例来预测移植后结果。InsighTx 模型 AUROC（受试者工作特征曲线下面积）在训练和独立测试数据集中分别为 79 ± 3%、75 ± 4% 和 85 ± 3%。在预测不适合移植的肺部 (AUROC: 90 ± 4%) 和移植结果良好 (AUROC: 80 ± 4%) 方面观察到出色的性能。在我们机构的 EVLP 专家进行的一项回顾性盲法实施研究中，InsighTx 增加了移植合适供体肺的可能性 [比值比 = 13；95% CI:4-45]并降低了移植不合适供体肺的可能性[比值比=0.4；95%置信区间:0.16–0.98]。在此，我们为采用机器学习算法来优化 EVLP 评估提供了强有力的理由，并表明 InsighTx 可能会导致移植率的安全增加。

"点击查看英文标题和摘要"

A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization

Ex vivo lung perfusion (EVLP) is a data-intensive platform used for the assessment of isolated lungs outside the body for transplantation; however, the integration of artificial intelligence to rapidly interpret the large constellation of clinical data generated during ex vivo assessment remains an unmet need. We developed a machine-learning model, termed InsighTx, to predict post-transplant outcomes using n = 725 EVLP cases. InsighTx model AUROC (area under the receiver operating characteristic curve) was 79 ± 3%, 75 ± 4%, and 85 ± 3% in training and independent test datasets, respectively. Excellent performance was observed in predicting unsuitable lungs for transplantation (AUROC: 90 ± 4%) and transplants with good outcomes (AUROC: 80 ± 4%). In a retrospective and blinded implementation study by EVLP specialists at our institution, InsighTx increased the likelihood of transplanting suitable donor lungs [odds ratio=13; 95% CI:4-45] and decreased the likelihood of transplanting unsuitable donor lungs [odds ratio=0.4; 95%CI:0.16–0.98]. Herein, we provide strong rationale for the adoption of machine-learning algorithms to optimize EVLP assessments and show that InsighTx could potentially lead to a safe increase in transplantation rates.

更新日期：2023-08-10

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南