Achalasia subtypes can be identified with functional luminal imaging probe (FLIP) panometry using a supervised machine learning process.
Achalasia subtypes can be identified with functional luminal imaging probe (FLIP) panometry using a supervised machine learning process.
复制标题
DOI：
10.1111/nmo.13932
复制
发表时间：
2021-03
影响因子：
3.5
通讯作者：
Pandolfino JE
中科院分区：
文献类型：
--
作者：
Carlson DA;Kou W;Rooney KP;Baumann AJ;Donnan E;Triggs JR;Teitelbaum EN;Holmstrom A;Hungness E;Sethi S;Kahrilas PJ;Pandolfino JE
高分辨率测压 (HRM) 的贲门失弛缓症亚型可预测治疗反应并帮助指导治疗计划。我们的目的是利用功能性管腔成像探针 (FLIP) 全景测量中扩张引起的收缩性和加压参数以及机器学习来预测 HRM 贲门失弛缓症亚型。纳入了 180 名接受 FLIP 全景测量的成年患者，其患有根据 HRM 根据芝加哥分类 (40 名 I 型、99 名 II 型、41 名 III 型贲门失弛缓症) 定义的初治贲门失弛缓症：140 名患者用作训练队列，40 名患者用作测试队列。对使用 16 厘米 FLIP 组件进行的 FLIP 全景测量研究进行回顾性分析，以评估扩张压和扩张引起的食管收缩力。采用相关分析、单树和随机森林来开发分类树来识别贲门失弛缓症亚型。 60ml 填充体积时的球囊内压力，以及缺乏收缩反应、重复逆行收缩模式、闭塞性收缩、持续闭塞性收缩 (SOC)、收缩相关压力变化 >10mmHg 的患者比例在 HRM-贲门失弛缓症亚型之间均存在差异，并用于构建基于决策树的分类模型。该模型在训练组和测试组中识别痉挛性（III 型）与非痉挛性（I 型和 II 型）贲门失弛缓症的准确率分别为 90% 和 78%。在训练组和测试组中，贲门失弛缓症亚型 I、II 和 III 的识别准确率分别为 71% 和 55%。使用监督机器学习过程，开发了一个初步模型，通过 FLIP 全景测量将 III 型贲门失弛缓症与非痉挛性贲门失弛缓症区分开来。测量的进一步细化和更多的经验（数据）可以提高其临床相关应用的能力。
Achalasia subtypes on high-resolution manometry (HRM) prognosticate treatment response and help direct management plan. We aimed to utilize parameters of distension-induced contractility and pressurization on functional luminal imaging probe (FLIP) panometry and machine learning to predict HRM achalasia subtypes. 180 adult patients with treatment-naïve achalasia defined by HRM per Chicago Classification (40 type I, 99 type II, 41 type III achalasia) who underwent FLIP-panometry were included: 140 patients were used as the training cohort and 40 patients as the test cohort. FLIP panometry studies performed with 16-cm FLIP assemblies were retrospectively analyzed to assess distensive pressure and distension-induced esophageal contractility. Correlation analysis, single tree, and random forest were adopted to develop classification trees to identify achalasia subtypes. Intra-balloon pressure at 60ml fill volume, and proportions of patients with absent contractile response, repetitive retrograde contractile pattern, occluding contractions, sustained occluding contractions (SOC), contraction-associated pressure changes >10mmHg all differed between HRM-achalasia subtypes and were used to build the decision-tree-based classification model. The model identified spastic (type III) versus non-spastic (types I and II) achalasia with 90% and 78% accuracy in the train and test cohorts, respectively. Achalasia subtypes I, II, and III were identified with 71% and 55% accuracy in the train and test cohorts, respectively. Using a supervised machine learning process, a preliminary model was developed that distinguished type III achalasia from non-spastic achalasia with FLIP panometry. Further refinement of the measurements and more experience (data) may improve its ability for clinically relevant application.
登录
查看更多内容
影响因子：
3.5
作者：
Lin, Z.;Kahrilas, P. J.;Pandolfino, J. E.
通讯作者：
Pandolfino, J. E.
影响因子：
158.5
作者：
Werner, Yuki B.;Hakanson, Bengt;Roesch, Thomas
通讯作者：
Roesch, Thomas
影响因子：
9.8
作者：
Carlson, Dustin A.;Kahrilas, Peter J.;Pandolfino, John E.
通讯作者：
Pandolfino, John E.
影响因子：
29.4
作者：
Carlson DA;Lin Z;Kahrilas PJ;Sternbach J;Donnan EN;Friesen L;Listernick Z;Mogni B;Pandolfino JE
通讯作者：
Pandolfino JE
影响因子：
29.4
作者：
Park S;Zifan A;Kumar D;Mittal RK
通讯作者：
Mittal RK