摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报告的主题。根据来自波士顿的新闻报道，Unit Ed States，NewsRx记者说，“我们创建了一个无代码机器学习的基础设施(NML)平台，供非编程医生创建NML模型。我们通过创建一个NML模型来测试该平台，以对有无锁骨骨折的X线片进行分类。”我们的新闻编辑引用了麻省总医院和哈佛医学院的研究，“我们的IRB批准的回顾性研究包括2039名患者的4135张锁骨X线片（平均年龄52±20岁，平均年龄52±20岁）。”F:M 102:1017)来自13家医院。每个患者都有X线和前后投影的双视图锁骨X线照片。阳性的X线照片要么是移位的，要么是非移位的锁骨骨折。我们配置了NML平台，通过Web访问DICOM对象从医院虚拟网络档案中自动检索符合条件的检查。P latform训练一个模型，直到验证丢失平台。NM L平台成功检索到3917张（3917/4135，94.7%）照片，并对其进行分析，建立了ML分类器，其中包括2151张照片，100张照片用于验证，1666张照片用于测试数据集（772张锁骨骨折照片）。NETW ORK识别锁骨骨折的敏感性为90%，特异性为87%，准确度为88%，AUC为0.95（置信区间为0.94-0.96）。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating from Boston, Unit ed States, by NewsRx correspondents, research stated, "We created an infrastruct ure for no code machine learning (NML) platform for non-programming physicians t o create NML model. We tested the platform by creating an NML model for classify ing radiographs for the presence and absence of clavicle fractures." Our news editors obtained a quote from the research from Massachusetts General H ospital and Harvard Medical School, "Our IRB-approved retrospective study includ ed 4135 clavicle radiographs from 2039 patients (mean age 52 ± 20 years, F:M 102 2:1017) from 13 hospitals. Each patient had two-view clavicle radiographs with a xial and anterior-posterior projections. The positive radiographs had either dis placed or non-displaced clavicle fractures. We configured the NML platform to au tomatically retrieve the eligible exams using the series' unique identification from the hospital virtual network archive via web access to DICOM Objects. The p latform trained a model until the validation loss plateaus. Once the testing was complete, the platform provided the receiver operating characteristics curve an d confusion matrix for estimating sensitivity, specificity, and accuracy. The NM L platform successfully retrieved 3917 radiographs (3917/4135, 94.7 % ) and parsed them for creating a ML classifier with 2151 radiographs in the trai ning, 100 radiographs for validation, and 1666 radiographs in testing datasets ( 772 radiographs with clavicle fracture, 894 without clavicle fracture). The netw ork identified clavicle fracture with 90 % sensitivity, 87 % specificity, and 88 % accuracy with AUC of 0.95 (confidence interv al 0.94-0.96)."
NETL
NSTL