[A Transformer-based multimodal model for predicting hospital-acquired infections using imaging and clinical laboratory data]. [PDF]
Zhang M +7 more
europepmc +1 more source
O-RADS联合超声造影与ROMA
目的基于O-RADS构建并评估融合超声造影(CEUS)及标准化z值的卵巢恶性肿瘤风险预测模型(ROMA z-score)的多参数诊断模型,以期提升对良性、交界性和恶性卵巢上皮性肿瘤(OETs)的三分类诊断准确性。方法本研究回顾性纳入2018年5月至2024年12月经病理确诊的129例卵巢上皮性肿瘤患者。收集患者临床资料(包括年龄、绝经状态、体质量指数、HE4、CA125)及超声影像资料(常规超声特征与超声造影特征)。根据病理结果将肿瘤分为良性、交界性及恶性三类。采用随机森林算法构建预测模型 ...
袁鲲 +6 more
doaj
[Machine learning-based prediction model for caries in the first molars of 9-year-old children in Suzhou]. [PDF]
Chen L, Wang X, Zhu K, Ren K, Wu Z.
europepmc +1 more source
[Establishment of a Noninvasive Diagnostic Model for Wilson Disease Using Metallomics and Machine Learning]. [PDF]
Zhou H +6 more
europepmc +1 more source
在变压器故障诊断过程中,进行合理的特征优选,将有助于提高诊断模型的诊断精度,为此,文中提出了一种基于金豺优化算法(golden Jackal optimization,GJO)特征量优选与AO-RF的变压器故障诊断模型。首先,采用GJO对构建的21维变压器油中溶解气体特征量进行优选;然后,根据GJO得到的特征优选结果,采用天鹰算法(aquila optimizer,AO)优化随机森林(random forest,RF)的变压器故障诊断模型对变压器故障进行诊断,并与不同特征量 ...
叶育林 +8 more
doaj
[Research progress in artificial intelligence for the diagnosis and management of diseases in preterm infants]. [PDF]
Yuan Y, Tang LH, Guan LR.
europepmc +1 more source
目的本研究旨在融合多种易获取的临床数据与二维常规超声图像,构建用于评估脂肪性肝病(SLD)不同严重程度的深度学习神经网络模型。方法回顾性收集649例行超声衰减成像(ATI)检查患者的临床数据和超声图像,以ATI作为参考标准,将患者分为正常(S0)及轻(S1)、中(S2)、重度(S3)脂肪肝4组,按8∶2比例随机划分为训练集和验证集。采用对比语言-图像预训练(CLIP)模型提取临床与图像多模态特征,并分别训练随机森林(RF)和多层感知器(MLP)模型。在验证集中对比多模态模型与单一模态的诊断性能 ...
蒙文仪 +4 more
doaj
[A Transformer-based model using laboratory indicators efficiently differentiates ovarian cancer]. [PDF]
Tan S +6 more
europepmc +1 more source
[A protein-ligand binding affinity prediction model integrating multi-scale interaction features]. [PDF]
Liu H, Yan L, Wang S, Peng J.
europepmc +1 more source
[MS-DTNet: an efficient model combining multi-scale convolution and dual-tower attention for detecting abnormal heart sounds]. [PDF]
Wen Y, Lu X, Wu Q, Chen H, Chen C.
europepmc +1 more source

