Search Articles

View query in Help articles search

Search Results (1 to 10 of 145 Results)

Download search results: END BibTex RIS


An App Developed for Detecting Nurse Burnouts Using the Convolutional Neural Networks in Microsoft Excel: Population-Based Questionnaire Study

An App Developed for Detecting Nurse Burnouts Using the Convolutional Neural Networks in Microsoft Excel: Population-Based Questionnaire Study

If the CNN BO model’s parameters have been estimated by the CNN algorithm, the classification of nurse BO by responding to the MBI-HSS can alert individual nurses more accurately and warn them to alleviate their mental strain before it becomes a serious BO

Yi-Lien Lee, Willy Chou, Tsair-Wei Chien, Po-Hsin Chou, Yu-Tsen Yeh, Huan-Fang Lee

JMIR Med Inform 2020;8(5):e16528


Telemedicine in Neonatal Home Care: Identifying Parental Needs Through Participatory Design

Telemedicine in Neonatal Home Care: Identifying Parental Needs Through Participatory Design

addressing the needs identified in this study, and to implement that solution (Phase 3), which will be the topic of future papers.Setting and ParticipantsParents with preterm infants admitted to two NICUs (see Table 1)—Hvidovre Hospital (HH) and Hans Christian Andersen

Kristina Garne, Anne Brødsgaard, Gitte Zachariassen, Jane Clemensen

JMIR Res Protoc 2016;5(3):e100


Multi-Level Representation Learning for Chinese Medical Entity Recognition: Model Development and Validation

Multi-Level Representation Learning for Chinese Medical Entity Recognition: Model Development and Validation

., cn), BERT was formulated as follows:h1 = EToken + ESegment + EPosition (1)hl = Trm(hl–1) (2)YBERT = Softmax(wOhL + bO) (3)where h1 represents input embedding for a sequence and is made up of EToken, ESegment, and EPosition, which mean token, segment, and

Zhichang Zhang, Lin Zhu, Peilin Yu

JMIR Med Inform 2020;8(5):e17637


Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation

Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation

The equations are as follows:ft=σ(Wfxt+Ufh(t-1)+bf) (5) ot=σ(Woxt+Uoh(t-1)+bo) (6) gt=tanh(Wgxt+Ugh(t-1)+bg) (7) it=σ(Wixt+Uih(t-1)+bi) (8) ct=ft⊙c(t-1)+ it⊙gt (9)ht= ot⊙tanh(ct) (10)where W, U, b are the weight and bias

Jian Wang, Xiaoyu Chen, Yu Zhang, Yijia Zhang, Jiabin Wen, Hongfei Lin, Zhihao Yang, Xin Wang

JMIR Med Inform 2020;8(7):e17638


Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation

Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation

Mathematically, a general unidirectional LSTM can be described as follows.Let Wi, Wc, Wo be three weight matrices and bi, bc, bo be three bias vectors. These parameters are learned during the training.

Sven Festag, Cord Spreckelsen

JMIR Form Res 2020;4(5):e14064


Clinical Named Entity Recognition From Chinese Electronic Health Records via Machine Learning Methods

Clinical Named Entity Recognition From Chinese Electronic Health Records via Machine Learning Methods

The implementation of the LSTM unit is shown as follows:it = σ(Wxi xt + whi ht-1 + Wci ct-1 + bi)ft = σ(Wxf xt + Whf ht-1 + Wcf ct-1 + bf)ct = ft • ct-1 + it • tanh(Wxc xt + Whc ht-1 + bc)ot = σ(Wxo xt + Who ht-1 + Wco ct + bo)ht = ot • tanh(ct),where σ denotes

Yu Zhang, Xuwen Wang, Zhen Hou, Jiao Li

JMIR Med Inform 2018;6(4):e50