Treatment initiation prediction by EHR mapped PPD tensor based convolutional neural networks boosting algorithm

Xiao, Xueli; Wei, Guanhao; Zhou, Li; Pan, Yi; Jing, Huan; Zhao, Emily; Yuan, Yilian

doi:10.1016/j.jbi.2021.103840

Cited by 6 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the representation algorithm, features used to represent a patient were also critical. Many previous studies focused on some features in the original form of medical codes, such as disease diagnoses, procedures, and medications [ 1 , 11 , 14 , 37 ]. For laboratory tests that contained much diagnosis and prognosis-relevant information about patients, we included the normal status of the laboratory tests into the feature sets, rather than simply using the number of laboratory tests and test co-occurrences [ 12 , 38 ].…”

Section: Discussionmentioning

confidence: 99%

“…Electronic medical records (EMRs) contain diverse and heterogeneous information, such as demographic data, disease diagnoses, laboratory tests, radiological findings, examinations and procedures, and medications. EMR data can be used to not only reflect the health status of patients and record the treatment trajectory, but also help doctors in making clinical decisions [1][2][3][4][5][6] and improving the efficiency of diagnosis and treatment [1,7,8]. One of the most prevalent and practical tasks of the secondary use of EMR data is building models to predict the disease status [8][9][10] and treatment outcomes [11][12][13][14][15][16][17] for a patient, using machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Huang¹,

Zheng²,

Ma³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

Background The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention. Objective We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI). Methods Medical concepts, including patients’ age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score. Results Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice. Conclusions The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Huang¹,

Zheng²,

Ma³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…to achieve balance within the dataset[18],[19],[20]. Two experiments were conducted during this phase.…”

mentioning

confidence: 99%

Sentiment Analysis of TikTok Shop Closure in Indonesia on Twitter Using Supervised Machine Learning

Al Habesyah,

Herteno,

Indriani

et al. 2024

j.electron.electromedical.eng.med.inform

View full text Add to dashboard Cite

TikTok Shop is one of the features in TikTok application which facilitates users to buy and sell products. The integration of TikTok Shop with social media has provided new opportunities to reach customers and increase sales. However, the closure of TikTok Shop has caused controversy among the public. This study aims to analyze the views and responses of TikTok users in Indonesia to the closure of TikTok Shop. The dataset used was obtained from Twitter. The research methodology consists of labeling, oversampling, splitting, and machine learning, which includes SVM, Random Forest, Decision Tree, and Deep Learning (H2O). The contribution of this research enriches our understanding of the implementation of machine learning, especially in sentiment analysis of TikTok Shop closures. From the test results, it is known that Deep Learning (H2O) + SMOTE obtained AUC 0.900, without using SMOTE, AUC 0.867. SVM + SMOTE obtained AUC 0.885, without using SMOTE AUC 0.881. Random Forest + SMOTE obtained AUC 0.822, while without using SMOTE AUC 0.830. Decision Tree + SMOTE AUC 0.59; without SMOTE, AUC 0.646. Deep Learning (H2O) with SMOTE produces better performance compared to SVM, Random Forest, and Decision Tree. With an AUC of 0.900; it can be said that Deep Learning (H2O) has excellent performance for sentiment analysis of TikTok Shop closures. This research has significant implications for social electronic commerce due to its potential utilization by social media analysts.

show abstract

DenseNet-based ensemble network for land cover and land use classification of patch-based denoised SAR images

Meseci,

Ozcan,

Ozdemir

et al. 2023

Arab J Geosci

View full text Add to dashboard Cite

Treatment initiation prediction by EHR mapped PPD tensor based convolutional neural networks boosting algorithm

Cited by 6 publications

References 19 publications

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Sentiment Analysis of TikTok Shop Closure in Indonesia on Twitter Using Supervised Machine Learning

DenseNet-based ensemble network for land cover and land use classification of patch-based denoised SAR images

Contact Info

Product

Resources

About