ParTRE: A relational triple extraction model of complicated entities and imbalanced relations in Parkinson’s disease
Display Omitted
AbstractThe relational triple extraction of unstructured medical texts about Parkinson’s disease is critical for the construction of a medical knowledge graph. However, the triple entities in Parkinson’s disease are usually complicated and overlapped, ...
Participant flow diagrams for health equity in AI
- Jacob G. Ellen,
- João Matos,
- Martin Viola,
- Jack Gallifant,
- Justin Quion,
- Leo Anthony Celi,
- Nebal S. Abu Hussein
Display Omitted
AbstractSelection bias can arise through many aspects of a study, including recruitment, inclusion/exclusion criteria, input-level exclusion and outcome-level exclusion, and often reflects the underrepresentation of populations historically disadvantaged ...
Soft phenotyping for sepsis via EHR time-aware soft clustering
Sepsis is one of the most serious hospital conditions associated with high mortality. Sepsis is the result of a dysregulated immune response to infection that can lead to multiple organ dysfunction and death. Due to the wide ...
Graphical abstractDisplay Omitted
Creating a computer assisted ICD coding system: Performance metric choice and use of the ICD hierarchy
Machine learning methods hold the promise of leveraging available data and generating higher-quality data while alleviating the data collection burden on healthcare professionals. International Classification of Diseases (ICD) ...
Graphical abstractDisplay Omitted
FedFSA: Hybrid and federated framework for functional status ascertainment across institutions
- Sunyang Fu,
- Heling Jia,
- Maria Vassilaki,
- Vipina K. Keloth,
- Yifang Dang,
- Yujia Zhou,
- Muskan Garg,
- Ronald C. Petersen,
- Jennifer St Sauver,
- Sungrim Moon,
- Liwei Wang,
- Andrew Wen,
- Fang Li,
- Hua Xu,
- Cui Tao,
- Jungwei Fan,
- Hongfang Liu,
- Sunghwan Sohn
Display Omitted
Abstract IntroductionPatients' functional status assesses their independence in performing activities of daily living, including basic ADLs (bADL), and more complex instrumental activities (iADL). Existing studies have discovered that patients’ ...
Developing deep learning-based strategies to predict the risk of hepatocellular carcinoma among patients with nonalcoholic fatty liver disease from electronic health records
- Zhao Li,
- Lan Lan,
- Yujia Zhou,
- Ruoxing Li,
- Kenneth D. Chavin,
- Hua Xu,
- Liang Li,
- David J.H. Shih,
- W. Jim Zheng
Display Omitted
Abstract ObjectiveThe accuracy of deep learning models for many disease prediction problems is affected by time-varying covariates, rare incidence, covariate imbalance and delayed diagnosis when using structured electronic health records data. The ...
Automatic categorization of self-acknowledged limitations in randomized controlled trial publications
Acknowledging study limitations in a scientific publication is a crucial element in scientific transparency and progress. However, limitation reporting is often inadequate. Natural language processing (NLP) methods could support ...
Graphical abstract
Display Omitted
Highlights
- Annotated a corpus of RCT publications with self-acknowledged limitation types.
- Created a sentence classification model to detect and recognize limitation types.
- Analyzed the model output on 12K RCTs to describe the commonly ...
Artificial intelligence-powered pharmacovigilance: A review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets
Display Omitted
Abstract ObjectiveThe primary objective of this review is to investigate the effectiveness of machine learning and deep learning methodologies in the context of extracting adverse drug events (ADEs) from clinical benchmark datasets. We conduct an in-...
A comprehensive performance evaluation, comparison, and integration of computational methods for detecting and estimating cross-contamination of human samples in cancer next-generation sequencing analysis
- Huijuan Chen,
- Bing Wang,
- Lili Cai,
- Xiaotian Yang,
- Yali Hu,
- Yiran Zhang,
- Xue Leng,
- Wen Liu,
- Dongjie Fan,
- Beifang Niu,
- Qiming Zhou
Display Omitted
AbstractCross-sample contamination is one of the major issues in next-generation sequencing (NGS)-based molecular assays. This type of contamination, even at very low levels, can significantly impact the results of an analysis, especially in the ...
Computational frameworks integrating deep learning and statistical models in mining multimodal omics data
Display Omitted
Highlights
- Integrative deep learning and statistical model frameworks hold potential in analyzing high-dimensional multimodal omics data.
- These integration frameworks use either multi-stage or end-to-end strategies to analyze and combine various ...
In health research, multimodal omics data analysis is widely used to address important clinical and biological questions. Traditional statistical methods rely on the strong assumptions of distribution. Statistical methods such as ...
