Researching public health datasets in the era of deep learning: a systematic literature review DOI Creative Commons
Rand Obeidat, Izzat Alsmadi, Qanita Bani Baker

et al.

Health Informatics Journal, Journal Year: 2025, Volume and Issue: 31(1)

Published: Jan. 1, 2025

Objective: Explore deep learning applications in predictive analytics for public health data, identify challenges and trends, then understand the current landscape. Materials Methods: A systematic literature review was conducted June 2023 to search articles on data context of learning, published from inception medical computer science databases through 2023. The focused diverse datasets, abstracting applications, challenges, advancements learning. Results: 2004 were reviewed, identifying 14 disease categories. Observed trends include explainable-AI, patient embedding integrating different sources employing models informatics. Noted technical reproducibility handling sensitive data. Discussion: There has been a notable surge publications since 2015. Consistent continue be applied across Despite wide standard approach still does not exist addressing outstanding issues this field. Conclusion: Guidelines are needed applying improve FAIRness, efficiency, transparency, comparability, interoperability research. Interdisciplinary collaboration among scientists, experts, policymakers is harness full potential

Language: Английский

Synthetic data in machine learning for medicine and healthcare DOI Open Access
Richard J. Chen, Ming Y. Lu, Tiffany Chen

et al.

Nature Biomedical Engineering, Journal Year: 2021, Volume and Issue: 5(6), P. 493 - 497

Published: June 15, 2021

Language: Английский

Citations

480
Fake news detection based on news content and social contexts: a transformer-based approach DOI Open Access
Shaina Raza, Chen Ding

International Journal of Data Science and Analytics, Journal Year: 2022, Volume and Issue: 13(4), P. 335 - 362

Published: Jan. 30, 2022

Language: Английский

Citations

187
Deep Learning for Natural Language Processing in Radiology—Fundamentals and a Systematic Review DOI Open Access
Vera Sorin, Yiftach Barash, Eli Konen

et al.

Journal of the American College of Radiology, Journal Year: 2020, Volume and Issue: 17(5), P. 639 - 648

Published: Jan. 28, 2020

Language: Английский

Citations

160
Extracting social determinants of health from electronic health records using natural language processing: a systematic review DOI Creative Commons
Braja Gopal Patra, Mohit Sharma, Veer Vekaria

et al.

Journal of the American Medical Informatics Association, Journal Year: 2021, Volume and Issue: 28(12), P. 2716 - 2727

Published: Aug. 5, 2021

Social determinants of health (SDoH) are nonclinical dispositions that impact patient risks and clinical outcomes. Leveraging SDoH in decision-making can potentially improve diagnosis, treatment planning, Despite increased interest capturing electronic records (EHRs), such information is typically locked unstructured notes. Natural language processing (NLP) the key technology to extract from text expand its utility care research. This article presents a systematic review state-of-the-art NLP approaches tools focus on identifying extracting data EHRs.

Language: Английский

Citations

158
Neural Natural Language Processing for unstructured data in electronic health records: A review DOI
Irene Li, Jessica Pan,

Jeremy Goldwasser

et al.

Computer Science Review, Journal Year: 2022, Volume and Issue: 46, P. 100511 - 100511

Published: Sept. 22, 2022

Language: Английский

Citations

129
Med7: A transferable clinical natural language processing model for electronic health records DOI
Andrey Kormilitzin, Nemanja Vaci, Qiang Liu

et al.

Artificial Intelligence in Medicine, Journal Year: 2021, Volume and Issue: 118, P. 102086 - 102086

Published: May 18, 2021

Language: Английский

Citations

122
Natural Language Processing for Smart Healthcare DOI
Binggui Zhou, Guanghua Yang, Zheng Shi

et al.

IEEE Reviews in Biomedical Engineering, Journal Year: 2022, Volume and Issue: 17, P. 4 - 18

Published: Sept. 28, 2022

Smart healthcare has achieved significant progress in recent years. Emerging artificial intelligence (AI) technologies enable various smart applications across scenarios. As an essential technology powered by AI, natural language processing (NLP) plays a key role due to its capability of analysing and understanding human language. In this work, we review existing studies that concern NLP for from the perspectives technique application. We first elaborate on different approaches pipeline technical point view. Then, context employing techniques, introduce representative scenarios, including clinical practice, hospital management, personal care, public health, drug development. further discuss two specific medical issues, i.e., coronavirus disease 2019 (COVID-19) pandemic mental which NLP-driven important role. Finally, limitations current works identify directions future works.

Language: Английский

Citations

106
TextConvoNet: a convolutional neural network based architecture for text classification DOI Open Access

Sanskar Soni,

Satyendra Singh Chouhan, Santosh Singh Rathore

et al.

Applied Intelligence, Journal Year: 2022, Volume and Issue: 53(11), P. 14249 - 14268

Published: Oct. 22, 2022

Language: Английский

Citations

75
Adverse drug event detection using natural language processing: A scoping review of supervised learning methods DOI Creative Commons
Rachel M. Murphy, Joanna E. Klopotowska, Nicolette F. de Keizer

et al.

PLoS ONE, Journal Year: 2023, Volume and Issue: 18(1), P. e0279842 - e0279842

Published: Jan. 3, 2023

To reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), computerized approach analyze text data, has shown promising results for the purpose of detection context pharmacovigilance. However, detailed qualitative assessment critical appraisal NLP methods is lacking. Therefore, we have conducted scoping review close this knowledge gap, provide directions future research practice. We included articles where was applied detect ADEs clinical narratives within electronic health records inpatients. Quantitative data items relating were extracted critically appraised. Out 1,065 screened eligibility, 29 met inclusion criteria. Most frequent tasks named entity recognition (n = 17; 58.6%) relation extraction/classification 15; 51.7%). Clinical involvement reported nine studies (31%). Multiple modelling approaches seem suitable, with Long Short Term Memory Conditional Random Field most commonly used. Although overall performance systems high, it provides an inflated impression given steep drop when predicting or class. When annotating corpora, treating as between non-drug seems best Future should focus on semi-automated manual annotation effort, examine implementation

Language: Английский

Citations

48
Automated Machine Learning for Healthcare and Clinical Notes Analysis DOI Creative Commons
Akram Mustafa, Mostafa Rahimi Azghadi

Computers, Journal Year: 2021, Volume and Issue: 10(2), P. 24 - 24

Published: Feb. 22, 2021

Machine learning (ML) has been slowly entering every aspect of our lives and its positive impact astonishing. To accelerate embedding ML in more applications incorporating it real-world scenarios, automated machine (AutoML) is emerging. The main purpose AutoML to provide seamless integration various industries, which will facilitate better outcomes everyday tasks. In healthcare, already applied easier settings with structured data such as tabular lab data. However, there still a need for applying interpreting medical text, being generated at tremendous rate. For this happen, promising method clinical notes analysis, an unexplored research area representing gap research. objective paper fill comprehensive survey analytical study towards notes. that end, we first introduce the technology review tools techniques. We then literature healthcare industry discuss developments specific settings, well those using general applications. With background, challenges working highlight benefits developing processing. Next, relevant analyze field industry. Furthermore, propose future directions shed light on opportunities emerging holds. this, aim assist community implementation platform notes, if realized can revolutionize patient outcomes.

Language: Английский

Citations

104