Clinical information extraction for preterm birth risk prediction

Sterckx, Lucas; Vandewiele, Gilles; Dehaene, Isabelle; Janssens, Olivier; Ongenae, Femke; Backere, Femke De; Turck, Filip De; Roelens, Kristien; Decruyenaere, Johan; Hoecke, Sofie Van; Demeester, Thomas

doi:10.1016/j.jbi.2020.103544

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, discovery of potential markers that can be used to predict late PTB unaffected by previously proposed hypothetical mechanisms. As the etiology of PTB is not fully definitive, the clinical support decision model is crucial in helping doctors provide early intervention for women at high risk of PTB [ 61 ]. In this setting, we tested to garner a predictive model combining cfRNA markers and clinical factors associated with PTB, which provide a novel strategy for the development of PTB prediction model with clinical benefit.…”

Section: Discussionmentioning

confidence: 99%

Identification of novel cell-free RNAs in maternal plasma as preterm biomarkers in combination with placental RNA profiles

et al. 2023

View full text Add to dashboard Cite

Background Preterm birth (PTB) is the main driver of newborn deaths. The identification of pregnancies at risk of PTB remains challenging, as the incomplete understanding of molecular mechanisms associated with PTB. Although several transcriptome studies have been done on the placenta and plasma from PTB women, a comprehensive description of the RNA profiles from plasma and placenta associated with PTB remains lacking. Methods Candidate markers with consistent trends in the placenta and plasma were identified by implementing differential expression analysis using placental tissue and maternal plasma RNA-seq datasets, and then validated by RT-qPCR in an independent cohort. In combination with bioinformatics analysis tools, we set up two protein–protein interaction networks of the significant PTB-related modules. The support vector machine (SVM) model was used to verify the prediction potential of cell free RNAs (cfRNAs) in plasma for PTB and late PTB. Results We identified 15 genes with consistent regulatory trends in placenta and plasma of PTB while the full term birth (FTB) acts as a control. Subsequently, we verified seven cfRNAs in an independent cohort by RT-qPCR in maternal plasma. The cfRNA ARHGEF28 showed consistence in the experimental validation and performed excellently in prediction of PTB in the model. The AUC achieved 0.990 for whole PTB and 0.986 for late PTB. Conclusions In a comparison of PTB versus FTB, the combined investigation of placental and plasma RNA profiles has shown a further understanding of the mechanism of PTB. Then, the cfRNA identified has the capacity of predicting whole PTB and late PTB.

show abstract

Section: Discussionmentioning

confidence: 99%

Identification of novel cell-free RNAs in maternal plasma as preterm biomarkers in combination with placental RNA profiles

et al. 2023

View full text Add to dashboard Cite

show abstract

“…conversation-style responses to user input 5 and is optimized for dialogue, conversation, and language.`6 ChatGPT excels in language applications such as simplifying complex ideas and writing. 7 In obstetrics and gynecology, publications on practical uses of NLP is limited but include identifying discrepancies in surgical history, 8 predicting preterm birth, 9 and predicting prognosis after ovarian cancer surgery. 2,10 To the best of our knowledge, there has not been any research evaluating the utility of NLP or LLMs in the field of urogynecology.…”

Section: Why This Mattersmentioning

confidence: 99%

Evaluation of ChatGPT for Pelvic Floor Surgery Counseling

Johnson,

Bradley,

Kenne

et al. 2024

UROGC

View full text Add to dashboard Cite

Importance Large language models are artificial intelligence applications that can comprehend and produce human-like text and language. ChatGPT is one such model. Recent advances have increased interest in the utility of large language models in medicine. Urogynecology counseling is complex and time-consuming. Therefore, we evaluated ChatGPT as a potential adjunct for patient counseling. Objective Our primary objective was to compare the accuracy and completeness of ChatGPT responses to information in standard patient counseling leaflets regarding common urogynecological procedures. Study Design Seven urogynecologists compared the accuracy and completeness of ChatGPT responses to standard patient leaflets using 5-point Likert scales with a score of 3 being “equally accurate” and “equally complete,” and a score of 5 being “much more accurate” and much more complete, respectively. This was repeated 3 months later to evaluate the consistency of ChatGPT. Additional analysis of the understandability and actionability was completed by 2 authors using the Patient Education Materials Assessment Tool. Analysis was primarily descriptive. First and second ChatGPT queries were compared with the Wilcoxon signed rank test. Results The median (interquartile range) accuracy was 3 (2–3) and completeness 3 (2–4) for the first ChatGPT query and 3 (3–3) and 4 (3–4), respectively, for the second query. Accuracy and completeness were significantly higher in the second query (P < 0.01). Understandability and actionability of ChatGPT responses were lower than the standard leaflets. Conclusions ChatGPT is similarly accurate and complete when compared with standard patient information leaflets for common urogynecological procedures. Large language models may be a helpful adjunct to direct patient-provider counseling. Further research to determine the efficacy and patient satisfaction of ChatGPT for patient counseling is needed.

show abstract

“…This could potentially lead to enhanced performance [62]. Beyond BiLSTM and BERT, several other notable deep learning models have been explored, including convolutional neural networks (CNNs) [31,44,[76][77][78][79][80][81][82][83], and the hybrid CNN-BiLSTM-CRF model [84][85][86]. These alternative approaches have been applied in various contexts and have been demonstrated to be particularly effective for Chinese corpora [87].…”

Section: Classification Modelsmentioning

confidence: 99%

Named Entity Recognition in Electronic Health Records: A Methodological Review

Durango,

Torres-Silva,

Orozco-Duque

2023

Healthc Inform Res

View full text Add to dashboard Cite

Objectives: A substantial portion of the data contained in Electronic Health Records (EHR) is unstructured, often appearing as free text. This format restricts its potential utility in clinical decision-making. Named entity recognition (NER) methods address the challenge of extracting pertinent information from unstructured text. The aim of this study was to outline the current NER methods and trace their evolution from 2011 to 2022.Methods: We conducted a methodological literature review of NER methods, with a focus on distinguishing the classification models, the types of tagging systems, and the languages employed in various corpora.Results: Several methods have been documented for automatically extracting relevant information from EHRs using natural language processing techniques such as NER and relation extraction (RE). These methods can automatically extract concepts, events, attributes, and other data, as well as the relationships between them. Most NER studies conducted thus far have utilized corpora in English or Chinese. Additionally, the bidirectional encoder representation from transformers using the BIO tagging system architecture is the most frequently reported classification scheme. We discovered a limited number of papers on the implementation of NER or RE tasks in EHRs within a specific clinical domain.Conclusions: EHRs play a pivotal role in gathering clinical information and could serve as the primary source for automated clinical decision support systems. However, the creation of new corpora from EHRs in specific clinical domains is essential to facilitate the swift development of NER and RE models applied to EHRs for use in clinical practice.

show abstract

Clinical information extraction for preterm birth risk prediction

Cited by 12 publications

References 34 publications

Identification of novel cell-free RNAs in maternal plasma as preterm biomarkers in combination with placental RNA profiles

Identification of novel cell-free RNAs in maternal plasma as preterm biomarkers in combination with placental RNA profiles

Evaluation of ChatGPT for Pelvic Floor Surgery Counseling

Named Entity Recognition in Electronic Health Records: A Methodological Review

Contact Info

Product

Resources

About