An Automated System for Identifying Alcohol Use Status from Clinical Text

Alzoubi, Hadeel; Ramzan, Naeem; Alzubi, Raid; Ehsan, Mehdi

doi:10.1109/iccecome.2018.8658578

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the previous works that applied NLP techniques in extracting alcohol-related information from unstructured clinical notes [45][46][47][48], our use of the transformer-based language models also introduces various future research directions from a machine learning perspective. For example, Hao et al [77] noted that fine-tuning a transformer language model induces significant changes in the feature extraction capabilities within its intermediate and last layers.…”

Section: Discussionmentioning

confidence: 99%

“…Lix et al [45] represented free-text clinical notes with both unigram and bigrams to train support vector machine classifiers that automatically classify alcohol use in the patients from the Canadian Primary Care Sentinel Surveillance Network. Alzoubi et al [46] used a pre-defined set of alcoholrelated keywords to detect alcohol-related sentences. Subsequently, they also used unigram and bigrams along with various machine learning classifiers to identify patients who were currently consuming alcohol.…”

Section: Related Workmentioning

confidence: 99%

“…Compared to the traditional NLP methods used in the previous works [45][46][47][48], our work is the first to adopt transformer-based language models to extract alcohol-related information from clinical notes. Large-scale transformerbased language models explored in this paper learn contextualized word embedding based on the masked language model objective [50].…”

Section: Related Workmentioning

confidence: 99%

“…To validate its extraction performance, we compare its performance with other NLP algorithms. As used in previous literature in alcohol-related information extraction from clinical notes [45][46][47][48]58], we use the bag-of-words (BoW) as a baseline. It represents each sentence using the frequencies of the words in the dataset.…”

Section: B Extraction Performancementioning

confidence: 99%

See 3 more Smart Citations

Identifying Alcohol-Related Information From Unstructured Bilingual Clinical Notes With Multilingual Transformers

Kim

Park

et al. 2023

IEEE Access

View full text Add to dashboard Cite

As a key modifiable risk factor, alcohol consumption is clinically crucial information that allows medical professionals to further understand their patients' medical conditions and suggest appropriate lifestyle modifying interventions. However, identifying alcohol-related information from unstructured freetext clinical notes is often challenging. Not only are the formats of the notes inconsistent, but they also include a massive amount of non-alcohol-related information. Furthermore, for medical institutions outside of English-speaking countries, these clinical notes contain both a mixture of English and local languages, inducing additional difficulty in the extraction. Thanks to the increasing availability of electronic medical record (EMR), several previous works explored the idea of using natural language processing (NLP) to train machine learning models that automatically identify alcohol-related information from unstructured clinical notes. However, all these previous works are limited to English clinical notes, thereby able to leverage various large-scale external ontologies during the text preprocessing. Furthermore, they rely on simple NLP techniques such as the bag-of-words models that suffer from high dimensionality and out-ofvocabulary issues. Addressing these issues, we adopt fine-tuning multilingual transformers. By leveraging their linguistically rich contextual information learned during their pre-training, we are able to extract alcohol-related information from unstructured clinical notes without preprocessing the clinical notes on any external ontologies. Furthermore, our work is the first to explore the use of transformers in bilingual clinical notes to extract alcohol-related information. Even with minimal text preprocessing, we achieve extraction accuracy of 84.70% in terms of macro F-1 score. INDEX TERMS clinical informatics, alcohol information extraction, natural language processing, information extraction from clinical notes, multilingual transformers I. INTRODUCTIONAs medical institutions worldwide are widely adopting electronic medical record (EMR), vast amounts of healthcare data are produced and stored electronically [1-5]. As a significant component of EMR, clinical notes, which record patients' conditions in free text, provide essential information such as patients' medical history, social history, or lifestyle patterns. Despite being a vital data source, its practical use in medical decision support systems is hampered by challenges in extracting key information from its unstructured text format [6][7][8][9]. For medical institutions in non-English speaking countries, these challenges are compounded by the use of both English and local languages in their clinical notes. Besides standardizing the notes to resolve any inconsistent formats or structures, they need to handle the multilingual aspect of their notes simultaneously. Due to this additional

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: B Extraction Performancementioning

confidence: 99%

See 2 more Smart Citations

Identifying Alcohol-Related Information From Unstructured Bilingual Clinical Notes With Multilingual Transformers

Kim

Park

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The risk of over-fitting can be avoided by applying a cross-validation technique which helps to provide a more objective evaluation of the performance in unseen cases. The most popular supervised techniques that were used in the literature are Support Vector Machine (SVM), Decision Tree, and multiple logistic regression methods [111,112]. Table 4 presents the classification algorithms and evaluation metrics for studies that used supervised learning as a classification technique.…”

Section: Supervised Learningmentioning

confidence: 99%

A Review of Automatic Phenotyping Approaches using Electronic Health Records

et al. 2019

Self Cite

View full text Add to dashboard Cite

Electronic Health Records (EHR) are a rich repository of valuable clinical information that exist in primary and secondary care databases. In order to utilize EHRs for medical observational research a range of algorithms for automatically identifying individuals with a specific phenotype have been developed. This review summarizes and offers a critical evaluation of the literature relating to studies conducted into the development of EHR phenotyping systems. This review describes phenotyping systems and techniques based on structured and unstructured EHR data. Articles published on PubMed and Google scholar between 2013 and 2017 have been reviewed, using search terms derived from Medical Subject Headings (MeSH). The popularity of using Natural Language Processing (NLP) techniques in extracting features from narrative text has increased. This increased attention is due to the availability of open source NLP algorithms, combined with accuracy improvement. In this review, Concept extraction is the most popular NLP technique since it has been used by more than 50% of the reviewed papers to extract features from EHR. High-throughput phenotyping systems using unsupervised machine learning techniques have gained more popularity due to their ability to efficiently and automatically extract a phenotype with minimal human effort.

show abstract