A Natural Language Processing and Machine Learning Approach to Identification of Incidental Radiology Findings in Trauma Patients Discharged from the Emergency Department

Evans, Christopher S.; Dorris, Hugh D.; Kane, Michael T.; Mervak, Benjamin M.; Brice, Jane H.; Gray, Barbara; Moore, Carlton

doi:10.1016/j.annemergmed.2022.08.450

Cited by 9 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of neuroimaging, LLMs can identify noteworthy information in radiology reports in emergency department settings. 30 In cases of stroke, for instance, where timely intervention is critical and patient communication may be impaired due to aphasia or other neurologic deficits, an LLM could serve as an effective tool to flag essential neuroimaging findings for providers.…”

Section: Electronic Health Record Text Classificationmentioning

confidence: 99%

Large Language Models in Neurology Research and Future Practice

Romano,

Shih,

Paschalidis

et al. 2023

Neurology

View full text Add to dashboard Cite

Recent advancements in generative artificial intelligence, particularly using large language models (LLMs), are gaining increased public attention. We provide a perspective on the potential of LLMs to analyze enormous amounts of data from medical records and gain insights on specific topics in neurology. Additionally, we explore use cases for LLMs such as early diagnosis, supporting patient and caregivers, and acting as an assistant for clinicians. We point to the potential ethical and technical challenges raised by LLMs, such as concerns about privacy and data security, potential biases in the data for model training, and the need for careful validation of results. Researchers must consider these challenges and take steps to address them to ensure that their work is conducted in a safe and responsible manner. Despite these challenges, LLMs offer promising opportunities for improving care and treatment of various neurological disorders.

show abstract

Section: Electronic Health Record Text Classificationmentioning

confidence: 99%

Large Language Models in Neurology Research and Future Practice

Romano,

Shih,

Paschalidis

et al. 2023

Neurology

View full text Add to dashboard Cite

show abstract

“…It consisted of four studies involving 23,707 patients focused on syndromic surveillance, 27,29,33,41 12 studies covering 155,402 patients targeting diseases/events/syndromes recognition, [36][37][38][39][40][42][43][44][45]47,48,53 and 11 studies involving 9025 images concentrating on radiology interpretations. 28,[30][31][32]34,35,46,[49][50][51][52] Detailed descriptions of each study are provided in Table 2. The mean sensitivity across studies was 0.87 CI 0.82-0.91), specificity was 0.95 (95% CI 0.92-0.97), PPV was 0.18 (95% CI 0.18-0.18), NPV was 1.00 (95% CI 1.00-1.00), LR+ was 17.4 (95% CI 10.3-29.5), and LR− was 0.13 (95% CI 0.09-0.19).…”

Section: Resultsmentioning

confidence: 99%

“…Overall, this meta‐analysis included 27 studies with 179,109 patients and 9025 images. It consisted of four studies involving 23,707 patients focused on syndromic surveillance, 27,29,33,41 12 studies covering 155,402 patients targeting diseases/events/syndromes recognition, 36–40,42–45,47,48,53 and 11 studies involving 9025 images concentrating on radiology interpretations 28,30–32,34,35,46,49–52 . Detailed descriptions of each study are provided in Table 2.…”

Section: Resultsmentioning

confidence: 99%

Using natural language processing in emergency medicine health service research: A systematic review and meta‐analysis

Wang,

Alanis,

Haygood

et al. 2024

Academic Emergency Medicine

View full text Add to dashboard Cite

ObjectivesNatural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting.MethodsWe systematically searched publications related to EM research and NLP across databases including MEDLINE, Embase, Scopus, CENTRAL, and ProQuest Dissertations & Theses Global. Independent reviewers screened, reviewed, and evaluated article quality and bias. NLP usage was categorized into syndromic surveillance, radiologic interpretation, and identification of specific diseases/events/syndromes, with respective sensitivity analysis reported. Performance metrics for NLP usage were calculated and the overall area under the summary of receiver operating characteristic curve (SROC) was determined.ResultsA total of 27 studies underwent meta‐analysis. Findings indicated an overall mean sensitivity (recall) of 82%–87%, specificity of 95%, with the area under the SROC at 0.96 (95% CI 0.94–0.98). Optimal performance using NLP was observed in radiologic interpretation, demonstrating an overall mean sensitivity of 93% and specificity of 96%.ConclusionsOur analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP‐based research to augment EM health care management.

show abstract

“…A Natural Language Processing (NLP) approach was used to train an algorithm to identify text patterns in the CT report relating to the binary-coded outcome (incidental finding present/not present) 5. The best cut-off was defined as the receiver operating characteristic curve point which maximised both sensitivity and specificity.…”

Section: A Natural Language Processing and Machine Learning Approach ...mentioning

confidence: 99%

Journal update monthly top five

et al. 2023

View full text Add to dashboard Cite

Word count including subheadings & bottom line (excluding references): 1485This month's update is by the EMJ journal update monthly top five core team. We used a multimodal search strategy, drawing on free open-access medical education resources and literature searches. We identified the five most interesting and relevant papers (decided by consensus) and highlight the main findings, key limitations and clinical bottom line for each paper.The papers are ranked as: Worth a peek-interesting, but not yet ready for prime time. Head turner-new concepts. Game changer-this paper could/should change practice.

show abstract

A Natural Language Processing and Machine Learning Approach to Identification of Incidental Radiology Findings in Trauma Patients Discharged from the Emergency Department

Cited by 9 publications

References 14 publications

Large Language Models in Neurology Research and Future Practice

Large Language Models in Neurology Research and Future Practice

Using natural language processing in emergency medicine health service research: A systematic review and meta‐analysis

Journal update monthly top five

Contact Info

Product

Resources

About