Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction

Lee, Seung‐Hee; Shin, Jeongwon; Kim, Hyeon Seong; Lee, Min Je; Yoon, Jung Min; Lee, Sohee; Kim, Yong-Suk; Kim, Jong‐Yeup; Lee, Suehyun

doi:10.1007/s40264-021-01123-6

Cited by 8 publications

(64 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 34–42 Four studies (40%) stated the medical specialty studied. 34 , 38 , 40 , 42 Segal et al included data from the internal medicine department 42 and Lee et al from the pediatric department. 40 Beaudoin et al focused on (inappropriate) antimicrobial prescriptions, in specific piperacillin-tazobactam prescriptions.…”

Section: Resultsmentioning

confidence: 99%

The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: a scoping review

Graafsma,

Murphy,

van de Garde

et al. 2024

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective Current Clinical Decision Support Systems (CDSSs) generate medication alerts that are of limited clinical value, causing alert fatigue. Artificial Intelligence (AI)-based methods may help in optimizing medication alerts. Therefore, we conducted a scoping review on the current state of the use of AI to optimize medication alerts in a hospital setting. Specifically, we aimed to identify the applied AI methods used together with their performance measures and main outcome measures. Materials and Methods We searched Medline, Embase, and Cochrane Library database on May 25, 2023 for studies of any quantitative design, in which the use of AI-based methods was investigated to optimize medication alerts generated by CDSSs in a hospital setting. The screening process was supported by ASReview software. Results Out of 5625 citations screened for eligibility, 10 studies were included. Three studies (30%) reported on both statistical performance and clinical outcomes. The most often reported performance measure was positive predictive value ranging from 9% to 100%. Regarding main outcome measures, alerts optimized using AI-based methods resulted in a decreased alert burden, increased identification of inappropriate or atypical prescriptions, and enabled prediction of user responses. In only 2 studies the AI-based alerts were implemented in hospital practice, and none of the studies conducted external validation. Discussion and Conclusion AI-based methods can be used to optimize medication alerts in a hospital setting. However, reporting on models’ development and validation should be improved, and external validation and implementation in hospital practice should be encouraged.

show abstract

Section: Resultsmentioning

confidence: 99%

The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: a scoping review

Graafsma,

Murphy,

van de Garde

et al. 2024

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

show abstract

“…ScispaCy is a rule-based and Named Entity Recognition (NER)-based Python library for biomedical text processing, which has demonstrated robust results on several Named Entity Recognition (NER) tasks compared to the neural network models of the time. 5 It is trained on gene data, PubMed articles, medications datasets, and one of their proprietary datasets. We implemented scispaCy version 0.5.2 following the code structure specified in their documentation.…”

Section: Methodsmentioning

confidence: 99%

“…Rule-based, machine learning-based, and deep-learning models have been applied to phenotype extraction. [1][2][3][4][5][6][7] While rule-based models extract phenotypes based on pre-defined patterns, most machine learning and deep-learning approaches are trained on sentences or documents labeled with the relevant phenotypes and the model subsequently classifies texts into these phenotypes. 5,8 SpaCy models, including MedspaCy 7 and scispaCy 9 are two recent and frequently used hybrid frameworks that utilize statistical and machine-learning named entity recognition methods in conjunction with rule-based NLP to identify clinical phenotypes.…”

Section: Introductionmentioning

confidence: 99%

“…[1][2][3][4][5][6][7] While rule-based models extract phenotypes based on pre-defined patterns, most machine learning and deep-learning approaches are trained on sentences or documents labeled with the relevant phenotypes and the model subsequently classifies texts into these phenotypes. 5,8 SpaCy models, including MedspaCy 7 and scispaCy 9 are two recent and frequently used hybrid frameworks that utilize statistical and machine-learning named entity recognition methods in conjunction with rule-based NLP to identify clinical phenotypes. There are studies that have utilized medspaCy and scispaCy to identify specific sections within EHR text for NER, extract phenotypes from relation extraction documents, and generate text embeddings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging GPT-4 for Identifying Cancer Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo, Flan-T5 and spaCy’s Rule-based & Machine Learning-based methods

Bhattarai,

Oh,

Sierra

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveAccurately identifying clinical phenotypes from Electronic Health Records (EHRs) provides additional insights into patients’ health, especially when such information is unavailable in structured data. This study evaluates the application of OpenAI’s transformer-based Generative Pre-trained Transformer (GPT)-4 model to identify clinical phenotypes from EHR text in non-small cell lung cancer (NSCLC) patients. The goal is to identify disease stages, treatments and progression utilizing GPT-4, and compare its performance against GPT-3.5-turbo, and two rule-based and machine learning-based methods, namely, scispaCy and medspaCy.Materials and MethodsPhenotypes such as initial cancer stage, initial treatment, evidence of cancer recurrence, and affected organs during recurrence were identified from 13,646 records for 63 NSCLC patients from Washington University in St. Louis, Missouri. The performance of the GPT-4 model is evaluated against GPT-3.5-turbo, medspaCy and scispaCy by comparing precision, recall, and weighted F1 scores.ResultsGPT-4 achieves higher F1 score, precision, and recall compared to medspaCy and scispaCy’s models. GPT-3.5-turbo performs similar to that of GPT-4. GPT models are not constrained by explicit rule requirements for contextual pattern recognition. SpaCy models rely on predefined patterns, leading to their suboptimal performance.Discussion and ConclusionGPT-4 improves clinical phenotype identification due to its robust pre-training and remarkable pattern recognition capability on the embedded tokens. It demonstrates data-driven effectiveness even with limited context in the input. While rule-based models remain useful for some tasks, GPT models offer improved contextual understanding of the text, robust clinical phenotype extraction, and improved ability to provide better care to the patients.

show abstract

“…In-silico physicochemical, drug-likeness, and pharmacokinetics of identified bioactive compounds were predicted by the Swiss ADME web tool 13 . The Pre ADMET tool was used to assess the toxicological properties of compounds 14 .…”

Section: In-silico Adme/tox Prediction Of Compoundsmentioning

confidence: 99%

Untitled

2023

IJPSR

View full text Add to dashboard Cite

Rheumatoid arthritis is a systemic autoimmune and inflammatory disease that primarily affects the synovial joints and eventually destroys them. Schleichera oleosa is a plant of Indian provenance that exhibits anti-rheumatoid arthritis activity. The phytochemical constituents in the methanol extract of barks from Schleichera oleosa were identified using gas chromatography-mass spectrometry (GC-MS) in the current study. The GC-MS analysis in bark extract identified 21 phytochemical compounds. The PASS server assessed the biological activity of the reported compounds and identified six compounds with anti-arthritic and anti-inflammatory activities. Subsequently, these compounds were screened through ADME/Tox and molecular docking approaches. Two compounds 2,4-Di-tert-butylphenol and 2,6-DI-Tert-butylphenol qualify for all the criteria of ADME/Tox. The molecular docking method identified compounds 2,4-Di-tert-butylphenol and 2,6-DI-Tert-butylphenol had binding affinity ranging between -4.89 to -6.49 kcal/mol with the active site of anti-arthritic target proteins Chitotriosidase-1 and Vascular cell adhesion molecule 1. The findings of this study will create a way to invent herbal medicines for Rheumatoid Arthritis using the Schleichera oleosa plant, potentially leading to the development of new drugs. INTRODUCTION:Rheumatoid arthritis (RA) is a chronic autoimmune inflammatory disease that can affect numerous tissues and organs but is most commonly associated with synovial joints 1 . RA affects approximately 1% of the world's population, and there is no cure 2 . Rheumatoid arthritis can also produce diffuse inflammation of the lungs, pericardium, pleura, and sclera, as well as nodular lesions, which are most frequent in subcutaneous tissue 3 .

show abstract

Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction

Cited by 8 publications

References 14 publications

The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: a scoping review

The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: a scoping review

Leveraging GPT-4 for Identifying Cancer Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo, Flan-T5 and spaCy’s Rule-based & Machine Learning-based methods

Untitled

Contact Info

Product

Resources

About