Automatic Classification of Cancer Pathology Reports: A Systematic Review

Santos, Thiago; Tariq, Amara; Gichoya, Judy Wawira; Trivedi, Hari; Banerjee, Imon

doi:10.1016/j.jpi.2022.100003

Cited by 15 publications

(8 citation statements)

References 49 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Santos et al released an open source pre-trained transformer model (PathologyBERT), which was trained on 347,173 pathology reports. It was found to be accurate in breast cancer severity classification, and may be utilized for other information extraction and classification tasks involving pathology reports [35].…”

Section: Information Extractionmentioning

confidence: 99%

Applications of Large Language Models in Pathology

Cheng

2024

Bioengineering

View full text Add to dashboard Cite

Large language models (LLMs) are transformer-based neural networks that can provide human-like responses to questions and instructions. LLMs can generate educational material, summarize text, extract structured data from free text, create reports, write programs, and potentially assist in case sign-out. LLMs combined with vision models can assist in interpreting histopathology images. LLMs have immense potential in transforming pathology practice and education, but these models are not infallible, so any artificial intelligence generated content must be verified with reputable sources. Caution must be exercised on how these models are integrated into clinical practice, as these models can produce hallucinations and incorrect results, and an over-reliance on artificial intelligence may lead to de-skilling and automation bias. This review paper provides a brief history of LLMs and highlights several use cases for LLMs in the field of pathology.

show abstract

Section: Information Extractionmentioning

confidence: 99%

Applications of Large Language Models in Pathology

Cheng

2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…12 Other recently published studies have focused on the coding of pathologic information using widely known terminologies, such as International Statistical Classification of Diseases and Related Health Problems for Oncology (ICD-O) and SNOMED-CT. 8,13,14 Previous publications have provided systematic reviews on what trends have emerged about the use of NLP in pathology. 1,15,16 However, in this review, we explore the evolution of component processes in NLP, by which natural language can be converted into logical or mathematical components, and which methods are mostly applied in practice. Use cases and applications in NLP, such as automatic classification, information extraction, and summary generation, are also discussed.…”

Section: Q6mentioning

confidence: 99%

Natural Language Processing in Pathology

López-Úbeda¹,

Martín-Noguerol²,

Aneiros‐Fernández³

et al. 2022

The American Journal of Pathology

View full text Add to dashboard Cite

“…Integrating this information into AI systems can enhance their accuracy and reliability in disease diagnosis and treatment planning. However, manually extracting this information is time-consuming, so a commonly adopted approach to extracting these findings is to use a mixture of rule-based systems with regular expressions [15][16][17] .…”

Section: Introductionmentioning

confidence: 99%

“…Automatic extraction of information from human-written text is challenging for three primary reasons. Firstly, while rule-based systems are sensitive to minor changes in the input 17 , 18 , natural language allows for an almost limitless range of expressions that preserve the same meaning. Secondly, negation poses a significant challenge, and hence contextual understanding is often required for this task.…”

Section: Introductionmentioning

confidence: 99%

Improving Information Extraction from Pathology Reports using Named Entity Recognition

Dutt

Witowski

et al. 2023

Preprint

View full text Add to dashboard Cite

Pathology reports are considered the gold standard in medical research due to their comprehensive and accurate diagnostic information. Natural language processing (NLP) techniques have been developed to automate information extraction from pathology reports. However, existing studies suffer from two significant limitations. First, they typically frame their tasks as report classification, which restricts the granularity of extracted information. Second, they often fail to generalize to unseen reports due to variations in language, negation, and human error. To overcome these challenges, we propose a BERT (bidirectional encoder representations from transformers) named entity recognition (NER) system to extract key diagnostic elements from pathology reports. We also introduce four data augmentation methods to improve the robustness of our model. Trained and evaluated on 1438 annotated breast pathology reports, acquired from a large medical center in the United States, our BERT model trained with data augmentation achieves an entity F1-score of 0.916 on an internal test set, surpassing the BERT baseline (0.843). We further assessed the model's generalizability using an external validation dataset from the United Arab Emirates, where our model maintained satisfactory performance (F1-score 0.860). Our findings demonstrate that our NER systems can effectively extract fine-grained information from widely diverse medical reports, offering the potential for large-scale information extraction in a wide range of medical and AI research. We publish our code at https://github.com/nyukat/pathology_extraction.

show abstract

Automatic Classification of Cancer Pathology Reports: A Systematic Review

Cited by 15 publications

References 49 publications

Applications of Large Language Models in Pathology

Applications of Large Language Models in Pathology

Natural Language Processing in Pathology

Improving Information Extraction from Pathology Reports using Named Entity Recognition

Contact Info

Product

Resources

About