Clinical language search algorithm from free-text: facilitating appropriate imaging
Abstract Background The comprehensiveness and maintenance of the American College of Radiology (ACR) Appropriateness Criteria (AC) makes it a unique resource for evidence-based clinical imaging decision support, but it is underutilized by clinicians. To facilitate the use of imaging recommendations,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-02-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-022-00740-6 |
| _version_ | 1818486325350760448 |
|---|---|
| author | Gunvant R. Chaudhari Yeshwant R. Chillakuru Timothy L. Chen Valentina Pedoia Thienkhai H. Vu Christopher P. Hess Youngho Seo Jae Ho Sohn |
| author_facet | Gunvant R. Chaudhari Yeshwant R. Chillakuru Timothy L. Chen Valentina Pedoia Thienkhai H. Vu Christopher P. Hess Youngho Seo Jae Ho Sohn |
| author_sort | Gunvant R. Chaudhari |
| collection | DOAJ |
| description | Abstract Background The comprehensiveness and maintenance of the American College of Radiology (ACR) Appropriateness Criteria (AC) makes it a unique resource for evidence-based clinical imaging decision support, but it is underutilized by clinicians. To facilitate the use of imaging recommendations, we develop a natural language processing (NLP) search algorithm that automatically matches clinical indications that physicians write into imaging orders to appropriate AC imaging recommendations. Methods We apply a hybrid model of semantic similarity from a sent2vec model trained on 223 million scientific sentences, combined with term frequency inverse document frequency features. AC documents are ranked based on their embeddings’ cosine distance to query. For model testing, we compiled a dataset of simulated simple and complex indications for each AC document (n = 410) and another with clinical indications from randomly sampled radiology reports (n = 100). We compare our algorithm to a custom google search engine. Results On the simulated indications, our algorithm ranked ground truth documents as top 3 for 98% of simple queries and 85% of complex queries. Similarly, on the randomly sampled radiology report dataset, the algorithm ranked 86% of indications with a single match as top 3. Vague and distracting phrases present in the free-text indications were main sources of errors. Our algorithm provides more relevant results than a custom Google search engine, especially for complex queries. Conclusions We have developed and evaluated an NLP algorithm that matches clinical indications to appropriate AC guidelines. This approach can be integrated into imaging ordering systems for automated access to guidelines. |
| first_indexed | 2024-12-10T16:21:27Z |
| format | Article |
| id | doaj.art-046f093aa07f41fc9a6de5b78a678369 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-12-10T16:21:27Z |
| publishDate | 2022-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-046f093aa07f41fc9a6de5b78a6783692022-12-22T01:41:47ZengBMCBMC Medical Imaging1471-23422022-02-012211910.1186/s12880-022-00740-6Clinical language search algorithm from free-text: facilitating appropriate imagingGunvant R. Chaudhari0Yeshwant R. Chillakuru1Timothy L. Chen2Valentina Pedoia3Thienkhai H. Vu4Christopher P. Hess5Youngho Seo6Jae Ho Sohn7Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Center for Intelligent Imaging, Radiology and Biomedical Imaging, University of California San Francisco (UCSF)Abstract Background The comprehensiveness and maintenance of the American College of Radiology (ACR) Appropriateness Criteria (AC) makes it a unique resource for evidence-based clinical imaging decision support, but it is underutilized by clinicians. To facilitate the use of imaging recommendations, we develop a natural language processing (NLP) search algorithm that automatically matches clinical indications that physicians write into imaging orders to appropriate AC imaging recommendations. Methods We apply a hybrid model of semantic similarity from a sent2vec model trained on 223 million scientific sentences, combined with term frequency inverse document frequency features. AC documents are ranked based on their embeddings’ cosine distance to query. For model testing, we compiled a dataset of simulated simple and complex indications for each AC document (n = 410) and another with clinical indications from randomly sampled radiology reports (n = 100). We compare our algorithm to a custom google search engine. Results On the simulated indications, our algorithm ranked ground truth documents as top 3 for 98% of simple queries and 85% of complex queries. Similarly, on the randomly sampled radiology report dataset, the algorithm ranked 86% of indications with a single match as top 3. Vague and distracting phrases present in the free-text indications were main sources of errors. Our algorithm provides more relevant results than a custom Google search engine, especially for complex queries. Conclusions We have developed and evaluated an NLP algorithm that matches clinical indications to appropriate AC guidelines. This approach can be integrated into imaging ordering systems for automated access to guidelines.https://doi.org/10.1186/s12880-022-00740-6Natural language processingInformation retrievalAppropriateness criteriaTerm frequency-inverse document frequency |
| spellingShingle | Gunvant R. Chaudhari Yeshwant R. Chillakuru Timothy L. Chen Valentina Pedoia Thienkhai H. Vu Christopher P. Hess Youngho Seo Jae Ho Sohn Clinical language search algorithm from free-text: facilitating appropriate imaging BMC Medical Imaging Natural language processing Information retrieval Appropriateness criteria Term frequency-inverse document frequency |
| title | Clinical language search algorithm from free-text: facilitating appropriate imaging |
| title_full | Clinical language search algorithm from free-text: facilitating appropriate imaging |
| title_fullStr | Clinical language search algorithm from free-text: facilitating appropriate imaging |
| title_full_unstemmed | Clinical language search algorithm from free-text: facilitating appropriate imaging |
| title_short | Clinical language search algorithm from free-text: facilitating appropriate imaging |
| title_sort | clinical language search algorithm from free text facilitating appropriate imaging |
| topic | Natural language processing Information retrieval Appropriateness criteria Term frequency-inverse document frequency |
| url | https://doi.org/10.1186/s12880-022-00740-6 |
| work_keys_str_mv | AT gunvantrchaudhari clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT yeshwantrchillakuru clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT timothylchen clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT valentinapedoia clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT thienkhaihvu clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT christopherphess clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT younghoseo clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging AT jaehosohn clinicallanguagesearchalgorithmfromfreetextfacilitatingappropriateimaging |