Natural Language Processing Algorithm Used for Staging Pulmonary Oncology from Free-Text Radiological Reports : "Including PET-CT and Validation Towards Clinical Use"
© 2024. The Author(s)..
Natural language processing (NLP) can be used to process and structure free text, such as (free text) radiological reports. In radiology, it is important that reports are complete and accurate for clinical staging of, for instance, pulmonary oncology. A computed tomography (CT) or positron emission tomography (PET)-CT scan is of great importance in tumor staging, and NLP may be of additional value to the radiological report when used in the staging process as it may be able to extract the T and N stage of the 8th tumor-node-metastasis (TNM) classification system. The purpose of this study is to evaluate a new TN algorithm (TN-PET-CT) by adding a layer of metabolic activity to an already existing rule-based NLP algorithm (TN-CT). This new TN-PET-CT algorithm is capable of staging chest CT examinations as well as PET-CT scans. The study design made it possible to perform a subgroup analysis to test the external validation of the prior TN-CT algorithm. For information extraction and matching, pyContextNLP, SpaCy, and regular expressions were used. Overall TN accuracy score of the TN-PET-CT algorithm was 0.73 and 0.62 in the training and validation set (N = 63, N = 100). The external validation of the TN-CT classifier (N = 65) was 0.72. Overall, it is possible to adjust the TN-CT algorithm into a TN-PET-CT algorithm. However, outcomes highly depend on the accuracy of the report, the used vocabulary, and its context to express, for example, uncertainty. This is true for both the adjusted PET-CT algorithm and for the CT algorithm when applied in another hospital.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:37 |
|---|---|
| Enthalten in: |
Journal of imaging informatics in medicine - 37(2024), 1 vom: 12. Feb., Seite 3-12 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Nobel, J Martijn [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Classification system |
|---|
| Anmerkungen: |
Date Completed 04.03.2024 Date Revised 29.03.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1007/s10278-023-00913-x |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36833385X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36833385X | ||
| 003 | DE-627 | ||
| 005 | 20240330000925.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240213s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10278-023-00913-x |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1355.xml |
| 035 | |a (DE-627)NLM36833385X | ||
| 035 | |a (NLM)38343237 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Nobel, J Martijn |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Natural Language Processing Algorithm Used for Staging Pulmonary Oncology from Free-Text Radiological Reports |b "Including PET-CT and Validation Towards Clinical Use" |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 04.03.2024 | ||
| 500 | |a Date Revised 29.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2024. The Author(s). | ||
| 520 | |a Natural language processing (NLP) can be used to process and structure free text, such as (free text) radiological reports. In radiology, it is important that reports are complete and accurate for clinical staging of, for instance, pulmonary oncology. A computed tomography (CT) or positron emission tomography (PET)-CT scan is of great importance in tumor staging, and NLP may be of additional value to the radiological report when used in the staging process as it may be able to extract the T and N stage of the 8th tumor-node-metastasis (TNM) classification system. The purpose of this study is to evaluate a new TN algorithm (TN-PET-CT) by adding a layer of metabolic activity to an already existing rule-based NLP algorithm (TN-CT). This new TN-PET-CT algorithm is capable of staging chest CT examinations as well as PET-CT scans. The study design made it possible to perform a subgroup analysis to test the external validation of the prior TN-CT algorithm. For information extraction and matching, pyContextNLP, SpaCy, and regular expressions were used. Overall TN accuracy score of the TN-PET-CT algorithm was 0.73 and 0.62 in the training and validation set (N = 63, N = 100). The external validation of the TN-CT classifier (N = 65) was 0.72. Overall, it is possible to adjust the TN-CT algorithm into a TN-PET-CT algorithm. However, outcomes highly depend on the accuracy of the report, the used vocabulary, and its context to express, for example, uncertainty. This is true for both the adjusted PET-CT algorithm and for the CT algorithm when applied in another hospital | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Classification system | |
| 650 | 4 | |a Free text | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Natural language processing | |
| 650 | 4 | |a Radiology | |
| 650 | 4 | |a Reporting | |
| 700 | 1 | |a Puts, Sander |e verfasserin |4 aut | |
| 700 | 1 | |a Krdzalic, Jasenko |e verfasserin |4 aut | |
| 700 | 1 | |a Zegers, Karen M L |e verfasserin |4 aut | |
| 700 | 1 | |a Lobbes, Marc B I |e verfasserin |4 aut | |
| 700 | 1 | |a F Robben, Simon G |e verfasserin |4 aut | |
| 700 | 1 | |a Dekker, André L A J |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of imaging informatics in medicine |d 2024 |g 37(2024), 1 vom: 12. Feb., Seite 3-12 |w (DE-627)NLM367974452 |x 2948-2933 |7 nnns |
| 773 | 1 | 8 | |g volume:37 |g year:2024 |g number:1 |g day:12 |g month:02 |g pages:3-12 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/s10278-023-00913-x |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 37 |j 2024 |e 1 |b 12 |c 02 |h 3-12 | ||