Natural language processing for populating lung cancer clinical research data
Abstract Background Lung cancer is the second most common cancer for men and women; the wide adoption of electronic health records (EHRs) offers a potential to accelerate cohort-related epidemiological studies using informatics approaches. Since manual extraction from large volumes of text materials...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-019-0931-8 |
| _version_ | 1818384711211286528 |
|---|---|
| author | Liwei Wang Lei Luo Yanshan Wang Jason Wampfler Ping Yang Hongfang Liu |
| author_facet | Liwei Wang Lei Luo Yanshan Wang Jason Wampfler Ping Yang Hongfang Liu |
| author_sort | Liwei Wang |
| collection | DOAJ |
| description | Abstract Background Lung cancer is the second most common cancer for men and women; the wide adoption of electronic health records (EHRs) offers a potential to accelerate cohort-related epidemiological studies using informatics approaches. Since manual extraction from large volumes of text materials is time consuming and labor intensive, some efforts have emerged to automatically extract information from text for lung cancer patients using natural language processing (NLP), an artificial intelligence technique. Methods In this study, using an existing cohort of 2311 lung cancer patients with information about stage, histology, tumor grade, and therapies (chemotherapy, radiotherapy and surgery) manually ascertained, we developed and evaluated an NLP system to extract information on these variables automatically for the same patients from clinical narratives including clinical notes, pathology reports and surgery reports. Results Evaluation showed promising results with the recalls for stage, histology, tumor grade, and therapies achieving 89, 98, 78, and 100% respectively and the precisions were 70, 88, 90, and 100% respectively. Conclusion This study demonstrated the feasibility and accuracy of automatically extracting pre-defined information from clinical narratives for lung cancer research. |
| first_indexed | 2024-12-14T03:26:36Z |
| format | Article |
| id | doaj.art-180830bfbc1c40999bc24fb90d3e2f21 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-14T03:26:36Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-180830bfbc1c40999bc24fb90d3e2f212022-12-21T23:18:51ZengBMCBMC Medical Informatics and Decision Making1472-69472019-12-0119S511010.1186/s12911-019-0931-8Natural language processing for populating lung cancer clinical research dataLiwei Wang0Lei Luo1Yanshan Wang2Jason Wampfler3Ping Yang4Hongfang Liu5Department of Health Sciences Research, Mayo Clinic College of MedicineDepartment of Good Clinical Practice, Guizhou Province People’s HospitalDepartment of Health Sciences Research, Mayo Clinic College of MedicineDepartment of Health Sciences Research, Mayo Clinic College of MedicineDepartment of Health Sciences Research, Mayo Clinic College of MedicineDepartment of Health Sciences Research, Mayo Clinic College of MedicineAbstract Background Lung cancer is the second most common cancer for men and women; the wide adoption of electronic health records (EHRs) offers a potential to accelerate cohort-related epidemiological studies using informatics approaches. Since manual extraction from large volumes of text materials is time consuming and labor intensive, some efforts have emerged to automatically extract information from text for lung cancer patients using natural language processing (NLP), an artificial intelligence technique. Methods In this study, using an existing cohort of 2311 lung cancer patients with information about stage, histology, tumor grade, and therapies (chemotherapy, radiotherapy and surgery) manually ascertained, we developed and evaluated an NLP system to extract information on these variables automatically for the same patients from clinical narratives including clinical notes, pathology reports and surgery reports. Results Evaluation showed promising results with the recalls for stage, histology, tumor grade, and therapies achieving 89, 98, 78, and 100% respectively and the precisions were 70, 88, 90, and 100% respectively. Conclusion This study demonstrated the feasibility and accuracy of automatically extracting pre-defined information from clinical narratives for lung cancer research.https://doi.org/10.1186/s12911-019-0931-8Natural language processingLung cancerStageHistologyTumor gradeTreatments |
| spellingShingle | Liwei Wang Lei Luo Yanshan Wang Jason Wampfler Ping Yang Hongfang Liu Natural language processing for populating lung cancer clinical research data BMC Medical Informatics and Decision Making Natural language processing Lung cancer Stage Histology Tumor grade Treatments |
| title | Natural language processing for populating lung cancer clinical research data |
| title_full | Natural language processing for populating lung cancer clinical research data |
| title_fullStr | Natural language processing for populating lung cancer clinical research data |
| title_full_unstemmed | Natural language processing for populating lung cancer clinical research data |
| title_short | Natural language processing for populating lung cancer clinical research data |
| title_sort | natural language processing for populating lung cancer clinical research data |
| topic | Natural language processing Lung cancer Stage Histology Tumor grade Treatments |
| url | https://doi.org/10.1186/s12911-019-0931-8 |
| work_keys_str_mv | AT liweiwang naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata AT leiluo naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata AT yanshanwang naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata AT jasonwampfler naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata AT pingyang naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata AT hongfangliu naturallanguageprocessingforpopulatinglungcancerclinicalresearchdata |