Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context
Summary: Background: Nonalcoholic fatty liver disease (NAFLD) is a major cause of liver-related morbidity in people with and without diabetes, but it is underdiagnosed, posing challenges for research and clinical management. Here, we determine if natural language processing (NLP) of data in the ele...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589537023003267 |
| _version_ | 1797738928170598400 |
|---|---|
| author | Carolin V. Schneider Tang Li David Zhang Anya I. Mezina Puru Rattan Helen Huang Kate Townsend Creasy Eleonora Scorletti Inuk Zandvakili Marijana Vujkovic Leonida Hehl Jacob Fiksel Joseph Park Kirk Wangensteen Marjorie Risman Kyong-Mi Chang Marina Serper Rotonya M. Carr Kai Markus Schneider Jinbo Chen Daniel J. Rader |
| author_facet | Carolin V. Schneider Tang Li David Zhang Anya I. Mezina Puru Rattan Helen Huang Kate Townsend Creasy Eleonora Scorletti Inuk Zandvakili Marijana Vujkovic Leonida Hehl Jacob Fiksel Joseph Park Kirk Wangensteen Marjorie Risman Kyong-Mi Chang Marina Serper Rotonya M. Carr Kai Markus Schneider Jinbo Chen Daniel J. Rader |
| author_sort | Carolin V. Schneider |
| collection | DOAJ |
| description | Summary: Background: Nonalcoholic fatty liver disease (NAFLD) is a major cause of liver-related morbidity in people with and without diabetes, but it is underdiagnosed, posing challenges for research and clinical management. Here, we determine if natural language processing (NLP) of data in the electronic health record (EHR) could identify undiagnosed patients with hepatic steatosis based on pathology and radiology reports. Methods: A rule-based NLP algorithm was built using a Linguamatics literature text mining tool to search 2.15 million pathology report and 2.7 million imaging reports in the Penn Medicine EHR from November 2014, through December 2020, for evidence of hepatic steatosis. For quality control, two independent physicians manually reviewed randomly chosen biopsy and imaging reports (n = 353, PPV 99.7%). Findings: After exclusion of individuals with other causes of hepatic steatosis, 3007 patients with biopsy-proven NAFLD and 42,083 patients with imaging-proven NAFLD were identified. Interestingly, elevated ALT was not a sensitive predictor of the presence of steatosis, and only half of the biopsied patients with steatosis ever received an ICD diagnosis code for the presence of NAFLD/NASH. There was a robust association for PNPLA3 and TM6SF2 risk alleles and steatosis identified by NLP. We identified 234 disorders that were significantly over- or underrepresented in all subjects with steatosis and identified changes in serum markers (e.g., GGT) associated with presence of steatosis. Interpretation: This study demonstrates clear feasibility of NLP-based approaches to identify patients whose steatosis was indicated in imaging and pathology reports within a large healthcare system and uncovers undercoding of NAFLD in the general population. Identification of patients at risk could link them to improved care and outcomes. Funding: The study was funded by US and German funding sources that did provide financial support only and had no influence or control over the research process. |
| first_indexed | 2024-03-12T13:50:56Z |
| format | Article |
| id | doaj.art-54d545ab8c4f481f8d80186030f7ad3b |
| institution | Directory Open Access Journal |
| issn | 2589-5370 |
| language | English |
| last_indexed | 2024-03-12T13:50:56Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj.art-54d545ab8c4f481f8d80186030f7ad3b2023-08-23T04:34:08ZengElsevierEClinicalMedicine2589-53702023-08-0162102149Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in contextCarolin V. Schneider0Tang Li1David Zhang2Anya I. Mezina3Puru Rattan4Helen Huang5Kate Townsend Creasy6Eleonora Scorletti7Inuk Zandvakili8Marijana Vujkovic9Leonida Hehl10Jacob Fiksel11Joseph Park12Kirk Wangensteen13Marjorie Risman14Kyong-Mi Chang15Marina Serper16Rotonya M. Carr17Kai Markus Schneider18Jinbo Chen19Daniel J. Rader20Division of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Department of Medicine III, RWTH Aachen University, Aachen, Germany; Corresponding author. RWTH Aachen University, Pauwelsstr.30, Aachen 52074, Germany.Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Gastroenterology and Hepatology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Gastroenterology and Hepatology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Division of Gastroenterology and Hepatology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Division of Digestive Diseases, Department of Internal Medicine, College of Medicine, University of Cincinnati, Cincinnati, OH 45267, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Corporal Michael J. Crescenz VA Medical Center, Philadelphia, PA 19104, USADepartment of Medicine III, RWTH Aachen University, Aachen, GermanyDepartment of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADepartment of Medicine, Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN 55902, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Gastroenterology and Hepatology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Corporal Michael J. Crescenz VA Medical Center, Philadelphia, PA 19104, USADivision of Gastroenterology and Hepatology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; Corporal Michael J. Crescenz VA Medical Center, Philadelphia, PA 19104, USADepartment of Medicine, Division of Gastroenterology, University of Washington, Seattle, WA 98195, USADepartment of Medicine III, RWTH Aachen University, Aachen, GermanyDepartment of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADivision of Translational Medicine and Human Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USASummary: Background: Nonalcoholic fatty liver disease (NAFLD) is a major cause of liver-related morbidity in people with and without diabetes, but it is underdiagnosed, posing challenges for research and clinical management. Here, we determine if natural language processing (NLP) of data in the electronic health record (EHR) could identify undiagnosed patients with hepatic steatosis based on pathology and radiology reports. Methods: A rule-based NLP algorithm was built using a Linguamatics literature text mining tool to search 2.15 million pathology report and 2.7 million imaging reports in the Penn Medicine EHR from November 2014, through December 2020, for evidence of hepatic steatosis. For quality control, two independent physicians manually reviewed randomly chosen biopsy and imaging reports (n = 353, PPV 99.7%). Findings: After exclusion of individuals with other causes of hepatic steatosis, 3007 patients with biopsy-proven NAFLD and 42,083 patients with imaging-proven NAFLD were identified. Interestingly, elevated ALT was not a sensitive predictor of the presence of steatosis, and only half of the biopsied patients with steatosis ever received an ICD diagnosis code for the presence of NAFLD/NASH. There was a robust association for PNPLA3 and TM6SF2 risk alleles and steatosis identified by NLP. We identified 234 disorders that were significantly over- or underrepresented in all subjects with steatosis and identified changes in serum markers (e.g., GGT) associated with presence of steatosis. Interpretation: This study demonstrates clear feasibility of NLP-based approaches to identify patients whose steatosis was indicated in imaging and pathology reports within a large healthcare system and uncovers undercoding of NAFLD in the general population. Identification of patients at risk could link them to improved care and outcomes. Funding: The study was funded by US and German funding sources that did provide financial support only and had no influence or control over the research process.http://www.sciencedirect.com/science/article/pii/S2589537023003267Liver diseaseNAFLDBiopsyEHRNatural language processing |
| spellingShingle | Carolin V. Schneider Tang Li David Zhang Anya I. Mezina Puru Rattan Helen Huang Kate Townsend Creasy Eleonora Scorletti Inuk Zandvakili Marijana Vujkovic Leonida Hehl Jacob Fiksel Joseph Park Kirk Wangensteen Marjorie Risman Kyong-Mi Chang Marina Serper Rotonya M. Carr Kai Markus Schneider Jinbo Chen Daniel J. Rader Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context EClinicalMedicine Liver disease NAFLD Biopsy EHR Natural language processing |
| title | Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context |
| title_full | Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context |
| title_fullStr | Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context |
| title_full_unstemmed | Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context |
| title_short | Large-scale identification of undiagnosed hepatic steatosis using natural language processingResearch in context |
| title_sort | large scale identification of undiagnosed hepatic steatosis using natural language processingresearch in context |
| topic | Liver disease NAFLD Biopsy EHR Natural language processing |
| url | http://www.sciencedirect.com/science/article/pii/S2589537023003267 |
| work_keys_str_mv | AT carolinvschneider largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT tangli largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT davidzhang largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT anyaimezina largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT pururattan largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT helenhuang largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT katetownsendcreasy largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT eleonorascorletti largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT inukzandvakili largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT marijanavujkovic largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT leonidahehl largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT jacobfiksel largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT josephpark largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT kirkwangensteen largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT marjorierisman largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT kyongmichang largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT marinaserper largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT rotonyamcarr largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT kaimarkusschneider largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT jinbochen largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext AT danieljrader largescaleidentificationofundiagnosedhepaticsteatosisusingnaturallanguageprocessingresearchincontext |