An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus
The therapeutic goal for diabetes mellitus is to maintain normal blood glucose levels, but in some cases, hypoglycemia may occur as a consequence of treatment. Identifying patients with hypoglycemia is critical to preventing adverse events and mortality. However, hypoglycemic events are often not ac...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442524000832 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540367949398016 |
|---|---|
| author | J.E. Camacho-Cogollo Cristhian Felipe Patiño Zambrano Christian Lochmuller Claudia C. Colmenares-Mejia Nicolas Rozo Mario A. Isaza-Ruget Paul Rodriguez Andrés García |
| author_facet | J.E. Camacho-Cogollo Cristhian Felipe Patiño Zambrano Christian Lochmuller Claudia C. Colmenares-Mejia Nicolas Rozo Mario A. Isaza-Ruget Paul Rodriguez Andrés García |
| author_sort | J.E. Camacho-Cogollo |
| collection | DOAJ |
| description | The therapeutic goal for diabetes mellitus is to maintain normal blood glucose levels, but in some cases, hypoglycemia may occur as a consequence of treatment. Identifying patients with hypoglycemia is critical to preventing adverse events and mortality. However, hypoglycemic events are often not accurately documented in electronic health records (EHRs). This study presents a retrospective analysis of the EHRs of patients with diabetes mellitus. We hypothesize that text analytics and machine learning can identify possible hypoglycemic incidents from unstructured physician notes in electronic health records. Our analysis applies these techniques using the Python programming language as a tool. It also considers words that describe symptoms related to hypoglycemia. The analysis involves searching physicians' notes for keywords and applying supervised classification methods to 146,542 records. Natural language processing (NLP) and machine learning algorithms are used to identify possible hypoglycemic events and related symptoms in physicians’ notes. A multi-layer perceptron (MLP) model produces the best classification performance among all the models tested in this study, with an obtained accuracy of 0.87. We show that the NLP approach can effectively identify and automate the text-based detection process of potential hypoglycemic events, and can subsequently be used to make informed decisions about potential patient risks. |
| format | Article |
| id | doaj-art-082320be80964b9b891a542c40d1291f |
| institution | Kabale University |
| issn | 2772-4425 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj-art-082320be80964b9b891a542c40d1291f2025-02-05T04:32:50ZengElsevierHealthcare Analytics2772-44252025-06-017100381An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitusJ.E. Camacho-Cogollo0Cristhian Felipe Patiño Zambrano1Christian Lochmuller2Claudia C. Colmenares-Mejia3Nicolas Rozo4Mario A. Isaza-Ruget5Paul Rodriguez6Andrés García7Universidad EIA, Colombia; Corresponding author. Universidad EIA, Calle 23 AA Sur Nro. 5- 200, Kilómetro 2+200 Variante al Aeropuerto José María Córdova, Envigado, 055428, Colombia.Universidad EIA, ColombiaUniversidad EIA, ColombiaFundación Universitaria Sanitas, ColombiaColsanitas, ColombiaFundación Universitaria Sanitas, Grupo de investigación INPAC, Bogotá, ColombiaUniversidad del Rosario, ColombiaUniversidad del Rosario, ColombiaThe therapeutic goal for diabetes mellitus is to maintain normal blood glucose levels, but in some cases, hypoglycemia may occur as a consequence of treatment. Identifying patients with hypoglycemia is critical to preventing adverse events and mortality. However, hypoglycemic events are often not accurately documented in electronic health records (EHRs). This study presents a retrospective analysis of the EHRs of patients with diabetes mellitus. We hypothesize that text analytics and machine learning can identify possible hypoglycemic incidents from unstructured physician notes in electronic health records. Our analysis applies these techniques using the Python programming language as a tool. It also considers words that describe symptoms related to hypoglycemia. The analysis involves searching physicians' notes for keywords and applying supervised classification methods to 146,542 records. Natural language processing (NLP) and machine learning algorithms are used to identify possible hypoglycemic events and related symptoms in physicians’ notes. A multi-layer perceptron (MLP) model produces the best classification performance among all the models tested in this study, with an obtained accuracy of 0.87. We show that the NLP approach can effectively identify and automate the text-based detection process of potential hypoglycemic events, and can subsequently be used to make informed decisions about potential patient risks.http://www.sciencedirect.com/science/article/pii/S2772442524000832Natural language processingMachine learningDiabetes mellitusElectronic health recordsHypoglycemiaClassification |
| spellingShingle | J.E. Camacho-Cogollo Cristhian Felipe Patiño Zambrano Christian Lochmuller Claudia C. Colmenares-Mejia Nicolas Rozo Mario A. Isaza-Ruget Paul Rodriguez Andrés García An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus Healthcare Analytics Natural language processing Machine learning Diabetes mellitus Electronic health records Hypoglycemia Classification |
| title | An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| title_full | An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| title_fullStr | An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| title_full_unstemmed | An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| title_short | An application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| title_sort | application of natural language processing for hypoglycemic event identification in patients with diabetes mellitus |
| topic | Natural language processing Machine learning Diabetes mellitus Electronic health records Hypoglycemia Classification |
| url | http://www.sciencedirect.com/science/article/pii/S2772442524000832 |
| work_keys_str_mv | AT jecamachocogollo anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT cristhianfelipepatinozambrano anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT christianlochmuller anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT claudiaccolmenaresmejia anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT nicolasrozo anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT marioaisazaruget anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT paulrodriguez anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT andresgarcia anapplicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT jecamachocogollo applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT cristhianfelipepatinozambrano applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT christianlochmuller applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT claudiaccolmenaresmejia applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT nicolasrozo applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT marioaisazaruget applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT paulrodriguez applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus AT andresgarcia applicationofnaturallanguageprocessingforhypoglycemiceventidentificationinpatientswithdiabetesmellitus |