Classification models for predicting the source of gastrointestinal bleeding in the absence of hematemesis
Management of acute gastrointestinal bleeding necessitates the identification of the source of bleed. The source of bleeding which is clear in patients presenting with hematemesis, is unclear in the absence of it. Logistic regression, decision tree, naïve Bayes, LogitBoost and KNN models were...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Basic Research Journal
2013
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/30232/1/Classification%20models%20for%20predicting%20the%20source%20of%20gastrointestinal%20bleeding%20in%20the%20absence%20of%20hematemesis.pdf |
| _version_ | 1825947666291359744 |
|---|---|
| author | Nazziwa Aisha, Adam, Mohd Bakri Shohaimi, Shamarina |
| author_facet | Nazziwa Aisha, Adam, Mohd Bakri Shohaimi, Shamarina |
| author_sort | Nazziwa Aisha, |
| collection | UPM |
| description | Management of acute gastrointestinal bleeding necessitates the identification of the source of bleed.
The source of bleeding which is clear in patients presenting with hematemesis, is unclear in the
absence of it. Logistic regression, decision tree, naïve Bayes, LogitBoost and KNN models were
constructed from non endoscopic data of 325 patients admitted via the emergence department (ED) for
GIB without hematemesis. The performance of the models in predicting the source of bleeding into
upper gastrointestinal bleeding or lower gastrointestinal bleeding was compared. Overall the models
demonstrate good performance with regards to sensitivity specificity, PPV, NPV and classification
accuracy on the simulated data. On the GIB data, the naive Bayes model performed best with a
prediction accuracy and sensitivity of 86%, specificity of 85% and area under curve of 92%.
Classification models can help to predict the source of gastrointestinal bleeding for patients
presenting without hematemesis and may generally be useful in decision support in the ED. The
models should be explored further for clinical relevance in other settings. |
| first_indexed | 2024-03-06T08:16:53Z |
| format | Article |
| id | upm.eprints-30232 |
| institution | Universiti Putra Malaysia |
| language | English English |
| last_indexed | 2024-03-06T08:16:53Z |
| publishDate | 2013 |
| publisher | Basic Research Journal |
| record_format | dspace |
| spelling | upm.eprints-302322015-12-07T08:36:39Z http://psasir.upm.edu.my/id/eprint/30232/ Classification models for predicting the source of gastrointestinal bleeding in the absence of hematemesis Nazziwa Aisha, Adam, Mohd Bakri Shohaimi, Shamarina Management of acute gastrointestinal bleeding necessitates the identification of the source of bleed. The source of bleeding which is clear in patients presenting with hematemesis, is unclear in the absence of it. Logistic regression, decision tree, naïve Bayes, LogitBoost and KNN models were constructed from non endoscopic data of 325 patients admitted via the emergence department (ED) for GIB without hematemesis. The performance of the models in predicting the source of bleeding into upper gastrointestinal bleeding or lower gastrointestinal bleeding was compared. Overall the models demonstrate good performance with regards to sensitivity specificity, PPV, NPV and classification accuracy on the simulated data. On the GIB data, the naive Bayes model performed best with a prediction accuracy and sensitivity of 86%, specificity of 85% and area under curve of 92%. Classification models can help to predict the source of gastrointestinal bleeding for patients presenting without hematemesis and may generally be useful in decision support in the ED. The models should be explored further for clinical relevance in other settings. Basic Research Journal 2013 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/30232/1/Classification%20models%20for%20predicting%20the%20source%20of%20gastrointestinal%20bleeding%20in%20the%20absence%20of%20hematemesis.pdf Nazziwa Aisha, and Adam, Mohd Bakri and Shohaimi, Shamarina (2013) Classification models for predicting the source of gastrointestinal bleeding in the absence of hematemesis. Basic Research Journal of Medicine and Clinical Sciences, 2 (4-7). pp. 75-79. ISSN 2315-6864 http://www.basicresearchjournals.org/medicine/content/April-July%2013.html English |
| spellingShingle | Nazziwa Aisha, Adam, Mohd Bakri Shohaimi, Shamarina Classification models for predicting the source of gastrointestinal bleeding in the absence of hematemesis |
| title | Classification models for predicting the source of
gastrointestinal bleeding in the absence of hematemesis |
| title_full | Classification models for predicting the source of
gastrointestinal bleeding in the absence of hematemesis |
| title_fullStr | Classification models for predicting the source of
gastrointestinal bleeding in the absence of hematemesis |
| title_full_unstemmed | Classification models for predicting the source of
gastrointestinal bleeding in the absence of hematemesis |
| title_short | Classification models for predicting the source of
gastrointestinal bleeding in the absence of hematemesis |
| title_sort | classification models for predicting the source of gastrointestinal bleeding in the absence of hematemesis |
| url | http://psasir.upm.edu.my/id/eprint/30232/1/Classification%20models%20for%20predicting%20the%20source%20of%20gastrointestinal%20bleeding%20in%20the%20absence%20of%20hematemesis.pdf |
| work_keys_str_mv | AT nazziwaaisha classificationmodelsforpredictingthesourceofgastrointestinalbleedingintheabsenceofhematemesis AT adammohdbakri classificationmodelsforpredictingthesourceofgastrointestinalbleedingintheabsenceofhematemesis AT shohaimishamarina classificationmodelsforpredictingthesourceofgastrointestinalbleedingintheabsenceofhematemesis |