Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data
ABSTRACT Background and Aims Appendicitis is the most common surgical emergency in pediatric patients, requiring timely diagnosis to prevent complications. This study introduces an innovative approach by integrating clinical, laboratory, and imaging features with advanced machine‐learning techniques...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-04-01
|
| Series: | Health Science Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/hsr2.70756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850280845264289792 |
|---|---|
| author | Mahdi Navaei Zohre Doogchi Fatemeh Gholami Moein Kermanizadeh Tavakoli |
| author_facet | Mahdi Navaei Zohre Doogchi Fatemeh Gholami Moein Kermanizadeh Tavakoli |
| author_sort | Mahdi Navaei |
| collection | DOAJ |
| description | ABSTRACT Background and Aims Appendicitis is the most common surgical emergency in pediatric patients, requiring timely diagnosis to prevent complications. This study introduces an innovative approach by integrating clinical, laboratory, and imaging features with advanced machine‐learning techniques to enhance diagnostic accuracy in pediatric appendicitis. Methods A retrospective analysis was conducted on 782 pediatric patients from the Regensburg Pediatric Appendicitis Data set. Clinical scores, laboratory markers, and imaging findings were analyzed. Statistical comparisons were performed using independent t‐tests and χ2 tests, with significance set at p < 0.05. Predictive models, including logistic regression and machine learning classifiers, were developed and evaluated using accuracy, precision, recall, and F1‐score. Results Significant differences were observed in clinical scores (e.g., Alvarado Score and Pediatric Appendicitis Score) and laboratory markers (e.g., WBC count and neutrophil percentage) between appendicitis (AA) and non‐appendicitis (Non‐AA) groups (p < 0.001). Imaging features, including appendix diameter, also demonstrated diagnostic value. Among predictive models, the Random Forest classifier achieved the highest accuracy (94.5%), with strong precision (93.8%) and recall (95.2%) for appendicitis diagnosis. Conclusion This study represents a novel application of machine learning models, particularly Random Forest, to enhance diagnostic accuracy for pediatric appendicitis. The integration of clinical, laboratory, and imaging features offers a comprehensive and precise diagnostic framework. Further validation in diverse populations is recommended. |
| format | Article |
| id | doaj-art-b42f3e51c1f04e7da22cd839043b75fa |
| institution | OA Journals |
| issn | 2398-8835 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Health Science Reports |
| spelling | doaj-art-b42f3e51c1f04e7da22cd839043b75fa2025-08-20T01:48:34ZengWileyHealth Science Reports2398-88352025-04-0184n/an/a10.1002/hsr2.70756Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging DataMahdi Navaei0Zohre Doogchi1Fatemeh Gholami2Moein Kermanizadeh Tavakoli3Department of Information Technology University of Applied Science and Technology Tehran IranDepartment of Education and Research University of Applied Science and Technology Tehran IranDepartment of Computer Science Amirkabir University of Technology (Tehran Polytechnic) Tehran IranDepartment of Medical Engineering and Analytics Carinthia University of Applied Sciences Villach AustriaABSTRACT Background and Aims Appendicitis is the most common surgical emergency in pediatric patients, requiring timely diagnosis to prevent complications. This study introduces an innovative approach by integrating clinical, laboratory, and imaging features with advanced machine‐learning techniques to enhance diagnostic accuracy in pediatric appendicitis. Methods A retrospective analysis was conducted on 782 pediatric patients from the Regensburg Pediatric Appendicitis Data set. Clinical scores, laboratory markers, and imaging findings were analyzed. Statistical comparisons were performed using independent t‐tests and χ2 tests, with significance set at p < 0.05. Predictive models, including logistic regression and machine learning classifiers, were developed and evaluated using accuracy, precision, recall, and F1‐score. Results Significant differences were observed in clinical scores (e.g., Alvarado Score and Pediatric Appendicitis Score) and laboratory markers (e.g., WBC count and neutrophil percentage) between appendicitis (AA) and non‐appendicitis (Non‐AA) groups (p < 0.001). Imaging features, including appendix diameter, also demonstrated diagnostic value. Among predictive models, the Random Forest classifier achieved the highest accuracy (94.5%), with strong precision (93.8%) and recall (95.2%) for appendicitis diagnosis. Conclusion This study represents a novel application of machine learning models, particularly Random Forest, to enhance diagnostic accuracy for pediatric appendicitis. The integration of clinical, laboratory, and imaging features offers a comprehensive and precise diagnostic framework. Further validation in diverse populations is recommended.https://doi.org/10.1002/hsr2.70756abdominal painclinical practicedecision treesdiagnostic accuracyemergency roomensemble methods |
| spellingShingle | Mahdi Navaei Zohre Doogchi Fatemeh Gholami Moein Kermanizadeh Tavakoli Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data Health Science Reports abdominal pain clinical practice decision trees diagnostic accuracy emergency room ensemble methods |
| title | Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data |
| title_full | Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data |
| title_fullStr | Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data |
| title_full_unstemmed | Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data |
| title_short | Leveraging Machine Learning for Pediatric Appendicitis Diagnosis: A Retrospective Study Integrating Clinical, Laboratory, and Imaging Data |
| title_sort | leveraging machine learning for pediatric appendicitis diagnosis a retrospective study integrating clinical laboratory and imaging data |
| topic | abdominal pain clinical practice decision trees diagnostic accuracy emergency room ensemble methods |
| url | https://doi.org/10.1002/hsr2.70756 |
| work_keys_str_mv | AT mahdinavaei leveragingmachinelearningforpediatricappendicitisdiagnosisaretrospectivestudyintegratingclinicallaboratoryandimagingdata AT zohredoogchi leveragingmachinelearningforpediatricappendicitisdiagnosisaretrospectivestudyintegratingclinicallaboratoryandimagingdata AT fatemehgholami leveragingmachinelearningforpediatricappendicitisdiagnosisaretrospectivestudyintegratingclinicallaboratoryandimagingdata AT moeinkermanizadehtavakoli leveragingmachinelearningforpediatricappendicitisdiagnosisaretrospectivestudyintegratingclinicallaboratoryandimagingdata |