A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health
Abstract Background The practice of medicine has evolved significantly during the past decade, with the emergence of Machine Learning (ML) that offers the opportunity of personalized patient-tailored care. However, ML models still face some challenges when classifying patients where clear-cut bounda...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-025-06228-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849341964233736192 |
|---|---|
| author | Bassel Hammoud Aline Semaan Lenka Benova Imad H. Elhajj |
| author_facet | Bassel Hammoud Aline Semaan Lenka Benova Imad H. Elhajj |
| author_sort | Bassel Hammoud |
| collection | DOAJ |
| description | Abstract Background The practice of medicine has evolved significantly during the past decade, with the emergence of Machine Learning (ML) that offers the opportunity of personalized patient-tailored care. However, ML models still face some challenges when classifying patients where clear-cut boundaries between classes are hard to identify. In this work, we propose an ML architecture to improve the sensitivity of detecting patients in intermediate “hard-to-classify” classes. Methods The proposed architecture replaces a single classifier with a group of cascaded increasingly specialized classifiers: the ‘Human-like’, the ‘Segregating’, and the ‘Deep’ classifiers. Its effectiveness is tested, using 8 ML algorithms (Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Random Forest, XGBoost, CatBoost, and Artificial Neural Network) to predict the feeling of protection among healthcare workers during the COVID-19 pandemic, based on a global online survey, then validated on two other outputs. Results The results show, for most algorithms, an enhanced detection of data points belonging to intermediate classes (up to 14% absolute increase in accuracy), as well as an overall improvement in the models’ accuracies (up to 5.8% absolute increase). The validation experiments yielded similar results with improved accuracies for most algorithms when compared to the single classifier architecture. Conclusion This novel architecture is proving to be a very promising tool for improving accuracy of the models when classifying patients in intermediate classes, regardless of the algorithm used. Accuracy-improvement for likert-type scale measures offers an opportunity for rapidly identifying “risk-profiles” during emergencies and beyond. This applies equally to patients and healthcare providers, with potential for improving quality of care and strengthening patient-centered healthcare systems that prioritize healthcare providers’ wellbeing. |
| format | Article |
| id | doaj-art-171e1e5fc9524be19b7d6eef0e3c6920 |
| institution | Kabale University |
| issn | 1471-2105 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj-art-171e1e5fc9524be19b7d6eef0e3c69202025-08-20T03:43:31ZengBMCBMC Bioinformatics1471-21052025-07-0126111710.1186/s12859-025-06228-8A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public healthBassel Hammoud0Aline Semaan1Lenka Benova2Imad H. Elhajj3Biomedical Engineering Program, Faculty of Medicine–Maroun Semaan Faculty of Engineering and Architecture, American University of BeirutDepartment of Public Health, Institute of Tropical MedicineDepartment of Public Health, Institute of Tropical MedicineElectrical and Computer Engineering Department, Maroun Semaan Faculty of Engineering and Architecture, American University of BeirutAbstract Background The practice of medicine has evolved significantly during the past decade, with the emergence of Machine Learning (ML) that offers the opportunity of personalized patient-tailored care. However, ML models still face some challenges when classifying patients where clear-cut boundaries between classes are hard to identify. In this work, we propose an ML architecture to improve the sensitivity of detecting patients in intermediate “hard-to-classify” classes. Methods The proposed architecture replaces a single classifier with a group of cascaded increasingly specialized classifiers: the ‘Human-like’, the ‘Segregating’, and the ‘Deep’ classifiers. Its effectiveness is tested, using 8 ML algorithms (Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Random Forest, XGBoost, CatBoost, and Artificial Neural Network) to predict the feeling of protection among healthcare workers during the COVID-19 pandemic, based on a global online survey, then validated on two other outputs. Results The results show, for most algorithms, an enhanced detection of data points belonging to intermediate classes (up to 14% absolute increase in accuracy), as well as an overall improvement in the models’ accuracies (up to 5.8% absolute increase). The validation experiments yielded similar results with improved accuracies for most algorithms when compared to the single classifier architecture. Conclusion This novel architecture is proving to be a very promising tool for improving accuracy of the models when classifying patients in intermediate classes, regardless of the algorithm used. Accuracy-improvement for likert-type scale measures offers an opportunity for rapidly identifying “risk-profiles” during emergencies and beyond. This applies equally to patients and healthcare providers, with potential for improving quality of care and strengthening patient-centered healthcare systems that prioritize healthcare providers’ wellbeing.https://doi.org/10.1186/s12859-025-06228-8Artificial intelligenceMachine learningMaternityPublic health |
| spellingShingle | Bassel Hammoud Aline Semaan Lenka Benova Imad H. Elhajj A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health BMC Bioinformatics Artificial intelligence Machine learning Maternity Public health |
| title | A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health |
| title_full | A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health |
| title_fullStr | A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health |
| title_full_unstemmed | A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health |
| title_short | A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health |
| title_sort | novel machine learning architecture to improve classification of intermediate cases in health workflow and case study for public health |
| topic | Artificial intelligence Machine learning Maternity Public health |
| url | https://doi.org/10.1186/s12859-025-06228-8 |
| work_keys_str_mv | AT basselhammoud anovelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT alinesemaan anovelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT lenkabenova anovelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT imadhelhajj anovelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT basselhammoud novelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT alinesemaan novelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT lenkabenova novelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth AT imadhelhajj novelmachinelearningarchitecturetoimproveclassificationofintermediatecasesinhealthworkflowandcasestudyforpublichealth |