Ahmet Fatih Deveci
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ahmet Fatih Deveci has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Izzet Turkalp Akbasli
Department of Pediatric Intensive Care Medicine, Department of Pediatrics, Faculty of Medicine, Hacettepe University
3 shared publications - Muhsin Zahid Ugur
Department of Health Information Systems, University of Health Sciences, Istanbul, Turkey
3 shared publications - Oguzhan Serin
Division of Pediatric Emergency Medicine, Department of Pediatrics, Faculty of Medicine, Hacettepe University, Ankara, Türkiye
3 shared publications - Sena Bocutcu Cetin
Department of Pediatrics, Hacettepe University Medical School, Gevher Nesibe Avenue, Altindag, Ankara, 06230, Turkey, 90 3051350
3 shared publications - Yasemin Ozsurekci
Department of Pediatric Infectious Diseases, Hacettepe University, Ankara, Turkey
3 shared publications - Busra Koseoglu
Department of Pediatrics, Hacettepe University Medical School
2 shared publications
Latest Publications
- Open Access
- 4 March 2025
- Published by JMIR Publications Inc. in JMIRx Med
- Vol. 6 (1) , e71098
Authors’ Response to Peer Reviews of “Predicting Escalation of Care for Childhood Pneumonia Using Machine Learning: Retrospective Analysis and Model Development”
This is the author(s)’ responses to peer review reports related to MS ID 57719
- 4 March 2025
- Published by JMIR Publications Inc. in JMIRx Med
- Vol. 6 (1) , e71098
Open AccessAuthors’ Response to Peer Reviews of “Predicting Escalation of Care for Childhood Pneumonia Using Machine Learning: Retrospective Analysis and Model Development”
This is the author(s)’ responses to peer review reports related to MS ID 57719
- Open Access
- 4 March 2025
- Published by JMIR Publications Inc. in JMIRx Med
- Vol. 6 (1) , e57719
Predicting Escalation of Care for Childhood Pneumonia Using Machine Learning: Retrospective Analysis and Model Development
Background: Pneumonia is a leading cause of mortality in children aged z score, and complaint duration as the most important clinical predictors independent of laboratory diagnostics. Conclusions: This study demonstrates the feasibility of applying ML techniques to create a prognostic care decision tool for childhood pneumonia. It provides early identification of cases requiring escalation of care by combining foundational clinical skills with data science methods.
- 4 March 2025
- Published by JMIR Publications Inc. in JMIRx Med
- Vol. 6 (1) , e57719
Open AccessPredicting Escalation of Care for Childhood Pneumonia Using Machine Learning: Retrospective Analysis and Model Development
Background: Pneumonia is a leading cause of mortality in children aged z score, and complaint duration as the most important clinical predictors independent of laboratory diagnostics. Conclusions: This study demonstrates the feasibility of applying ML techniques to create a prognostic care decision tool for childhood pneumonia. It provides early identification of cases requiring escalation of care by combining foundational clinical skills with data science methods.
- Open Access
Advancing primary care for childhood pneumonia: a machine learning-based approach to prognosis and case management
Background Pneumonia is the leading cause of preventable mortality under five years of age. Appropriate case management is as essential as disease prevention interventions, especially in primary care settings. Computer science has been used accurately and widely for pneumonia diagnosis; however, prognosis studies are relatively low. Herein, we developed a machine learning-based clinical decision support system tool for childhood pneumonia to provide prognostic support for case management. Methods We analyzed data from 437 children admitted to our clinic with a pneumonia diagnosis between 2014 and 2020. Pediatricians encoded the raw dataset according to candidate features. Before the experimental study of the machine learning algorithms of Pycaret, SMOTE-Tomek was utilized for managing imbalanced datasets. The feature selection was made by examining the SHAP values of the algorithm with the highest performance and re-modeled with the most important clinical features. We optimized hyperparameters and employed ensemble methods to develop a robust predictive model. Results Optimized models predicted pneumonia prognosis with %77-88 accuracy. It was shown that severity could be determined over %84 by five clinical features: hypoxia, respiratory distress, age, Z score of weight for age, and antibiotic usage before admission. Conclusions In this experimental study, we demonstrated that contemporary data science methods, such as oversampling, feature selection, and machine learning tools, are promising in predicting the critical care need of patients. Even in small-size samples like our study, ML methods can reach current wisdom. Highlights Pneumonia accounts for 14% of mortality in children under 5, with over 740,000 deaths in 2019 alone. WHO and UNICEF’s GAPPD aims to cut mortality rates by focusing on vaccinations, sanitation, breastfeeding, and addressing pediatric HIV. Accurate diagnosis and timely treatment can reduce pneumonia mortality by up to 28%, yet diagnosing can be challenging. Many in underdeveloped regions lack access to essential equipment and trained staff, exacerbating mortality rates. Data science and machine learning offer promising solutions for pneumonia management, especially in LMICs, with a focus on prognostic support.
Open AccessAdvancing primary care for childhood pneumonia: a machine learning-based approach to prognosis and case management
Background Pneumonia is the leading cause of preventable mortality under five years of age. Appropriate case management is as essential as disease prevention interventions, especially in primary care settings. Computer science has been used accurately and widely for pneumonia diagnosis; however, prognosis studies are relatively low. Herein, we developed a machine learning-based clinical decision support system tool for childhood pneumonia to provide prognostic support for case management. Methods We analyzed data from 437 children admitted to our clinic with a pneumonia diagnosis between 2014 and 2020. Pediatricians encoded the raw dataset according to candidate features. Before the experimental study of the machine learning algorithms of Pycaret, SMOTE-Tomek was utilized for managing imbalanced datasets. The feature selection was made by examining the SHAP values of the algorithm with the highest performance and re-modeled with the most important clinical features. We optimized hyperparameters and employed ensemble methods to develop a robust predictive model. Results Optimized models predicted pneumonia prognosis with %77-88 accuracy. It was shown that severity could be determined over %84 by five clinical features: hypoxia, respiratory distress, age, Z score of weight for age, and antibiotic usage before admission. Conclusions In this experimental study, we demonstrated that contemporary data science methods, such as oversampling, feature selection, and machine learning tools, are promising in predicting the critical care need of patients. Even in small-size samples like our study, ML methods can reach current wisdom. Highlights Pneumonia accounts for 14% of mortality in children under 5, with over 740,000 deaths in 2019 alone. WHO and UNICEF’s GAPPD aims to cut mortality rates by focusing on vaccinations, sanitation, breastfeeding, and addressing pediatric HIV. Accurate diagnosis and timely treatment can reduce pneumonia mortality by up to 28%, yet diagnosing can be challenging. Many in underdeveloped regions lack access to essential equipment and trained staff, exacerbating mortality rates. Data science and machine learning offer promising solutions for pneumonia management, especially in LMICs, with a focus on prognostic support.
- 30 June 2022
- Published by Journal of Statistics and Applied Sciences in İstatistik ve Uygulamalı Bilimler Dergisi
- No. 5,p. 17-27
Medikal Sentetik Veri Üretimiyle Veri Dengelemesi
Sağlık hizmetleri planlaması, klinik deneyler ve araştırma geliştirme çalışmaları gibi sağlık verisi kullanımını gerektiren alanlarda, kişisel sağlık verisinin elde edilmesi ve kullanımında etik, bürokratik ve operasyonel zorluklar yaşanmaktadır. Elektronik kişisel sağlık kayıtlarının güvenliği ve kişisel veri mahremiyeti konularındaki kısıtlamalar başta olmak üzere, klinik ve saha çalışmalarından veri elde edilmesinin maliyetli ve zaman alıcı olması, gerçek veriye en yakın şekilde yapay veri üretilmesini gerekli kılmaktadır. Bu çalışmada, son dönemde sağlık alanında artan veri kullanımı ihtiyacı doğrultusunda, sentetik veri kullanımının önemi ele alınarak, sentetik veri üretiminde kullanılan SMOTE, SMOTEENN, BorderlineSMOTE, SMOTETomek ve ADASYN yöntemlerinin performanslarının karşılaştırılması amaçlanmıştır. Çalışmada, gözlem ve sınıf sayısı birbirinden farklı ve ikisi de kamuya açık, 390 hastaya ait 15 değişkenden oluşan veri seti ile 19.212 COVID-19 hastasına ilişkin 16 değişkenden oluşan veri seti kullanılmıştır. Çalışma sonucunda SMOTE tekniğinin gözlem ve sınıf sayısının fazla olduğu veri setini dengelemede daha başarılı olduğu ve sentetik veri üretiminde hibrit tekniklere göre etkin olarak kullanılabileceği sonucuna ulaşılmıştır.
- 30 June 2022
- Published by Journal of Statistics and Applied Sciences in İstatistik ve Uygulamalı Bilimler Dergisi
- No. 5,p. 17-27
Medikal Sentetik Veri Üretimiyle Veri Dengelemesi
Sağlık hizmetleri planlaması, klinik deneyler ve araştırma geliştirme çalışmaları gibi sağlık verisi kullanımını gerektiren alanlarda, kişisel sağlık verisinin elde edilmesi ve kullanımında etik, bürokratik ve operasyonel zorluklar yaşanmaktadır. Elektronik kişisel sağlık kayıtlarının güvenliği ve kişisel veri mahremiyeti konularındaki kısıtlamalar başta olmak üzere, klinik ve saha çalışmalarından veri elde edilmesinin maliyetli ve zaman alıcı olması, gerçek veriye en yakın şekilde yapay veri üretilmesini gerekli kılmaktadır. Bu çalışmada, son dönemde sağlık alanında artan veri kullanımı ihtiyacı doğrultusunda, sentetik veri kullanımının önemi ele alınarak, sentetik veri üretiminde kullanılan SMOTE, SMOTEENN, BorderlineSMOTE, SMOTETomek ve ADASYN yöntemlerinin performanslarının karşılaştırılması amaçlanmıştır. Çalışmada, gözlem ve sınıf sayısı birbirinden farklı ve ikisi de kamuya açık, 390 hastaya ait 15 değişkenden oluşan veri seti ile 19.212 COVID-19 hastasına ilişkin 16 değişkenden oluşan veri seti kullanılmıştır. Çalışma sonucunda SMOTE tekniğinin gözlem ve sınıf sayısının fazla olduğu veri setini dengelemede daha başarılı olduğu ve sentetik veri üretiminde hibrit tekniklere göre etkin olarak kullanılabileceği sonucuna ulaşılmıştır.