Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction
Post-operative kyphosis represents a significant complication following pediatric spinal corrective surgery, necessitating sophisticated prediction methods to identify high-risk patients. This study developed and evaluated machine learning models for kyphosis prediction using a dataset of 81 pediatr...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2025-06-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | https://jurnal.iaii.or.id/index.php/RESTI/article/view/6606 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849744471897407488 |
|---|---|
| author | Raja Ayu Mahessya Dian Eka Putra Rostam Ahmad Efendi Rayendra Rozi Meri Riyan Ikhbal Salam Dedi Mardianto Ikhsan Ismael Arif Rizki Marsa |
| author_facet | Raja Ayu Mahessya Dian Eka Putra Rostam Ahmad Efendi Rayendra Rozi Meri Riyan Ikhbal Salam Dedi Mardianto Ikhsan Ismael Arif Rizki Marsa |
| author_sort | Raja Ayu Mahessya |
| collection | DOAJ |
| description | Post-operative kyphosis represents a significant complication following pediatric spinal corrective surgery, necessitating sophisticated prediction methods to identify high-risk patients. This study developed and evaluated machine learning models for kyphosis prediction using a dataset of 81 pediatric patients by comparing the logistic regression and decision tree approaches. Despite achieving a higher overall accuracy (82%), the logistic regression model failed to identify any kyphosis cases, rendering it clinically ineffective. Conversely, the decision tree model demonstrated superior clinical utility by successfully identifying 33% of kyphosis cases while maintaining 71% accuracy. Feature importance analysis established starting vertebral position as the dominant predictor (importance=0.554), followed by patient age (0.416), with vertebrae count contributing minimally (0.030). The decision tree identified critical thresholds for risk stratification: operations beginning at or above T8-T9, particularly in children aged 5-9 years, carried a substantially elevated kyphosis risk. Our methodological approach emphasizes sensitivity over conventional accuracy metrics, recognizing that missing high-risk patients have greater clinical consequences than unnecessary monitoring. This study demonstrates the capacity of decision tree models to extract clinically meaningful patterns from small, imbalanced surgical datasets that elude conventional statistical approaches. |
| format | Article |
| id | doaj-art-7f09a5ae96d74fb3923e9de7fd85454a |
| institution | DOAJ |
| issn | 2580-0760 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj-art-7f09a5ae96d74fb3923e9de7fd85454a2025-08-20T03:15:47ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-06-019360160810.29207/resti.v9i3.66066606Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis PredictionRaja Ayu Mahessya0Dian Eka Putra1Rostam Ahmad Efendi2Rayendra3Rozi Meri4Riyan Ikhbal Salam5Dedi Mardianto6Ikhsan7Ismael8Arif Rizki Marsa9Universitas Putra Indonesia ‘YPTK’ PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPoliteknik Negeri PadangPost-operative kyphosis represents a significant complication following pediatric spinal corrective surgery, necessitating sophisticated prediction methods to identify high-risk patients. This study developed and evaluated machine learning models for kyphosis prediction using a dataset of 81 pediatric patients by comparing the logistic regression and decision tree approaches. Despite achieving a higher overall accuracy (82%), the logistic regression model failed to identify any kyphosis cases, rendering it clinically ineffective. Conversely, the decision tree model demonstrated superior clinical utility by successfully identifying 33% of kyphosis cases while maintaining 71% accuracy. Feature importance analysis established starting vertebral position as the dominant predictor (importance=0.554), followed by patient age (0.416), with vertebrae count contributing minimally (0.030). The decision tree identified critical thresholds for risk stratification: operations beginning at or above T8-T9, particularly in children aged 5-9 years, carried a substantially elevated kyphosis risk. Our methodological approach emphasizes sensitivity over conventional accuracy metrics, recognizing that missing high-risk patients have greater clinical consequences than unnecessary monitoring. This study demonstrates the capacity of decision tree models to extract clinically meaningful patterns from small, imbalanced surgical datasets that elude conventional statistical approaches.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6606pediatric spinal surgerypost-operative kyphosismachine learningdecision treesimbalanced classification |
| spellingShingle | Raja Ayu Mahessya Dian Eka Putra Rostam Ahmad Efendi Rayendra Rozi Meri Riyan Ikhbal Salam Dedi Mardianto Ikhsan Ismael Arif Rizki Marsa Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) pediatric spinal surgery post-operative kyphosis machine learning decision trees imbalanced classification |
| title | Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction |
| title_full | Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction |
| title_fullStr | Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction |
| title_full_unstemmed | Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction |
| title_short | Optimizing Sensitivity in Machine Learning Models for Pediatric Post-operative Kyphosis Prediction |
| title_sort | optimizing sensitivity in machine learning models for pediatric post operative kyphosis prediction |
| topic | pediatric spinal surgery post-operative kyphosis machine learning decision trees imbalanced classification |
| url | https://jurnal.iaii.or.id/index.php/RESTI/article/view/6606 |
| work_keys_str_mv | AT rajaayumahessya optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT dianekaputra optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT rostamahmadefendi optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT rayendra optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT rozimeri optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT riyanikhbalsalam optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT dedimardianto optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT ikhsan optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT ismael optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction AT arifrizkimarsa optimizingsensitivityinmachinelearningmodelsforpediatricpostoperativekyphosisprediction |