A New Evaluation Model for Traumatic Severe Pneumothorax Based on Interpretable Machine Learning
DOI:
https://doi.org/10.15837/ijccc.2025.1.6830Keywords:
Pneumothorax, Interpretable machine learning, XGBoost, Evaluation Model.Abstract
Traumatic pneumothorax is a complex condition that is challenging to diagnose, particularly in hospitals, underdeveloped areas, and during mass casualty events. This study aimed to evaluate the potential of machine learning (ML) for diagnosing and assessing traumatic pneumothorax. We extracted 33 vital signs and blood gas parameters from the MIMIC-IV database, selecting 12 clinically significant features as inputs to four ML algorithms: extreme gradient boosting (XGBoost), artificial neural network (ANN), support vector machine (SVM), and k-nearest neighbors (KNN). Five-fold cross-validation was used to train and test the models, with external validation performed on the EICU database. Model performance was evaluated using AUROC, recall, and accuracy, with SHAP interpretability employed to understand feature importance. In total, 3871 participants from the MIMIC-IV database and 22,022 participants from the EICU database were analyzed. Hemoglobin, Oxygenation Index, and pH were found to be key indicators of severe traumatic pneumothorax. XGBoost exhibited the best performance, achieving an AUROC of 0.979 (95% CI: [0.966, 0.989]) on the MIMIC-IV dataset and 0.806 (95% CI: [0.740, 0.864]) on the EICU dataset. The results suggest that ML, particularly XGBoost, is faster and more convenient than traditional imaging methods, making it well-suited for emergency or mass casualty situations. ML algorithms show promise for initial diagnosis of traumatic pneumothorax, with XGBoost demonstrating strong interpretability and robust external validation.
References
Austin, Peter C., et al. "Missing data in clinical research: a tutorial on multiple imputation." Canadian Journal of Cardiology 37.9 (2021): 1322-1331. https://doi.org/10.1016/j.cjca.2020.11.010
Anderson DE, Kocik VI, Rizzo JA, et al. A Narrative Review of Traumatic Pneumothorax Diagnoses and Management. Med J (Ft Sam Houst Tex). 2023;(Per 23-1/2/3):3-10.
Beckett A, Savage E, Pannell D, Acharya S, Kirkpatrick A, Tien HC. Needle decompression for tension pneumothorax in Tactical Combat Casualty Care: do catheters placed in the midaxillary line kink more often than those in the midclavicular line?. J Trauma. 2011;71(5 Suppl 1):S408- S412. https://doi.org/10.1097/TA.0b013e318232e558
Bharati S, Podder P, Mondal MRH. Hybrid deep learning for detecting lung diseases from X-ray images. Informatics in Medicine Unlocked. 2020;20:100391. https://doi.org/10.1016/j.imu.2020.100391
Chen T, Guestrin C. XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Published online 2016. https://doi.org/10.1145/2939672.2939785
Cover T, Hart P. Nearest neighbor pattern classification. IEEE Transactions on Information Theory. 1967;13(1):21-27. https://doi.org/10.1109/TIT.1967.1053964
Collins GS, de Groot JA, Dutton S, et al. External validation of multivariable prediction models: a systematic review of methodological conduct and reporting. BMC Med Res Methodol. 2014;14:40. https://doi.org/10.1186/1471-2288-14-40
Das D, Ito J, Kadowaki T, Tsuda K. An interpretable machine learning model for diagnosis of Alzheimer's disease. PeerJ. 2019;7:e6543. https://doi.org/10.7717/peerj.6543
Estabrooks A, Jo T, Japkowicz N. A Multiple Resampling Method for Learning from Imbalanced Datasets. Computational Intelligence. 2004;20(1):18-36. https://doi.org/10.1111/j.0824-7935.2004.t01-1-00228.x
Fanton M, Nutting V, Solano F, et al. An interpretable machine learning model for predicting the optimal day of trigger during ovarian stimulation. Fertil Steril. 2022;118(1):101-108. https://doi.org/10.1016/j.fertnstert.2022.04.003
Hoehfeld M, Fahlman SE. Learning with limited numerical precision using the cascade-correlation algorithm. IEEE Transactions on Neural Networks. 1992;3(4):602-611. https://doi.org/10.1109/72.143374
Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intelligent Systems and their Applications. 1998;13(4):18-28. https://doi.org/10.1109/5254.708428
Hofmanninger J, Prayer F, Pan J, Röhrich S, Prosch H, Langs G. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. European Radiology Experimental. 2020;4:50-50. https://doi.org/10.1186/s41747-020-00173-2
[Online] Johnson A, Bulgarelli L, Pollard T, Horng S, Celi LA, Mark R. MIMIC-IV. MIMICIV v2.0. June 12, 2022. Accessed September 21, 2023. Available at: https://physionet.org/ content/mimiciv/2.0/.
Jakobsen JC, Gluud C, Wetterslev J, et al. When and how should multiple imputation be used for handling missing data in randomised clinical trials - a practical guide with flowcharts. BMC Med Res Methodol. 2017;17:162. https://doi.org/10.1186/s12874-017-0442-1
Jakhar K, Kaur A, Gupta M. Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax. arXiv.org. Ithaca: Cornell University Library; 2021.
Kapoor D, Xu C. Spinal Cord Injury AIS Predictions Using Machine Learning. eNeuro. 2023;10(1):ENEURO.0149-22.2022. Published 2023 Jan 4. https://doi.org/10.1523/ENEURO.0149-22.2022
Khairuddin MZF, Lu Hui P, Hasikin K, et al. Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance. Int J Environ Res Public Health. 2022;19(21):13962. Published 2022 Oct 27. https://doi.org/10.3390/ijerph192113962
Kitamura G, Deible C. Retraining an open-source pneumothorax detecting machine learning algorithm for improved performance to medical images. Clin Imaging. 2020;61:15-19. https://doi.org/10.1016/j.clinimag.2020.01.008
Kuo, W., et al. "Artificial Intelligence in Lung Disease Detection: A Review." Journal of Thoracic Imaging 35.3 (2020): 147-156.
Levine DJ, Sako EY, Peters J. Fishman's Pulmonary Diseases and Disorders. 4th ed. McGraw- Hill; 2008. ISBN 978-0-07-145739-2. Page 1519.
Light RW. Pleural Diseases. 5th ed. Lippincott Williams & Wilkins; 2007. ISBN 978-0-7817-6957- 0. Page 306.
Lundberg SM, Lee SI. A Unified Approach to Interpreting Model Predictions. In: Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds. Advances in Neural Information Processing Systems. 2017;30.
Lundberg SM, Erion GG, Lee SI. Consistent Individualized Feature Attribution for Tree Ensembles. ArXiv. 2018; abs/1802.03888.
Lee CC, Lin CS, Tsai CS, et al. A deep learning-based system capable of detecting pneumothorax via electrocardiogram. Eur J Trauma Emerg Surg. 2022;48:3317-3326. https://doi.org/10.1007/s00068-022-01904-3
MacDuff A, Arnold A, Harvey J, et al. (BTS Pleural Disease Guideline Group). Management of spontaneous pneumothorax: British Thoracic Society Pleural Disease Guideline 2010. Thorax. 2010;65(8 Suppl 2):ii18-ii31. https://doi.org/10.1136/thx.2010.136986
Nelson D, Porta C, Satterly S, et al. Physiology and cardiovascular effect of severe tension pneumothorax in a porcine model. J Surg Res. 2013;184(1):450-457. https://doi.org/10.1016/j.jss.2013.05.057
Nielsen MB, Cantisani V, Sidhu PS, et al. The Use of Handheld Ultrasound Devices - An EFSUMB Position Paper [published correction appears in Ultraschall Med. 2019 Feb;40(1):e1]. Ultraschall Med. 2019;40(1):30-39. https://doi.org/10.1055/a-0881-5251
Olthof AW, Shouche P, Fennema EM, et al. Machine learning based natural language processing of radiology reports in orthopaedic trauma. Comput Methods Programs Biomed. 2021;208:106304. https://doi.org/10.1016/j.cmpb.2021.106304
[Online] Pollard T. eICU. eICU Collaborative Research Database. Accessed September 21, 2023. Available at: https://eICU-crd.mit.edu/.
Park S, Lee SM, Kim N, et al. Application of deep learning-based computer-aided detection system: detecting pneumothorax on chest radiograph after biopsy. Eur Radiol. 2019;29(10):5341- 5348. https://doi.org/10.1007/s00330-019-06130-x
Rajpurkar, P., et al. "CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning." arXiv preprint arXiv:1711.05225 (2017).
Rubin, J., et al. "Classifying Pneumothorax in Chest X-Rays Using Convolutional Neural Networks." Journal of Digital Imaging 31 (2018): 379-384.
Saiphoklang N, Kanitsap A. Prevalence, clinical manifestations and mortality rate in patients with spontaneous pneumothorax in Thammasat University Hospital. J Med Assoc Thai. 2013;96(10):1290-1297.
Santos K, Dias JP, Amado C. A literature review of machine learning algorithms for crash injury severity prediction. J Safety Res. 2022;80:254-269. https://doi.org/10.1016/j.jsr.2021.12.007
Sanada S, Doi K, MacMahon H. Image feature analysis and computer-aided diagnosis in digital radiography: Automated detection of pneumothorax in chest images. Med Phys. 1992;19:1153- 1160. https://doi.org/10.1118/1.596790
Sobhi JM, Joly O, Kallmes D, et al. Interpretable Machine Learning Modeling for Ischemic Stroke Outcome Prediction. Front Neurol. 2022;13:884693. https://doi.org/10.3389/fneur.2022.884693
Thabtah F, Hammoud S, Kamalov F, Gonsalves A. Data imbalance in classification: Experimental evaluation. Information Sciences. 2020;513:429-441. https://doi.org/10.1016/j.ins.2019.11.004
Tian Y, Wang J, Yang W, Wang J, Qian D. Deep multi-instance transfer learning for pneumothorax classification in chest X-ray images. Med Phys. 2022;49:231-243. https://doi.org/10.1002/mp.15328
Vallmuur K. Machine learning approaches to analysing textual injury surveillance data: a systematic review. Accid Anal Prev. 2015;79:41-49. https://doi.org/10.1016/j.aap.2015.03.018
Wang Y, Sun L, Jin Q. Enhanced Diagnosis of Pneumothorax with an Improved Real-Time Augmentation for Imbalanced Chest X-rays Data Based on DCNN. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2021;18:951-962. https://doi.org/10.1109/TCBB.2019.2911947
Wang S, Tu J, Chen W. Development and Validation of a Prediction Pneumothorax Model in CT-Guided Transthoracic Needle Biopsy for Solitary Pulmonary Nodule. Biomed Res Int. 2019;2019:7857310. https://doi.org/10.1155/2019/7857310
Ye G, Balasubramanian V, Li JK, Kaya M. Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients. IEEE J Transl Eng Health Med. 2022;10:4901008. Published 2022 Jun 2. https://doi.org/10.1109/JTEHM.2022.3179874
Yang S, Lou L, Wang W, et al. Pneumothorax prediction using a foraging and hunting based ant colony optimizer assisted support vector machine. Comput Biol Med. 2023;161:106948. https://doi.org/10.1016/j.compbiomed.2023.106948
Zhao Y, Wang X, Wang Y, Zhu Z. Logistic regression analysis and a risk prediction model of pneumothorax after CT-guided needle biopsy. J Thorac Dis. 2017;9(11):4750-4757. https://doi.org/10.21037/jtd.2017.09.47
Additional Files
Published
Issue
Section
License
Copyright (c) 2024 Jing Li, Yinzhen Lv, Jiayi Weng, Wei Chen, He Huang, Yuzhuo Zhao
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
ONLINE OPEN ACCES: Acces to full text of each article and each issue are allowed for free in respect of Attribution-NonCommercial 4.0 International (CC BY-NC 4.0.
You are free to:
-Share: copy and redistribute the material in any medium or format;
-Adapt: remix, transform, and build upon the material.
The licensor cannot revoke these freedoms as long as you follow the license terms.
DISCLAIMER: The author(s) of each article appearing in International Journal of Computers Communications & Control is/are solely responsible for the content thereof; the publication of an article shall not constitute or be deemed to constitute any representation by the Editors or Agora University Press that the data presented therein are original, correct or sufficient to support the conclusions reached or that the experiment design or methodology is adequate.
