An Analytical Framework for Screening Cardiogenic Brain Abscess in Patients with Tetralogy of Fallot
An Analytical Framework for Screening Cardiogenic Brain Abscess in Patients with Tetralogy of Fallot |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-2 |
||
| Year of Publication : 2023 | ||
| Author : Subramaniyan Mani, Sumit Thakar, N. S. Suijth, R. Raghunatha Sarma |
||
| DOI : 10.14445/22315381/IJETT-V71I2P210 | ||
How to Cite?
Subramaniyan Mani, Sumit Thakar, N. S. Suijth, R. Raghunatha Sarma, "An Analytical Framework for Screening Cardiogenic Brain Abscess in Patients with Tetralogy of Fallot," International Journal of Engineering Trends and Technology, vol. 71, no. 2, pp. 78-88, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I2P210
Abstract
Patients diagnosed with the congenital heart condition called Tetralogy of Fallot(TOF) are prone to developing
cardiogenic brain abscess(CBA), the diagnosis of which is often delayed in a resource-limited setting. The current study is aimed
to demonstrate the effective application of various Machine Learning(ML) techniques through appropriate data-mining
strategies in the screening process for CBA. The data set for this retrospective study included clinical, echo-cardiographic and
radiological variables pertaining to TOF patients with CBA. The study demonstrates four data mining tasks to highlight the
importance of machine learning techniques for the screening of CBA in TOF patients. Firstly, suitable ML techniques are used
to classify the TOF patients with BA correctly. Conformal prediction is then used to provide levels of reliability for individual
predictions. ‘SHAP’ analysis is done to provide model explainability. Finally, Association Rule Mining(ARM) is utilized to draw
the relationships between the top features and the outcome, thus identifying variables that expressed optimal interestingness in
the study. The evaluation metrics for the ML models were better than those of the LR model, with Random forest(RF) performing
the best (precision: 0.94; recall, accuracy, F-score and Area under the curve: 0.93). Conformal prediction analysis revealed an
accuracy of 0.95. Association rule mining identified a combination of ‘Neutrophil/Lymphocyte ratio’, absence of ‘branch
confluence’ and the ‘presence of cyanosis’ to have a significant ‘Irule’ value (1.03). Machine learning outperforms the ‘BATOF score’, a logistic regression-based score in identifying biomarkers for TOF patients. The RF algorithm demonstrated the
best evaluation metrics of the various models tested. A combination of three variables can accurately and reliably aid the
clinician in suspecting a CBA in male TOF patients. An ML framework designed with careful analysis to provide definitive and
largely interpretable results with high confidence is proven to be an able tool in clinical decision-making.
Keywords
Association rule mining, Cardiogenic brain abscess, Logistic regression, Machine learning, Random forest.
References
[1] Vidyasagar Kanneganti et al., “Clinical and Laboratory Markers of Brain Abscess in Tetralogy of Fallot ('BA-TOF' Score): Results of a
Case-Control Study and Implications for Community Surveillance,” Journal of Neurosciences in Rural Practice, vol. 12, no. 2, pp.
m302-307, 2021. Crossref, https://doi.org/10.1055/s-0041-1722819
[2] Tim Smolea et al., “A Machine Learning-based Risk Stratification Model for Ventricular Tachycardia and Heart Failure in Hypertrophic
Cardiomyopathy,” Computers in Biology and Medicine, vol. 135, p. 104648, 2021. Crossref,
https://doi.org/10.1016/j.compbiomed.2021.104648
[3] Dan Li et al., “Machine Learning-aided Risk Stratification System for the Prediction of Coronary Artery Disease,” International Journal
of Cardiology, vol. 326, pp. 30-34, 2021. Crossref, https://doi.org/10.1016/j.ijcard.2020.09.070
[4] Damien K. Ming et al., “Applied Machine Learning for the Risk-stratification and Clinical Decision Support of Hospitalised Patients
with Dengue in Vietnam,” PLOS Digit Health, vol. 1, no. 1, 2022. Crossref, https://doi.org/10.1371/journal.pdig.0000005
[5] Justin J Boutilier et al., “Risk Stratification for Early Detection of Diabetes and Hypertension in Resource-Limited Settings: Machine
Learning Analysis,” Journal of Medical Internet Research, vol. 23, no. 1, 2021. Crossref, https://doi.org/10.2196/20123
[6] Brett K. Beaulieu-Jones et al., “Machine Learning for Patient Risk Stratification: Standing on, or Looking over, The Shoulders of
Clinicians?,” Digital Medicine, vol. 4, no. 62, 2021. Crossref, https://doi.org/10.1038/s41746-021-00426-3
[7] Ziad Obermeyer, and Ezekiel J. Emanuel, “Predicting the Future - Big Data, Machine Learning, and Clinical Medicine,” The New
England Journal of Medicine, vol. 375, no. 13, pp. 1216–1219, 2016. Crossref, https://doi.org/10.1056%2FNEJMp1606181
[8] Joeky T. Senders et al., “Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review,” World Neurosurgery, vol.
109, pp. 476–486, 2018. Crossref, https://doi.org/10.1016/j.wneu.2017.09.149
[9] Victor E. Staartjes et al., “Deep Learning-based Preoperative Predictive Analytics for Patient-reported Outcomes following Lumbar
Discectomy: Feasibility of Center-specific Modeling,” The Spine Journal, vol. 19, no. 5, pp. 853–861, 2019. Crossref,
https://doi.org/10.1016/j.spinee.2018.11.009
[10] Victor E. Staartjes et al., “Neural Network-based Identification of Patients at High Risk for Intraoperative Cerebrospinal Fluid Leaks in
Endoscopic Pituitary Surgery,” Journal of Neurosurgery, pp. 1–7, 2019. Crossref, https://doi.org/10.3171/2019.4.jns19477
[11] Christiaan H.B. Van Niftrik et al., “Machine Learning Algorithm Identifies Patients at High Risk for Early Complications after
Intracranial Tumor Surgery: Registry-Based Cohort Study,” Neurosurgery, vol. 85, no. 4, pp. E756-E764, 2019. Crossref,
https://doi.org/10.1093/neuros/nyz145
[12] Yohannes Kassahun et al., “Automatic Classification of Epilepsy Types Using Ontology-based and Genetics-based Machine Learning,”
Artificial Intelligence in Medicine, vol. 61, no. 2, pp. 79–88, 2014. Crossref, https://doi.org/10.1016/j.artmed.2014.03.001
[13] Adam P. Marcus et al., “Improved Prediction of Surgical Resectability in Patients with Glioblastoma using an Artificial Neural Network,”
Scientific Reports, vol. 10, no. 5143, 2020. Crossref, https://doi.org/10.1038/s41598-020-62160-2
[14] Travis M. Dumont, Anand I. Rughani, and Bruce I. Tranmer, “Prediction of Symptomatic Cerebral Vasospasm after Aneurysmal
Subarachnoid Hemorrhage with an Artificial Neural Network: Feasibility and Comparison with Logistic Regression Models,” World
Neurosurgery, vol. 75, no. 1, pp. 57–63, 2011. Crossref, https://doi.org/10.1016/j.wneu.2010.07.007
[15] C.W. Pfirrmann et al., “Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration,” Spine, vol. 26, no. 17, pp.
1873–1878, 2001. Crossref, https://doi.org/10.1097/00007632-200109010-00011
[16] K. Yamashita et al., “Performance Evaluation of Radiologists with Artificial Neural Network for Differential Diagnosis of Intra-axial
Cerebral Tumors on MR Images,” AJNR American Journal of Neuroradiology, vol. 29, no. 6, pp. 1153–1158, 2008. Crossref,
https://doi.org/10.3174/ajnr.a1037
[17] Parisa Azimi et al., “Use of Artificial Neural Networks to Predict Surgical Satisfaction in Patients with Lumbar Spinal Canal Stenosis:
Clinical Article,” Journal of Neurosurgery, Spine, vol. 20, no. 3, pp. 300–305, 2014. Crossref,
https://doi.org/10.3171/2013.12.spine13674
[18] Loftus CM, Osenbach RK, and Biller J, Diagnosis and Management of Brain Abscess. In: Wilkins RH, Rengachary SS, eds.
Neurosurgery. New York: McGraw-Hill; 1996:3285–3298
[19] M. N. Rajesh, B. S. Chandrasekar, and S. Shivakumar Swamy, “Prostate Cancer Detection using Radiomics-based Feature Analysis with
ML Algorithms and MR Images,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 42-58, 2022.
Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P206
[20] S. Sivasubramaniam, and S. P. Balamurugan, “Nature Inspired Optimization with Hybrid Machine Learning Model for Cardiovascular
Disease Detection and Classification,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 127-137, 2022.
Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P214
[21] Abdullah M. Baqasah, “A Survey of Machine Learning Methods to Detect COVID-19 Severity, Mortality, and Vaccines Efficacy,”
International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 28-46, 2022. Crossref,
https://doi.org/10.14445/22315381/IJETT-V70I11P204
[22] Nandakumar Pandiyan, and Subhashini Narayan, “Prediction of Cardiac Disease using Kernel Extreme Learning Machine Model,”
International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 364-377, 2022. Crossref,
https://doi.org/10.14445/22315381/IJETT-V70I11P238
[23] Sudha Prathyusha Jakkaladiki, and Filip maly, “Potential Role of Artificial Intelligence in Breast Cancer Detection - A Review,”
International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 130-139, 2022. Crossref,
https://doi.org/10.14445/22315381/IJETT-V70I7P214
[24] Atul Kumar Ramotra, and Vibhakar Mansotra, “Feature Raking and Stacked Sparse Autoencoder based Framework for the Prediction
of Breast Cancer,” International Journal of Engineering Trends and Technology, vol. 70, no. 5, pp. 103-110, 2022. Crossref,
https://doi.org/10.14445/22315381/IJETT-V70I5P213
[25] Xuan Songa et al., “Comparison of Machine Learning and Logistic Regression Models in Predicting Acute Kidney Injury: A Systematic
Review and Meta-analysis,” International Journal of Medical Informatics, vol. 151, p. 104484, 2021. Crossref,
https://doi.org/10.1016/j.ijmedinf.2021.104484
[26] Nitesh V. Chawla et al., “SMOTE : Synthetic Minority Oversampling Technique,” Journal of Artificial intelligence research, vol. 16,
2002. Crossref, https://doi.org/10.1613/jair.953
[27] Koichi Fujiwara et al., “Over- and Under-sampling Approach for Extremely Imbalanced and Small Minority Data Problem in Health
Record Analysis,” Frontiers Public Health, vol. 8, 2020. Crossref, https://doi.org/10.3389/fpubh.2020.00178
[28] Mikel Galar et al., “A Review on Ensembles for the Class Imbalance Problem: Bagging, Boosting-, and Hybrid-based Approaches,”
IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Review), vol. 42, no. 4, pp. 463–484, 2012. Crossref,
https://doi.org/10.1109/TSMCC.2011.2161285
[29] VN Balasubramanian et al., “Support Vector Machine Based Conformal Predictors for Risk of Complications following a Coronary Drug
Eluting Stent Procedure,” 36th Annual Computers in Cardiology, pp. 5−8, 2009.
[30] Anastasios N. Angelopoulos, and Stephen Bates, “A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty
Quantification,” Machine Learning, 2022. Crossref, https://doi.org/10.48550/arXiv.2107.07511
[31] Glenn Shafer, and Vladimir Vovk, “A Tutorial on Conformal Prediction,” Journal of Machine Learning Research, vol. 9, pp. 371-421,
2008.
[32] Scott M. Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” 31st Conference on Neural Information
Processing Systems, pp. 4768-4777, 2017.
[33] AnkitChoudhary, A Unique Method for Machine Learning Interpretability: Game Theory & Shapley Values, Analytics Vidya, 2019.
[Online]. Available: https://www.analyticsvidhya.com/blog/2019/11/shapley-value-machine-learning-interpretability-game-theory/
[34] Yanchang Zhao et al., “Combined Pattern Mining: From Learned Rules to Actionable Knowledge,” AI 2008: Adavances in Artificial
Intelligence, pp. 393-403, 2008. Crossref, https://doi.org/10.1007/978-3-540-89378-3_40
[35] Shahadat Uddin et al., “Comparing Different Supervised Machine Learning Algorithms for Disease Prediction,” BMC Medical
Informatics and Decision Making, vol. 19, 2019. Crossref, https://doi.org/10.1186/s12911-019-1004-8
[36] Minseok Song et al., “Diagnostic Classification and Biomarker Identification of Alzheimer’s Disease with Random Forest Algorithm,”
Brain Sciences, vol. 11, no. 4, p. 453, 2021. Crossref, https://doi.org/10.3390/brainsci11040453
[37] Janette Vazquez, and Julio C. Facelli, “Conformal Prediction in Clinical Medical Sciences,” Journal of Healthcare Informatics Research,
vol. 6, pp. 241-252, 2022. Crossref, https://doi.org/10.1007/s41666-021-00113-8
[38] Fauzia Imtiaz et al., “Neutrophil Lymphocyte Ratio as a Measure of Systemic Inflammation in Prevalent Chronic Diseases in Asian
Population,” International Archives of Medicine, vol. 5, no. 1, 2012. Crossref, https://doi.org/10.1186/1755-7682-5-2
[39] Peng ping, and Qiang, “Discretion Conserving Mining of Association Rules,” SSRG International Journal of Mobile Computing and
Application, vol. 4, no. 3, pp. 1-5, 2017. Crossref, https://doi.org/10.14445/23939141/IJMCA-V4I6P101
[40] Abhinav Shashank, The Importance of Risk Stratification in Population Health Management, Innovaccer Inc., 2017. [Online]. Available:
https://hitconsultant.net/2017/03/13/risk-stratification-population-health-management/
[41] Christo I. Tchervenkov et al., “The Improvement of Care for Paediatric and Congenital Cardiac Disease across the World: A Challenge
for the World Society for Pediatric and Congenital Heart Surgery,” Cardiology in the Young, vol. 18, no. 2, pp. 63–69, 2008. Crossref,
https://doi.org/10.1017/s1047951108002801
[42] Kareem Mohamed, and Ümmü Altan Bayraktar, “Artificial Intelligence in Public Relations and Association Rule Mining as a Decision
Support Tool,” SSRG International Journal of Humanities and Social Science, vol. 9, no. 3, pp. 23-32, 2022. Crossref,
https://doi.org/10.14445/23942703/IJHSS-V9I3P105
[43] Suhas Udayakumaran, Chiazor U. Onyia, and R. Krishna Kumar, “Forgotten? Not yet. Cardiogenic Brain Abscess in Children: A Case
Series-Based Review,” World Neurosurgery, vol. 107, pp. 124–129, 2017. Crossref, https://doi.org/10.1016/j.wneu.2017.07.144