Early Diagnosis of Carotid Stenosis by Ultrasound Doppler Investigations: A Classification Method for the Hemodynamic Parameter
Abstract
:1. Introduction
2. Algorithm Description
2.1. Neighborhood Components Analysis (NCA) for Dimension Reduction
2.2. RUSBoost with Empirical Weights
2.2.1. Empirical Weight
2.2.2. RUS
2.2.3. Boosted Tree
2.3. Positive Sample Analysis
3. Experiments and Results
3.1. Data Acquisition and Processing
3.2. Training Process
3.3. Comparison of Methods
3.4. Positive Sample Analysis
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Appendix A
Algorithm A1. Training procedure of the proposed approach |
Input: Set of examples ,…,. Number of iterations T |
Output: The final hypothesis . |
1: Initialize for sample . |
2: Do for . |
a. Create temporary training dataset with distribution using random undersampling. b. Calculate weak learner based on examples and their weights . c. Calculate the classification error rate for : e. Update the weight of samples: |
3: Return . |
References
- Olin, J.W.; Piedmonte, M.R.; Young, J.R.; DeAnna, S.; Grubb, M.; Childs, M.B. The Utility of Duplex Ultrasound Scanning of the Renal Arteries for Diagnosing Significant Renal Artery Stenosis. Ann. Intern. Med. 1995, 122, 833–838. [Google Scholar] [CrossRef]
- Hirsch, A.T.; Haskal, Z.J.; Hertzer, N.R.; Bakal, C.W.; Creager, M.A.; Halperin, J.L.; Rosenfield, K.A. ACC/AHA 2005 Practice Guidelines for the Management of Patients with Peripheral Arterial Disease (Lower Extremity, Renal, Mesenteric, and Abdominal Aortic). Circulation 2006, 113. [Google Scholar] [CrossRef] [Green Version]
- Morin, L.; Den Hof Van, M.C. SOGC clinical practice guidelines. Ultrasound evaluation of first trimester pregnancy complications. Int. J. Gynecol. Obstet. 2006, 93, 77–81. [Google Scholar]
- Reneman, R.S.; Meinders, J.M.; Hoeks, A.P. Non-invasive ultrasound in arterial wall dynamics in humans: What have we learned and what remains to be solved. Eur. Heart J. 2005, 26, 960–966. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Grant, E.G.; Benson, C.B.; Moneta, G.L.; Alexandrov, A.V.; Baker, J.D.; Bluth, E.I.; Katanick, S. Carotid Artery Stenosis: Gray-Scale and Doppler US Diagnosis—Society of Radiologists in Ultrasound Consensus Conference. Radiology 2003, 229, 340–346. [Google Scholar] [CrossRef] [PubMed]
- Carpenter, J.P.; Lexa, F.J.; Davis, J.T. Determination of sixty percent or greater carotid artery stenosis by duplex Doppler ultrasonography. J. Vasc. Surg. 1995, 22, 697–705. [Google Scholar] [CrossRef] [Green Version]
- Moneta, G.L.; Edwards, J.M.; Chitwood, R.W.; Taylor, L.M., Jr.; Lee, R.W.; Cummings, C.A.; Porter, J.M. Correlation of North American Symptomatic Carotid Endarterectomy Trial (NASCET) angiographic definition of 70% to 99% internal carotid artery stenosis with duplex scanning. J. Vasc. Surg. 1993, 17, 152–159. [Google Scholar] [CrossRef] [Green Version]
- Suwanwela, N.; Can, U.; Furie, K.L.; Southern, J.F.; Macdonald, N.R.; Ogilvy, C.S.; Kistler, J.P. Carotid Doppler Ultrasound Criteria for Internal Carotid Artery Stenosis Based on Residual Lumen Diameter Calculated from En Bloc Carotid Endarterectomy Specimens. Stroke 1996, 27, 1965–1969. [Google Scholar] [CrossRef]
- Rochelson, B.; Schulman, H.; Farmakides, G.; Bracero, L.; Ducey, J.; Fleischer, A.; Winter, D. The significance of absent end-diastolic velocity in umbilical artery velocity waveforms. Am. J. Obstet. Gynecol. 1987, 156, 1213–1218. [Google Scholar] [CrossRef]
- Wladimiroff, J.W.; Tonge, H.M.; Stewart, P.A. Doppler ultrasound assessment of cerebral blood flow in the human fetus. Br. J. Obstet. Gynaecol. 1986, 93, 471–475. [Google Scholar] [CrossRef]
- Bitó, T.; Vajda, G.; Hajdu, J.; Pál, A. Cerebral and umbilical arterial blood flow velocity wave-form measurements in growth-retarded fetuses. J. Perinat. Med. 1992, 20, 267. [Google Scholar]
- Gaziano, E.P.; Knox, G.E.; Wager, G.P.; Bendel, R.P.; Olson, J.D. Pulsed Doppler umbilical artery waveforms: Significance of elevated umbilical artery systolic/diastolic ratios in the normally grown fetus. Obstet. Gynecol. 1990, 75, 189–193. [Google Scholar] [PubMed]
- Wladimiroff, J.W.; Degani, S.; Noordam, M.J.; Tonge, H.M. Cerebral and umbilical arterial blood flow velocity waveforms in normal and growth-retarded pregnancies. Obstet. Gynecol. 1987, 69, 705–709. [Google Scholar] [PubMed]
- Hadi, A.S. Identifying multiple outliers in multivariate data. J. R. Stat. Soc. Ser. B. 1992, 54, 761–771. [Google Scholar] [CrossRef]
- Mathan, K.; Kumar, P.M.; Panchatcharam, P.; Manogaran, G.; Varadharajan, R. A novel Gini index decision tree data mining method with neural network classifiers for prediction of heart disease. Des. Autom. Embed. Syst. 2018, 22, 225–242. [Google Scholar] [CrossRef]
- Olanow, C.W.; Koller, W.C. An algorithm (decision tree) for the management of Parkinson’s disease: Treatment guidelines. Neurology 1998, 50, S1–S88. [Google Scholar] [CrossRef] [PubMed]
- Jiang, Q.; Wang, G.; Jin, S.; Li, Y.; Wang, Y. Predicting human microRNA-disease associations based on support vector machine. Data Min. Bioinform. 2013, 8, 282–293. [Google Scholar] [CrossRef]
- Breslow, N.E.; Mccann, B. Statistical Estimation of Prognosis for Children with Neuroblastoma. Cancer Res. 1971, 31, 2098–2103. [Google Scholar]
- Lloyd, B.G.R. Support Vector Machines for classification and regression. Analyst 2010, 135, 230–267. [Google Scholar]
- Seiffert, C.; Khoshgoftaar, T.M.; Van Hulse, J.; Napolitano, A. RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. Syst. Man Cybern. 2010, 40, 185–197. [Google Scholar] [CrossRef]
- Hosmer, D.W.; Lemeshow, S. Applied Logistic Regression; John Wiley & Sons: Hoboken, NJ, USA, 2013. [Google Scholar]
- Goldberger, J.; Hinton, G.E.; Roweis, S.T.; Salakhutdinov, R.R. Neighbourhood Components Analysis. In Advances in Neural Information Processing Systems; The MIT Press: Cambridge, MA, USA, 2005; pp. 513–520. [Google Scholar]
- Đurovic, Ž.; Kovacevic, B. QQ-plot approach to robust Kalman filtering. Int. J. Control 1995, 61, 837–857. [Google Scholar] [CrossRef]
- Cieslak, D.A.; Chawla, N.V. Learning decision trees for unbalanced data. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases; Springer: Berlin/Heidelberg, Germany, 2008; pp. 241–256. [Google Scholar]
- Oates, C. Vascular Ultrasound: How, Why and When, 3rd ed. Ultrasound 2010, 18, 99. [Google Scholar] [CrossRef]
- Chavhan, G.B.; Parra, D.A.; Mann, A.; Navarro, O.M. Normal Doppler spectral waveforms of major pediatric vessels: Specific patterns. Radiographics 2008, 28, 691–706. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Heijenbrok-Kal, M.H.; Buskens, E.; Nederkoorn, P.J.; Van der Graaf, Y.; Hunink, M.M. Optimal Peak Systolic Velocity Threshold at Duplex US for Determining the Need for Carotid Endarterectomy: A Decision Analytic Approach 1. Radiology 2006, 238, 480–488. [Google Scholar] [CrossRef]
- Ali, F.A. Duplex criteria for determining ≥50% and ≥80% internal carotid artery stenosis following carotid endarterectomy with patch angioplasty. Vascular 2011. [Google Scholar] [CrossRef]
- Scissons, R.P. Should Carotid Duplex Velocity Thresholds Be Modified for Patients Undergoing Computed Tomographic Angiography? J. Vasc. Ultrasound 2012. [Google Scholar] [CrossRef]
- Tokunaga, K.; Koga, M.; Yoshimura, S.; Arihiro, S.; Suzuki, R.; Nagatsuka, K.; Toyoda, K. Optimal Peak Systolic Velocity Thresholds for Predicting Internal Carotid Artery Stenosis Greater than or Equal to 50%, 60%, 70%, and 80%. J. Stroke Cerebrovasc. Dis. Off. J. Natl. Stroke Assoc. 2016, 25, 921–926. [Google Scholar] [CrossRef] [PubMed]
Item | Parameter | Description |
---|---|---|
1 | Acceleration (ACCL) | |
2 | Acceleration Time (ACCT) | − |
3 | End-diastolic Velocity (EDV) | |
4 | Heart Rate (HR) | |
5 | Pulsatility Index (PI) | ( |
6 | Peak Systolic Velocity (PSV) | |
7 | Resistance Index (RI) | |
8 | Spectral Broadening (SB) | |
9 | Systolic/Diastolic Ratio (S/D) | |
10 | Time Average Velocity (TAV) | |
11 | Volume Flow per Cycle (VFC) | , A indicates cross-sectional area of vessel. |
12 | Volume Flow per Minute (VFM) | |
13 | Velocity Time Integral (VTI) |
Method | Accuracy | Sensitivity | Specificity | AUC |
---|---|---|---|---|
Linear SVM | 87.9% | 27% | 100% | 0.82 |
Gaussian SVM | 88.6% | 34% | 99% | 0.88 |
Logistic Regression | 86.4% | 41% | 95% | 0.80 |
Decision Trees | 87.5% | 57% | 93% | 0.83 |
RUSBoostd Trees | 87.1% | 64% | 92% | 0.83 |
RUSBoost with Empirical Weights | 90.1% | 70% | 94% | 0.89 |
Study, Year | PSV, cm/s | Accuracy | Sensitivity | Specificity |
---|---|---|---|---|
Carpenter et al., 1995 | >170 | 83.5% | 4% | 100% |
Heijenbrok-Kal et al.1, 2006 | >180 | 83.5% | 4% | 100% |
Ali et al., 2011 | >213 | 82.1% | 0% | 100% |
Scissons et al., 2012 | >152 | 82.1% | 4% | 99% |
Tokunaga et al., 2016 | >130 | 79.6% | 12% | 95% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xiao, H.; Zhang, Y.; Yin, H.; Liu, P.; Liu, D.C. Early Diagnosis of Carotid Stenosis by Ultrasound Doppler Investigations: A Classification Method for the Hemodynamic Parameter. Information 2020, 11, 493. https://doi.org/10.3390/info11110493
Xiao H, Zhang Y, Yin H, Liu P, Liu DC. Early Diagnosis of Carotid Stenosis by Ultrasound Doppler Investigations: A Classification Method for the Hemodynamic Parameter. Information. 2020; 11(11):493. https://doi.org/10.3390/info11110493
Chicago/Turabian StyleXiao, Huiyue, Yi Zhang, Hao Yin, Paul Liu, and Dong Chyuan Liu. 2020. "Early Diagnosis of Carotid Stenosis by Ultrasound Doppler Investigations: A Classification Method for the Hemodynamic Parameter" Information 11, no. 11: 493. https://doi.org/10.3390/info11110493