Using topological data analysis for diagnosis pulmonary embolism

• Autorzy: Rucco M. , Merelli E. , Herman D. , Ramanan D. , Petrossian T. , Falsetti L. , Nitti C. , Salvi A.
• Języki publikacji: EN

Abstrakty

EN

Pulmonary Embolism (PE) is a common and potentially lethal condition. Most patients die within the first few hours from the event. Despite diagnostic advances, delays and underdiagnosis in PE are common. Moreover, many investigations pursued in the suspect of PE result negative and no more than 10% of the pulmonary angio-CT scan performed to confirm PE confirm the suspected diagnosis. To increase the diagnostic performance in PE, current diagnostic work-up of patients with suspected acute pulmonary embolism usually starts with the assessment of clinical pretest probability using plasma d-Dimer measurement and clinical prediction rules. One of the most validated and widely used clinical decision rules are the Wells and Geneva Revised scores. However, both indices have limitations. We aimed to develop a new clinical prediction rule (CPR) for PE based on a new approach for features selection based on topological concepts and artificial neural network. Filter or wrapper methods for features reduction cannot be applied to our dataset: the application of these algorithms can only be performed on datasets without missing data. Alternatively, eliminating rows with null values in the dataset would reduce the sample size significantly and result in a covariance matrix that is singular. Instead, we applied Topological data analysis (TDA) to overcome the hurdle of processing datasets with null values missing data. A topological network was developed using the Ayasdi-Iris software (Ayasdi, Inc., Palo Alto). The PE patient topology identified two flares in the pathological group and hence two distinct clusters of PE patient populations. Additionally, the topological network detected several sub-groups among healthy patients that likely are affected with non-PE diseases. To be diagnosed properly even though they are not affected by PE, in a next study we will introduce also the survival curves for the patients. TDA was further utilized to identify key features which are best associated as diagnostic factors for PE and used this information to define the input space for a back-propagation artificial neural network (BP-ANN). It is shown that the area under curve (AUC) of BP-ANN is greater than the AUCs of the scores (Wells and revised Geneva) used among physicians. The results demonstrate topological data analysis and the BP-ANN, when used in combination, can produce better predictive models than Wells or revised Geneva scores system for the analyzed cohort. The new CPR can help physicians to predict the probability of PE.

Słowa kluczowe

EN

Clinical Prediction Rule (CPR); Pulmonary Embolism; Topological Data Analysis; Artificial Neural Network (ANN); Computer Aided Diagnosis (CAD)

• Wydawca: Komisja Informatyki Polskiej Akademii Nauk, Oddział w Gdańsku
• Czasopismo: Journal of Theoretical and Applied Computer Science
• Rocznik: 2015
• Tom: Vol. 9, nr 1
• Strony: 41--55
• Opis fizyczny: Bibliogr. 41 poz., rys., tab.

Twórcy

autor

Rucco M.

• University of Camerino, School of Science and Technology, Italy

autor

Merelli E.

• University of Camerino, School of Science and Technology, Italy

autor

Herman D.

• Ayasdi, Inc., USA

autor

Ramanan D.

• Ayasdi, Inc., USA

autor

Petrossian T.

autor

Falsetti L.

• Internal and Subintensive Medicine of Ospedali Riuniti - Ancona, IT

autor

Nitti C.

• Internal and Subintensive Medicine of Ospedali Riuniti - Ancona, IT

autor

Salvi A.

• Internal and Subintensive Medicine of Ospedali Riuniti - Ancona, IT

Bibliografia

• [1] Cangelosi, D., Blengio, F., Versteeg, R., Eggert, A., Garaventa, A., Gambini, C., Conte, M., Eva, A., Muselli, M., Varesio, L.: Logic Learning Machine creates explicit and stable rules stratifying neuroblastoma patients. BMC Bioinformatics, 14(Suppl 7), p. S12, 2013.
• [2] Kotsiantis, S. B., Zaharakis, I. D., Pintelas, P. E.: Machine learning: a review of classification and combining techniques. Artif. Intell. Rev., 26(3), pp. 159–190, 2006. ISSN 0269-2821.
• [3] Tourassi, G., Floyd, C., Sostman, H., Coleman, R.: Acute pulmonary embolism: artificial neural network approach for diagnosis. Radiology, 189, pp. 555–558, 1993.
• [4] Patil, S.: Neural network in the clinical diagnosis of acute pulmonary embolism. Chest, 1, pp. 1685–1689, 1993.
• [5] Tang, L., Wang, L., Pan, S., Su, Y., Chen, Y.: A neural network to pulmonary embolism aided diagnosis with a feature selection approach. In: Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on, volume 6, pp. 2255–2260. Oct.
• [6] Tagalakis, V., Patenaude, V., Kahn, S., S., S.: Incidence of and Mortality from Venous Thromboembolism in a Real-world Population: The Q-VTE Study Cohort. Am J Med, 126(9), pp. 832.e13–21, 2013. Doi: 10.1016/j.amjmed.2013.02.024. Epub 2013 Jul 3. PubMed PMID: 23830539.
• [7] Silverstein, M., Heit, J., Mohr, D., Petterson, T., O’Fallon, W., Melton, L. J.: Trends in the incidence of deep vein thrombosis and pulmonary embolism: a 25-year population-based study. Arch Intern Med., 158(6), pp. 585–93, 1998. PubMed PMID: 9521222.
• [8] Wells, P., Anderson, D., Rodger, M., Stiell, I., Dreyer, J., Barnes, D., Forgie, M., Kovacs, G., Ward, J., Kovacs, M.: Excluding pulmonary embolism at the bedside without diagnostic imaging: management of patients with suspected pulmonary embolism presenting to the emergency department by using a simple clinical model and d-dimer. Ann Intern Med., 135(2), pp. 98–107, 2001. PubMed PMID: 11453709.
• [9] Wolf, S., McCubbin, T., Nordenholz, K., Naviaux, N., Haukoos, J.: Assessment of the pulmonary embolism rule-out criteria rule for evaluation of suspected pulmonary embolism in the emergency department. Am J Emerg Med, 26(2), pp. 181–5, 2008. Doi: 10.1016/j.ajem.2007.04.026. PubMed PMID: 18272098.
• [10] Wood, K.: Major pulmonary embolism: review of a pathophysiologic approach to the golden hour of hemodynamically significant pulmonary embolism. Chest, 121(3), pp. 877–905, 2002.
• [11] Kline, J., Hernandez-Nino, J., Jones, A., Rose, G., Norton, H., Camargo, C. J.: Prospective study of the clinical features and outcomes of emergency department patients with delayed diagnosis of pulmonary embolism. Acad Emerg Med., 14(7), pp. 592–8, 2007.
• [12] Torbicki, A., Perrier, A., Konstantinides, S., Agnelli, G., Gali, N., Pruszczyk, P., Bengel, F., Brady, A., Ferreira, D., Janssens, U., Klepetko, W., Mayer, E., Remy-Jardin, M., Bassand, J.: ESC Committee for Practice Guidelines (CPG). Guidelines on the diagnosis and management of acute pulmonary embolism: the Task Force for the Diagnosis and Management of Acute Pulmonary Embolism of the European Society of Cardiology (ESC). Eur Heart J., 29(18), pp. 2276–315, 2008. Doi: 10.1093/eurheartj/ehn310. Epub 2008 Aug 30. PubMed PMID: 18757870.
• [13] Einstein, A., Henzlova, M., Rajagopalan, S.: Estimating risk of cancer associated with radiation exposure from 64-slice computed tomography coronary angiography. JAMA, 298, p. 317323, 2007.
• [14] Mitchell, A., Kline, J.: Contrast nephropathy following computed tomography angiography of the chest for pulmonary embolism in the emergency department. J Thromb Haemost, 5, pp. 50–54, 2007.
• [15] Brunot, S., Corneloup, O., Latrabe, V., Montaudon, M., Laurent, F.: Reproducibility of multi-detector spiral computed tomography in detection of sub-segmental acute pulmonary embolism. Eur.Radiol., 15, pp. 2057–2063, 2005.
• [16] Haap, M., Gatidis, S., Horger, M., Riessen, R., Lehnert, H., Haas, C.: Computed tomography angiography in patients with suspected pulmonary embolism-too often considered? Am J Emerg Med, 30(2), pp. 325–30, 2012.
• [17] Beck, K., Holzschuh, J.: Schattauer GmbH - Verlag für Medizin. Naturwissenschaften - The Science of Nature, 2011.
• [18] Sanchez, O., Trinquart, L., Caille, V., Couturaud, F., Pacouret, G., Meneveau, N., Verschuren, F., Roy, P.-M., Parent, F., Righini, M., et al.: Prognostic factors for pulmonary embolism: the prepstudy, a prospective multicenter cohort study. American journal of respiratory and critical care medicine, 181(2), pp. 168–173, 2010.
• [19] Lum, P., Singh, G., Lehman, A., et al.: Extracting insights from the shape of complex data using topology. Scientific Reports - Nature, 3, pp. 561–577, 2013.
• [20] Singh, G., Memoli, F., Carlsson, G.: Topological Methods for the Analysis of High Dimensional Data Sets and 3D Object Recognition. In: Botsch, M., Pajarola, R., Chen, B., Zwicker, M. (eds.), Symposium on Point Based Graphics, pp. 91–100. Eurographics Association, 2007.
• [21] Albert, R., Barabási, A.-L.: Statistical mechanics of complex networks. Reviews of modern physics, 74(1), p. 47, 2002.
• [22] Lippmann, R.: An introduction to computing with neural nets. ASSP Magazine, IEEE, 4(2), pp. 4–22, Apr.
• [23] Rosenblatt, F.: Principles of neurodynamics. Perceptrons and the theory of brain mechanisms. Spartan Books, Washington, 1962.
• [24] Rojas, R.: Neural Networks: A Systematic Introduction. 1996.
• [25] Kauffman, S. A.: The Origins of Order: Self-Organization and Selection in Evolution. Oxford University Press, New York, 1993.
• [26] Kolmogorov-Smirnov test.
• [27] Hanley, J., McNeil, B.: The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve. Radiology., 143(1), pp. 29–36, 1982.
• [28] McClish, D. K.: Analyzing a Portion of the ROC Curve. Medical Decision Making, 9, pp. 190–195, 1989.
• [29] Jaccard Coefficient.
• [30] Lloyd, N. T., Bau, D.: NUMERICAL LINEAR ALGEBRA. pp. xii+361. Society for Industrial and Applied Mathematics, UK, iii edition, 1997.
• [31] Kohavi, R., et al.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, volume 14, pp. 1137–1145. 1995.
• [32] Ayasdi-Iris.
• [33] Singh, G., Mémoli, F., Carlsson, G. E.: Topological Methods for the Analysis of High Dimensional physics, 74(1), p. 47, 2002.
• [34] Rulex 2.0.
• [35] MedCalc.
• [36] Penaloza, A., Melot, C., Motte, S.: Comparison of the Wells score with the simplified revised Geneva score for assessing pretest probability of pulmonary embolism. Thromb Res, 127(2), pp. 81–4, 2011.
• [37] Picard, R., Cook, D.: Cross-Validation of Regression Models. Journal of the American Statistical Association., 79(387), p. 575583, 1984.
• [38] DeLong, E., DeLong, D., Clarke-Pearson, D.: Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics, 44, pp. 837–845, 81–4, 2011.
• [39] Griner, P., Mayewski, R., Mushlin, A., Greenland, P.: Selection and interpretation of diagnostic tests and procedures. Annals of Internal Medicine, 94, pp. 555–600, 1981.
• [40] Metz, C.: Basic principles of ROC analysis. Seminars in Nuclear Medicine. Annals of Internal Medicine, 8, pp. 283–298, 1978.
• [41] Zweig, M., Campbell, G.: Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical Chemistry, 39, pp. 561–577, 1993.