Bacterial infections are a leading cause of death in almost every nation, causing more than 6.7 million deaths every year [3][4]. In the United States alone, these infections require $33 billion for annual healthcare spending, equivalent to 8.7% of the total healthcare expenditure [5], and hence are particularly costly.
To detect and identify the bacteria and its antibiotic resistance, current diagnostic methods include sample culture. However, this is a slow process, that can take days even in state-of-the-art laboratories [6][7]. New methods for rapid culture-free diagnosis of bacterial infections are therefore required. Raman spectroscopy has the potential to identify the species of bacteria and, consequently, its antibiotic susceptibility. Molecular compositions describe different bacterial phenotypes, leading to subtle variations in their corresponding Raman spectra.
In this project, we initially conceive a Convolutional Neural Network (CNN) to classify bacterial spectra and the related antibiotic treatment, measuring the isolate-level accuracies and comparing it with a state-of-the-art CNN. Secondly, we compare two popular machine learning algorithms against our CNN model, in order to evaluate if a deep approach could lead to better performance.
[3] C. Fleischmann, A. Scherag, N. K. Adhikari, C. S. Hartog, T. Tsaganos, P. Schlattmann, D. C. Angus, and K. Reinhart, “Assessment of global inci- dence and mortality of hospital-treated sepsis. current estimates and limita- tions,” American journal of respiratory and critical care medicine, vol. 193, no. 3, pp. 259–272, 2016.
[4] R. DeAntonio, J.-P. Yarzabal, J. P. Cruz, J. E. Schmidt, and J. Kleijnen, “Epi- demiology of community-acquired pneumonia and implications for vaccination of children living in developing and newly industrialized countries: A systematic literature review,” Human vaccines & immunotherapeutics, vol. 12, no. 9, pp. 2422–2440, 2016.
[5] C. M. Torio and B. J. Moore, “National inpatient hospital costs: the most expensive conditions by payer, 2013: statistical brief# 204,” 2016.
[6] R. P. Dellinger, M. M. Levy, A. Rhodes, D. Annane, H. Gerlach, S. M. Opal, J. E. Sevransky, C. L. Sprung, I. S. Douglas, R. Jaeschke et al., “Surviving sepsis campaign: international guidelines for management of severe sepsis and septic shock, 2012,” Intensive care medicine, vol. 39, no. 2, pp. 165–228, 2013.
[7] A. Chaudhuri, P. Martin, P. Kennedy, R. Andrew Seaton, P. Portegies, M. Bo- jar, I. Steiner, and E. T. Force, “Efns guideline on the management of community-acquired bacterial meningitis: report of an efns task force on acute bacterial meningitis in older children and adults,” European journal of neurol- ogy, vol. 15, no. 7, pp. 649–659, 2008.