Loading...

Application of Fourier Transform Infrared (FTIR) Spectroscopy of Biofluids in Disease Diagnosis

Ganji, Mohammad | 2017

1217 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 49285 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Nejat, Hossein; Meghdari, Ali; Beigzadeh, Borhan
  7. Abstract:
  8. The ability to diagnose a disease rapidly, non-invasively, with high confidence level and low cost can be of great importance in many ways such as 'detection and on-time conduction of remedial strategies. Hence It can reduce fatality rate and costs in the hygiene field. Currently some pathological diagnosis methods are not suitable considering their precision and costs and in addition to that, most of them are single-function and are developed for diagnosis of a particular disease and don't perform well in the case of multiple disease factors. Many diseases are caused by metabolic disorders and thus direct study of metabolic factors can provide us with a lot of evidence on the disease. One of the developing methods of studying the metabolic factors is metabolic fingerprinting. Fourier transform Infrared spectroscopy also know as FTIR, due to its high speed, low cost, non-invasive nature and high fuctional ability, is a high-potential metabolic fingerprinting method in discriminating samples with special biological condition from reference samples. This method is based on multivariate analysis of FTIR data. In this research, potential of FTIR spectroscopy of serum samples in diagnosis of leukemia is investigated. Leukemia is a group of cancers that usually begins in the bone marrow and results in high numbers of abnormal white blood cells. For this purpose, a dataset consisting of thirteen serum samples belonging to leukemia patients and twelve serum samples belonging to normal people as control group was collected and their FTIR spectrums were obtained and studied. Processing of this dataset proved good discrimination potential of FTIR spectroscopy in the case of leukemia serum samples. By supervised processing of the data and investigating different algorithms, the best model for classification of the data was obtained. This model includes preprocessing the data with fist order Savitzky Golay differentiation followed by vector normalization, feature selection with a univariate filter method based on p-value of two-sample t-test and classification with SVM. Four of the samples were recognized as outlier, noisy data and therefore were eliminated from the dataset. This elimination increased the model performance so that specificity and sensitivity of 78% and 87% respectively were reached with this model
  9. Keywords:
  10. Fourier Transform Infra Red (FT-IR)Spectroscopy ; Biofluid ; Cancer Diagnosis ; Biomarker ; Multivariate Data Analysis ; Serum ; Leukemia

 Digital Object List

 Bookmark