Steenhuis, E. (Eline) (2019) eNose: de alternatieve follow-up methode voor colorectaal carcinoom. thesis, Medicine.
Full text available on request.Abstract
Introduction: Colorectal carcinoma (CRC) is widespread in the western world, with a worldwide incidence of 1.4 million patients and a large share in cancer-related mortality. After curative treatment, patients are eligible for a follow-up of usually 5 years. 30-50% of patients treated curatively still develop a metastasis or recurrence. Treatment of metastases is generally successful, particularly in early-stage tumours. However, current follow-up examinations have low sensitivity and have a major impact on patients wellbeing. This justifies the search for a new patient-friendly diagnostic tool with a high sensitivity. Analysis of exhaled air through an electronic nose is a promising new method of diagnostics. This study investigates how well eNose can detect metastases. Materials and method: 62 patients were included in this cross-sectional study, of which 36 patients had no metastases and 26 patients had a local recurrence or metastasis. The profile of Volatile Organic Compounds (VOCs) in exhaled air was analysed with an eNose (AeonoseTM) and an artificial neural network (ANN) was created by machine learning, which can be used to predict metastases. An ROC-curve and scatterplot were made and the sensitivity and specificity were calculated with different discrimination thresholds. Results: The discrimination threshold with the best ratio between sensitivity and specificity was -0.21. Hereby a sensitivity and specificity of 89% and 81% with an accuracy of 84% was achieved. Conclusion: eNose is very capable of detecting recurrences and metastases within the follow-up of CRC and is therefore a promising, patient-friendly diagnostic within the follow-up of CRC.
| Item Type: | Thesis (UNSPECIFIED) |
|---|---|
| Supervisor name: | De Vos tot Nederveen Cappel,, dr. W.H. and Brohet, dr. R.M. |
| Faculty: | Medical Sciences |
| Date Deposited: | 10 Sep 2020 11:01 |
| Last Modified: | 10 Sep 2020 11:01 |
| URI: | https://umcg.studenttheses.ub.rug.nl/id/eprint/2757 |
Actions (login required)
 |
View Item |