Table 3. Predictive models based on the sensor array output for the pairwise comparison between HNSCC, benign tumours and healthy states, as well as between different sites and stages of HNSCC.
| DFA model no. | Target group | Control group | Total number of samples | Number of sensing features for DFA model | Accuracy (% after cross-validation) | Sensitivity (%) | Specificity (%) |
|---|---|---|---|---|---|---|---|
| 1 |
HNSCC |
Healthy |
41 |
3 |
83 |
77 |
90 |
| 2 |
HNSCC |
Benign tumours |
43 |
3 |
84 |
77 |
90 |
| 3 |
Benign tumours |
Healthy |
40 |
3 |
73 |
71 |
75 |
| 4 |
HNSCC: larynx |
HNC: pharynx |
22 |
3 |
91 |
92 |
90 |
| 5 | Early HNSCC | Late HNSCC | 21 | 3 | 95 | 100 | 91 |
Abbreviations: DFA=discriminant factor analysis; HNC=head and neck cancer; HNSCC=squamous cell carcinoma of the head and neck. The samples were classified using DFA, keeping the ratio between the number of independent measurements and the number of DFA input features below 7. Sensitivity, specificity and overall classification accuracy were calculated via leave-one-out cross-validation.