Use of fuzzy neural networks in modeling relationships of HPV infection with apoptotic and proliferation markers in potentially malignant oral lesions.

To evaluate in oral leukoplakia the relationship between HPV infection and markers of apoptosis (bcl-2, survivin) and proliferation (PCNA), also conditionally to age, gender, smoking and drinking habits of patients, by means of Fuzzy neural networks (FNN) system 21 cases of oral leukopakia, clinically and histologically diagnosed, were examined for HPV DNA presence, bcl-2, survivin and PCNA expression. HPV DNA was investigated in exfoliated oral mucosa cells by nested PCR (nPCR: MY09-MY11/GP5-GP6), and the HPV genotype determined by direct DNA sequencing. All markers were investigated by means of standardised immunohistochemistry procedure. Data were analysed by chi-square test, crude OR and the 95% CI; in blindness, FNN was applied. HPV DNA was found in 8/21 OL (38.1%); survivin, PCNA, and tobacco smoking were associated in univariate analysis (p = 0.04) with HPV DNA status. HPV-18 was the most frequently detected genotype (6/8), followed by HPV-16 (2/8). FNN revealed that survivin and PCNA, both being expressed in all of OL HPV+ve, were associated with HPV infection. In conclusion, the FNN allowed to hypothesise a model of specific variables associated to HPV infection in OL. The relevance of survivin and PCNA suggest that they may be involved in HPV-mediated deregulation of epithelial maturation and, conversely, that HPV may have a role in the expression level of these two markers. FNN system seems to be an effective tool in the analysis of correlates of OL and HPV infection.