Our aim was to evaluate in oral squamous cell carcinoma (OSCC) the relationship between some cell cycle markers and HPV infection, conditionally to age, gender and certain habits of patients, and to assess the ability of fuzzy neural networks (FNNs) in building up an adequate predictive model based on logic inference rules. Eighteen cases of OSCC were examined by immunohistochemistry for MIB-1, PCNA and survivin expression; presence of HPV DNA was investigated in exfoliated oral mucosa cells by nested PCR (nPCR, MY09-MY11/GP5-GP6), and HPV genotype was determined by direct DNA sequencing. Data were analyzed by traditional statistics (TS) and FNNs. HPV DNA was found in 9/18 OSCCs (50.0 %) without any significant higher risk of HPV infection with respect to the sociodemographic variables considered ( p > 0.2), apart from tobacco smoking, reported in 44.4% of OSCC HPV-positive vs. 100% HPV-negative subjects ( p = 0.029). Regarding cell cycle markers, TS and FNN revealed that survivin was expressed significantly more in HPV-negative than in HPVpositive OSCC [root mean-square error (RMSE) = 5.89 3 10 -6 , % predicted 100.0]; furthermore, smoking played a protective role for survivin expression in HPV-positive cases (OR = 0.019, 95%CI 0.001-0.723, RMSE = 0.20, % of prevision 94.4). FNN, although on a small sample size, allowed us to confirm data by TS and to hypothesize a different cell cycle pattern for HPV-positive vs. HPV-negative OSCC. In the latter cases, the relevance of apoptotic vs. proliferative markers suggested that they may be related to the different supposed outcome of HPV-negative OSCC and that HPV may have a protective role in the expression level of survivin, especially in tobacco smokers. ' 2005 Wiley-Liss, Inc.Key words: human papillomavirus; survivin; oral squamous cell carcinoma; fuzzy neural network; carcinogenesis OSCC is rapidly increasing in incidence and represents the most frequent malignant oral tumor. The incidence of metastasis depends on the degree of cellular differentiation, deep invasion and site of the primary tumor; however, outcome is difficult to predict if only standard clinicopathologic parameters are taken into account. Biologic markers that can help to identify lesions with an aggressive phenotype and worse prognosis need to be identified.Since the majority of human neoplasms are characterized by an imbalance of the regulatory cell cycle control processes, the study of OSCC using the expression of proteins involved in the critical checkpoints of cell apoptosis and growth starts by elucidating the processes of carcinogenesis and appears to have good prognostic value. 1 Indeed, we know that apoptosis, or programmed cell death, and its suppression are involved in the carcinogenesis of several tumors; this process, mediated by caspases and cysteine proteinases present as proenzymes, is inhibited by several proteins, such as those of the Bcl-2 and IAP families. Survivin is an IAP protein, which is abundantly expressed in most solid and hematologic malignancies but undetectable in ...