Artificial neural networks allow response prediction in squamous cell carcinoma of the scalp treated with radiotherapy

Background Epithelial neoplasms of the scalp account for approximately 2% of all skin cancers and for about 10-20% of the tumours affecting the head and neck area. Radiotherapy is suggested for localized cutaneous squamous cell carcinomas (cSCC) without lymph node involvement, multiple or extensive lesions, for patients refusing surgery, for patients with a poor general medical status, as adjuvant for incompletely excised lesions and/or as a palliative treatment. To date, prognostic risk factors in scalpcSCCpatients are poorly characterized. Objective To identify patterns of patients with higher risk of postradiotherapy recurrence. Methods A retrospective observational study was performed on scalpcSCCpatients with histological diagnosis who underwent conventional radiotherapy (50-120 kV) (between 1996 and 2008, follow-up from 1 to 140 months, median 14 months). Out of the 79 enrolled patients, 22 (27.8%) had previously undergone a surgery. Two months after radiotherapy, 66 (83.5%) patients achieved a complete remission, 6 (7.6%) a partial remission, whereas 2 (2.5%) proved non-responsive to the treatment and 5 cases were lost to follow-up. Demographical and clinical data were preliminarily analysed with classical descriptive statistics and with principal component analysis. All data were then re-evaluated with a machine learning-based approach using a 4th generation artificial neural networks (ANNs)-based algorithm. Results Artificial neural networks analysis revealed four scalpcSCCprofiles among radiotherapy responsive patients, not previously described: namely, (i) stage T2cSCCtype, aged 70-80 years; (ii) frontalcSCCtype, aged <70 years; (iii) non-recurrent nodular or nodulo-ulcerated, stage T3cSCCtype, of the vertex and treated with >60 Grays (Gy); and (iv) flat, occipital, stage T1cSCCtype, treated with 50-59 Gy. The model uncovering these four predictive profiles displayed 85.7% sensitivity, 97.6% specificity and 91.7% overall accuracy. Conclusions Patient profiling/phenotyping with machine learning may be a new, helpful method to stratify patients with scalpcSCCs who may benefit from aRT-treatment.