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 scalp cSCC patients are poorly characterized. OBJECTIVE: To identify patterns of patients with higher risk of postradiotherapy recurrence. METHODS: A retrospective observational study was performed on scalp cSCC patients 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 scalp cSCC profiles among radiotherapy responsive patients, not previously described: namely, (i) stage T2 cSCC type, aged 70-80 years; (ii) frontal cSCC type, aged <70 years; (iii) non-recurrent nodular or nodulo-ulcerated, stage T3 cSCC type, of the vertex and treated with >60 Grays (Gy); and (iv) flat, occipital, stage T1 cSCC type, 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 scalp cSCCs who may benefit from a RT-treatment.

Photoadaptation to ultraviolet B TL01 in psoriatic patients.

BACKGROUND: In the biologic era, narrow-band ultraviolet B (NB-UVB) phototherapy still remains a valuable, effective, inexpensive, safe anti-psoriatic treatment. Patients can lose response to NB-UVB over time due to photoadaptation. This phenomenon is the tendency of the skin to respond to ultraviolet (UV) exposure by undergoing changes that may result in a decreased future response to an equivalent dose of radiation, thus leading to the need for an increased exposure during phototherapy course. AIM: To characterize and quantify the determinants of photoadaptation in NB-UVB treated psoriatic patients. METHODS: We enrolled 57 adult patients with moderate plaque psoriasis. Patients underwent 24 sessions of NB-UVB phototherapy delivered thrice a week. Dosing was started with 70% of the minimal erythema dose (MED) with percentage-based dose increments every two treatments. MED as well as change in the erythema and melanin index (MI) were measured at baseline and at the end of phototherapy course. Moreover, an adaptation factor (AF) was calculated for each patient. RESULTS: Adaptation factor was not influenced by both baseline MED and skin type. We found a weak correlation between higher cumulative dosages and the initial MED (Spearman's rho = 0.32, P = 0.0154) as well as with the mean initial MI (Spearman's rho = 0.25, P = 0.0624, statistically borderline). Clearance and mean number of treatments were correlated (Spearman's rho = 0.48, P < 0.001). CONCLUSION: Photoadaptation is a physiological skin response that negatively influences NB-UVB responsiveness and is not predictable by the baseline MED and skin type. Thus, starting with more aggressive protocols and increasing rapidly dosage progression to prevent AF may increase NB-UVB response.

Psoriatic and psoriatic arthritis patients with and without jet-lag: does it matter for disease severity scores? Insights and implications from a pilot, prospective study.

Background: Jet-lag may affect air-travelers crossing at least two time-zones and has several health-care implications. It occurs when the human biological rhythms are out of synch with respect to the day-night cycle at the country destination. Its effect in psoriasis is missing. We aimed to evaluate the effect of Jet-lag in psoriatic patients' management. Methods: This is a prospective observational study that enrolled psoriatic patients that underwent a flight: patients who experienced jet-lag were compared to patients who did not experience jet-lag. Before the flight, a dermatologist recorded clinical and demographical data with particular attention to Psoriasis Area Severity Index (PASI) and Disease Activity in Psoriatic Arthritis (DAPSA). Patients performed Self-Administered Psoriasis Area Severity Index (SAPASI), the Dermatology Life Quality Index (DLQI) and the pruritus Visual Analog Scale (VAS) scores. After the flight, patients completed the SAPASI, DLQI and pruritus-VAS scores. Results: The sample recruited comprised of 70 psoriatic patients aged 42.4 ± 9.7 years (median 42.5 years). Thirty (42.9%) were males, mean BMI was 25.5 ± 2.2 kg/m2. Average disease duration was 15.2 ± 7.1 years, and 20 (28.6%) subjects had developed PsA. Average hours of flight were 5.4 ± 3.5 (median 3.5 h), with 34 (48.6%) subjects reporting jet-lag. At the multivariate regression analysis, the change in the SAPASI score resulted correlated with jet-lag (regression coefficient 1.63, p = .0092), as well the change in the DLQI score (regression coefficient = 1.73, p = .0009), but no change on the pruritus VAS scale was found. Conclusions: The present study suggests that jet-lag may influence disease severity and DLQI scores, but not itch in psoriatic patients.

'High dose' vs. 'medium dose' UVA1 phototherapy in italian patients with severe atopic dermatitis.

BACKGROUND: The current evidences attest UVA1 phototherapy as effective in the treatment of severe atopic dermatitis (AD). Furthermore, in this indication, 'medium dose' is as effective as 'high dose' regimen. To date, a randomized comparison study evaluating the effectiveness as well as safety of different UVA1 protocols in different skin types in the treatment of adult patients with severe AD is still lacking. OBJECTIVE: The aim of the present study was to compare the safety and the efficacy of medium and high dose UVA1 either in fair or in dark skin types. METHODS: Twenty-seven adult patients with severe AD were consecutively included in a randomized, controlled, open, two arms trial Severity of AD was determined by means of SCORAD index and clinical improvement was also monitored. A total of 13 out of 27 patients were treated with high dose (130 J/cm2 ) UVA1 protocol while 14 out of 27 patients received medium dose (60 J/cm2 ) UVA1 protocol. Phototherapy was performed five times weekly up to 3 weeks. Before and after UVA1 treatment each patient was evaluated for skin pigmentation through Melanin Index (MI) quantitative evaluation. RESULTS: Skin status improved in all patients resulting in a reduction of SCORAD index in all groups. Our results demonstrated that among patients with darker skin types and higher MI, high dose UVA1 was significantly more effective than medium dose (P < 0.0001) while within the groups with skin type II, no significant differences between high and medium dose protocols were observed. CONCLUSION: Our study, confirms previous observations that UVA1 phototherapy should be considered among the first approaches in the treatment of patients with severe generalized AD and also demonstrates that in darker skin types, high dose UVA1 phototherapy is more effective than medium dose in the treatment of adult patients with severe AD.