Speaking with mask in the COVID-19 era: Multiclass machine learning classification of acoustic and perceptual parameters.

The intensive use of personal protective equipment often requires increasing voice intensity, with possible development of voice disorders. This paper exploits machine learning approaches to investigate the impact of different types of masks on sustained vowels /a/, /i/, and /u/ and the sequence /a'jw/ inside a standardized sentence. Both objective acoustical parameters and subjective ratings were used for statistical analysis, multiple comparisons, and in multivariate machine learning classification experiments. Significant differences were found between mask+shield configuration and no-mask and between mask and mask+shield conditions. Power spectral density decreases with statistical significance above 1.5 kHz when wearing masks. Subjective ratings confirmed increasing discomfort from no-mask condition to protective masks and shield. Machine learning techniques proved that masks alter voice production: in a multiclass experiment, random forest (RF) models were able to distinguish amongst seven masks conditions with up to 94% validation accuracy, separating masked from unmasked conditions with up to 100% validation accuracy and detecting the shield presence with up to 86% validation accuracy. Moreover, an RF classifier allowed distinguishing male from female subject in masked conditions with 100% validation accuracy. Combining acoustic and perceptual analysis represents a robust approach to characterize masks configurations and quantify the corresponding level of discomfort.

A randomized study comparing filgrastim versus lenograstim versus molgramostim plus chemotherapy for peripheral blood progenitor cell mobilization.

We conducted a prospective randomized clinical trial to assess the mobilizing efficacy of filgrastim, lenograstim and molgramostim following a disease-specific chemotherapy regimen. Mobilization consisted of high-dose cyclophosphamide in 45 cases (44%), and cisplatin/ifosfamide/etoposide or vinblastine in 22 (21%), followed by randomization to either filgrastim or lenograstim or molgramostim at 5 microg/kg/day. One hundred and three patients were randomized, and 82 (79%) performed apheresis. Forty-four (43%) patients were chemonaive, whereas 59 (57%) were pretreated. A median number of one apheresis per patient (range, 1-3) was performed. The median number of CD34+ cells obtained after mobilization was 8.4 x 10(6)/kg in the filgrastim arm versus 5.8 x 10(6)/kg in the lenograstim arm versus 4.0 x 10(6)/kg in the molgramostim arm (P=0.1). A statistically significant difference was observed for the median number of days of growth factor administration in favor of lenograstim (12 days) versus filgrastim (13 days) and molgramostim (14 days) (P<0.0001) and for the subgroup of chemonaive patients (12 days) versus pretreated patients (14 days) (P<0.001). In conclusion, all three growth factors were efficacious in mobilizing peripheral blood progenitor cells with no statistically significant difference between CD34+ cell yield and the different regimens, and the time to apheresis is likely confounded by the different mobilization regimens.

Adjuvant chemotherapy in the treatment of colon cancer: randomized multicenter trial of the Italian National Intergroup of Adjuvant Chemotherapy in Colon Cancer (INTACC).

BACKGROUND: To determine whether the addition of leucovorin to the combination 5-fluorouracil plus levamisole prolongs disease-free survival and overall survival in patients with radically resected colon cancer (Dukes' B(2-3) and C). PATIENTS AND METHODS: Patients (1703) were accrued between March 1992 and February 1995 in a large-scale clinical trial within five Italian cooperative groups. After stratification for center, patients were randomized as follows: arm A, 5-fluorouracil [450 mg/m(2) intravenous (i.v.) bolus on days 1-5] and levamisole (150 mg orally for 3 days, every 14 days for 6 months) versus arm B, 6-S-leucovorin (100 mg/m(2) i.v. bolus on days 1-5) followed by 5-fluorouracil (370 mg/m(2) i.v. bolus on days 1-5), plus levamisole (as arm A), every 4 weeks for six cycles. RESULTS: After a median follow-up of 6.4 years no significant difference was seen for either disease-free survival (58% versus 60%, not significant) or 5-year overall survival (68% versus 71%, not significant), respectively. Gastrointestinal toxicity (World Health Organization grade 3/4) was more frequent in arm B (8% versus 18%, not significant). CONCLUSIONS: In this trial the schedules used showed no statistically significant differences in terms of disease-free survival or overall survival in the treatment of colorectal cancer.

Combination chemotherapy in advanced ovarian carcinoma.

Ovarian carcinoma is the fifth most common cause of death among women in western countries. It is often diagnosed in an advanced stage (FIGO Stage III and IV) and requires effective chemotherapy as first-line treatment. The advent of cis-platin combined with adriamycin and cyclophosphamide has remarkably increased the response rate in advanced disease. The authors report 31 cases of epithelial ovarian neoplasia, without prior chemotherapy, treated with cis-platin, adriamycin and cyclophosphamide (PAC I). Of the 30 evaluable patients, 15 had clinical complete remissions (cCR = 50%), 10 clinical partial remissions (cPR = 33%) and 5 no response (NR = 17%). The total response (cCR + cPR) was equal to 83%. Twelve of the 15 patients in cCR underwent second-look laparotomy; in 8 of these cases, histologic and cytologic confirmation of CR was obtained. PAC I was found to be a highly effective therapeutic regimen with moderate toxicity. The individual toxicity reported was gastroenteric (nausea and vomiting), but transitory. No chronic toxic side-effects from cisplatin or adriamycin were noted. However, more definitive results must be obtained to verify its impact on the prolongation of survival.