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.

Long-term outcomes in patients with schizophrenia treated with risperidone long-acting injection or oral antipsychotics in Spain: results from the electronic Schizophrenia Treatment Adherence Registry (e-STAR).

BACKGROUND: The electronic Schizophrenia Treatment Adherence Registry (e-STAR) is a prospective, observational study of patients with schizophrenia designed to evaluate long-term treatment outcomes in routine clinical practice. METHODS: Parameters were assessed at baseline and at 3 month intervals for 2 years in patients initiated on risperidone long-acting injection (RLAI) (n=1345) or a new oral antipsychotic (AP) (n=277; 35.7% and 36.5% on risperidone and olanzapine, respectively) in Spain. Hospitalization prior to therapy was assessed by a retrospective chart review. RESULTS: At 24 months, treatment retention (81.8% for RLAI versus 63.4% for oral APs, p<0.0001) and reduction in Clinical Global Impression Severity scores (-1.14 for RLAI versus -0.94 for APs, p=0.0165) were significantly higher with RLAI. Compared to the pre-switch period, RLAI patients had greater reductions in the number (reduction of 0.37 stays per patient versus 0.2, p<0.05) and days (18.74 versus 13.02, p<0.01) of hospitalizations at 24 months than oral AP patients. CONCLUSIONS: This 2 year, prospective, observational study showed that, compared to oral antipsychotics, RLAI was associated with better treatment retention, greater improvement in clinical symptoms and functioning, and greater reduction in hospital stays and days in hospital in patients with schizophrenia. Improved treatment adherence, increased efficacy and reduced hospitalization with RLAI offer the opportunity of substantial therapeutic improvement in schizophrenia.

Immunocytochemical characterization of adenohypophyseal cells in the greater weever fish (Trachinus draco).

The adenohypophysis of the greater weever fish (Trachinus draco) was studied using histochemical and immunocytochemical methods. The adenohypophysis comprised the rostral pars distalis (RPD), the proximal pars distalis (PPD), and the pars intermedia (PI). Neurohypophysis showed a patent hypophyseal stalk which was divided into several branches intermingled with the adenohypophysis. Salmon prolactin (PRL)-immunoreactive (ir) cells, arranged in follicles, resided in the RPD and the most rostral part of the ventral PPD. Human adrenocorticotropin (ACTH)-ir cells were located in the RPD between PRL-ir cells and the neurohypophyseal processes. Salmon and seabream somatotropin (GH)-ir cells were located in both the dorsal and the ventral PPD. Some GH-ir cells were seen in surrounding and in contact with neurohypophyseal branches, whereas other isolated or clustered GH-ir cells were embedded in adenohypophyseal cells of the PPD. In addition, isolated or clustered GH-ir cells were also detected in the tissue of the PPD covering the most rostral part of PI. Only one class of salmon and carp gonadotropin (GTH)-ir cells was detected. Isolated or clustered GTH-ir cells resided in both the dorsal and the ventral PPD and were seen surrounding the PI and in the tissue of the PPD covering the most rostral part of PI. In addition, a few scattered GTH-ir cells were observed in the ventral RPD. Scattered groups of thyrotropin (TSH)-ir cells were present in the anteroventral PPD. Salmon and seabream somatolactin (SL)-ir and bovine melanotropin (MSH)-ir cells were intermingled surrounding the neurohypophyseal tissue. SL-ir cells were negative to periodic acid-Schiff technique. MSH-ir cells showed a very weak immunoreactivity to anti-human ACTH((1-24)) serum. In addition to the PI location, few isolated or clustered SL- and MSH-ir cells were observed in the dorsal PPD.