A Machine Learning Model for Predicting Hospitalization in Patients with Respiratory Symptoms during the COVID-19 Pandemic.

A machine learning approach is a useful tool for risk-stratifying patients with respiratory symptoms during the COVID-19 pandemic, as it is still evolving. We aimed to verify the predictive capacity of a gradient boosting decision trees (XGboost) algorithm to select the most important predictors including clinical and demographic parameters in patients who sought medical support due to respiratory signs and symptoms (RAPID RISK COVID-19). A total of 7336 patients were enrolled in the study, including 6596 patients that did not require hospitalization and 740 that required hospitalization. We identified that patients with respiratory signs and symptoms, in particular, lower oxyhemoglobin saturation by pulse oximetry (SpO2) and higher respiratory rate, fever, higher heart rate, and lower levels of blood pressure, associated with age, male sex, and the underlying conditions of diabetes mellitus and hypertension, required hospitalization more often. The predictive model yielded a ROC curve with an area under the curve (AUC) of 0.9181 (95% CI, 0.9001 to 0.9361). In conclusion, our model had a high discriminatory value which enabled the identification of a clinical and demographic profile predictive, preventive, and personalized of COVID-19 severity symptoms.

Grau de quantidade de fala e intensidade vocal de teleoperadores em ambiente laboral e extralaboral / Talkativeness and vocal loudness in call center operators during labor and extra-labor situations

OBJETIVO: Investigar a autopercepção do grau de quantidade de fala e intensidade vocal de teleoperadores em ambiente laboral e extralaboral e comparar com autoavaliação vocal e análise perceptivo-auditiva da voz. MÉTODOS: Participaram 299 teleoperadores ativos e receptivos, de ambos os gêneros, com média de idade de 27,1 anos. Foi aplicado o "Teste de grau de quantidade de fala e grau de intensidade vocal" em duas situações de comunicação: voz laboral e extralaboral, além da realização de autoavaliação vocal e análise perceptivo-auditiva. RESULTADOS: No setor de telesserviços há um maior número de mulheres em relação ao número de homens, com média de idade de 27,1 anos. Em relação ao gênero, mulheres falam mais em ambiente laboral quando comparadas aos homens. Ao comparar quantidade de fala e intensidade de voz dentro e fora do trabalho, é observado maior uso e intensidade vocal no ambiente laboral. CONCLUSÃO: O teleoperador é um profissional da voz que relata falar mais e falar mais alto em situações de trabalho. Mulheres dessa categoria profissional falam mais que homens em qualquer uma das situações avaliadas. Não se observou correlação entre quantidade de fala, intensidade de voz e autoavaliação da voz.

PURPOSE: To investigate self-perceived talkativeness and vocal loudness in call center operators during labor and extra-labor situations and compare it with vocal self-assessment and perceptual analysis. METHODS: Participants were 299 male and female call center operators working in an inbound and outbound mode. Their average age was 27.1 years. The procedures were as follows: Talkativeness and Vocal Loudness Test in two situations of communication - work and extra-work; vocal self-assessment and perceptual analysis. RESULTS: There are more women than men working in telemarketing. Regarding gender, women talk more in the work situation when compared to men. By comparing talkativeness and vocal loudness in work and extra-work situations, increased talkativeness and vocal loudness were observed in the work environment. CONCLUSION: The call center operator is a voice professional that reports speaking more and more loudly in work situations. Women talk more than men in any of the situations evaluated. There was no significant correlation between talkativeness, vocal loudness and self-assessment of voice.