Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add filters

Language
Year range
1.
EuropePMC; 2022.
Preprint in English | EuropePMC | ID: ppcovidwho-334275

ABSTRACT

Beyond the health consequences, coronavirus disease 2019 (COVID-19) has shown the inadequacies and limitations of healthcare systems all over the world. Predictions of good and bad outcomes could improve lockdown and curfew policies and reduce the COVID-19 health impact. We describe a multimodal machine learning (ML) approach for predicting early hospital discharge and other key clinical outcomes, such as respiratory worsening, intensive care unit admission or the need for rescue therapy. Using this model, our hospital occupancy could have decreased by about 50% during the first wave of the pandemic. Our model used both raw laboratory results (LR) and electronic health records (EHR), which allow better anticipation of worsening through selective reporting of LRs. Our approach could be a useful, customizable, and adaptable hospital resource management tool, especially to assist in interventions targeted at reducing COVID-19 infection rates.

2.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-319361

ABSTRACT

Beyond health consequences, coronavirus disease 2019 (COVID19) has shown inadequacies and limitations of healthcare systems all over the world. Predictions of good and bad outcomes might improve lockdown and curfew policies and reduce the COVID19 health impact. We describe a multimodal machine learning (ML) approach through which we predict early hospital discharge and other key clinical outcomes as respiratory worsening, intensive care unit admission or the need of rescue therapy. Using this model, our hospital occupation might have decreased around 50% during the first wave of the pandemic. Our model used both, raw laboratory results (LR) and electronic health records (EHR), which allow a better anticipation of worsening through selective reporting of LRs. Thus, EHR models can be considered as a human preprocessing enhancing ML classification. Our approach may be a useful, customizable, and adaptable hospital resource management tool, especially to help interventions targeted at lowering COVID19 infection rates.

3.
Epilepsy Behav ; 125: 108379, 2021 12.
Article in English | MEDLINE | ID: covidwho-1458792

ABSTRACT

BACKGROUND: To assess the prevalence, severity, and mortality of COVID-19 in people with epilepsy (PWE) and evaluate seizure control in PWE during and after COVID-19. METHODS: Retrospective, observational, multicenter study conducted in 14 hospitals. Medical records of randomly selected PWE followed at neurology outpatient clinics were reviewed. Proportion of PWE with a positive test for SARS-CoV-2 during 2020 was calculated. Risk factors associated with COVID-19 and its morbimortality were evaluated. RESULTS: 2751 PWE were included, mean age 48.8 years (18-99), 72.4% had focal epilepsy, and 35% were drug-refractory. COVID-19 prevalence in PWE was 5.53%, while in the Spanish population was 4.26%. Proportion of admissions to hospital, ICU, and deaths in PWE were 17.1%, 2%, and 4.61% of COVID-19 cases, while in Spanish population were 10.81%, 0.95%, and 2.57%, respectively. A severe form of COVID-19 occurred in 11.8%; dyslipidemia, institutionalization at long-term care facilities, intellectual disability, and older age were associated risk factors. Older age, hypertension, dyslipidemia, cardiac disease, and institutionalization were associated with mortality from COVID-19. Seizure control was stable in 90.1% of PWE during acute COVID-19, while 8.6% reported an increase in seizure frequency. During post-COVID-19 follow-up, 4.6% reported seizure control worsening. CONCLUSIONS: COVID-19 was moderately prevalent in PWE. One out of 5 patients required medical attention and 4.6% died due to COVID-19. Older age, dyslipidemia, institutionalization, and intellectual disability were significant risk factors associated with severe COVID-19. Seizure control remained stable during COVID-19 and throughout long-term follow-up in most PWE who contracted the infection.


Subject(s)
COVID-19 , Epilepsy , Aged , Epilepsy/epidemiology , Humans , Middle Aged , Prevalence , Retrospective Studies , SARS-CoV-2
SELECTION OF CITATIONS
SEARCH DETAIL