Hybrid-based framework for COVID-19 prediction via federated machine learning models.

The COronaVIrus Disease 2019 (COVID-19) pandemic is unfortunately highly transmissible across the people. In order to detect and track the suspected COVID-19 infected people and consequently limit the pandemic spread, this paper entails a framework integrating the machine learning (ML), cloud, fog, and Internet of Things (IoT) technologies to propose a novel smart COVID-19 disease monitoring and prognosis system. The proposal leverages the IoT devices that collect streaming data from both medical (e.g., X-ray machine, lung ultrasound machine, etc.) and non-medical (e.g., bracelet, smartwatch, etc.) devices. Moreover, the proposed hybrid fog-cloud framework provides two kinds of federated ML as a service (federated MLaaS); (i) the distributed batch MLaaS that is implemented on the cloud environment for a long-term decision-making, and (ii) the distributed stream MLaaS, which is installed into a hybrid fog-cloud environment for a short-term decision-making. The stream MLaaS uses a shared federated prediction model stored into the cloud, whereas the real-time symptom data processing and COVID-19 prediction are done into the fog. The federated ML models are determined after evaluating a set of both batch and stream ML algorithms from the Python's libraries. The evaluation considers both the quantitative (i.e., performance in terms of accuracy, precision, root mean squared error, and F1 score) and qualitative (i.e., quality of service in terms of server latency, response time, and network latency) metrics to assess these algorithms. This evaluation shows that the stream ML algorithms have the potential to be integrated into the COVID-19 prognosis allowing the early predictions of the suspected COVID-19 cases.

Lack of association between C3123A polymorphism of the angiotensin II type 2 receptor gene and hypertension in Tunisian population.

BACKGROUND: Hypertension is a polygenic disease. Various singlenucleotide gene polymorphisms of renin angiotensin system have been explored in hypertension. Angiotensin II, the major biologically active component of this system, exerts its effect via two pharmacologically distinct subtypes of angiotensin II receptors, the angiotensin II type 1 receptor and the angiotensin II type 2 receptor. AIM: To examine whether the 3123 C/A polymorphism of angiotensin II type 2 receptor gene is involved in hypertension in a sample of Tunisian population. METHODS: Atotal of 403 normotensive subjects and 382 hypertensive patients were included in the study. Genotyping was performed by polymerase chain reaction followed by Alu I restriction digestion. RESULTS: The frequency of "A" genotype was not significantly different between the two groups in men (¯2=1.18; p=0.16). The estimated odds prevalence for hypertension ("A" versus "C") was 0.77 (95% CI 0.49 to 1.22, p=0.27). After adjustment for confounding factors, the OR for hypertension remained no significant (OR: 1.49, 95% CI: 0.84-2.63, p=0.16). In women, genotype distributions for C3123A variant in hypertensive patients were not significantly different from normotensive subjects (¯2=3.16; p=0.20). Multiple logistic regression analysis showed that the AA genotype was not significantly associated with hypertension (OR: 1.09, 95% CI: 0.58-2.06, p=0.77). CONCLUSION: In the present study, we showed that the 3123 C/A polymorphism of AGT2R gene is not a significant factor for hypertension in a sample of Tunisian population.

Plasma homocysteine in schizophrenia: determinants and clinical correlations in Tunisian patients free from antipsychotics.

The existence of association between hyperhomocysteinaemia (HHC) and schizophrenia has been suggested by several recent studies. This study aimed to determine the prevalence of HHC and its main determinants, and sought a correlation with clinical features in Tunisian patients with schizophrenia. Plasma homocysteine (Hcy), folate, and vitamin B12, as well as the C677T methylene tetrahydrofolate reductase (MTHFR) polymorphism, were studied in 33 patients with schizophrenia, all free from antipsychotic treatment, and 35 age- and smoking-habit-matched healthy subjects as controls. Biochemical determinations and psychometric evaluations were carried out in patients before the administration of antipsychotics. The prevalence of HHC was higher and plasma B12 vitamin was significantly lower in patients. There was no significant difference in genotypic distribution and allelic frequency of the C677T MTHFR polymorphism between groups. Hcy was significantly correlated to the 'anhedonia-asociality' subscales of the Scale for the Assessment of Negative Symptoms (SANS). This study showed an association between HHC and schizophrenia, especially with the negative symptoms of the disease. In the Tunisian population, HHC in schizophrenia seems to be linked to vitamin B12 deficiency, likely caused by a lack of dietary animal proteins.