Machine Learning for Hypertension Prediction: a Systematic Review.

PURPOSE OF REVIEW: To provide an overview of the literature regarding the use of machine learning algorithms to predict hypertension. A systematic review was performed to select recent articles on the subject. RECENT FINDINGS: The screening of the articles was conducted using a machine learning algorithm (ASReview). A total of 21 articles published between January 2018 and May 2021 were identified and compared according to variable selection, train-test split, data balancing, outcome definition, final algorithm, and performance metrics. Overall, the articles achieved an area under the ROC curve (AUROC) between 0.766 and 1.00. The algorithms most frequently identified as having the best performance were support vector machines (SVM), extreme gradient boosting (XGBoost), and random forest. Machine learning algorithms are a promising tool to improve preventive clinical decisions and targeted public health policies for hypertension. However, technical factors such as outcome definition, availability of the final code, predictive performance, explainability, and data leakage need to be consistently and critically evaluated.

Lippia gracilis essential oil in ß-cyclodextrin inclusion complexes: an environmentally safe formulation to control Aedes aegypti larvae.

BACKGROUND: One of the most efficient ways to prevent arboviruses, such as dengue fever, yellow fever, chikungunya and Zika, is by controlling their vector, the Aedes aegypti. Because this vector is becoming resistant to most larvicides used, the development of new larvicides should be considered. ß-Cyclodextrin (ß-CD) complexes have been investigated as an interesting way of enabling the use of essential oils in water as larvicides. This study comprised the development of Lippia gracilis essential oil (LGEO) and ß-CD inclusion complexes for control of Ae. aegypti. RESULTS: Thermal analysis clearly showed the formation of complexes using kneading and co-evaporation methods. Gas chromatography analysis showed that kneading without co-solvent (KW) gave the highest content (∼ 15%) of the LGEO major component. Moreover, KW showed that the complex had a 50% lethal concentration (LC50 ; 33 ppm) lower than that of pure LGEO (39 ppm); in other words, complexing LGEO with ß-CD improved the larvicidal activity. In addition, LGEO complexed with ß-CD (KW) was not harmful to non-target organisms at the concentrations needed to control Ae. aegypti larvae. CONCLUSION: The inclusion complex with LGEO was a feasible formulation, being economically viable, easy-to-apply and without impact on non-target organisms and, therefore, is a potential alternative larvicide for Ae. aegypti control. © 2018 Society of Chemical Industry.

ß-caryophyllene, a dietary cannabinoid, complexed with ß-cyclodextrin produced anti-hyperalgesic effect involving the inhibition of Fos expression in superficial dorsal horn.

AIMS: Evaluate the anti-hyperalgesic effect of the complex containing ß-caryophyllene (ßCP) and ß-cyclodextrin (ßCD) in a non-inflammatory chronic muscle pain mice model and investigated its action on superficial dorsal horn of the lumbar spinal cord. MAIN METHODS: The ßCP-ßCD complex were prepared and characterized through the DSC, TG/DTG, FTIR, XRD and SEM. The model of chronic muscle pain was induced by two injections of pH4.0 saline (20µL) into left gastrocnemius 5days apart. After confirming hyperalgesia, male mice were treated with ßCP-ßCD (10 or 20mg/kg; p.o.) or vehicle (saline 0.9%, p.o.) daily for 9days. 1h after, the mechanical hyperalgesia, muscle withdrawal thresholds and motor performance were evaluated. To evaluate the ßCP-ßCD action on spinal cord, animals induced with chronic muscle pain were treated with ßCP-ßCD (20mg/kg; p.o.) or vehicle (saline 0.9%, p.o.) and 90min. after, were perfused, the lumbar spinal cord collected, crioprotected, cut and submitted in an immunofluorescence protocol for Fos protein. KEY FINDINGS: The characterization tests indicated that ßCP were efficiently incorporated into ßCD. The oral treatment with ßCP-ßCD, at all doses tested, produced a significant (p<0.05) reduction on mechanical hyperalgesia and a significant (p<0.05) increase in muscle withdrawal thresholds, without produce any alteration in force. In addition, ßCP-ßCD was able to significantly (p<0.05) decrease Fos expression in the superficial dorsal horn. SIGNIFICANCE: Thus, ßCP-ßCD attenuates the non-inflammatory chronic muscle pain in mice and inhibits the Fos expression in the lumbar spinal cord.

Physicochemical characterization and analgesic effect of inclusion complexes of essential oil from Hyptis pectinata L. Poit leaves with ß-cyclodextrin.

The formation of inclusion complexes of Hyptis pectinata essential oil (EOHP), with potent activities such as anti-nociceptive, anti-inflammatory, among others, with ß -cyclodextrin (ß-CD), was obtained by slurry (SC) and paste procedures (PC). The gas chromatography coupled to the mass spectrometry (GC/MS) analysis demonstrated a total of 36.4% monoterpenes and 63.6% sesquiterpenes in the EOHP. The major components of EOHP were identified as (E)- caryophyllene (54.07%). The analysis of samples (PM, PC and SC) by GC/MS involved the surface and the total extracted oils. The GC/MS results suggested important differences between in SC and PC methods indicating the complexation of mono and sesquiterpenoids in different ratios. Furthermore, the thermal analysis techniques suggests the complexation, especially in SC, which show a thermogravimetry/derivative thermogravimetry (TG/DTG) peak at 140-270ºC, probably related to oil loss. Scanning electron microscopy (SEM) images showed reduction size of the samples mainly in the SC product. Additionally, EOHP/ ß-CD improves pharmacological profile of EOHP alone in formalin-induced pain protocol in mice.