A Multimodal Approach for the Risk Prediction of Intensive Care and Mortality in Patients with COVID-19

Background: Although several studies have been launched towards the prediction of risk factors for mortality and admission in the intensive care unit (ICU) in COVID-19, none of them focuses on the development of explainable AI models to define an ICU scoring index using dynamically associated biological markers. Methods: We propose a multimodal approach which combines explainable AI models with dynamic modeling methods to shed light into the clinical features of COVID-19. Dynamic Bayesian networks were used to seek associations among cytokines across four time intervals after hospitalization. Explainable gradient boosting trees were trained to predict the risk for ICU admission and mortality towards the development of an ICU scoring index. Results: Our results highlight LDH, IL-6, IL-8, Cr, number of monocytes, lymphocyte count, TNF as risk predictors for ICU admission and survival along with LDH, age, CRP, Cr, WBC, lymphocyte count for mortality in the ICU, with prediction accuracy 0.79 and 0.81, respectively. These risk factors were combined with dynamically associated biological markers to develop an ICU scoring index with accuracy 0.9. Conclusions: to our knowledge, this is the first multimodal and explainable AI model which quantifies the risk of intensive care with accuracy up to 0.9 across multiple timepoints.

The Effectiveness of Lumbricus rubellus Extract Toward Interleukin-10 and Immunoglobulin E and Atopic Dermatitis Scoring Index (SCORAD)

BACKGROUND: Atopic dermatitis (AD) is a chronic inflammatory skin condition characterized by severe pruritic symptoms and chronic AD related to clinical features in form of lichenification associated with a history of atopic disease both for himself and family. AIM: This study aims to determine the effectiveness of using earthworm extract (Lumbricus rubellus) to increase interleukin (IL)-10 and decrease immunoglobulin E (IgE), and to describe the AD (SCORAD) scoring index of patients with AD. METHODS: This research used quantitative with quasi experiment method. The data were analyzed using SPSS v19 program. To determine the basic characteristics of numerical variables, the mean standard deviation is functioned if the data distribution amount is even, if it is not, it used the median. Meanwhile, to observe the relationship between L. rubellus extract and IgE, Mann-Whitney test analysis (U-Test) was used. RESULTS: The results of this study indicate that the administration of L. rubellus extract showed a changes and differences before and after being involved with the extract. IgE levels between ERL and no ERL groups had differences (p < 0.05), however on day 15 both groups did not show any differences. Meanwhile, the SCORAD index indicated that the influence of lumbricus rebellus extract has an effect on low number of AD patients. CONCLUSION: It can be concluded that the administration of L. rubellus extract in patients with AD is quite effective.

Machine Learning to Predict the Progression of Bone Mass Loss Associated with Personal Characteristics and a Metabolic Syndrome Scoring Index

A relationship exists between metabolic syndrome (MetS) and human bone health; however, whether the combination of demographic, lifestyle, and socioeconomic factors that are associated with MetS development also simultaneously affects bone density remains unclear. Using a machine learning approach, the current study aimed to estimate the usefulness of predicting bone mass loss using these potentially related factors. The present study included a sample of 23,497 adults who routinely visited a health screening center at a large health center at least once during each of three 3-year stages (i.e., 2006–2008, 2009–2011, and 2012–2014). The demographic, socioeconomic, lifestyle characteristics, body mass index (BMI), and MetS scoring index recorded during the first 3-year stage were used to predict the subsequent occurrence of osteopenia using a non-concurrence design. A concurrent prediction was also performed using the features recorded from the same 3-year stage as the predicted outcome. Machine learning algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were applied to build predictive models using a unique feature set. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score were used to evaluate the predictive performances of the models. The XGBoost model presented the best predictive performance among the non-concurrence models. This study suggests that the ensemble learning model with a MetS severity score can be used to predict the progression of osteopenia. The inclusion of an individual’s features into a predictive model over time is suggested for future studies.

A non-inferiority randomized controlled clinical trial comparing Unani formulations & PUVAsol in non-segmental vitiligo

Objectives Greco-Arab medicine is an ancient system of medicine with greater treasure on therapeutics of vitiligo. The trial Unani formulations have not been scientifically explored for their safety and efficacy, but have been repeatedly prescribed by the great Unani physicians in the management of Baraṣ (vitiligo). Hence, these interventions were selected for the trial. Methods In this randomized, controlled, open-label clinical trial, 82 participants with non-segmental vitiligo aged 18–40 years were block randomized to either receive Unani interventions or control for 16 weeks. Out of 82 participants, 42 were randomized to the Unani group and 40 were randomized to the control group. The primary outcome measure was change in vitiligo area scoring index (VASI), which was assessed on weeks 4, 8, 12 and 16. The secondary outcome measures included the patient’s global assessment on VAS and investigator’s global assessment based on photographic evaluation at baseline and after the treatment. Safety parameters included hemogram, LFTs, RFTs, CXR, ECG, urine, and stool examinations, which were evaluated at baseline and after the treatment. Results The per-protocol analysis was done on 30 participants in each group and the response in Unani group was not inferior to those receiving control group. The mean ± SD of vitiligo area scoring index (VASI) decreased from 4.09 ± 2.87 and 5.50 ± 5.73 at baseline to 3.13 ± 2.20 and 4.29 ± 4.95 at the end of the trial in both the Unani and control groups respectively. Conclusions The study inferred that both the interventions are equally effective and well-tolerated in patients with non-segmental vitiligo.

Recursive Genetic Micro-Aggregation Technique: Information Loss, Disclosure Risk and Scoring Index

This research investigates the micro-aggregation problem in secure statistical databases by integrating the divide and conquer concept with a genetic algorithm. This is achieved by recursively dividing a micro-data set into two subsets based on the proximity distance similarity. On each subset the genetic operation “crossover” is performed until the convergence condition is satisfied. The recursion will be terminated if the size of the generated subset is satisfied. Eventually, the genetic operation “mutation” will be performed over all generated subsets that satisfied the variable group size constraint in order to maximize the objective function. Experimentally, the proposed micro-aggregation technique was applied to recommended real-life data sets. Results demonstrated a remarkable reduction in the computational time, which sometimes exceeded 70% compared to the state-of-the-art. Furthermore, a good equilibrium value of the Scoring Index (SI) was achieved by involving a linear combination of the General Information Loss (GIL) and the General Disclosure Risk (GDR).

GASTROPROTECTIVE ACTIVITY OF EQUISETUM HYEMALE IN EXPERIMENTAL GASTRIC ULCER RAT MODELS

Equisetum hyemale is traditionally used for dyspepsia and stomach pain. The aim of the present study was to evaluate the gastroprotective activity of the aqueous ethanolic extract of the aerial parts of Equisetum hyemale in gastric ulcer rat models. Gastric ulcer models were induced by ethanol (5 mL/kg bw), acetylsalicylic acid (ASA) (200 mg/kg bw) and pylorus ligation separately. The pH, total acidity, ulcer scoring index and histopathological evaluation were performed. Oral administration of Equisetum hyemale extract (250 and 500 mg/kg bw) significantly reduced the development of gastric lesions in all gastric ulcer models. The pH, total acidity and ulcer scoring index also decreased significantly when compared with the Diseased control group. Histopathological studies are in good agreement with the biochemical findings. Equisetum hyemale might show its gastroprotective activity by decreasing oxidative damage, blockage of H2 receptors activation, increase prostaglandins secretion and formation of mucus layer in different gastric ulcer models. The findings of the present study validate the traditional use of Equisetum hyemale to treat stomach pain, however the determination of phytochemical compounds responsible for gastroprotective activity is required for further confirmation.