Affordable and real-time antimicrobial resistance prediction from multimodal electronic health records.

The spread of antimicrobial resistance (AMR) leads to challenging complications and losses of human lives plus medical resources, with a high expectancy of deterioration in the future if the problem is not controlled. From a machine learning perspective, data-driven models could aid clinicians and microbiologists by anticipating the resistance beforehand. Our study serves as the first attempt to harness deep learning (DL) techniques and the multimodal data available in electronic health records (EHR) for predicting AMR. In this work, we utilize and preprocess the MIMIC-IV database extensively to produce separate structured input sources for time-invariant and time-series data customized to the AMR task. Then, a multimodality fusion approach merges the two modalities with clinical notes to determine resistance based on an antibiotic or a pathogen. To efficiently predict AMR, our approach builds the foundation for deploying multimodal DL techniques in clinical practice, leveraging the existing patient data.

Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text.

The increase in people's use of mobile messaging services has led to the spread of social engineering attacks like phishing, considering that spam text is one of the main factors in the dissemination of phishing attacks to steal sensitive data such as credit cards and passwords. In addition, rumors and incorrect medical information regarding the COVID-19 pandemic are widely shared on social media leading to people's fear and confusion. Thus, filtering spam content is vital to reduce risks and threats. Previous studies relied on machine learning and deep learning approaches for spam classification, but these approaches have two limitations. Machine learning models require manual feature engineering, whereas deep neural networks require a high computational cost. This paper introduces a dynamic deep ensemble model for spam detection that adjusts its complexity and extracts features automatically. The proposed model utilizes convolutional and pooling layers for feature extraction along with base classifiers such as random forests and extremely randomized trees for classifying texts into spam or legitimate ones. Moreover, the model employs ensemble learning procedures like boosting and bagging. As a result, the model achieved high precision, recall, f1-score and accuracy of 98.38%.

Bergamot oil as an integral component of nanostructured lipid carriers and a photosensitizer for photodynamic treatment of vitiligo: Characterization and clinical experimentation.

Background: Bergamot oil (BO) is a photosensitizer that can be used for photodynamic therapy (PDT) of dermatological diseases such as vitiligo. Being an oil, it can be integrated within the lipidic matrix of nanostructured lipid carriers (NLCs) as the liquid lipid constituent, hence exhibiting a dual role. Research design and methods: NLCs were prepared with different emulsifiers and coemulsifiers, and the effect of the preparation method and formulation variables on the NLCs' size was elucidated. The prepared NLCs were further characterized for their in vitro release, viscosity, thermal behavior, and in vitro photostability. Furthermore, a preclinical photodynamic study on animal skin was conducted, followed by clinical experimentation on patients with vitiligo. Results: Results showed that BO was successfully incorporated within the NLCs. The selected NLCs formulation was in the nanometer range with a gel consistency, and it provided sustained release of BO for 24 h. NLCs improved the photostability and photodynamic properties of BO, and displayed promising preclinical and clinical results for the topical PDT of vitiligo. Expert Opinion: BO containing NLCs was proven to be promising means for PDT of vitiligo, and can be further explored in other dermatological diseases.

Novel bergamot oil nanospanlastics combined with PUVB therapy as a clinically translatable approach for vitiligo treatment.

The impact of nanomedicine has grown in the current decade; however, only very few clinical translational attempts have been realized. Therefore in the present study, we hypothesized that bergamot oil, a psoralen-containing oil, would produce an optimized melanogenic effect in the clinical treatment of vitiligo when loaded within an elastic nanocarrier (spanlastics) and combined with PUVB for activation of psoralens. Spanlastics were prepared and characterized for particle size, physical stability, in vitro release, thermal behavior, deformability, morphology, and in vitro photostability. The efficacy of the selected formula was tested histopathologically on rat skin and clinically translated in patients suffering from vitiligo. Results revealed that the spanlastics were of reasonable nanosize, deformable, and provided sustained release of bergamot oil. The incorporation of bergamot oil within spanlastics improved its photostability and its photodynamic activity. Spanlastics exhibited promising clinical results in terms of extent and onset of repigmentation in vitiligo patients. Therefore, it can be concluded that spanlastics can be introduced as a promising nanotreatment modality for vitiligo.