RESUMEN
Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has emerged as a plausible diagnostic site for AD detection owing to its anatomical connection with the brain. However, existing AI models for this purpose have yet to provide a rational explanation behind their decisions and have not been able to infer the stage of the disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granu la ̲ r Neuron-le v ̲ el Expl a ̲ iner (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to directly assess the continuum of AD from the retinal imaging without the need for longitudinal or clinical evaluations. This innovative approach aims to validate retinal vasculature as a biomarker and diagnostic modality for evaluating Alzheimer's Disease. Leveraged UK Biobank cognitive tests and vascular morphological features demonstrate significant promise and effectiveness of LAVA in identifying AD stages across the progression continuum.
Asunto(s)
Enfermedad de Alzheimer , Enfermedades Neurodegenerativas , Humanos , Enfermedad de Alzheimer/diagnóstico por imagen , Fondo de Ojo , Retina/diagnóstico por imagen , Neuronas , Imagen por Resonancia MagnéticaRESUMEN
Parkinson's disease is the world's fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson's disease and automate diagnostics would greatly improve the treatment of patients with Parkinson's disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson's disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson's disease from UK Biobank fundus imaging. Our results suggest Parkinson's disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson's disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations.
Asunto(s)
Aprendizaje Profundo , Enfermedad de Parkinson , Humanos , Enfermedad de Parkinson/diagnóstico por imagen , Enfermedad de Parkinson/epidemiología , Biobanco del Reino Unido , Bancos de Muestras Biológicas , Fondo de OjoRESUMEN
In the original publication [...].
RESUMEN
Antibiotic growth promoters (AGPs) suppress the growth of infectious pathogens. These pathogens negatively impact agricultural production worldwide and often cause health problems if left untreated. Here, we evaluate six Bacillus strains (BPR-11, BPR-12, BPR-13, BPR-14, BPR-16 and BPR-17), which are known for their ability to survive harsh environmental conditions, as AGP replacements in animal feed. Four of these Bacillus strains (BPR-11, BPR-14, BPR-16 and BPR-17) showed antimicrobial activity against the pathogenic strains Clostridium perfringens, Escherichia coli and Staphylococcus aureus at 25 µg/mL, with BPR-16 and BPR-17 also able to inhibit Pseudomonas aeruginosa and Salmonella enterica at 100 µg/mL. Further chemical investigation of BPR-17 led to the identification of eight metabolites, namely C16, C15, C14 and C13 surfactin C (1-4), maculosin (5), maculosine 2 (6), genistein (7) and daidzein (8). Purified compounds (1-4) were able to inhibit all the tested pathogens with MIC values ranging from 6.25 to 50 µg/mL. Maculosin (5) and maculosine 2 (6) inhibited C. perfringens, E. coli and S. aureus with an MIC of 25 µg/mL while genistein (7) and daidzein (8) showed no activity. An animal trial involving feeding BPR-11, BPR-16 and BPR-17 to a laboratory poultry model led to an increase in animal growth, and a decrease in feed conversion ratio and mortality. The presence of surfactin C analogues (3-4) in the gut following feeding with probiotics was confirmed using an LC-MS analysis. The investigation of these Bacillus probiotics, their metabolites, their impacts on animal performance indicators and their presence in the gastrointestinal system illustrates that these probiotics are effective alternatives to AGPs.
RESUMEN
The agricultural industry utilizes antibiotic growth promoters to promote livestock growth and health. However, the World Health Organization has raised concerns over the ongoing spread of antibiotic resistance transmission in the populace, leading to its subsequent ban in several countries, especially in the European Union. These restrictions have translated into an increase in pathogenic outbreaks in the agricultural industry, highlighting the need for an economically viable, non-toxic, and renewable alternative to antibiotics in livestock. Probiotics inhibit pathogen growth, promote a beneficial microbiota, regulate the immune response of its host, enhance feed conversion to nutrients, and form biofilms that block further infection. Commonly used lactic acid bacteria probiotics are vulnerable to the harsh conditions of the upper gastrointestinal system, leading to novel research using spore-forming bacteria from the genus Bacillus. However, the exact mechanisms behind Bacillus probiotics remain unexplored. This review tackles this issue, by reporting antimicrobial compounds produced from Bacillus strains, their proposed mechanisms of action, and any gaps in the mechanism studies of these compounds. Lastly, this paper explores omics approaches to clarify the mechanisms behind Bacillus probiotics.