Clinical applications of machine learning in the diagnosis, classification, and prediction of heart failure.

Machine learning and artificial intelligence are generating significant attention in the scientific community and media. Such algorithms have great potential in medicine for personalizing and improving patient care, including in the diagnosis and management of heart failure. Many physicians are familiar with these terms and the excitement surrounding them, but many are unfamiliar with the basics of these algorithms and how they are applied to medicine. Within heart failure research, current applications of machine learning include creating new approaches to diagnosis, classifying patients into novel phenotypic groups, and improving prediction capabilities. In this paper, we provide an overview of machine learning targeted for the practicing clinician and evaluate current applications of machine learning in the diagnosis, classification, and prediction of heart failure.

Permanganate-based synthesis of manganese oxide nanoparticles in ferritin.

This paper investigates the comproportionation reaction of MnII with [Formula: see text] as a route for manganese oxide nanoparticle synthesis in the protein ferritin. We report that [Formula: see text] serves as the electron acceptor and reacts with MnII in the presence of apoferritin to form manganese oxide cores inside the protein shell. Manganese loading into ferritin was studied under acidic, neutral, and basic conditions and the ratios of MnII and permanganate were varied at each pH. The manganese-containing ferritin samples were characterized by transmission electron microscopy, UV/Vis absorption, and by measuring the band gap energies for each sample. Manganese cores were deposited inside ferritin under both the acidic and basic conditions. All resulting manganese ferritin samples were found to be indirect band gap materials with band gap energies ranging from 1.01 to 1.34 eV. An increased UV/Vis absorption around 370 nm was observed for samples formed under acidic conditions, suggestive of MnO2 formation inside ferritin.

Tuning Ferritin's band gap through mixed metal oxide nanoparticle formation.

This study uses the formation of a mixed metal oxide inside ferritin to tune the band gap energy of the ferritin mineral. The mixed metal oxide is composed of both Co and Mn, and is formed by reacting aqueous Co2+ with [Formula: see text] in the presence of apoferritin. Altering the ratio between the two reactants allowed for controlled tuning of the band gap energies. All minerals formed were indirect band gap materials, with indirect band gap energies ranging from 0.52 to 1.30 eV. The direct transitions were also measured, with energy values ranging from 2.71 to 3.11 eV. Tuning the band gap energies of these samples changes the wavelengths absorbed by each mineral, increasing ferritin's potential in solar-energy harvesting. Additionally, the success of using [Formula: see text] in ferritin mineral formation opens the possibility for new mixed metal oxide cores inside ferritin.