Machine Learning Approaches to Analyzing Adverse Events Following Durable LVAD Implantation.

BACKGROUND: This study employed machine learning approaches to analyze sequences of adverse events (AEs) after left ventricular assist device (LVAD) implantation. METHODS: Data on patients implanted with the HeartWare HVAD durable LVAD were extracted from the ENDURANCE and ENDURANCE Supplemental clinical trials, with follow-up through 5 years. Major AEs included device malfunction, major bleeding, major infection, neurological dysfunction, renal dysfunction, respiratory dysfunction, and right heart failure (RHF). Time interval and transition probability analyses were performed. We created a Sankey diagram to visualize transitions between AEs. Hierarchical clustering was applied to dissimilarity matrices based on the longest common subsequence to identify clusters of patients with similar AE profiles. RESULTS: A total of 568 patients underwent HVAD implantation with 3590 AEs. Bleeding and RHF comprised the highest proportion of early AEs after surgery whereas infection and bleeding accounted for most AEs occurring after 3 months. The highest transition probabilities were observed with infection to infection (0.34), bleeding to bleeding (0.31), RHF to bleeding (0.31), RHF to infection (0.28), and bleeding to infection (0.26). Five distinct clusters of patients were generated, each with different patterns of time intervals between AEs, transition rates between AEs, and clinical outcomes. CONCLUSIONS: Machine learning approaches allow for improved visualization and understanding of AE burden after LVAD implantation. Distinct patterns and relationships provide insights that may be important for quality improvement efforts.

Facile fabrication of mechanochromic-responsive colloidal crystal films.

This paper presents a simple approach to fabricate a reversible mechanochromic-responsive crystal film based on the room-temperature film-formation of monodisperse polymer latex by the aid of nanosilica particles. In this approach, when the "soft" colloidal polymer spheres were blended with colloidal silica particles and then cast on a substrate, followed by drying at room temperature for self-assembly, an elastic crystal film was directly obtained. This crystal film has not only reversible and repeatable mechanochromic-responsive property, but also tunable color and peak position covering almost entire visible spectral region, depending upon the sizes of polymer spheres and strains. This optical response is attributed to the variation of lattice spacing during deformation.

Synthesis and characterization of poly(N-isopropylacrylamide)/silica composite microspheres via inverse pickering suspension polymerization.

In this paper, stable poly (N-isopropylacrylamide)/silica composite microspheres are successfully synthesized via inverse Pickering suspension polymerization using various sizes of silica particles as stabilizers. The droplets of N-isopropylacrylamide aqueous solution were first dispersed in toluene and stabilized by silica particles, and then polymerized to obtain poly (N-isopropylacrylamide)/silica composite microspheres. Preliminary studies show that these PNIPAm/silica composite microspheres have similar thermal-responsive behavior as pure microgels with the LCST of 32 degrees C. The releasing property of the composite microspheres can be either controlled by the particle size of the silica or the temperature.