Comparison and use of explainable machine learning-based survival models for heart failure patients.

Objective: Explainable machine learning (XAI) was introduced in this study to improve the interpretability, explainability and transparency of the modelling results. The survex package in R was used to interpret and compare two survival models - the Cox proportional hazards regression (coxph) model and the random survival forest (rfsrc) model - and to estimate overall survival (OS) and its determinants in heart failure (HF) patients using these models. Methods: We selected 1159 HF patients hospitalised at the First Affiliated Hospital of Kunming Medical University. First, the performance of the two models was investigated using the C-index, the integrated C/D AUC, and the integrated Brier score. Second, a global explanation of the whole cohort was carried out using the time-dependent variable importance and the partial dependence survival profile. Finally, the SurvSHAP(t) and SurvLIME plots and the ceteris paribus survival profile were used to obtain a local explanation for each patient. Results: By comparing the C-index, the C/D AUC, and the Brier score, this study showed that the model performance of rfsrc was better than coxph. The global explanation of the whole cohort suggests that the C-reactive protein, lg BNP (brain natriuretic peptide), estimated glomerular filtration rate, albumin, age and blood chloride were significant unfavourable predictors of OS in HF patients in both the cxoph and the rfsrc models. By including individual patients in the model, we can provide a local explanation for each patient, which guides the clinician in individualising the patient's treatment. Conclusion: By comparison, we conclude that the model performance of rfsrc is better than that of coxph. These two predictive models, which address not only the whole population but also selected patients, can help clinicians personalise the treatment of each HF patient according to his or her specific situation.

Through-polymer, via technology-enabled, flexible, lightweight, and integrated devices for implantable neural probes.

In implantable electrophysiological recording systems, the headstage typically comprises neural probes that interface with brain tissue and integrated circuit chips for signal processing. While advancements in MEMS and CMOS technology have significantly improved these components, their interconnection still relies on conventional printed circuit boards and sophisticated adapters. This conventional approach adds considerable weight and volume to the package, especially for high channel count systems. To address this issue, we developed a through-polymer via (TPV) method inspired by the through-silicon via (TSV) technique in advanced three-dimensional packaging. This innovation enables the vertical integration of flexible probes, amplifier chips, and PCBs, realizing a flexible, lightweight, and integrated device (FLID). The total weight of the FLIDis only 25% that of its conventional counterparts relying on adapters, which significantly increased the activity levels of animals wearing the FLIDs to nearly match the levels of control animals without implants. Furthermore, by incorporating a platinum-iridium alloy as the top layer material for electrical contact, the FLID realizes exceptional electrical performance, enabling in vivo measurements of both local field potentials and individual neuron action potentials. These findings showcase the potential of FLIDs in scaling up implantable neural recording systems and mark a significant advancement in the field of neurotechnology.

Oxygen Vacancy Engineering of Titania-Induced by Sr2+ Dopants for Visible-Light-Driven Hydrogen Evolution.

A Sr2+-doping strategy is developed to engineer rich oxygen vacancies in porous titania for boosting visible-light-driven photocatalytic activity. The incorporation of strontium, with a larger atom radius than titanium, leads to the release of a lattice oxygen atom in the titania, causing the generation of an oxygen vacancy. The optimal Sr2+-doped titania sample with rich oxygen vacancies achieves a photocatalytic hydrogen production rate as high as 1092 µmol h-1 g-1, which is 4 and 16 times higher than the unmodified titania with less oxygen vacancies and the bench-marked P25, respectively.

Vinylene-Bridged Two-Dimensional Covalent Organic Frameworks via Knoevenagel Condensation of Tricyanomesitylene.

Vinylene-bridged covalent organic frameworks (COFs) have shown great potential for advanced applications because of their high chemical stability and intriguing semiconducting properties. Exploring new functional monomers available for the reticulation of vinylene-bridged COFs and establishing effective reaction conditions are extremely desired for enlarging the realm of this kind of material. In this work, a series of vinylene-bridged two-dimensional (2D) COFs are synthesized by Knoevenagel condensation of tricyanomesitylene with ditopic or tritopic aromatic aldehydes. With use of appropriate secondary amines as catalysts, high-crystalline vinylene-bridged COFs were achieved, exhibiting long-range ordered structures, well-defined nanochannels, high surface areas (up to 1231 m2 g-1), and excellent photophysical properties. Under a low loading amount and short reaction time, they enable aerobic photocatalytic transformation of arylboronic acids to phenols with high efficiency and excellent recyclability. This work demonstrates a new functional monomer, tricyanomesitylene, feasible for the general synthesis of vinylene-bridged COFs with potential application in photocatalytic organic transformation, which instigates further research on such kind of material.

The influence of structural isomerism on fluorescence and organic dye selective adsorption in two complexes based on flexible ligands.

Based on Cd(NO3)2·4H2O and 4,4'-((5-carboxy-1,3-phenylene)bis(oxy))dibenzoic acid (H3cpbda), two isomeric coordination polymers, {[Cd1.5(cpbda)(bpa)(H2O)2]·1.5H2O}n (1), [Cd(H2cpbda)2(bpa)0.5(H2O)]n (2), were synthesized by using different solvent-systems. The complexes were characterized by single-crystal X-ray diffraction, IR spectroscopy, powder X-ray diffraction, and thermogravimetric analysis. Owing to the obvious structural difference between the two isomeric complexes, the further fluorescence sensing and dye selection and adsorption were investigated. The 3D tight stacking structure of 1 strengthened the fluorescence emission and the loose 2D layer structure of 2 generated the active selection and adsorption of the Malachite Green Oxalate (MGO) dye.

[New dammarane type triterpene with cyclization at the side chain from oxidative alkaline-degradation products of PQS].

To study the oxidative alkaline-degradation products of PQS (Panax quinquefolium saponin), two compounds were isolated from the crude product of oxidative alkaline-degradation by silica gel column chromatography, Sephadex LH-20 column chromatography and recrystallized methods. On the basis of spectroscopic analysis, their structures were established as (12R, 20S, 24R)-20, 24; 12, 24-diepoxy-24-deisopropyl-dammarane-3beta-ol (1) and (20S, 24R)-20, 24-epoxydammarane-3beta3, 12beta, 25-triol (2). Compounds 1 and 2, dammarane type triterpene with cyclization at the side chain, were obtained for the first time from alkaline-degradation products of total ginsenosides of Panax quinquefolium L., compound 1 is a new compound.

A new coumarin glycoside from the husks of Xanthoceras sorbifolia.

From the husks of Xanthoceras sorbifolia, a new coumarin glycoside, isofraxetin-6-O-beta-D-glucopyranoside (1), was isolated. The structure was established on the basis of spectroscopic methods.