[Application of Medical Record Quality Control System Based on Artificial Intelligence]. / åŸºäºŽäººå·¥æ™ºèƒ½çš„ç— åŽ†è´¨æŽ§ç³»ç»Ÿçš„åº”ç”¨ç ”ç©¶.

Objective: In this study, we used artificial intelligence (AI) technology to explore for automated medical record quality control methods, standardize the process for medical record documentation, and deal with the drawbacks of manually implemented quality control. Methods: In this study, we constructed a medical record quality control system based on AI. We first designed and built, for the system, a quality control rule base based on authoritative standards and expert opinions. Then, medical records data were automatically collected through a data acquisition engine and were converted into structured data through a post-structured engine. Finally, the medical record quality control engine was combined with the rule base to analyze the data, identify quality problems, and realize automated intelligent quality control. This system was applied to the quality control of medical records and five quality control points were selected, including similarities in the history of the present illness, defects in the description of chief complaints, incomplete initial diagnosis, missing in formation in the history of menstruation, marriage, and childbirth, and mismatch between the chief complaints and the history of the present illness. We randomly selected 2 918 medical records of patients discharged in January 2022 to conduct AI quality control. Then we organized medical record quality control experts to conduct an accuracy review, made a comparison with previous manual quality control records, and analyzed the results. The number of quality problems that were verified in the accuracy review was taken as the gold standard and receiver operating characteristic (ROC) curves were drawn for the 5 quality control points. Results: According to the accuracy review performed by medical record quality control experts, the accuracy of AI quality control reached 89.57%. For the sampled medical records, the results of AI quality control were compared with those of previous manually performed quality control and only one problem detected by manual quality control of the sampled medical records was not detected by the AI quality control system. The number of medical record quality problems correctly detected by AI quality control was about 2.97 times that of manual quality control. Analysis of the ROC curves showed that the AUC of the five quality control points of the AI quality control system were statistically significant (P<0.05) and all the AUC values approximated or exceeded 0.9. In contrast, results obtained through manually performed quality control found significant AUC (0.797) for only one quality control point-similarities in the history of present illness (P<0.05). Comparison of the AUC values of the two quality control methods showed that AI quality control system had an advantage over manually performed quality control for the five quality control points. Conclusion: Through the application of medical record quality control system based on AI, efficient full quality control of medical record documentation can be achieved and the detection rate of quality problems can be effectively improved. In addition, the system helps save manpower and improve the quality of medical record documentation.

Field-free spin-orbit torque switching in ferromagnetic trilayers at sub-ns timescales.

Current-induced spin torques enable the electrical control of the magnetization with low energy consumption. Conventional magnetic random access memory (MRAM) devices rely on spin-transfer torque (STT), this however limits MRAM applications because of the nanoseconds incubation delay and associated endurance issues. A potential alternative to STT is spin-orbit torque (SOT). However, for practical, high-speed SOT devices, it must satisfy three conditions simultaneously, i.e., field-free switching at short current pulses, short incubation delay, and low switching current. Here, we demonstrate field-free SOT switching at sub-ns timescales in a CoFeB/Ti/CoFeB ferromagnetic trilayer, which satisfies all three conditions. In this trilayer, the bottom magnetic layer or its interface generates spin currents with polarizations in both in-plane and out-of-plane components. The in-plane component reduces the incubation time, while the out-of-plane component realizes field-free switching at a low current. Our results offer a field-free SOT solution for energy-efficient scalable MRAM applications.

Deterministic switching of perpendicular magnetization by out-of-plane anti-damping magnon torques.

Spin-wave excitations of magnetic moments (or magnons) can transport spin angular momentum in insulating magnetic materials. This property distinguishes magnonic devices from traditional electronics, where power consumption results from electrons' movement. Recently, magnon torques have been used to switch perpendicular magnetization in the presence of an external magnetic field. Here we present a material system composed of WTe2/antiferromagnetic insulator NiO/ferromagnet CoFeB heterostructures that allows magnetic field-free switching of the perpendicular magnetization. The magnon currents, with a spin polarization canting of -8.5° relative to the sample plane, traverse the 25-nm-thick polycrystalline NiO layer while preserving their original polarization direction, subsequently exerting an out-of-plane anti-damping magnon torque on the ferromagnetic layer. Using this mechanism, we achieve a 190-fold reduction in power consumption in PtTe2/WTe2/NiO/CoFeB heterostructures compared to Bi2Te3/NiO/CoFeB control samples, which only exhibit in-plane magnon torques. Our field-free demonstration contributes to the realization of all-electric, low-power, perpendicular magnetization switching devices.

Effects of different extraction methods on the physico-chemical characteristics and biological activities of polysaccharides from Clitocybe squamulosa.

This study comparatively evaluated the effects of the commonly used six extraction methods (acidic, alkaline, enzymatic, ultrasonic, high-pressure, and microwave) on the physico-chemical properties, processing characteristics, and biological activities of polysaccharides from Clitocybe squamulosa (CSFPs). The results show that polysaccharides extracted using an enzyme-assisted extraction method has a relatively high extraction yield (4.46 ± 1.62 %) and carbohydrate content (70.79 ± 6.25 %) compared with others. Furthermore, CSFPs were all composed of glucose, galactose, mannose, xylose, and glucosamine hydrochloride. Only ultrasonic-assisted extraction of polysaccharides (CSFP-U) has a triple helix chain conformation. Scanning electron microscopy (SEM) revealed significant differences in the microstructure of polysaccharides prepared using different methods. Besides that, the polysaccharides prepared by alkali extraction (CSFP-B) and high-pressure assisted extraction (CSFP-H) have good water (2.86 ± 0.29 g/g and 3.15 ± 0.29 g/g) and oil (8.13 ± 0.32 g/g and 7.97 ± 0.04 g/g) holding properties. The rheological behavior demonstrated that CSFPs solutions were typical non-Newtonian fluid. Apart from this, the antioxidant capacity (clearing DPPH (IC50 = 0.29) and ABTS free radicals (IC50 = 0.19), total reduction ability (IC50 = 3.02)) of polysaccharides prepared by the microwave-assisted extraction (CSFP-M) method was significantly higher than that of other extraction methods. By contrast, the polysaccharide prepared by acid extraction (CSFP-A) has the optimum binding capacity (bile acid salt (71.30 ± 6.78 %) and cholesterol (57.07 ± 3.26 mg/g)). The antibacterial activity of CSFPs was positively correlated with their concentration. Thus, the research results can provide a theoretical basis for the development and utilization of polysaccharides from C. squamulosa.

Boosting Deep Learning for Interpretable Brain MRI Lesion Detection through the Integration of Radiology Report Information.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To guide a deep learning (DL) model's attention toward brain lesion MRI characteristics by incorporating radiology report-derived textual features to achieve interpretable lesion detection. Materials and Methods In this retrospective study, 35282 brain MRI scans (January 2018-June 2023) and corresponding radiology reports from center 1 were used for training, validation, and internal testing. 2655 brain MRI scans (January 2022-December 2022) from centers 2-5 were reserved for external testing. Textual features were extracted from radiology reports to guide a DL model (ReportGuidedNet) focusing on lesion characteristics. Another DL model (PlainNet) without textual features was developed for comparative analysis. Both models diagnosed 15 conditions, including 14 diseases and normal brains. Performance of each model was assessed by calculating macro-and microaveraged area under the receiver operating characteristic curves (ma-AUC, mi-AUC). Attention maps, visualizing model attention, were assessed with a 5-point Likert scale. Results ReportGuidedNet outperformed PlainNet for all diagnoses on both internal (ma-AUC: 0.93 [95% CI: 0.91- 0.95] versus 0.85 [95% CI: 0.81-0.88]; mi-AUC: 0.93 [95% CI: 0.90-0.95] versus 0.89 [95% CI: 0.83-0.92]) and external (ma-AUC: 0.91 [95% CI: 0.88-0.93] versus 0.75 [95% CI: 0.72-0.79]; mi-AUC: 0.90 [95% CI: 0.87-0.92] versus 0.76 [95% CI: 0.72-0.80]) testing sets. The performance difference between internal and external testing sets was smaller for ReportGuidedNet than for PlainNet (Δma-AUC: 0.03 versus 0.10; Δmi-AUC: 0.02 versus 0.13). The Likert scale score of ReportGuidedNet was higher than that of PlainNet (mean ± SD: 2.50 ± 1.09 versus 1.32 ± 1.20; P < .001). Conclusion The integration of radiology report textual features improved the DL model's ability to detect brain lesions, enhancing interpretability and generalizability. Published under a CC BY 4.0 license.

Erratum: How ß-cyclodextrin- loaded mesoporous SiO2 nanospheres ensure efficient adsorption of rifampicin.

[This corrects the article DOI: 10.3389/fchem.2022.1040435.].

Effects of in vitro digestion and fecal fermentation on physico-chemical properties and metabolic behavior of polysaccharides from Clitocybe squamulosa.

The aim of this study was to establish a human digestion model in vitro to explore the degradation characteristics of a novel high-purity polysaccharide from Clitocybe squamulosa (CSFP2). The results showed that the content of reducing sugars (CR ) of CSFP2 increased from 0.13 to 0.23 mg/mL, the molecular weight (Mw) of CSFP2 decreased significantly during the saliva-gastrointestinal digestion. The constituent monosaccharides of CSFP2, including galactose, glucose, and mannose, were stable during in vitro digestion, but their molar ratios were changed from 0.023: 0.737: 0.234 to 0.496: 0.478: 0.027. The surface of CSFP2 changes from a rough flaky structure to a scattered flocculent or rod-shaped structure after the gastrointestinal digestion. However, the apparent viscosity of CSFP2 was overall stable during in vitro digestion. Moreover, CSFP2 still maintains its strong antioxidant capacity after saliva-gastrointestinal digestion. The results showed that CSFP2 can be partially decomposed during digestion. Meanwhile, some physico-chemical properties of the fermentation broth containing CSFP2 changed significantly after gut microbiota fermentation. For example, the pH value (from 8.46 to 4.72) decreased significantly (p < 0.05) after 48 h of fermentation. the OD 600 value increased first and then decreased (from 2.00 to 2.68 to 1.32) during 48-h fermentation. In addition, CSFP2 could also increase the amounts of short-chain fatty acids (SCFAs) (from 5.5 to 37.15 mmol/L) during fermentation (in particular, acetic acid, propionic acid, and butyric acid). Furthermore, the relative abundances of Bacteriodes, Bifidobacterium, Catenibacterium, Lachnospiraceae_NK4A136_group, Megasphaera, Prevotella, Megamonas, and Lactobacillus at genus level were markedly increased with the intervention of CSFP2. These results provided a theoretical basis for the further development of functional foods related to CSFP2.

Two Novel Polysaccharides From Clitocybe squamulosa: Their Isolation, Structures, and Bioactivities.

The crude polysaccharides from the fruiting bodies of Clitocybe squamulosa (CSFP) were isolated by hot-water extraction. Two novel polysaccharides, CSFP1-ß and CSFP2-α, were further purified by DEAE-52 anion exchange and Sephacryl S-400 gel filtration chromatography, and the purities reached 98.44 and 97.83%, respectively. The structural characteristics and bioactivities of CSFP, CSFP1-ß, and CSFP2-α were identified by the combination of chemical and instrumental analysis. Results showed that CSFP was formed by the aggregation of honeycomb spherical materials; CSFP1-ß and CSFP2-α were interwoven by reticular and fibrous structures, respectively. Purified components of both CSFP1-ß and CSFP2-α showed typical infrared absorption peaks of polysaccharides, and contents of nucleic acid and protein decreased significantly. Simultaneously, CSFP with a molecular weight (Mw) of 1.948 × 104 Da were composed mainly of glucose, mannose, galactose, and rhamnose. CSFP1-ß was composed mainly of glucose, galactose, and mannose, while CSFP2-α was composed of glucose, and both their Mw distributions were uneven. Compared with CSFP, the antioxidant activities of CSFP1-ß and CSFP2-α were significantly improved (p < 0.05), and they both showed good abilities to bind free cholesterol and bile acid salts in vitro. The binding abilities of the two compounds were found to be 68.62 and 64.43%, and 46.66 and 45.05 mg/g, respectively. CSFP, CSFP1-ß, and CSFP2-α had good bacteriostatic effects with a linear increasing relationship to increasing concentration. In addition, CSFP promoted the growth of RAW264.7 cells and has potential immunomodulatory, anti-inflammatory, and anti-tumor activities.

How ß-cyclodextrin- loaded mesoporous SiO2 nanospheres ensure efficient adsorption of rifampicin.

In this study, ß-CD@mesoporous SiO2 nanospheres (ß-CD@mSi) were prepared by loading ß-cyclodextrin (ß-CD) onto mesoporous silica nanospheres through an in situ synthesis. This not only solved the defect of ß-CD being easily soluble in water, but also changed the physical structure of the mesoporous silica nanospheres. FTIR and XPS results showed that ß-CD was successfully loaded onto mesoporous silica nanospheres (mSi), while enhancing the adsorption effect. ß-CD@mSi with a monomer diameter of about 150 nm were prepared. At a temperature of 298k, the removal efficiency of a 100 mg/L solution of rifampicin can reach 90% in 4 h and the adsorption capacity was 275.42 mg g-1 at high concentration. Through the calculation and analysis of adsorption kinetics, adsorption isotherms and adsorption thermodynamics based on the experimental data, the reaction is a spontaneous endothermic reaction dominated by chemical adsorption. The electron transfer pathway, structure-activity relationship and energy between ß-CD@mSi and rifampicin were investigated by quantum chemical calculations. The accuracy of the characterization test results to judge the adsorption mechanism was verified, to show the process of rifampicin removal by ß-CD@mSi more clearly and convincingly. The simulation results show that π-π interaction plays a major interaction in the reaction process, followed by intermolecular hydrogen bonding and electrostatic interactions.

Purification, Characterization, and Immobilization of a Novel Protease-Resistant α-Galactosidase from Oudemansiella radicata and Its Application in Degradation of Raffinose Family Oligosaccharides from Soymilk.

α-galactosidase (EC 3.2.1.22) are glycosidases that catalyze the hydrolysis of α-1,6-linked D-galactosyl residues of different substrates, which has been widely applied in the food industry. Oudemansiella radicata is a kind of precious edible medicinal mushroom, which is a healthy, green, and safe food-derived enzyme source. In this study, a novel acidic α-galactosidase was purified from the dry fruiting bodies of O. radicata by ion-exchange chromatography and gel filtration, and designated as ORG (O. radicata α-galactosidase). ORG was further immobilized to obtain iORG by the sodium alginate-chitosan co-immobilization method. Then, the characterization of free and immobilized enzymes and their potential application in the removal of the RFOs from soymilk were investigated. The results showed that ORG might be a 74 kDa heterodimer, and it exhibited maximum activity at 50 °C and pH 3.0, whereas iORG showed maximum activity at 50 °C and pH 5.5. In addition, iORG exhibited higher thermal stability, pH stability, storage stability, and a better degradation effect on raffinose family oligosaccharides (RFOs) in soymilk than ORG, and iORG completely hydrolyzed RFOs in soymilk at 50 °C within 3 h. Therefore, iORG might be a promising candidate in the food industry due to its excellent stability, high removal efficiency of RFOs from soymilk, and great reusability.

In vitro digestion and fermentation by human fecal microbiota of polysaccharides from Clitocybe squamulose.

The present study aimed to evaluate the effects of in vitro simulated saliva-gastrointestinal digestion and fecal fermentation behavior on the chemical composition, structure and bioactivity of polysaccharides from Clitocybe squamulosa (CSFP). Results showed that gastric digestion significantly changed the chemical composition and structural properties of CSFP, such as total uronic acid, reducing sugar, molecular weight, rheological properties, particle size, and microscopic morphology. In particular, the molecular weight decreased from 19,480 Da to 10,945 Da, while the reducing-sugar content increased from 0.149 mg/mL to 0.293 mg/mL. Gastric digestion also affected the biological activity of CSFP. Although after gastric digestion, CSFP retained its vigorous antioxidant activity, ability to inhibit α-amylase activity, and the binding ability to bile acid, fat, and free cholesterol in vitro. However, there was an apparent weakening trend. After in vitro fermentation of gut microbiota, the content of total sugar was significantly decreased from 11.6 mg/mL to 2.4 mg/mL, and the pH value in the fecal culture significantly decreased to 5.20, indicating that CSFP could be broken down and utilized by gut microbiota. Compared to the blank, the concentrations of total short-chain fatty acids (SCFAs) including acetic, propionic and n-butyric significantly increased. Simultaneously, CSFP could remarkably reduce the proportions of Firmicutes and Bacteroides (F/B) and promote the growth of some beneficial intestinal microbiota. Therefore, CSFP can potentially be a new functional food as prebiotics to promote human gut health.