Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review.

BACKGROUND: A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation. METHODS: PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789). RESULTS: In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively. CONCLUSION: AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

Psoralen and Isopsoralen, Two Estrogen-Like Natural Products from Psoraleae Fructus, Induced Cholestasis via Activation of ERK1/2.

With the increasing use of oral contraceptives and estrogen replacement therapy, the incidence of estrogen-induced cholestasis (EC) has tended to rise. Psoralen (P) and isopsoralen (IP) are the major bioactive components in Psoraleae Fructus, and their estrogen-like activities have already been recognized. Recent studies have also reported that ERK1/2 plays a critical role in EC in mice. This study aimed to investigate whether P and IP induce EC and reveal specific mechanisms. It was found that P and IP increased the expression of esr1, cyp19a1b and the levels of E2 and VTG at 80 µM in zebrafish larvae. Exemestane (Exe), an aromatase antagonist, blocked estrogen-like activities of P and IP. At the same time, P and IP induced cholestatic hepatotoxicity in zebrafish larvae with increasing liver fluorescence areas and bile flow inhibition rates. Further mechanistic analysis revealed that P and IP significantly decreased the expression of bile acids (BAs) synthesis genes cyp7a1 and cyp8b1, BAs transport genes abcb11b and slc10a1, and BAs receptor genes nr1h4 and nr0b2a. In addition, P and IP caused EC by increasing the level of phosphorylation of ERK1/2. The ERK1/2 antagonists GDC0994 and Exe both showed significant rescue effects in terms of cholestatic liver injury. In conclusion, we comprehensively studied the specific mechanisms of P- and IP-induced EC and speculated that ERK1/2 may represent an important therapeutic target for EC induced by phytoestrogens.

Natural Product Baohuoside I Impairs the Stability and Membrane Location of MRP2 Reciprocally Regulated by SUMOylation and Ubiquitination in Hepatocytes.

Epimedii Folium (EF) is a botanical dietary supplement to benefit immunity. Baohuoside I (BI), a prenylated flavonoid derived from EF, has exhibited the cholestatic risk before. Here, the mechanism of BI on the stability and membrane localization of liver MRP2, a bile acid exporter in the canalicular membrane of hepatocytes, was investigated. The fluorescent substrate of MRP2, CMFDA was accumulated in sandwich-cultured primary mouse hepatocytes (SCH) under BI stimulation, followed by reduced membrane MRP2 expression. BI triggered MRP2 endocytosis associated with oxidative stress via inhibition of the NRF2 signaling pathway. Meanwhile, BI promoted the degradation of MRP2 by reducing its SUMOylation and enhancing its ubiquitination level. Co-IP and fluorescence colocalization experiments all proved that MRP2 was a substrate protein for SUMOylation for SUMO proteins. CHX assays showed that SUMO1 prolonged the half-life of MRP2 and further increased its membrane expression, which could be reversed by UBC9 knockdown. Correspondingly, MRP2 accumulated in the cytoplasm by GP78 knockdown or under MG132 treatment. Additionally, the SUMOylation sites of MRP2 were predicted by the algorithm, and a conversion of lysines to arginines at positions 940 and 953 of human MRP2 caused its decreased stability and membrane location. K940 was further identified as the essential ubiquitination site for MRP2 by an in vitro ubiquitination assay. Moreover, the decreased ubiquitination of MRP2 enhanced the SUMOylation MRP2 and vice versa, and the crosstalk of these two modifiers could be disrupted by BI. Collectively, our findings indicated the process of MRP2 turnover from the membrane to cytoplasm at the post-translational level and further elucidated the novel toxicological mechanism of BI.

Response surface methodology optimization of extraction and enrichment conditions of total triterpenoid saponins from Celosiae Semen and evaluation of its lipid-lowering activity.

The saponin-enriched extract from Celosiae Semen is a promising resource owing to its lipid-lowering activity. However, triterpenoid saponins are difficult to extract owing to their high molecular weight and strong water solubility. The aim of this paper was to explore an eco-friendly and effective technology of extraction and enrichment of total triterpenoid saponins to obtain high lipid-lowering fractions. Initially, Box-Behnken design experiments were employed to optimize the heat reflux extraction process on the basic of mono-factor experiments. Afterwards, the crude extract was further purified using D-101 resin, and the purification parameters were investigated based on adsorption/desorption experiments and biological activity assay. Under optimal conditions, the purity of the finally obtained total triterpenoid saponins was increased by 7.28-fold. The lipid-lowering activities of the six main triterpenoid saponins were evaluated in HepG2 cells induced by palmitic acid. The results of Oil Red O staining showed that the compounds all exhibited potential lipid-lowering activity. The structure-activity relationship analysis suggested that the oligosaccharide chain at C-28 played an essential role in their lipid-lowering activity and the substituent group at C-23 site also showed important effects. The optimal extraction and purification methods may facilitate the utilization of Celosiae Semen for the industrial production as a functional food and drug.

Unleashing the Potential of Internet Hospitals: An In-Depth Examination of Information Platform Functionality and Performance.

BACKGROUND: Internet hospitals (IHs) have rapidly developed as a promising strategy to address supply-demand imbalances in China's medical industry, with their capabilities directly dependent on information platform functionality. Moreover, a novel theory of "Trinity" smart hospital has provided advanced guidelines of IHs construction. OBJECTIVE: To explore the construction experience, construction models, and development prospects based on operational data from IHs. METHODS: Based on existing information systems and internet service functionalities, our hospital has built a "Smart Hospital Internet Information Platform (SHIIP)" for IHs operation, actively to expand online services, digitalize traditional healthcare, and explore healthcare services modes throughout the entire process and lifecycle. This article encompasses the platform architecture design, technological applications, patient service content and processes, healthcare professional support features, administrative management tools, and associated operational data. RESULTS: Our platform has presented a remarkable set of data, including 82,279,669 visits, 420,120 online medical consultations, 124,422 electronic prescriptions, 92,285 medication deliveries, 6,965,566 pre-diagnosis triages, 4,995,824 offline outpatient appointments, 2,025 medical education articles with a total of 15,148,310 views, and so on. These data demonstrate the significant role of IH as an indispensable component of our physical hospital services, with a deep integration between online and offline healthcare systems. CONCLUSIONS: Attributing to extreme convenience and improved efficiency, our IH has achieved a wide recognition and use from both the public and healthcare workers, and the upward trends in multiple data metrics suggest a promising outlook for its sustained and positive development in the future. Our pioneering exploration holds tremendous significance and serves as a valuable guiding reference for IHs construction and the progressive development of the internet healthcare sector.

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions.

In recent years, there has been explosive development in artificial intelligence (AI), which has been widely applied in the health care field. As a typical AI technology, machine learning models have emerged with great potential in predicting cardiovascular diseases by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of cardiovascular diseases. Although the field has become a research hot spot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, and reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of a comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, data set characteristics, model design, and statistical methods, as well as clinical implications, and provide possible solutions to these problems, such as gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, using specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, and enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

Development Trends and Prospects of Technology-Based Solutions for Health Challenges in Aging Over the Past 25 Years: Bibliometric Analysis.

BACKGROUND: As the global population ages, we witness a broad scientific and technological revolution tailored to meet the health challenges of older adults. Over the past 25 years, technological innovations, ranging from advanced medical devices to user-friendly mobile apps, are transforming the way we address these challenges, offering new avenues to enhance the quality of life and well-being of the aging demographic. OBJECTIVE: This study aimed to systematically review the development trends in technology for managing and caring for the health of older adults over the past 25 years and to project future development prospects. METHODS: We conducted a comprehensive bibliometric analysis of literatures related to technology-based solutions for health challenges in aging, published up to March 18, 2024. The search was performed using the Web of Science Core Collection, covering a span from 1999 to 2024. Our search strategy was designed to capture a broad spectrum of terms associated with aging, health challenges specific to older adults, and technological interventions. RESULTS: A total of 1133 publications were found in the Web of Science Core Collection. The publication trend over these 25 years showed a gradual but fluctuating increase. The United States was the most productive country and participated in international collaboration most frequently. The predominant keywords identified through this analysis included "dementia," "telemedicine," "older-adults," "telehealth," and "care." The keywords with citation bursts included "telemedicine" and "digital health." CONCLUSIONS: The scientific and technological revolution has significantly improved older adult health management, particularly in chronic disease monitoring, mobility, and social connectivity. The momentum for innovation continues to build, with future research likely to focus on predictive analytics and personalized health care solutions, further enhancing older adults' independence and quality of life.

Baohuoside I inhibits FXR signaling pathway to interfere with bile acid homeostasis via targeting ER α degradation.

Epimedii folium (EF) is an effective herbal medicine in osteoporosis treatment, but the clinical utilization of EF has been limited due to potential hepatotoxicity. The previous studies identified that baohuoside I (BI), the main active component of EF, was relevant to EF-induced liver injury. However, the mechanisms of BI causing direct injury to hepatocytes remain unclear. Here, we reveal that BI inhibits FXR-mediated signaling pathway via targeting estrogen receptor α (ER α), leading to the accumulation of bile acids (BAs). Targeted bile acid analyses show BI alters the BA composition and distribution, resulting in impaired BA homeostasis. Mechanistically, BI induces FXR-dependent hepatotoxicity at transcriptional level. Additionally, ER α is predicted to bind to the FXR promoter region based on transcription factor binding sites databases and we further demonstrate that ER α positively regulates FXR promoter activity and affects the expression of target genes involved in BA metabolism. Importantly, we discover that ER α and its mediated FXR transcription regulation might be involved in BI-induced liver injury via ligand-dependent ER α degradation. Collectively, our findings indicate that FXR is a newly discovered target gene of ER α mediated BI-induced liver injury, and suggest BI may be responsible for EF-induced liver injury.

Global, regional, and national trends of syphilis from 1990 to 2019: the 2019 global burden of disease study.

BACKGROUND: Syphilis is a sexually transmitted disease caused by Treponema pallidum, and the infection source is syphilis patients. This study aimed to estimate the incidence, mortality rate, and disability-adjusted life years (DALYs) of syphilis to improve the understanding of the current global situation of syphilis. METHODS: This study collected data on syphilis incidence, mortality, and DALYs from the 2019 Global Burden of Disease database. RESULTS: The global number of incident cases and age-standardized incidence rate (ASIR) increased from 8,845,220 (95% UI: 6,562,510-11,588,860) in 1990 to 14,114,110 (95% UI: 10,648,490-18,415,970) in 2019 and 160.03/100,000 persons (95% UI: 120.66-208.1) to 178.48/100,000 persons (95% UI: 134.94-232.34), respectively. The estimated annual percentage change (EAPC) in the ASIR was 0.16 (95% CI: 0.07-0.26). The EAPC in the ASIR associated with high and high-middle sociodemographic indices increased. The ASIR increased among males but decreased among females, and the incidence peaked among males and females between the ages of 20 and 30 years. The EAPCs in the age-standardized death rate and age-standardized DALY rate decreased. CONCLUSIONS: The incidence and ASIR of syphilis increased worldwide from 1990 to 2019. Only the regions with high and high-middle sociodemographic indices showed an increase in the ASIR. Moreover, the ASIR increased among males but decreased among females. The age-standardized death rate and DALY rate both declined worldwide. The increase in the global ASIR of syphilis is a challenge.

Evidence for exposure biomarkers in dictamnine-induced liver injury resulting from metabolic activation in vitro and in mice.

Dictamnine (DTN), a furoquinoline alkaloid isolated from Dictamni Cortex, is responsible for the liver injury caused by Dictamni Cortex and the preparations. Discovering new biomarkers with high specificity and sensitivity for diagnosis and tracing the source of DTN-induced liver injury is urgently needed. Considering that metabolic activation of DTN has been suggested as a primary trigger initiating hepatotoxicity, the present study aimed to investigate the bio-activation process of DTN in vitro and in mice and to explore whether the adducts could be developed as exposure biomarkers. When trapping with N-acetyl-cysteine (NAC) and glutathione (GSH) in mouse liver microsomes and CYP3A4 overexpressed L02 cells, two isomers of DTN-NAC adducts were detected in both systems and one DTN-GSH adduct was found in mouse liver microsomes. As expected, one DTN-NAC adduct was also found in plasma and bile of mice with liver injury after DTN exposure. Moreover, mouse liver microsomes were used to simulate the conjugation of serum albumin with metabolically activated DTN. The sole modified peptide 25 DAHKSEVAHR34 was found, and the oxidative metabolites of DTN might bind to the side chain amino of albumin at Arg34. The above findings not only provided confirmative evidence that DTN was metabolically activated to induce liver injury but also suggested that the adducts had the potential to be developed as exposure biomarkers of DTN-induced liver injury.