RESUMO
INTRODUCTION AND OBJECTIVES: The increasing incidence of hepatocellular carcinoma (HCC) in China is an urgent issue, necessitating early diagnosis and treatment. This study aimed to develop personalized predictive models by combining machine learning (ML) technology with a demographic, medical history, and noninvasive biomarker data. These models can enhance the decision-making capabilities of physicians for HCC in hepatitis B virus (HBV)-related cirrhosis patients with low serum alpha-fetoprotein (AFP) levels. PATIENTS AND METHODS: A total of 6,980 patients treated between January 2012 and December 2018 were included. Pre-treatment laboratory tests and clinical data were obtained. The significant risk factors for HCC were identified, and the relative risk of each variable affecting its diagnosis was calculated using ML and univariate regression analysis. The data set was then randomly partitioned into validation (20 %) and training sets (80 %) to develop the ML models. RESULTS: Twelve independent risk factors for HCC were identified using Gaussian naïve Bayes, extreme gradient boosting (XGBoost), random forest, and least absolute shrinkage and selection operation regression models. Multivariate analysis revealed that male sex, age >60 years, alkaline phosphate >150 U/L, AFP >25 ng/mL, carcinoembryonic antigen >5 ng/mL, and fibrinogen >4 g/L were the risk factors, whereas hypertension, calcium <2.25 mmol/L, potassium ≤3.5 mmol/L, direct bilirubin >6.8 µmol/L, hemoglobin <110 g/L, and glutamic-pyruvic transaminase >40 U/L were the protective factors in HCC patients. Based on these factors, a nomogram was constructed, showing an area under the curve (AUC) of 0.746 (sensitivity = 0.710, specificity=0.646), which was significantly higher than AFP AUC of 0.658 (sensitivity = 0.462, specificity=0.766). Compared with several ML algorithms, the XGBoost model had an AUC of 0.832 (sensitivity = 0.745, specificity=0.766) and an independent validation AUC of 0.829 (sensitivity = 0.766, specificity = 0.737), making it the top-performing model in both sets. The external validation results have proven the accuracy of the XGBoost model. CONCLUSIONS: The proposed XGBoost demonstrated a promising ability for individualized prediction of HCC in HBV-related cirrhosis patients with low-level AFP.
Assuntos
Carcinoma Hepatocelular , Cirrose Hepática , Neoplasias Hepáticas , Aprendizado de Máquina , alfa-Fetoproteínas , Humanos , Carcinoma Hepatocelular/sangue , Carcinoma Hepatocelular/virologia , Carcinoma Hepatocelular/epidemiologia , Carcinoma Hepatocelular/diagnóstico , Carcinoma Hepatocelular/etiologia , Neoplasias Hepáticas/sangue , Neoplasias Hepáticas/virologia , Neoplasias Hepáticas/epidemiologia , Neoplasias Hepáticas/etiologia , Neoplasias Hepáticas/diagnóstico , alfa-Fetoproteínas/análise , alfa-Fetoproteínas/metabolismo , Masculino , Feminino , Pessoa de Meia-Idade , Cirrose Hepática/sangue , Cirrose Hepática/virologia , Cirrose Hepática/diagnóstico , Medição de Risco , Fatores de Risco , China/epidemiologia , Hepatite B Crônica/complicações , Hepatite B Crônica/sangue , Valor Preditivo dos Testes , Adulto , Nomogramas , Biomarcadores Tumorais/sangue , Hepatite B/complicações , Hepatite B/sangue , Hepatite B/diagnóstico , Idoso , Estudos RetrospectivosRESUMO
Background: Macrophages play important roles in the immune response to, and successful implantation of, biomaterials. Titanium nanotubes are considered promising heart valve stent materials owing to their effects on modulation of macrophage behavior. However, the effects of nanotube-regulated macrophages on endothelial cells, which are essential for stent endothelialization, are unknown. Therefore, in this study we evaluated the inflammatory responses of endothelial cells to titanium nanotubes prepared at different voltages. Methods and results: In this study we used three different voltages (20, 40, and 60 V) to produce titania nanotubes with three different diameters by anodic oxidation. The state of macrophages on the samples was assessed, and the supernatants were collected as conditioned media (CM) to stimulate human umbilical vein endothelial cells (HUVECs), with pure titanium as a control group. The results indicated that titanium dioxide (TiO2) nanotubes induced macrophage polarization toward the anti-inflammatory M2 state and increased the expression of arginase-1, mannose receptor, and interleukin 10. Further mechanistic analysis revealed that M2 macrophage polarization controlled by the TiO2 nanotube surface activated the phosphatidylinositol 3-kinase/AKT and extracellular signal-regulated kinase 1/2 pathways through release of vascular endothelial growth factor to influence endothelialization. Conclusion: Our findings expanded our understanding of the complex influence of nanotubes in implants and the macrophage inflammatory response. Furthermore, CM generated from culture on the TiO2 nanotube surface may represent an integrated research model for studying the interactions of two different cell types and may be a promising approach for accelerating stent endothelialization through immunoregulation.
Assuntos
Biomarcadores/análise , Células Endoteliais da Veia Umbilical Humana/efeitos dos fármacos , Macrófagos/efeitos dos fármacos , Nanotubos/química , Neovascularização Fisiológica/efeitos dos fármacos , Titânio/farmacologia , Células Cultivadas , Humanos , Macrófagos/metabolismo , Proteína Quinase 1 Ativada por Mitógeno/genética , Proteína Quinase 1 Ativada por Mitógeno/metabolismo , Proteína Quinase 3 Ativada por Mitógeno/genética , Proteína Quinase 3 Ativada por Mitógeno/metabolismo , Fosfatidilinositol 3-Quinases/genética , Fosfatidilinositol 3-Quinases/metabolismo , Fármacos Fotossensibilizantes/química , Fármacos Fotossensibilizantes/farmacologia , Proteínas Proto-Oncogênicas c-akt/genética , Proteínas Proto-Oncogênicas c-akt/metabolismo , Titânio/química , Fator A de Crescimento do Endotélio Vascular/genética , Fator A de Crescimento do Endotélio Vascular/metabolismoRESUMO
Decellularized valve stents are widely used in tissue-engineered heart valves because they maintain the morphological structure of natural valves, have good histocompatibility and low immunogenicity. However, the surface of the cell valve loses the original endothelial cell coverage, exposing collagen and causing calcification and decay of the valve in advance. In this study, poly ε-caprolactone (PCL) nanoparticles loaded with osteoprotegerin (OPG) were bridged to a decellularized valve using a nanoparticle drug delivery system and tissue engineering technology to construct a new anti-calcification composite valve with sustained release function. The PCL nanoparticles loaded with OPG were prepared via an emulsion solvent evaporation method, which had a particle size of 133 nm and zeta potential of -27.8 mV. Transmission electron microscopy demonstrated that the prepared nanoparticles were round in shape, regular in size, and uniformly distributed, with an encapsulation efficiency of 75%, slow release in vitro, no burst release, no cytotoxicity to BMSCs, and contained OPG nanoparticles in vitro. There was a delay in the differentiation of BMSCs into osteoblasts. The decellularized valve modified by nanoparticles remained intact and its collagen fibers were continuous. After 8 weeks of subcutaneous implantation in rats, the morphological structure of the valve was almost complete, and the composite valve showed anti-calcification ability to a certain extent.