RESUMO
OBJECTIVES: Given the high incidence and mortality rate of sepsis, early identification of high-risk patients and timely intervention are crucial. However, existing mortality risk prediction models still have shortcomings in terms of operation, applicability, and evaluation on long-term prognosis. This study aims to investigate the risk factors for death in patients with sepsis, and to construct the prediction model of short-term and long-term mortality risk. METHODS: Patients meeting sepsis 3.0 diagnostic criteria were selected from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and randomly divided into a modeling group and a validation group at a ratio of 7ê3. Baseline data of patients were analyzed. Univariate Cox regression analysis and full subset regression were used to determine the risk factors of death in patients with sepsis and to screen out the variables to construct the prediction model. The time-dependent area under the curve (AUC), calibration curve, and decision curve were used to evaluate the differentiation, calibration, and clinical practicability of the model. RESULTS: A total of 14 240 patients with sepsis were included in our study. The 28-day and 1-year mortality were 21.45% (3 054 cases) and 36.50% (5 198 cases), respectively. Advanced age, female, high sepsis-related organ failure assessment (SOFA) score, high simplified acute physiology score II (SAPS II), rapid heart rate, rapid respiratory rate, septic shock, congestive heart failure, chronic obstructive pulmonary disease, liver disease, kidney disease, diabetes, malignant tumor, high white blood cell count (WBC), long prothrombin time (PT), and high serum creatinine (SCr) levels were all risk factors for sepsis death (all P<0.05). Eight variables, including PT, respiratory rate, body temperature, malignant tumor, liver disease, septic shock, SAPS II, and age were used to construct the model. The AUCs for 28-day and 1-year survival were 0.717 (95% CI 0.710 to 0.724) and 0.716 (95% CI 0.707 to 0.725), respectively. The calibration curve and decision curve showed that the model had good calibration degree and clinical application value. CONCLUSIONS: The short-term and long-term mortality risk prediction models of patients with sepsis based on the MIMIC-IV database have good recognition ability and certain clinical reference significance for prognostic risk assessment and intervention treatment of patients.
Assuntos
Sepse , Humanos , Sepse/mortalidade , Sepse/diagnóstico , Feminino , Masculino , Fatores de Risco , Prognóstico , Bases de Dados Factuais , Medição de Risco/métodos , Unidades de Terapia Intensiva/estatística & dados numéricos , Pessoa de Meia-Idade , Área Sob a Curva , Idoso , Escores de Disfunção Orgânica , Modelos de Riscos ProporcionaisRESUMO
The accurate prediction of chlorophyll-a (chl-a) concentration in coastal waters is essential to coastal economies and ecosystems as it serves as the key indicator of harmful algal blooms. Although powerful machine learning methods have made strides in forecasting chl-a concentrations, there remains a gap in effectively modeling the dynamic temporal patterns and dealing with data noise and unreliability. To wiggle out of quagmires, we introduce an innovative deep learning prediction model (termed ChloroFormer) by integrating Transformer networks with Fourier analysis within a decomposition architecture, utilizing coastal in-situ data from two distinct study areas. Our proposed model exhibits superior capabilities in capturing both short-term and middle-term dependency patterns in chl-a concentrations, surpassing the performance of six other deep learning models in multistep-ahead predictive accuracy. Particularly in scenarios involving extreme and frequent blooms, our proposed model shows exceptional predictive performance, especially in accurately forecasting peak chl-a concentrations. Further validation through Kolmogorov-Smirnov tests attests that our model not only replicates the actual dynamics of chl-a concentrations but also preserves the distribution of observation data, showcasing its robustness and reliability. The presented deep learning model addresses the critical need for accurate prediction on chl-a concentrations, facilitating the exploration of marine observations with complex dynamic temporal patterns, thereby supporting marine conservation and policy-making in coastal areas.
RESUMO
We aimed to explore the association between FFP transfusion and outcomes of DC patients with significant coagulopathy. A total of 693 DC patients with significant coagulopathy were analyzed with 233 patients per group after propensity score matching (PSM). Patients who received FFP transfusion were matched with those receiving conventional therapy via PSM. Regression analysis showed FFP transfusion had no benefit in 30-day (HR: 1.08, 95% CI 0.83-1.4), 90-day (HR: 1.03, 95% CI 0.80-1.31) and in-hospital(HR: 1.30, 95% CI 0.90-1.89) mortality, associated with increased risk of liver failure (OR: 3.00, 95% CI 1.78-5.07), kidney failure (OR: 1.90, 95% CI 1.13-3.18), coagulation failure (OR: 2.55, 95% CI 1.52-4.27), respiratory failure (OR: 1.76, 95% CI 1.15-2.69), and circulatory failure (OR: 2.15, 95% CI 1.27-3.64), and even associated with prolonged the LOS ICU (ß: 2.61, 95% CI 1.59-3.62) and LOS hospital (ß: 6.59, 95% CI 2.62-10.57). In sensitivity analysis, multivariate analysis (HR: 1.09, 95%CI 0.86, 1.38), IPTW (HR: 1.11, 95%CI 0.95-1.29) and CAPS (HR: 1.09, 95% CI 0.86-1.38) showed FFP transfusion had no beneficial effect on the 30-day mortality. Smooth curve fitting demonstrated the risk of liver failure, kidney failure and circulatory failure increased by 3%, 2% and 2% respectively, for each 1 ml/kg increase in FFP transfusion. We found there was no significant difference of CLIF-SOFA and MELD score between the two group on day 0, 3, 7, 14. Compared with the conventional group, INR, APTT, and TBIL in the FFP transfusion group significantly increased, while PaO2/FiO2 significantly decreased within 14 days. In conclusion, FFP transfusion had no beneficial effect on the 30-day, 90-day, in-hospital mortality, was associated with prolonged the LOS ICU and LOS hospital, and the increased risk of liver failure, kidney failure, coagulation failure, respiratory failure and circulatory failure events. However, large, multi-center, randomized controlled trials, prospective cohort studies and external validation are still needed to verify the efficacy of FFP transfusion in the future.
Assuntos
Transtornos da Coagulação Sanguínea , Insuficiência Renal , Choque , Humanos , Transfusão de Componentes Sanguíneos/efeitos adversos , Estudos Retrospectivos , Estudos Prospectivos , Plasma , Transtornos da Coagulação Sanguínea/complicações , Transtornos da Coagulação Sanguínea/terapia , Unidades de Terapia Intensiva , Cirrose Hepática/complicações , Choque/complicações , Insuficiência Renal/complicaçõesRESUMO
Blood exchange therapy, specifically Whole blood exchange (WBE), is increasingly being utilized in clinical settings to effectively treat a range of diseases. Consequently, there is an urgent requirement to establish convenient and clinically applicable animal models that can facilitate the exploration of blood exchange therapy mechanisms. Our study conducted continuous WBE in rats through femoral and tail vein catheterization using dual-directional syringe pumps. To demonstrate the applicability of continuous WBE, drug-induced hemolytic anemia (DIHA) was induced through phenylhydrazine hydrochloride (PHZ) injection. Notability, the rats of DIHA + WBE group all survived and recovered within the subsequent period. After the implementation of continuous WBE therapy day (Day 1), the DIHA + WBE group exhibited a statistically significant increase in red blood cells (RBC) (P = 0.0343) and hemoglobin (HGB) levels (P = 0.0090) compared to DIHA group. The rats in the DIHA + WBE group exhibited a faster recovery rate compared to the DIHA group, indicating the successful establishment of a continuous blood exchange protocol. This experimental approach demonstrates not just promising efficacy in the treatment of DIHA and offers a valuable tool for investigating the underlying mechanisms of blood exchange. Furthermore, it has a great potential to the advancement of biomedical research such as drug delivery exploration.