ObjectiveTo systematically review the risk prediction model of intensive care unit (ICU) readmissions. MethodsCNKI, WanFang Data, VIP, CBM, PubMed, EMbase, Web of Science and The Cochrane Library databases were electronically searched to collect the related studies on risk prediction models of ICU readmissions from inception to June 12th, 2022. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies; then, the qualitative systematic review was performed. ResultsA total of 15 studies involving 23 risk prediction models were included. The area under the ROC curve of the models was 0.609-0.924. The most common five predictors of the included model were age, length of ICU hospitalization, heart rate, respiration, and admission diagnosis. ConclusionThe overall prediction performance of the risk prediction model of ICU readmissions is good; however, there are differences in research types and outcomes, and the clinical value of the model needs to be further studied.
ObjectiveTo systematically review the prediction models of blood-based biomarkers for non-small cell lung cancer (NSCLC). MethodsThe PubMed, Embase, Cochrane Library, Web of Science, VIP, WanFang Data and CNKI databases were electronically searched to collect studies related to the objectives from inception to June, 2023. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. Meta-analysis was then performed by using RevMan 5.4.1 software. ResultsA total of 8 studies were included and all of them were retrospective cohort studies. The models were internally validated in 2 studies and externally validated in 4 studies. The performances of the eight predictive models were stable, which was measured by the area under the curve of receiver operating characteristic curve lying between 0.664 and 0.783. However, the risk of bias was high, which may mainly be reflected in data processing, model validation and performance adjustment. Meta-analysis showed that LDH (HR=1.86, 95%CI 41.32 to 2.63, P<0.01), dNLR (HR=2.15, 95%CI 1.56 to 2.96, P<0.01) and NLR (HR=1.71, 95%CI 1.08 to 2.69, P=0.02) were independent factors of prognosis for NSCLC patients. Conclusion?Current evidence shows that the NSCLC prediction models based on peripheral blood biomarkers are still in the development stage, and the models have a high risk of bias.
Objective To explore the risk factors of female’s breast cancer in secondary cities of the west and establish a risk prediction model to identify high-risk groups， and provide the basis for the primary and secondary preve-ntion of breast cancer. Methods Random sampling （method of random digits table）? 1 700 women in secondary cities of the west （including 1 020 outpatient cases and 680 physical examination cases） were routinely accept the questionnaire survey. Sixty-two patients were confirmed breast cancer with pathologically. Based on the X-image of the mammary gland patients and questionnaire survey to put mammographic density which classificated into high- and low-density groups. The relationships between the mammographic density， age， body mass index （BMI）， family history of breast cancer， socio-economic status （SES）， lifestyle， reproductive fertility situation， and breast cancer were analyzed， then a risk prediction model of breast cancer which fitting related risk factors was established. Results Univariate analysis showed that risk factors for breast cancer were age （P=0.006）， BMI （P=0.007）， age at menarche （P=0.039）， occupation （P=0.001）， domicile place （P=0.000）， educational level （P=0.001）， health status compared to the previous year （P=0.046）， age at first birth （P=0.014）， whether menopause （P=0.003）， and age at menopause （P=0.006）. The unconditional logistic regr-ession analysis showed that the significant risk factors were age （P=0.003）， age at first birth （P=0.000）， occupation （P=0.010）， and domicile place （P=0.000）， and the protective factor was age at menarche （P=0.000）. The initially established risk prediction model in the region which fitting related risk factors was y=-5.557＋0.042x1-0.375x2＋1.206x3＋0.509x4＋2.135x5. The fitting coefficient （R square）=0.170， it could reflect 17% of the actual situation. Conclusions The breast cancer risk prediction model which established by using related risk factors analysis and epidemiological investigation could guide the future clinical work，but there is still need the validation studies of large populations for the model.
ObjectivesTo systematically review the delirium risk prediction models in intensive care unit (ICU) patients.MethodsThe Cochrane Library, PubMed, Web of Science, Ovid, VIP, WanFang Date and CNKI databases were electronically searched to collect studies on delirium risk prediction models in intensive care unit patients from inception to December, 2018. Two reviewers independently screened literature, extracted data, evaluated the included studies according to the CHARMS checklist, and then systematic review was performed to evaluate the risk prediction models.ResultsA total of 9 studies were included, of which 7 were prospective studies. Six models were internally validated. All studies reported the area under receiver operating characteristic curve (AUROC) over 0.7 (0.739-0.926). The reduction of cognitive reserve and increased blood urea nitrogen were the most commonly reported predisposing and precipitating factors of delirium among all prediction models. Methodologically, the absence or unreported of the blind method, to a certain extent, partially increase the risk of bias.ConclusionsNine prediction models all have great power in early identifying and screening patients who are at high risk of developing ICU delirium. On the basis of judiciously selecting a practical prediction model for clinical practice or carrying out a large sample-size prospective cohort study to construct the localized prediction model, stratified prevention strategies should be formulated and implemented according to the risk stratification results to reduce the incidence of ICU delirium and accelerate the rational allocation of medical resources for delirium prevention.
ObjectiveTo systematically review the research status of risk prediction models for cognitive impairment in patients with T2DM. MethodsThe CNKI, WanFang Data, VIP, CBM, PubMed, Embase, Web of Science, Cochrane Library databases and clinical trial registration platform were electronically searched to collect relevant literature on risk prediction models for cognitive impairment in patients with T2DM from inception to February 13th, 2025. Two researchers independently screened the literature, extracted data, and assessed the risk of bias of the included studies, and then qualitative description and meta-analysis was performed. ResultsA total of 20 studies were included, involving 25 risk prediction models. In terms of the risk of bias, 20 studies were considered as high risk. With regards to applicability, 20 studies were high applicability. The pooled area under the curve (AUC) for modeling set was 0.83 (95%CI 0.79 to 0.88) and for the validation set was 0.83 (95%CI 0.79 to 0.87). It suggested that the model had good discrimination ability. The most common predictors included age, education level, duration of diabetes and depression. ConclusionThe overall performance of the risk prediction model for cognitive impairment in patients with T2DM is good, but the quality of the model needs to be improved.
ObjectiveTo analyze the influencing factors of acute exacerbation readmission in elderly patients with chronic obstructive pulmonary disease (COPD) within 30 days, construct and validate the risk prediction model.MethodsA total of 1120 elderly patients with COPD in the respiratory department of 13 general hospitals in Ningxia from April 2019 to August 2020 were selected by convenience sampling method and followed up until 30 days after discharge. According to the time of filling in the questionnaire, 784 patients who entered the study first served as the modeling group, and 336 patients who entered the study later served as the validation group to verify the prediction effect of the model.ResultsEducation level, smoking status, number of acute exacerbations of COPD hospitalizations in the past 1 year, regular use of medication, rehabilitation and exercise, nutritional status and seasonal factors were the influencing factors of patients’ readmission to hospital. The risk prediction model was constructed: Z=–8.225–0.310×assignment of education level+0.564×assignment of smoking status+0.873×assignment of number of acute exacerbations of COPD hospitalizations in the past 1 year+0.779×assignment of regular use of medication+0.617×assignment of rehabilitation and exercise +0.970×assignment of nutritional status+assignment of seasonal factors [1.170×spring (0, 1)+0.793×autumn (0, 1)+1.488×winter (0, 1)]. The area under ROC curve was 0.746, the sensitivity was 75.90%, and the specificity was 64.30%. Hosmer-Lemeshow test showed that P=0.278. Results of model validation showed that the sensitivity, the specificity and the accuracy were 69.44%, 85.71% and 81.56%, respectively.ConclusionsEducation level, smoking status, number of acute exacerbations of COPD hospitalizations in the past 1 year, regular use of medication, rehabilitation and exercise, nutritional status and seasonal factors are the influencing factors of patients’ readmission to hospital. The risk prediction model is constructed based on these factor. This model has good prediction effect, can provide reference for the medical staff to take preventive treatment and nursing measures for high-risk patients.
ObjectiveTo investigate the association between the stress-induced hyperglycemia ratio (SHR) and all-cause, cardiovascular, and diabetes-related mortality in patients with advanced cardiovascular-kidney-metabolic (CKM) syndrome, and to evaluate the value of SHR as an independent prognostic marker. MethodsThis retrospective cohort study used data from the 1999–2018 U.S. National Health and Nutrition Examination Survey (NHANES). A total of 2 135 patients with advanced CKM (stages 3 and 4) were included. Kaplan-Meier analysis and multivariable Cox regression models were applied to assess the relationship between SHR and mortality outcomes. Restricted cubic spline (RCS) analysis was employed to explore potential non-linear associations. Subgroup analyses were conducted to identify possible effect modifiers. ResultsOver a mean follow-up of 248 months, 674 all-cause, 198 cardiovascular, and 31 diabetes-related deaths occurred. Elevated SHR was significantly associated with diabetes-related mortality (HR=3.48, P<0.001) in a dose-response manner. SHR exhibited a U-shaped relationship with both all-cause and cardiovascular mortality (non-linearity P<0.001), indicating increased risk at both low and high SHR levels. Subgroup analyses revealed that sex, BMI, and hyperlipidemia significantly modified the association between SHR and diabetes-related death. ConclusionSHR is an independent predictor of mortality risk in patients with advanced CKM syndrome, particularly for diabetes-related death. These findings support the integration of SHR into risk stratification of high-risk CKM populations and provide a basis for metabolic stress-targeted interventions.
This study introduced the construction of individualized risk assessment model based on Bayesian networks, comparing with traditional regression-based logistic models using practical examples. It evaluates the model's performance and demonstrates its implementation in the R software, serving as a valuable reference for researchers seeking to understand and utilize Bayesian network models.
Breast cancer is the most common malignant tumor among Chinese females. We should focus on the research of risk assessment models of gene-environmental factors to guide primary and secondary prevention, and this public health strategy is expected to maximize the health benefits of the population. This paper introduces previous studies of risk factors and predictive models for Chinese breast cancer and provides three points for future research. Firstly, we should explore the specific risk factors related to breast cancer risk in Chinese population, such as overweight or reproductive control measures. Secondly, we should use evidence-based and machine learning methods to select environmental-genetic risk factors. Finally, we should set up an information collective platform for breast cancer risk factors to test the validity of prediction models based on a long-term follow-up cohort of Chinese females.
ObjectiveTo systematically evaluate the prognostic prediction models for idiopathic pulmonary fibrosis (IPF). MethodsA computer-based search was conducted in the PubMed, Embase, Web of Science, and Cochrane Library databases for literature relevant to the research objectives, with the search period ranging from database inception to Jun 2025. Two researchers independently screened the articles. Data were extracted according to the key assessment and data extraction checklist for systematic reviews of prediction models (CHARMS). The risk of bias and applicability of the models were assessed using the PROBAST (Prediction model Risk of Bias Assessment Tool). The quality of model reporting was evaluated using the TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) checklist. ResultsA total of 49 studies were included, of which 26 (53.06%) reported both model development and validation. The most common predictors included gender, age, diffusing capacity for carbon monoxide, forced vital capacity (FVC), and FVC percentage of predicted value. In terms of bias risk, 32 studies (65.31%) were classified as high risk of bias, mainly due to factors related to study subjects and predictors. Regarding applicability, 26 studies (53.06%) were rated as high risk, 11 studies (22.45%) were rated as unclear, and only 12 studies (24.49%) were rated as low risk, suggesting limited clinical applicability of the models. As for reporting quality, existing models showed generally insufficient adherence to the TRIPOD statement, especially in key areas such as research methods and result reporting, where normative issues were prominent. Of the 22 signaling questions in the TRIPOD checklist, most studies achieved only moderate reporting quality, with 8 signaling questions (1, 5c, 6b, 7b, 8, 11e, 13a, 14a) showing key information omissions or vague descriptions. ConclusionExisting prognostic prediction models for IPF generally exhibit high methodological bias risk and reporting deficiencies. Future studies should control for modeling biases based on the PROBAST framework, adhere to the TRIPOD guidelines for transparent reporting, and optimize clinical applicability through external validation.
