Objective To systematically review prediction models of small for gestational age (SGA) based on machine learning and provide references for the construction and optimization of such a prediction model. Methods The PubMed, EMbase, Web of Science, CBM, WanFang Data, VIP and CNKI databases were electronically searched to collect studies on SGA prediction models from database inception to August 10, 2022. Two researchers independently screened the literature, extracted data, evaluated the risk of bias of the included studies, and conducted a systematic review. Results A total of 14 studies, comprising 40 prediction models constructed using 19 methods, such as logical regression and random forest, were included. The results of the risk of bias assessment from 13 studies were high; the area under the curve of the prediction models ranged from 0.561 to 0.953. Conclusion The overall risk of bias in the prediction models for SGA was high, and the predictive performance was average. Models built using extreme gradient boosting (XGBoost) demonstrated the best predictive performance across different studies. The stacking method can improve predictive performance by integrating different models. Finally, maternal blood pressure, fetal abdominal circumference, head circumference, and estimated fetal weight were important predictors of SGA.
As precision medicine continues to gain momentum, the number of predictive model studies is increasing. However, the quality of the methodology and reporting varies greatly, which limits the promotion and application of these models in clinical practice. Systematic reviews of prediction models draw conclusions by summarizing and evaluating the performance of such models in different settings and populations, thus promoting their application in practice. Although the number of systematic reviews of predictive model studies has increased in recent years, the methods used are still not standardized and the quality varies greatly. In this paper, we combine the latest advances in methodologies both domestically and abroad, and summarize the production methods and processes of a systematic review of prediction models. The aim of this study is to provide references for domestic scholars to produce systematic reviews of prediction models.
ObjectiveTo systematically review the risk prediction models for the occurrence of low anterior resection syndrome in patients with rectal cancer after surgery. MethodsThe PubMed, Web of Science, Embase, Cochrane Library, Scopus, CINHAL, CNKI, CBM, WanFang Data and VIP databases were electronically searched to collect studies related to the objectives from inception to June 13, 2023. Two reviewers independently screened the literature, extracted data using the critical appraisal and data extraction for systematic reviews of prediction modelling studies (CHARMS) checklist, and assessed quality of the included studies using prediction model risk of bias assessment tool (PROBAST). ResultsA total of 14 studies were included, all studies reported model discrimination, and 10 studies reported calibration. The models were internally validated in 8 studies, externally validated in 5 studies. The most common predictors included in the models were tumour distance from the anal verge, neoadjuvant therapy, anastomotic leak and BMI. Only 5 studies had good overall applicability, and all studies had a high risk of bias, with the risk of bias mainly stemming from the field of participants, outcomes and analysis. ConclusionThere are still many shortcomings in the risk prediction models for the occurrence of low anterior resection syndrome in patients with rectal cancer after surgery. Future studies may consider external validation and recalibration of existing models. New prediction models should be built and validated according to methodological guidelines.
ObjectiveTo observe the relationship between ventilator-associated pneumonia (VAP) and changes in bronchial mucosa and sputum in critically ill patients. A prediction model for SEH score was developed according to the abnormal degrees of airway sputum , mucosal edema and mucosal hyperemia , as well as to analyze the diagnostic value of the SEH scores for VAP during bronchoscopy. MethodsA collection of general data and initial bronchoscopy results was conducted for patients admitted to the department of intensive care unit at West China Hospital from March 1, 2024, to July 1, 2024. Patients were divided into infection group (n=138) and non-infection group (n=227) according to diagnostic criteria for VAP based on the date of their first bronchoscopy. T-tests were used to compare baseline data between groups, while analysis of variance was employed to assess differences in airway mucosal and sputum lesions. A binary logistic regression model was constructed using the SEH scores for predicting VAP risk, with receiver operating characteristic curve area under the curve (AUC) utilized to evaluate model accuracy. ResultsA total of 365 patients were included in this study, among which 138 cases (37.8%) were diagnosed with VAP. The AUC for using SEH scores in diagnosing VAP was found to be 0.81 [95% confidence interval (CI) 0.76-0.85], with an optimal cutoff value set at 6.5. The sensitivity and specificity of SEH scores for diagnosing VAP were determined as 79.7% (95% CI: 72.2%-85.6%) and 73.1% (95% CI:67.0%-78.5%). Patients with SEH scores over 6.5 exhibited a significantly higher rate of VAP infection (64.3% vs.14.4%, P<0.0001), elevated white blood cell count levels (WBC) [(13.3±7.5 vs.1.8±6.2), P=0.04], as well as increased hospital mortality rates (39.8 % vs.24.2 %, P=0.002). ConclusionsThe SEH scores has a certain efficacy in the diagnosis of VAP in patients with mechanical ventilation. Compared with the traditional VAP diagnostic criteria, SEH scores is easier to obtain in clinical practice, and has certain clinical application value.
ObjectiveTo systematically review mortality risk prediction models for acute type A aortic dissection (AAAD). MethodsPubMed, EMbase, Web of Science, CNKI, WanFang Data, VIP and CBM databases were electronically searched to collect studies of mortality risk prediction models for AAAD from inception to July 31th, 2021. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Systematic review was then performed. ResultsA total of 19 studies were included, of which 15 developed prediction models. The performance of prediction models varied substantially (AUC were 0.56 to 0.92). Only 6 studies reported calibration statistics, and all models had high risk of bias. ConclusionsCurrent prediction models for mortality and prognosis of AAAD patients are suboptimal, and the performance of the models varies significantly. It is still essential to establish novel prediction models based on more comprehensive and accurate statistical methods, and to conduct internal and a large number of external validations.
ObjectiveTo review individual treatment effect (ITE) models developed from randomized controlled trials, with the aim of systematically summarizing the current state of model development and assessing the risk of bias. MethodsPubMed and Embase databases were searched for studies published between 1990 and 14 June 2024. Data were extracted using the CHARMS inventory, and the PROBAST risk of bias tool was used to assess model quality. ResultsA total of 11 publications were included, containing 19 ITE models. The ITE modelling methods were regression models with interaction terms (n=8, 42.1%), dual-range models (n=5, 26.3%) and machine learning (n=6, 31.6%). The ITE models had a reporting rate of 78.9%, 73.2% and 10.5% for differentiation, calibration and clinical validity, respectively. Fourteen models were assessed as having a high risk of bias (73.7%), particularly in the area of statistical analysis, due to inappropriate handling of missing data (n=15, 78.9%), inappropriate consideration of model fit issues (n=5, 26.3%), etc. ConclusionCommon approaches to ITE model development include constructing interaction terms, dual procedure theory, and machine learning, but suffer from a low number of model developments, more complex modeling methods, and non-standardized reporting. In the future, emphasis should be placed on further exploration of ITE models, promoting diversified modeling methods and standardized reporting to improve the clinical promotion and practical application value of the models.
ObjectiveTo explore the risk factors for accompanying depression in patients with community type Ⅱ diabetes and to construct their risk prediction model. MethodsA total of 269 patients with type Ⅱ diabetes accompanied with depression and 217 patients with simple type Ⅱ diabetes from three community health service centers in two streets of Pingshan District, Shenzhen from October 2021 to April 2022 were included. The risk factors were analyzed and screened out, and a logistic regression risk prediction model was constructed. The goodness of fit and prediction ability of the model were tested by the Hosmer-Lemeshow test and the receiver operating characteristic (ROC) curve. Finally, the model was verified. ResultsLogistic regression analysis showed that smoking, diabetes complications, physical function, psychological dimension, medical coping for face, and medical coping for avoidance were independent risk factors for depressive disorder in patients with type Ⅱ diabetes. Modeling group Hosmer-Lemeshow test P=0.345, the area under the ROC curve was 0.987, sensitivity was 95.2% and specificity was 98.6%. The area under the ROC curve was 0.945, sensitivity was 89.8%, specificity was 84.8%, and accuracy was 86.8%, showing the model predictive value. ConclusionThe risk prediction model of type Ⅱ diabetes patients with depressive disorder constructed in this study has good predictive and discriminating ability.
ObjectiveTo construct a prediction model of diabetics distal symmetric polyneuropathy (DSPN) based on neural network algorithm and the characteristic data of traditional Chinese medicine and Western medicine. MethodsFrom the inpatients with diabetes in the First Affiliated Hospital of Anhui University of Chinese Medicine from 2017 to 2022, 4 071 cases with complete data were selected. The early warning model of DSPN was established by using neural network, and 49 indicators including general epidemiological data, laboratory examination, signs and symptoms of traditional Chinese medicine were included to analyze the potential risk factors of DSPN, and the weight values of variable features were sorted. Validation was performed using ten-fold crossover, and the model was measured by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and AUC value. ResultsThe mean duration of diabetes in the DSPN group was about 4 years longer than that in the non-DSPN group (P<0.001). Compared with non-DSPN patients, DSPN patients had a significantly higher proportion of Chinese medicine symptoms and signs such as numbness of limb, limb pain, dizziness and palpitations, fatigue, thirst with desire to drink, dry mouth and throat, blurred vision, frequent urination, slow reaction, dull complexion, purple tongue, thready pulse and hesitant pulse (P<0.001). In this study, the DSPN neural network prediction model was established by integrating traditional Chinese and Western medicine feature data. The AUC of the model was 0.945 3, the accuracy was 87.68%, the sensitivity was 73.9%, the specificity was 92.7%, the positive predictive value was 78.7%, and the negative predictive value was 90.72%. ConclusionThe fusion of Chinese and Western medicine characteristic data has great clinical value for early diagnosis, and the established model has high accuracy and diagnostic efficacy, which can provide practical tools for DSPN screening and diagnosis in diabetic population.
ObjectiveTo systematically review the research status of risk prediction models for gestational diabetes mellitus (GDM). MethodsThe CNKI, WanFang Data, VIP, CBM, PubMed, JBI EBP, Ovid MEDLINE, Embase, Web of Science and Cochrane Library databases were electronically searched to collect relevant literature on risk prediction models for GDM from inception to October 2022. Two researchers independently screened the literature, extracted data, and assessed the risk of bias of the included studies, and then qualitative description was performed. ResultsA total of 19 studies were included, involving 19 risk prediction models. The evaluation results showed that, in terms of the risk of bias, 18 studies were high risk, and 1 study was unclear. In terms of applicability, 14 studies were high risk, 2 studies were low risk, and 3 studies were unclear. The area under the receiver operating characteristic curve of the included models was 0.69 to 0.88. The most common predictors included age, weight, pre-pregnancy BMI, history of diabetes, family history of diabetes, and race. ConclusionThe overall performance of the risk prediction model for gestational diabetes mellitus is good, but the risk of bias of the model is high, and the clinical applicability of the model needs to be further verified.
ObjectiveConstructing a prediction model for seizures after stroke, and exploring the risk factors that lead to seizures after stroke. MethodsA retrospective analysis was conducted on 1 741 patients with stroke admitted to People's Hospital of Zhongjiang from July 2020 to September 2022 who met the inclusion and exclusion criteria. These patients were followed up for one year after the occurrence of stroke to observe whether they experienced seizures. Patient data such as gender, age, diagnosis, National Institute of Health Stroke Scale (NIHSS) score, Activity of daily living (ADL) score, laboratory tests, and imaging examination data were recorded. Taking the occurrence of seizures as the outcome, an analysis was conducted on the above data. The Least absolute shrinkage and selection operator (LASSO) regression analysis was used to screen predictive variables, and multivariate Logistic regression analysis was performed. Subsequently, the data were randomly divided into a training set and a validation set in a 7:3 ratio. Construct prediction model, calculate the C-index, draw nomogram, calibration plot, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) to evaluate the model's performance and clinical application value. ResultsThrough LASSO regression, nine non-zero coefficient predictive variables were identified: NIHSS score, homocysteine (Hcy), aspartate aminotransferase (AST), platelet count, hyperuricemia, hyponatremia, frontal lobe lesions, temporal lobe lesions, and pons lesions. Multivariate logistic regression analysis revealed that NIHSS score, Hcy, hyperuricemia, hyponatremia, and pons lesions were positively correlated with seizures after stroke, while AST and platelet count were negatively correlated with seizures after stroke. A nomogram for predicting seizures after stroke was established. The C-index of the training set and validation set were 0.854 [95%CI (0.841, 0.947)] and 0.838 [95%CI (0.800, 0.988)], respectively. The areas under the ROC curves were 0.842 [95%CI (0.777, 0.899)] and 0.829 [95%CI (0.694, 0.936)] respectively. Conclusion These nine variables can be used to predict seizures after stroke, and they provide new insights into its risk factors.