ObjectiveTo systematically evaluate the risk prediction model of knee osteoarthritis (KOA). MethodsThe CNKI, WanFang Data, VIP, PubMed, Embase, Web of Science and Cochrane Library databases were electronically searched to collect relevant studies on KOA’s risk prediction model from inception to April, 2024. After study screening and data extraction by two independent researchers, the PROBAST bias risk assessment tool was used to evaluate the bias risk and applicability of the risk prediction model. ResultsA total of 12 studies involving 21 risk prediction models for KOA were included. The number of predictors ranged from 3 to 12, and the most common predictors were age, sex, and BMI. The range of modeling AUC included in the model was 0.554-0.948, and the range of testing AUC was 0.6-0.94. The overall predictive performance of the models was mediocre and the risk of overall bias was high, and more than half of the models were not externally verified. ConclusionAt present, the overall quality and applicability of the KOA morbidity risk prediction model still have great room for improvement. Future modeling should follow the CHARMS and PROBAST to reduce the risk of bias, explore the combination of multiple modeling methods, and strengthen the external verification of the model.
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 construct and verify the nomogram prediction model of pregnant women's fear of childbirth. MethodsA convenient sampling method was used to select 675 pregnant women in tertiary hospital in Tangshan City, Hebei Province from July to September 2022 as the modeling group, and 290 pregnant women in secondary hospital in Tangshan City from October to December 2022 as the verification group. The risk factors were determined by logistic regression analysis, and the nomogram was drawn by R 4.1.2 software. ResultsSix predictors were entered into the model: prenatal education, education level, depression, pregnancy complications, anxiety and preference for delivery mode. The areas under the ROC curves of the modeling group and the verification group were 0.834 and 0.806, respectively. The optimal critical values were 0.113 and 0.200, respectively, with sensitivities of 67.2% and 77.1%, the specificities were 87.3% and 74.0%, and the Jordan indices were 0.545 and 0.511, respectively. The calibration charts of the modeling group and the verification group showed that the coincidence degree between the actual curve and the ideal curve was good. The results of Hosmer-Lemeshow goodness of fit test were χ2=6.541 (P=0.685) and χ2=5.797 (P=0.760), and Brier scores were 0.096 and 0.117, respectively. DCA in modeling group and verification group showed that when the threshold probability of fear of childbirth were 0.00 to 0.70 and 0.00 to 0.70, it had clinical practical value. ConclusionThe nomogram model has good discrimination, calibration and clinical applicability, which can effectively predict the risk of pregnant women's fear of childbirth and provide references for early clinical identification of high-risk pregnant women and targeted intervention.
ObjectiveTo systematically review the early clinical prediction value of machine learning (ML) for cardiac arrest (CA).MethodsPubMed, EMbase, WanFang Data and CNKI databases were electronically searched to retrieve all ML studies on predicting CA from January 2015 to February 2021. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. The value of each model was evaluated based on the area under receiver operating characteristic curve (AUC) and accuracy.ResultsA total of 38 studies were included. In terms of data sources, 13 studies were based on public database, and other studies retrospectively collected clinical data, in which 21 directly predicted CA, 3 predicted CA-related arrhythmias, and 9 predicted sudden cardiac death. A total of 51 models had been adopted, among which the most popular ML methods included artificial neural network (n=11), followed by random forest (n=9) and support vector machine (n=5). The most frequently used input feature was electrocardiogram parameters (n=20), followed by age (n=12) and heart rate variability (n=10). Six studies compared the ML models with other traditional statistical models and the results showed that the AUC value of ML was generally higher than that in traditional statistical models.ConclusionsThe available evidence suggests that ML can accurately predict the occurrence of CA, and the performance is significantly superior to traditional statistical model in certain cases.
Objective To observe the correlation between the level of advanced glycosylation end products (AGE) in skin and diabetic retinopathy (DR), and establish and preliminatively verify the nomogramolumbaric model for predicting the risk of DR. MethodsA clinical case-control study. A total of 346 patients with type 2 diabetes mellitus (T2DM) who were admitted to the Department of Endocrinology and Ophthalmology of the First Affiliated Hospital of Zhengzhou University from January 2023 to June 2024 were included in the study. Among them, 198 were males and 148 were females. The mean age was (54.77±10.92). According to whether the patients were accompanied by DR, the patients were divided into the non-DR group (NDR group) and the DR group (DR group), 174 and 172 cases, respectively. All patients underwent skin AGE detection using a noninvasive diabetes detector. Diabetes duration, hemoglobin A1c (HbA1c), fasting plasma glucose, Urea, creatinine (Crea), uric acid, total cholesterol, triglyceride, estimated glomerular filtration rate (eGFR), urinary albumin concentration (UALB), and body mass index (BMI) were collected in detail. Univariate analysis and multivariate logistic regression analysis were used to determine the independent risk factors for T2DM concurrent DR, and to construct a nomogram prediction model for DR risk. Receiver operating characteristic curve (ROC curve), calibration curve and decision curve (DCA) were used to evaluate the model. ResultsHypertension prevalence rate (χ2=3.892), Diabetes duration (Z=−7.708), BMI (Z=−2.627), HbA1c (Z=−4.484), Urea (Z=−4.620), Crea (Z=−3.526), UALB (Z=−6.999), AGE (Z=−8.097) in DR group were significantly higher than those in NDR group, with statistical significance (P＜0.05); eGFR was lower than that in NDR group, the difference was statistically significant (Z=−6.061, P＜0.05). Logistic regression analysis showed that AGE, diabetes duration, HbA1c, UALB and eGFR were independent risk factors for DR (P＜0.05). Based on the results of multi-factor regression analysis, a nomogram prediction model was constructed. The area under ROC curve of the model was 0.843, 95% confidence interval was 0.802-0.884, sensitivity and specificity were 79.1% and 75.9%, respectively. The calibration curve was basically consistent with the ideal curve. The results of DCA analysis showed that when the model predicted the risk threshold of patients with DR between 0.17 and 0.99, the clinical net benefit provided by the nomogram model was＞0. ConclusionsSkin AGE level is an independent risk factor for DR. The nomogram prediction model based on AGE, diabetes duration, HbA1c, eGFR and UALB can accurately predict the risk of DR, and has good clinical practicability.
ObjectiveTo systematically evaluate postpartum depression risk prediction models in order to provide references for the construction, application and optimization of related prediction models. MethodsThe CNKI, VIP, WanFang Data, PubMed, Web of Science and EMbase were electronically searched to collect studies on predictive model for the risk of postpartum from January 2013 to April 2023. Two reviewers independently screened the literature, extracted data, and assessed the quality of the included studies based on PROBAST tool. ResultsA total of 10 studies, each study with 1 optimal model were evaluated. Common predictors included prenatal depression, age, smoking history, thyroid hormones and other factors. The area under the curve of the model was greater than 0.7, and the overall applicability was general. Overall high risk of bias and average applicability, mainly due to insufficient number of events in the analysis domain for the response variable, improper handling of missing data, screening of predictors based on univariate analysis, lack of model performance assessment, and consideration of model overfitting. ConclusionThe model is still in the development stage. The included model has good predictive performance and can help early identify people with high incidence of postpartum depression. However, the overall applicability of the model needs to be strengthened, a large sample, multi-center prospective clinical study should be carried out to construct the optimal risk prediction model of PPD, in order to identify and prevent PPD as soon as possible.
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.
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.
Diffuse choroidal retinal atrophy (DCA) is a type of myopic macular disease that presents with yellowish-white atrophic changes at the posterior pole of the eyeball. DCA is an important critical feature in the diagnosis of pathological myopia. Early intervention and treatment of this disease are of great significance in delaying the progression of pathological myopia and reducing the impairment of visual function. Ophthalmic imaging data can be used to diagnose the disease, and color fundus photography is the most simple and intuitive. Choroidal thickness is also a key indicator in the diagnosis of DCA, but the diagnostic critical value of choroidal thickness has not been clearly defined. With the development and popularization of artificial intelligence technology, the analysis of lesion imaging data is more objective and accurate. In the future, it is expected to actively establish a standard quantitative evaluation system for DCA by means of artificial intelligence to achieve early detection, early diagnosis and early treatment of pathological myopia.
ObjectiveTo explore the independent factors related to clinical severe events in community acquired pneumonia patients and to find out a simple, effective and more accurate prediction method.MethodsConsecutive patients admitted to our hospital from August 2018 to July 2019 were enrolled in this retrospective study. The endpoint was the occurrence of severe events defined as a condition as follows intensive care unit admission, the need for mechanical ventilation or vasoactive drugs, or 30-day mortality during hospitalization. The patients were divided into severe event group and non-severe event group, and general clinical data were compared between two groups. Multivariate logistic regression analysis was performed to identify the independent predictors of adverse outcomes. Receiver operating characteristic (ROC) curve was constructed to calculate and compare the area under curve (AUC) of different prediction methods.ResultsA total of 410 patients were enrolled, 96 (23.4%) of whom experienced clinical severe events. Age (OR: 1.035, 95%CI: 1.012 - 1.059, P=0.003), high-density lipoprotein (OR: 0.266, 95%CI: 0.088 - 0.802, P=0.019) and lactate dehydrogenase (OR: 1.006, 95%CI: 1.004 - 1.059, P<0.001) levels on admission were independent factors associated with clinical severe events in CAP patients. The AUCs in the prediction of clinical severe events were 0.744 (95%CI: 0.699 - 0.785, P=0.028) and 0.814 (95%CI: 0.772 - 0.850, P=0.025) for CURB65 and PSI respectively. CURB65-LH, combining CURB65, HDL and LDH simultaneously, had the largest AUC of 0.843 (95%CI: 0.804 - 0.876, P=0.022) among these prediction methods and its sensitivity (69.8%) and specificity (81.5%) were higher than that of CURB65 (61.5% and 76.1%) respectively.ConclusionCURB65-LH is a simple, effective and more accurate prediction method of clinical severe events in CAP patients, which not only has higher sensitivity and specificity, but also significantly improves the predictive value when compared with CURB65.