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 systematically review the predictors of enteral nutrition feeding intolerance in critically ill patients. MethodsThe PubMed, Web of Science, Cochrane Library, Embase, CNKI, WanFang Data, VIP and CBM databases were searched to collect relevant observational studies from the inception to 6 August, 2022. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias of the included studies. Meta-analysis was then performed using RevMan 5.4 software. ResultsA total of 18 studies were included, including 28 847 patients. The results of the meta-analysis showed that gender, age, severity of illness, hypo-albuminemia, length of stay, postpyloric feeding, mechanical ventilation and mechanical ventilation time, use of prokinetics, use of sedation drugs, use of vasoactive drugs and use of antibiotics were predictors of enteral nutrition feeding intolerance in critically ill patients, among which postpyloric feeding (OR=0.46, 95%CI 0.29 to 0.71, P<0.01) was a protective factor. ConclusionAccording to the influencing factors, the medical staff can formulate a targeted enteral nutrition program at the time of admission to the ICU to reduce the occurrence of feeding intolerance. Due to the limited quantity and quality of the included studies, more high-quality studies are needed to verify the above conclusion.
Objective To perform data-driven, assisted prediction of health insurance reimbursement ratios for the major thoracic surgery group in CHS-DRG, in addition to providing an optional solution for health insurance providers and medical institutions to accurately and effectively predict the references of health insurance payments for the patient group. Methods Using the information on major thoracic surgery cases from a large tertiary hospital in Sichuan province in 2020 as a sample, 70% of the total dataset was used as a training dataset and 30% as a test dataset. This data was used to predict health insurance spending through a multiple linear regression model and an improved machine learning method that is based on feature selection. Results When the number of filtered features was the same via three machine learning methods including random forest, logistic regression, and support vector machine, there was no significant difference in the prediction effectiveness. The model with the best prediction effect had an accuracy of 78.96%, sensitivity of 83.93%, specificity of 71.27%, precision of 0.818 8, AUC value of 0.841 4, and a Kappa value of 0.610 8. Conclusion The basic characteristics such as the number of disease diagnoses and surgical operations, as well as the age of patients affect the reimbursement ratio. The cost of materials, drugs, and treatments has a greater impact on the reimbursement ratio. The combined method of feature selection and machine learning outperforms traditional statistical linear models. When dealing with a larger dataset that has many features, selecting the right number can enhance the prediction ability and efficiency of the model.
Objective To explore the predictive factors for long-term adverse prognosis in patients with tuberculosis meningitis. Methods We retrospectively analyzed the clinical data (general clinical data, laboratory test results, and imaging findings) of hospitalized cases of tuberculosis meningitis admitted to West China Hospital of Sichuan University from 00:00:00 on August 1st, 2011 to 23:59:59 on July 31st, 2012. We collected data of prognosis results after 6 years of illness by telephone follow-up, and quantified outcome measures by modified Rankin Scale (mRS) score (0–6 points). According to the mRS score, the cases obtaining 0 points≤mRS<3 points were divided into the good prognosis group and the cases obtaining 3≤mRS≤6 points were divided into the poor prognosis group, logistic regression analysis was executed to find the independent risk factors affecting long-term poor prognosis. Results A total of 119 cases were included, including 63 males and 56 females; the average age was (35±17) years. Among them, 53 patients had poor prognosis and 66 patients had good prognosis. After univariate analysis, the age (t=–3.812, P<0.001), systolic blood pressure at admission (t=–2.009, P=0.049), Glasgow Coma Scale score (t=3.987, P<0.001), Medical Research Council (MRC) staging system (Z=–4.854, P<0.001), headache (χ2=4.101, P=0.043), alter consciousness (χ2=10.621, P=0.001), cognitive dysfunction (χ2=4.075, P=0.044), cranial nerve palsy (χ2=5.853, P=0.016), peripheral nerve dysfunction (χ2=14.925, P<0.001), meningeal irritation (χ2=7.174, P=0.007), serum potassium (t=3.080, P=0.003), cerebrospinal fluid protein content (Z=–2.568, P=0.010), cerebrospinal fluid chlorine (t=2.543, P=0.012), hydrocephalus (χ2=11.766, P=0.001), and cerebral infarction (χ2=6.539, P=0.012) were associated with long-term poor prognosis of tuberculosis meningitis. Multivariate analysis showed that age [odds ratio (OR)=1.061, 95% confidence interval (CI) (1.027, 1.096), P<0.001], peripheral nerve dysfunction [OR=3.537, 95%CI (1.070, 11.697), P=0.038], MRC Stage Ⅱ[OR=9.317, 95%CI (1.692, 51.303), P=0.010], MRC Stage Ⅲ [OR=43.953, 95%CI (3.996, 483.398), P=0.002] were the independent risk factors for long-term poor prognosis of tuberculosis meningitis. Hydrocephalus [OR=2.826, 95%CI (0.999, 8.200), P=0.050] might be an independent risk factor for long-term poor prognosis of tuberculosis meningitis. Conclusions Age, MRC staging system (Stage Ⅱ, Stage Ⅲ) and peripheral neurological dysfunction are chronic poor-prognostic independent risk factors for tuberculosis meningitis. Hydrocephalus may be associated with long-term adverse prognosis of tuberculosis meningitis
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.
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.
ObjectiveThis study aims to analyze the trends in Parkinson’s disease incidence rates among the elderly population in China from 1990 to 2021 and to forecast incidence growth over the next 20 years, providing. MethodsJoinpoint regression and age-period-cohort models were employed to analyze temporal trends in Parkinson’s disease incidence, and the Nordpred model was used to predict case numbers and incidence rates among the elderly in China from 2022 to 2044. ResultsFindings indicated a significant increase in Parkinson’s disease incidence among China’s elderly population from 1990 to 2021, with crude and age-standardized incidence rates rising from 95.37 per 100 000 and 111.05 per 100 000 to 170.52 per 100 000 and 183.91 per 100 000, respectively. Predictions suggested that by 2044, the number of cases will rise to approximately 878 264, with the age-standardized incidence rate reaching 223.4 per 100 000, and men showing significantly higher incidence rates than women. The rapid increase in both cases and incidence rates indicated that Parkinson’s disease will continue to impose a heavy disease burden on China’s elderly population. ConclusionThe burden of Parkinson’s disease in China’s elderly population has grown significantly and is expected to worsen. To address the rising incidence rates effectively, it is recommended to enhance early screening and health education for high-risk groups, improve diagnostic and treatment protocols, and prioritize resource allocation to Parkinson’s disease prevention and care services to reduce future public health burdens.
ObjectiveTo establish a forecasting model for inpatient cases of pediatric limb fractures and predict the trend of its variation.MethodsAccording to inpatient cases of pediatric limb fractures from January 2013 to December 2018, this paper analyzed its characteristics and established the seasonal auto-regressive integrated moving average (SARIMA) model to make a short-term quantitative forecast.ResultsA total of 4 451 patients, involving 2 861 males and 1 590 females were included. The ratio of males to females was 1.8 to 1, and the average age was 5.655. There was a significant difference in age distribution between males and females (χ2=44.363, P<0.001). The inpatient cases of pediatric limb fractures were recorded monthly, with predominant peak annually, from April to June and September to October, respectively. Using the data of the training set from January 2013 to May 2018, a SARIMA model of SARIMA (0,1,1)(0,1,1)12 model (white noise test, P>0.05) was identified to make short-term forecast for the prediction set from June 2018 to November 2018, with RMSE=8.110, MAPE=9.386, and the relative error between the predicted value and the actual value ranged from 1.61% to 8.06%.ConclusionsCompared with the actual cases, the SARIMA model fits well with good short-term prediction accuracy, and it can help provide reliable data support for a scientific forecast for the inpatient cases of pediatric limb fractures.
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 develop a score system to predict the probability of failure of monotherapy in epilepsy patients with initial treatment, and then provide pillars for early use of polytherapy.MethodsThis is a retrospective analysis of the clinical data of 189 patients with epilepsy treated in Department of Neurology, the Third Xiangya Hospital of Central South University from January 2019 to July 2020. Patients were divided into monotherapy acceptable group and monotherapy poor effect group according to their drug treatment plan and drug efficacy. The influencing factors were screened out by single factor analysis and binary logistic regression analysis. And on the basis of this β value, a quantitative scoring table for predicting the unsatisfying treatment effect of monotherapy is developed. And the receiver operating curve (ROC curve) was used to evaluate the effectiveness of the scale.ResultsBased on a standard of 75% reduction in seizures during the observation period, 138 cases (73%) were effective with monotherapy plan, while 51 cases (23%) were unsatisfactory. Regression analysis showed that multiple forms of seizures, status epilepticus (t2), brain damage, and the number of seizures ≥ 7 times before treatment are independent risk factors for poor outcome of monotherapy. The resulting score sheet has a total score of 12 points; the area under the ROC curve is 0.779, and the critical score is 6 points (sensitivity: 0.314; specificity: 0.957). Patients with more than this score have a strong probability of poor response in monotherapy.ConclusionThis prediction model can effectively assess the risk of unsatisfactory therapeutic effect of monotherapy in epilepsy patients who are initially treated, and thus has reference function for the early selection of polytherapy.