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.
The specific binding of T cell receptors (TCRs) to antigenic peptides plays a key role in the regulation and mediation of the immune process and provides an essential basis for the development of tumour vaccines. In recent years, studies have mainly focused on TCR prediction of major histocompatibility complex (MHC) class I antigens, but TCR prediction of MHC class II antigens has not been sufficiently investigated and there is still much room for improvement. In this study, the combination of MHC class II antigen peptide and TCR prediction was investigated using the ProtT5 grand model to explore its feature extraction capability. In addition, the model was fine-tuned to retain the underlying features of the model, and a feed-forward neural network structure was constructed for fusion to achieve the prediction model. The experimental results showed that the method proposed in this study performed better than the traditional methods, with a prediction accuracy of 0.96 and an AUC of 0.93, which verifies the effectiveness of the model proposed in this paper.
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.
Objective To explore the predicted precision of discharged patients number using curve estimation combined with trend-season model. Methods Curve estimation and trend-season model were both applied, and the quarterly number of discharged patients of 363 hospital from 2009 to 2015 was collected and analyzed in order to predict discharged patients in 2016. Relative error between predicted value and actual number was also calculated. Results An optimal quadratic regression equation Yt=3 006.050 1+202.350 8×t–3.544 4×t2 was established (Coefficient of determination R2=0.927, P<0.001), and a total of 23 462 discharged patients were predicted based on this equation combined with trend-season model, with a relative error of 1.79% compared to the actual number. Conclusion The curve estimation combined with trend-season model is a convenient and visual tool for predicting analysis. It has a high predicted accuracy in predicting the number of hospital discharged patients or outpatients, which can provide a reference basis for hospital operation and management.
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 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 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.
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.
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.
ObjectiveThis study intends to analyze the changing disease burden of mood disorders in China from 1990 to 2021 and project the epidemiological trends in the next two decades. MethodsThis study uses data from the Global Burden of Disease (GBD) 2021 database on three mood disorders in China (bipolar disorder, major depressive disorder, and dysthymia) from 1990 to 2021. The indicators such as age-standardized number of diseases and disability-adjusted life years (DALYs) were used to explore the characteristics of time, gender, and age distribution of the disease burden of mental disorders. The BAPC model was used to predict the disease burden in the next two decades. ResultsIn 2021, the number of cases of dysthymia, MDD, and BD in China was 27.84 million, 26.0 million, and 2.85 million, with an increase of 73.24%, 38.33%, and 36.79% compared with 1990, respectively. In 2021, DALYs of dysthymic disorder, MDD and BD were 2.67 million, 5.2 million and 0.61 million person-years, which increased by 71.45%, 34.29% and 34.76% compared with 1990, respectively. The burden of mood disorders is heavier among women and the middle-aged and elderly population. In addition, it is expected that ASPR and ASDR of dysthymia will continue to increase after a brief decline, MDD will show a downward trend, while BD will show a slight upward trend in the next two decades. ConclusionThe disease burden of mood disorders in China remains substantial, with dysthymia and BD showing persistent upward tendency. More resources should be invested in mental health care.