Search

Copyright of Journal of Modern Laboratory Medicine is the property of Journal of Modern Laboratory Medicine Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

临床预测模型可基于从群体获得的效应证据去预测个体的结局或风险，是链接循证医学和精准医学的强有力工具。随着数据测量、存储、互联互通及分析技术的不断进步，临床预测模型的应用前景将越来越明朗，但与此同时，也面临着诸多问题和挑战。本文对临床预测模型的基础概念、应用场景以及现在面临的困境和发展机遇做一个梳理。 Abstract: Clinical prediction models can predict individual outcomes or risks based on effect evidence obtained from the population, serving as a powerful tool linking evidence-based medicine and precision medicine. With the continuous advancement of data measurement, storage, interoperability, and analytical techniques, the application prospect for clinical prediction models is becoming increasingly clear. However, it also faces many problems and challenges. This paper aims to provide an overview of the fundamental concepts, application scenarios, current dilemmas, and development opportunities of clinical prediction models.

临床预测模型在医学领域的应用受到越来越多的关注和重视。合理且充足的样本量对预测模型研究的可行性和质量保障具有重要意义。基于此，本文总结了临床预测模型开发和验证中的样本量估算策略，提出了在样本量估算时需重点关注的问题，同时探讨了样本量不足的问题，以期能够帮助研究者合理地估算预测模型所需的样本量，从而提高临床预测模型研究的质量。 Abstract: The application of clinical prediction models in the medical field is receiving increasing attention. Reasonable and sufficient sample size is of great importance to the feasibility and quality assurance of prediction model research. Based on this, this paper summarized the strategies for sample size estimation in the development and validation of clinical prediction models, outlined the key issues that should be paid attention to in sample size estimation, and also discussed the problems related to insufficient sample size, to help researchers estimate the sample size reasonably and improve the quality of clinical prediction model research.

摘要： 临床预测模型在医学研究中的应用越来越广泛，欲达到良好的预测性能，选择正确的模型非常关键。对于预测模型类型的选择，预测结局的类型起着决定性作用。本文从数据类型的角度出发，将结局变量分为连续变量（正态分布、偏态分布）、分类变量（二分类、无序多分类、有序多分类）以及时间-事件变量（无竞争风险、有竞争风险），分别介绍不同类型结局变量的特点、对应的模型、建模案例以及SAS实现程序，以期为研究者构建预测模型提供参考。 Abstract: The application of clinical prediction models in medical research is becoming increasingly widespread. To achieve good predictive performance, selecting the correct model is crucial. Regarding the choice of prediction model, the type of prediction outcome plays a decisive role. This paper, from the perspective of data types, divided outcomes into continuous variables (normal distribution, skewed distribution), categorical variables (binary, nominal, ordinal), and time-to-event variables (with or without competing risks), introducing the characteristics of different types of outcomes, the model types, examples and SAS programs to serve as a reference for researchers to develop prediction models.

摘要： 推进医保支付方式改革是医保高质量发展的需要，更是减轻人民群众就医负担、增进民生福祉的需要。近年来，我国多元复合式医保支付方式改革取得积极进展，同时也对医保基金管理和医疗机构管理提出了更高要求。在医疗健康大数据背景下，临床预测模型被成熟应用于药物试验等领域，在量化评估患者所患疾病风险程度、医疗资源消耗强度等方面展现出较好的能力。本文旨在借鉴医保风险调整机制和风险预测模型相关国际经验，研究临床预测模型应用于医保支付方式改革下疾病诊断相关分组和医保偿付风险调整的可行性，为进一步提高医疗机构服务质量，提升医保基金使用效能提供参考。 Abstract: Advancing the reform of medical insurance payment methods is not only a necessity for the high-quality development of medical insurance, but also a requirement for alleviating the burden of people’s medical expenses and enhancing their well-being. In recent years, China has made positive progress in the reform of diversified and composite medical insurance payment methods, which has also raised higher requirements for the management of medical insurance funds and medical institutions. Against the backdrop of health big data, clinical prediction models have been maturely applied in areas such as drug trials, demonstrating good capabilities in quantitatively assessing the risk level of patients’ diseases and the intensity of medical resource consumption. This paper aims to draw lessons from international experiences in medical insurance risk adjustment mechanisms and risk prediction models, explore the feasibility of applying clinical prediction models to diagnosis related groups and medical insurance reimbursement risk adjustment under the reform of medical insurance payment methods, and provide corresponding references for further improving the quality of medical institution services and enhancing the efficiency of medical insurance fund utilization.

目的探讨基于光学相干断层扫描血管成像技术（OCTA），筛查糖尿病肾脏病（DKD）高风险人群的临床预测模型。方法本研究以567例糖尿病患者为研究对象，在逐步logistic回归分析的基础上，运用随机森林算法筛选纳入建模的指标，构建基于OCTA糖尿病肾脏病临床预测模型。通过受试者工作特征曲线评价模型区分度，通过决策曲线分析评估模型临床有效性。结果构建基于OCTA的DKD临床预测模型，ROC曲线下面积为0.878，Brier=0.11。结论本研究构建了基于OCTA结果进行糖尿病肾脏病临床预测的列线图预测模型，并从多维度验证模型，从而达到早期预警、提前实施干预的目的。

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

临床预测模型在大数据与精准医学时代对精准风险分层、个性化诊疗和管理愈发重要。现有的缺血性卒中复发风险预测模型在开发队列人群、预测因子、预测结局、开发方法以及预测性能上存在较大差异。此外，开发方法上的缺陷、报告内容上的不完整以及外部验证和模型影响研究的缺失，使其临床应用效果受限。因此，后续的临床预测模型研究，一方面，应重视现有模型的验证和评价；另一方面，在开发新预测模型时，在预测因子的选取、模型的选用和拟合、展示方式及结果报告上，应遵循相应的方法学规范，以提高预测性能。 Abstract: In the era of big data and precision medicine, clinical prediction models are increasingly important in precise risk stratification, personalized diagnosis, and management. However, existing ischemic stroke recurrence risk prediction models vary significantly in terms of the population used for development, predictive factors, predicted outcomes, development methods, and predictive performance. Additionally, limitations in development methods, reporting, external validation, and model impact research have limited their clinical applicability. Therefore, future research on clinical prediction models should prioritize the validation and evaluation of existing models, while also adhering to methodological standards when developing new prediction models. This includes selecting predictive factors, model fitting, presentation methods, and reporting results, with the aim of enhancing predictive performance.

本文结合临床预测模型领域专家指出的现有研究中的不恰当做法，介绍了临床预测模型研究中的常见误区，解析了为什么特定的做法会对模型质量产生不良影响，以及如何避免重蹈覆辙。同时，通过评价ChatGPT给出的答案，探讨ChatGPT用于提供方法学指导的可行性。 Abstract: Taking the inappropriate practices in existing research pointed out by a leading expert in clinical prediction models as examples, this paper introduced common misunderstandings in clinical prediction model research, explained why specific practices will jeopardize the model quality, and how to avoid repeating the same mistakes in future studies. The feasibility of using ChatGPT to provide methodological guidance is discussed by evaluating the answers given by ChatGPT.

Objective To develop an effective predicative histological staging model for thymic epithelial tumors (TETs) by combining clinical data and CT features. Methods 114 patients who underwent TET resection from January 2018 to January 2023 were divided into low-risk (LR, 33) and high-risk (HR, 81) groups. CT features including maximum lesion diameter, tumor shape, contour, calcification, unenhanced and arterial phase enhanced CT values, extent and homogeneity in enhancement were retrospectively evaluated. Based on the patient's clinical information including gender, age, history of smoking, and presence of myasthenia gravis along with the above imaging features, multi-factor logistics regression was used to select related factors to build a prediction model and create a nomogram. The performance of the prediction model was evaluated by receiver operating characteristic curve and calibration curve. Results Arterial phase CT value (P=0.002), extent of enhancement (P=0.002), homogeneity in enhancement (P=0.049), and age of patient (P=0.038) were independent predictors of histological HR and LR staging of TETs. None of the remaining characteristics were statistically different. Both the training set (AUC=0.779) and validation set (AUC= 0.810) of the model showed good discrimination. Conclusion Clinical data and CT features are valuable in differentiating the HR and LR stages of TETs. The constructed prediction model of nomogram has good diagnostic performance. [ABSTRACT FROM AUTHOR]

BACKGROUND: Current studies only predict the loss of cervical lordosis after cervical surgery through imaging measurement indicators and other indicators at present. There are a few articles summarizing these prediction indicators. This paper establishes a prediction model to summarize these prediction indicators. OBJECTIVE: To investigate the risk variables for severe loss of cervical lordosis following posterior cervical spondylotic myelopathy surgery, as well as to develop and validate the prediction model. METHODS: Retrospective analysis was performed on the cervical spondylotic myelopathy patients who underwent posterior approach of cervical surgery in the Affiliated Hospital of Xuzhou Medical University from January 2015 to January 2020 and met the inclusion criteria. The observation indexes included age, sex, body mass index, surgical technique chosen, the number of operation segments, accumulation of C2 or C7, C2-7 Cobb angle prior to operation, Cobb angle of operation segment, C7 slope angle, sagittal vertical angle of the cervical spine, C2-C7 curvature, extension range of motion, and flexion range of motion. The difference between the cervical spine’s C2-7 Cobb angle before and after surgery (ΔCL) was used to calculate the change in cervical lordosis. Those with ΔCL ≤ - 10° had significant loss of cervical lordosis, while those with ΔCL > -10° had less severe loss of cervical lordosis. Prediction models were created and validated by doing single-factor and multi-factor analyses on these parameters to identify pertinent risk factors. RESULTS AND CONCLUSION: 117 patients in all, 48 females and 69 males, met the inclusion criteria. The follow-up time ranged from 12 to 26 months. Among these patients, 30 experienced a severe loss of cervical lordosis following surgery, while 87 patients did not have a severe loss of cervical lordosis. Statistical analysis showed that the choice of procedure, whether it involved the C2 or C7 vertebral bodies, the C2-7 Cobb angle, the C7 slope angle, the C2-C7 curvature, and flexion range of motion prior to the procedure were independent risk factors linked to serious loss of cervical lordosis following posterior cervical surgery. Most obviously, whether the surgical segment involved the C2 or C7 segment (OR=3.524, 95% CI:1.127-11.013), and the surgical approach chosen (OR=3.165, 95% CI: 1.013-9.889) were the factors that enhanced the probability of significant postoperative curvature loss. Further foundations were laid for the clinical prediction model (nomogram) and its validation. The model has an excellent capacity for prediction, as evidenced by the C-index of internal validation, which was 0.91, and the C-index of external validation in the validation group, which was 0.87. It is indicated that after posterior cervical surgery, the choice of operation method, whether the operation segment involves the C2 or C7 segment, the preoperative C2-7 Cobb angle, the C7 slope angle, and flexion mobility all are high risks of severe loss of cervical lordosis. [ABSTRACT FROM AUTHOR]

Postoperative complications of colorectal cancer (CRC) are the main cause of postoperative death and seriously affect the quality of life and survival time of patients. The application of a clinical prediction model for postoperative complications of CRC can help promptly identify high-risk patients. Accordingly, reasonable intervention measures can be actively taken to reduce the incidence of postoperative complications of CRC. A scientific basis can also be provided to improve the prognosis of patients. In this work, literature on the risk-factor analysis and prediction-model construction of postoperative complications of CRC at home and abroad in recent years was collected and reviewed. The evaluation content and efficiency of the clinical prediction models in postoperative complications of CRC were summarized. Their advantages and disadvantages were also analyzed. The purpose of this study was to provide a reference for the subsequent optimization of such models and the development of a strong, clinically practical, and universal risk-screening tool for postoperative complications of CRC. [ABSTRACT FROM AUTHOR]

Copyright of Practical Pharmacy & Clinical Remedies is the property of Editorial Department of Practical Pharmacy & Clinical Remedies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Stroke is the property of Chinese Journal of Stroke Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective: To establish a clinical prediction model for AKI occurrence in patients with heart failure, and to provide evidence for early identification of high-risk patients. Methods: A retrospective analysis was performed on 350 patients with heart failure confirmed by the First Affiliated Hospital of Xinjiang Medical University from January 2018 to December 2020, including 104 patients (29.7%) with AKI and 246 patients (70.3%) without AKI. They were randomly divided into a modeling queue (n=245) and a validation queue (n=105) in a 7:3 ratio. The LASSO regression analysis modeling cohort was constructed, and the Norton diagram of HF-AKI patients was constructed based on logistic regression results. Meanwhile, the model was calibrated and the benefits of the model were verified. Results: 24 differential variables were obtained by univariate analysis, LASSO regression, multi-factor stepstep logistics regression, and finally 5 differential variables were obtained: age, length of stay, admission creatinine, ejection fraction, antibiotic use or not.The clinical prediction model of HF-AKI patients was constructed and plotted into Norton diagram. The ROC curve AUC of the Norton diagram of the constructed training group and the verification group were 0.730 and 0.794, respectively. Hosmer-leme show test showed that the goodness of fit of the verification group was not as good as that of the training group, but P＞0.05. It shows that the Norton diagram model also has good calibration degree. Conclusion: The clinical prediction model of HF-AKI was successfully constructed in this study. After a series of validation, it was suggested that both the training group and the validation group of this model had a net income range and had certain clinical value. [ABSTRACT FROM AUTHOR]

Objective To analyze the influencing factors of total cerebral small vessel disease (CSVD) burden, and establish clinical prediction models of total CSVD burden. Methods The data of CSVD patients who were admitted in Department of Neurology of Tangshan Gongren Hospital and underwent MRI scan from January 2020 to June 2021 were retrospectively analyzed. According to the total CSVD burden based on MRI, the subjects were divided into five groups: 0, 1, 2, 3 and 4 score groups. Multivariate logistic regression analysis was used to determine the independent influencing factors of total CSVD burden, to construct the clinical prediction model. Results A total of 812 cases were included in the analysis. Multivariate logistic regression analysis showed that aging (OR 1.068, 95%CI 1.054-1.082), hypertension (OR 2.056, 95%CI 1.533-2.721), new-onset acute stroke (OR 2.303, 95%CI 1.696-3.016), previous stroke (OR 3.251, 95%CI 2.377-4.233) were independent risk factors of total CSVD burden. The prediction model of different total CSVD burden as follows: Ln (total CSVD burden ≤n )=C-(0.066×age+0.721×hypertension+0.816×acute stroke+1.155×previous stroke), and when n is 0, 1, 2 and 3, the corresponding C value is 1.028, 2.887, 4.866 and 6.321, respectively. The goodness of fit of Pearson and Deviance tests were χ 2=2204.357, P =0.897 and χ 2’=1596.575, P ’=0.967, respectively. The accuracy of prediction was 83.4%. Conclusions Aging, hypertension, acute stroke and previous stroke are independent influencing factors of total CSVD burden, and the prediction model constructed based on the above factors had good predictive value. 目的 探讨不同危险因素对脑小血管病（cerebral small vessel disease，CSVD）患者CSVD总负荷的影响，并建立CSVD总负荷的临床预测模型。方法 回顾性分析2020年1月-2021年6月于唐山市工人医院神经内科连续就诊且接受头颅MRI检查的CSVD患者。通过影像学评估CSVD总负荷，并将研究对象分为总负荷0分组、1分组、2分组、3分组和4分组。采集患者年龄、性别、高血压、糖尿病、高同型半胱氨酸血症、吸烟和饮酒史、是否合并新发或既往卒中、是否存在颅内大动脉狭窄等指标，通过单因素和多因素logistic回归分析探索CSVD总负荷的独立影响因素并建立临床预测模型。结果 共纳入812例CSVD患者，多因素分析显示，增龄（OR 1.068，95%CI 1.054～1.082）、高血压（OR 2.056，95%CI 1.533～2.721）、合并新发卒中（OR 2.303，95%CI 1.696～3.016）、合并既往卒中（OR 3.251，95%CI 2.377～4.233）是CSVD总负荷增加的独立危险因素。CSVD总负荷的预测模型为Ln（CSVD总负荷≤n）=C-（0.066×年龄+0.721×高血压+0.816×新发卒中+1.155×既往卒中），总负荷n =0、1、2、3时，所对应的常量C分别为1.028、2.887、4.866和6.321。Pearson和Deviance检验模型拟合优度分别为χ 2=2204.357，P =0.897和χ 2’=1596.575，P’=0.967，预测总准确度为83.4%。结论 增龄、高血压、合并新发或既往卒中是CSVD患者CSVD总负荷的独立影响因素，并且经验证，基于上述因素建立的临床预测模型具较好的预测效能。 CSVD发病隐匿，早期对其危险因素进行预估及干预有助于减缓或阻断病程发展，减少疾病后期造成的严重脑功能损伤。本文建立的针对CSVD患者CSVD总负荷的预测模型，有助于临床上对不同危险因素进行综合判断，从而制订针对患者的个体化干预方案。