Search

Objective: Currently, distinct use of clinical data, routine laboratory indicators or the detection of diabetic autoantibodies in the diagnosis and management of diabetes mellitus is limited. Hence, this study was aimed to screen the indicators, and to establish and validate a multifactorial logistic regression model nomogram for the non-invasive differential prediction of type 1 diabetes mellitus. Methods: Clinical data, routine laboratory indicators, and diabetes autoantibody profiles of diabetic patients admitted between September 2018 and December 2022 were retrospectively analyzed. Logistic regression was used to select the independent influencing factors, and a prediction nomogram based on the multiple logistic regression model was constructed using these independent factors. Moreover, the predictive accuracy and clinical application value of the nomogram were evaluated using Receiver Operating Characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and clinical impact curves (CIC). Results: A total of 522 diabetic patients were included in this study. These patients were randomized into training and validation sets in a 7:3 ratio. The predictors screened included age, prealbumin (PA), high-density lipoprotein cholesterol (HDL-C), islet cells autoantibodies (ICA), islets antigen 2 autoantibodies (IA-2A), glutamic acid decarboxylase antibody (GADA), and Cpeptide levels. Based on these factors, a multivariate model nomogram was constructed, which had an Area Under Curve (AUC) of 0.966 and 0.961 for the training set and validation set, respectively. Subsequently, the calibration curves demonstrated a strong accuracy of the graph; the DCA and CIC results indicated that the graph could be used as a non-invasive valid predictive tool for the differential diagnosis of type 1 diabetes mellitus, clinically. Conclusion: The established prediction model combining patient's age, PA, HDL-C, ICA, IA-2A, GADA, and C-peptide can assist in differential diagnosis of type 1 diabetes mellitus and type 2 diabetes mellitus and provides a basis for the clinical as well as therapeutic management of the disease. [ABSTRACT FROM AUTHOR]

Objective To establish a prediction model for lymph node metastasis （LNM） of gastric cancer based on routine laboratory indicators using machine learning algorithms. Methods This study collected data of 741 gastric cancer patients at Affiliated Hospital of Nantong University between January 2020 and January 2022 for model training and testing. Additionally, data of 102 gastric cancer patients between January 2023 and October 2023 were collected for model validation. XGBoost algorithm was used to calculate the importance of indicators and filter out a set of important indicators from 66 indicators. Five machine learning algorithms, including K-Nearest Neighbor, Support Vector Machine, Multilayer Perceptron, Random Forest and Adaboost, were constructed and trained for comparative analysis. Furthermore, the stability and accuracy of the model were further validated on the validation set. Results This study selected a set of important indicators composed of 9 routine laboratory indicators and trained the gastric cancer LNM prediction model, named V9. Additionally, through comparative experiments, it was found that the Adaboost algorithm based on the boosting strategy had the best performance, with evaluation metrics such as area under the curve, F1 score, accuracy, sensitivity, and specificity ranging from 0.833 to 0.968. The accuracy of the predictions on the validation set was 94.12%. Conclusion V9 was a gastric cancer LNM prediction model that has auxiliary clinical diagnostic value. It can be used to assess the risk of patients accurately and provide a basis for clinical decision-making. [ABSTRACT FROM AUTHOR]

Background: Globally, 10–15% of maternal deaths are statistically attributable to preeclampsia. Compared with late-onset PE, the severity of early-onset PE remains more harmful with higher morbidity and mortality. Objective: To establish an early-onset preeclampsia prediction model by clinical characteristics, risk factors and routine laboratory indicators were investigated from pregnant women at 6 to 10 gestational weeks. Methods: The clinical characteristics, risk factors, and 38 routine laboratory indicators (6–10 weeks of gestation) including blood lipids, liver and kidney function, coagulation, blood count, and other indicators of 91 early-onset preeclampsia patients and 709 normal controls without early-onset preeclampsia from January 2010 to May 2021 in Peking University Third Hospital (PUTH) were retrospectively analyzed. A logistic regression, decision tree model, and support vector machine (SVM) model were applied for establishing prediction models, respectively. ROC curves were drawn; area under curve (AUCROC), sensitivity, and specificity were calculated and compared. Results: There were statistically significant differences in the rates of diabetes, antiphospholipid syndrome (APS), kidney disease, obstructive sleep apnea (OSAHS), primipara, history of preeclampsia, and assisted reproductive technology (ART) (p < 0.05). Among the 38 routine laboratory indicators, there were no significant differences in the levels of PLT/LYM, NEU/LYM, TT, D-Dimer, FDP, TBA, ALP, TP, ALB, GLB, UREA, Cr, P, Cystatin C, HDL-C, Apo-A1, and Lp(a) between the two groups (p > 0.05). The levels of the rest indicators were all statistically different between the two groups (p < 0.05). If only 12 risk factors of PE were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.78, 0.74, and 0.66, respectively, while 12 risk factors of PE and 38 routine laboratory indicators were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.86, 0.77, and 0.93, respectively. Conclusions: The efficacy of clinical risk factors alone in predicting early-onset preeclampsia is not high while the efficacy increased significantly when PE risk factors combined with routine laboratory indicators. The SVM model was better than logistic regression model and decision tree model in early prediction of early-onset preeclampsia incidence. [ABSTRACT FROM AUTHOR]

Background: Globally, 10–15% of maternal deaths are statistically attributable to preeclampsia. Compared with late-onset PE, the severity of early-onset PE remains more harmful with higher morbidity and mortality. Objective: To establish an early-onset preeclampsia prediction model by clinical characteristics, risk factors and routine laboratory indicators were investigated from pregnant women at 6 to 10 gestational weeks. Methods: The clinical characteristics, risk factors, and 38 routine laboratory indicators (6–10 weeks of gestation) including blood lipids, liver and kidney function, coagulation, blood count, and other indicators of 91 early-onset preeclampsia patients and 709 normal controls without early-onset preeclampsia from January 2010 to May 2021 in Peking University Third Hospital (PUTH) were retrospectively analyzed. A logistic regression, decision tree model, and support vector machine (SVM) model were applied for establishing prediction models, respectively. ROC curves were drawn; area under curve (AUCROC), sensitivity, and specificity were calculated and compared. Results: There were statistically significant differences in the rates of diabetes, antiphospholipid syndrome (APS), kidney disease, obstructive sleep apnea (OSAHS), primipara, history of preeclampsia, and assisted reproductive technology (ART) (p < 0.05). Among the 38 routine laboratory indicators, there were no significant differences in the levels of PLT/LYM, NEU/LYM, TT, D-Dimer, FDP, TBA, ALP, TP, ALB, GLB, UREA, Cr, P, Cystatin C, HDL-C, Apo-A1, and Lp(a) between the two groups (p > 0.05). The levels of the rest indicators were all statistically different between the two groups (p < 0.05). If only 12 risk factors of PE were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.78, 0.74, and 0.66, respectively, while 12 risk factors of PE and 38 routine laboratory indicators were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.86, 0.77, and 0.93, respectively. Conclusions: The efficacy of clinical risk factors alone in predicting early-onset preeclampsia is not high while the efficacy increased significantly when PE risk factors combined with routine laboratory indicators. The SVM model was better than logistic regression model and decision tree model in early prediction of early-onset preeclampsia incidence.

Background: Discriminating active tuberculosis (ATB) from latent tuberculosis infection (LTBI) remains challenging. The present study aims to evaluate the performance of diagnostic models established using machine learning based on routine laboratory indicators in differentiating ATB from LTBI.Methods: Participants were respectively enrolled at Tongji Hospital (discovery cohort) and Sino-French New City Hospital (validation cohort). Diagnostic models were established based on routine laboratory indicators using machine learning.Results: A total of 2619 participants (1025 ATB and 1594 LTBI) were enrolled in discovery cohort and another 942 subjects (388 ATB and 554 LTBI) were recruited in validation cohort. ATB patients had significantly higher levels of tuberculosis-specific antigen/phytohemagglutinin ratio and coefficient variation of red blood cell volume distribution width, and lower levels of albumin and lymphocyte count than those of LTBI individuals. Six models were built and the optimal performance was obtained from GBM model. GBM model derived from training set (n = 1965) differentiated ATB from LTBI in the test set (n = 654) with a sensitivity of 84.38% (95% CI, 79.42%-88.31%) and a specificity of 92.71% (95% CI, 89.73%-94.88%). Further validation by an independent cohort confirmed its encouraging value with a sensitivity of 87.63% (95% CI, 83.98%-90.54%) and specificity of 91.34% (95% CI, 88.70%-93.40%), respectively.Conclusions: We successfully developed a model with promising diagnostic value based on machine learning for the first time. Our study proposed that GBM model may be of great benefit served as a tool for the accurate identification of ATB. [ABSTRACT FROM AUTHOR]

Objective: Currently, distinct use of clinical data, routine laboratory indicators or the detection of diabetic autoantibodies in the diagnosis and management of diabetes mellitus is limited. Hence, this study was aimed to screen the indicators, and to establish and validate a multifactorial logistic regression model nomogram for the non-invasive differential prediction of type 1 diabetes mellitus., Methods: Clinical data, routine laboratory indicators, and diabetes autoantibody profiles of diabetic patients admitted between September 2018 and December 2022 were retrospectively analyzed. Logistic regression was used to select the independent influencing factors, and a prediction nomogram based on the multiple logistic regression model was constructed using these independent factors. Moreover, the predictive accuracy and clinical application value of the nomogram were evaluated using Receiver Operating Characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and clinical impact curves (CIC)., Results: A total of 522 diabetic patients were included in this study. These patients were randomized into training and validation sets in a 7:3 ratio. The predictors screened included age, prealbumin (PA), high-density lipoprotein cholesterol (HDL-C), islet cells autoantibodies (ICA), islets antigen 2 autoantibodies (IA-2A), glutamic acid decarboxylase antibody (GADA), and C-peptide levels. Based on these factors, a multivariate model nomogram was constructed, which had an Area Under Curve (AUC) of 0.966 and 0.961 for the training set and validation set, respectively. Subsequently, the calibration curves demonstrated a strong accuracy of the graph; the DCA and CIC results indicated that the graph could be used as a non-invasive valid predictive tool for the differential diagnosis of type 1 diabetes mellitus, clinically., Conclusion: The established prediction model combining patient's age, PA, HDL-C, ICA, IA-2A, GADA, and C-peptide can assist in differential diagnosis of type 1 diabetes mellitus and type 2 diabetes mellitus and provides a basis for the clinical as well as therapeutic management of the disease., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Xian, Du, Yuan, Li, Pei, Hao, Zeng, Wang and Ye.)