Predicting Risk of Insulin Resistance in a Chinese Population with Polycystic Ovary Syndrome: Designing and Testing a New Predictive Nomogram

Progress of the application clinical prediction model in polycystic ovary syndrome

Clinical prediction models play an important role in the field of medicine. These can help predict the probability of an individual suffering from disease, complications, and treatment outcomes by applying specific methodologies. Polycystic ovary syndrome (PCOS) is a common disease with a high incidence rate, huge heterogeneity, short- and long-term complications, and complex treatments. In this systematic review study, we reviewed the progress of clinical prediction models in PCOS patients, including diagnosis and prediction models for PCOS complications and treatment outcomes. We aimed to provide ideas for medical researchers and clues for the management of PCOS. In the future, models with poor accuracy can be greatly improved by adding well-known parameters and validations, which will further expand our understanding of PCOS in terms of precision medicine. By developing a series of predictive models, we can make the definition of PCOS more accurate, which can improve the diagnosis of PCOS and reduce the likelihood of false positives and false negatives. It will also help discover complications earlier and treatment outcomes being known earlier, which can result in better outcomes for women with PCOS.

A novel web-based calculator to predict 30-day all-cause in-hospital mortality for 7,202 elderly patients with heart failure in ICUs: a multicenter retrospective cohort study in the United States

Background and aims

Heart failure (HF) is a significant cause of in-hospital mortality, especially for the elderly admitted to intensive care units (ICUs). This study aimed to develop a web-based calculator to predict 30-day in-hospital mortality for elderly patients with HF in the ICU and found a relationship between risk factors and the predicted probability of death.

Methods and results

Data (N = 4450) from the MIMIC-III/IV database were used for model training and internal testing. Data (N = 2,752) from the eICU-CRD database were used for external validation. The Brier score and area under the curve (AUC) were employed for the assessment of the proposed nomogram. Restrictive cubic splines (RCSs) found the cutoff values of variables. The smooth curve showed the relationship between the variables and the predicted probability of death. A total of 7,202 elderly patients with HF were included in the study, of which 1,212 died. Multivariate logistic regression analysis showed that 30-day mortality of HF patients in ICU was significantly associated with heart rate (HR), 24-h urine output (24h UOP), serum calcium, blood urea nitrogen (BUN), NT-proBNP, SpO2, systolic blood pressure (SBP), and temperature (P < 0.01). The AUC and Brier score of the nomogram were 0.71 (0.67, 0.75) and 0.12 (0.11, 0.15) in the testing set and 0.73 (0.70, 0.75), 0.13 (0.12, 0.15), 0.65 (0.62, 0.68), and 0.13 (0.12, 0.13) in the external validation set, respectively. The RCS plot showed that the cutoff values of variables were HR of 96 bmp, 24h UOP of 1.2 L, serum calcium of 8.7 mg/dL, BUN of 30 mg/dL, NT-pro-BNP of 5121 pg/mL, SpO2 of 93%, SBP of 137 mmHg, and a temperature of 36.4°C.

Conclusion

Decreased temperature, decreased SpO2, decreased 24h UOP, increased NT-proBNP, increased serum BUN, increased or decreased SBP, fast HR, and increased or decreased serum calcium increase the predicted probability of death. The web-based nomogram developed in this study showed good performance in predicting 30-day in-hospital mortality for elderly HF patients in the ICU.

Development and validation of a carotid atherosclerosis risk prediction model based on a Chinese population

Purpose

This study aimed to identify independent risk factors for carotid atherosclerosis (CAS) and construct and validate a CAS risk prediction model based on the Chinese population.

Methods

This retrospective study included 4,570 Chinese adults who underwent health checkups (including carotid ultrasound) at the Zhenhai Lianhua Hospital, Ningbo, China, in 2020. All the participants were randomly assigned to the training and validation sets at a ratio of 7:3. Independent risk factors associated with CAS were identified using multivariate logistic regression analysis. The least absolute shrinkage and selection operator combined with 10-fold cross-validation were screened for characteristic variables, and nomograms were plotted to demonstrate the risk prediction model. C-index and receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA) were used to evaluate the risk model’s discrimination, calibration, and clinical applicability.

Results

Age, body mass index, diastolic blood pressure, white blood cell count, mean platelet volume, alanine transaminase, aspartate transaminase, and gamma-glutamyl transferase were identified as independent risk factors for CAS. In the training, internal validation, and external validation sets, the risk model showed good discriminatory power with C-indices of 0.961 (0.953–0.969), 0.953 (0.939–0.967), and 0.930 (0.920–0.940), respectively, and excellent calibration. The results of DCA showed that the prediction model could be beneficial when the risk threshold probabilities were 1–100% in all sets. Finally, a network computer (dynamic nomogram) was developed to facilitate the physicians’ clinical operations. The website is https://nbuhgq.shinyapps.io/DynNomapp/.

Conclusion

The development of risk models contributes to the early identification and prevention of CAS, which is important for preventing and reducing adverse cardiovascular and cerebrovascular events.

Construction and Analysis of a Joint Diagnosis Model of Random Forest and Artificial Neural Network for Obesity

Obesity is a significant global health concern since it is connected to a higher risk of several chronic diseases. As a consequence, obesity may be described as a condition that reduces human life expectancy and significantly impacts life quality. Because traditional obesity diagnosis procedures have several flaws, it is vital to design new diagnostic models to enhance current methods. More obesity-related markers have been discovered in recent years as a result of improvements and enhancements in gene sequencing technology. Using current gene expression profiles from the Gene Expression Omnibus (GEO) collection, we identified differentially expressed genes (DEGs) associated with obesity and found 12 important genes (CRLS1, ANG, ALPK3, ADSSL1, ABCC1, HLF, AZGP1, TSC22D3, F2R, FXN, PEMT, and SPTAN1) using a random forest classifier. ALPK3, HLF, FXN, and SPTAN1 are the only genes that have never been linked to obesity. We also used an artificial neural network to build a novel obesity diagnosis model and tested its diagnostic effectiveness using public datasets.

Construction of a Personalized Insulin Resistance Risk Assessment Tool in Xinjiang Kazakhs Based on Lipid- and Obesity-Related Indices

Purpose

This study aimed to explore the relationship between obesity- and lipid-related indices and insulin resistance (IR) and construct a personalized IR risk model for Xinjiang Kazakhs based on representative indices.

Methods

This cross-sectional study was performed from 2010 to 2012. A total of 2170 Kazakhs from Xinyuan County were selected as research subjects. IR was estimated using the homeostasis model assessment of insulin resistance. Multivariable logistic regression analysis, least absolute shrinkage and selection operator penalized regression analysis, and restricted cubic spline were applied to evaluate the association between lipid- and obesity-related indices and IR. The risk model was developed based on selected representative variables and presented using a nomogram. The model performance was assessed using the area under the ROC curve (AUC), the Hosmer–Lemeshow goodness-of-fit test, and decision curve analysis (DCA).

Results

After screening out 25 of the variables, the final risk model included four independent risk factors: smoking, sex, triglyceride-glucose (TyG) index, and body mass index (BMI). A linear dose–response relationship was observed for the BMI and TyG indices against IR risk. The AUC of the risk model was 0.720 based on an independent test and 0.716 based on a 10-fold cross-validation. Calibration curves showed good consistency between actual and predicted IR risks. The DCA demonstrated that the risk model was clinically effective.

Conclusion

The TyG index and BMI had the strongest association with IR among all obesity- and lipid-related indices, and the developed model was useful for predicting IR risk among Kazakh individuals.

Diabetic retinopathy risk prediction in patients with type 2 diabetes mellitus using a nomogram model

BACKGROUND

This study aims to develop a diabetic retinopathy (DR) hazard nomogram for a Chinese population of patients with type 2 diabetes mellitus (T2DM).

METHODS

We constructed a nomogram model by including data from 213 patients with T2DM between January 2019 and May 2021 in the Affiliated Hospital of Zunyi Medical University. We used basic statistics and biochemical indicator tests to assess the risk of DR in patients with T2DM. The patient data were used to evaluate the DR risk using R software and a least absolute shrinkage and selection operator (LASSO) predictive model. Using multivariable Cox regression, we examined the risk factors of DR to reduce the LASSO penalty. The validation model, decision curve analysis, and C-index were tested on the calibration plot. The bootstrapping methodology was used to internally validate the accuracy of the nomogram.

RESULTS

The LASSO algorithm identified the following eight predictive variables from the 16 independent variables: disease duration, body mass index (BMI), fasting blood glucose (FPG), glycated hemoglobin (HbA1c), homeostatic model assessment-insulin resistance (HOMA-IR), triglyceride (TG), total cholesterol (TC), and vitamin D (VitD)-T3. The C-index was 0.848 (95% CI: 0.798-0.898), indicating the accuracy of the model. In the interval validation, high scores (0.816) are possible from an analysis of a DR nomogram's decision curve to predict DR.

CONCLUSION

We developed a non-parametric technique to predict the risk of DR based on disease duration, BMI, FPG, HbA1c, HOMA-IR, TG, TC, and VitD.

Development and Evaluation of a New Predictive Nomogram for Predicting Risk of Herpes Zoster Infection in a Chinese Population with Type 2 Diabetes Mellitus

Purpose

To identify potential risk factors for herpes zoster infection in type 2 diabetes mellitus in southeast Chinese population.

Patients and Methods

We built a model involving 266 herpes zoster patients collecting data from January 2018 to December 2019. The least absolute shrinkage and selection operator (Lasso) predictive model was used to test herpes zoster virus risk using the patient data. Multivariate regression was conducted to decide which variable would be the strongest to decrease the Lasso penalty. The predictive model was tested using the C-index, a calibration plot, and decision curve study. External validity was verified by bootstrapping by counting probabilities.

Results

In the prediction nomogram, the prediction variables included age, sex, weight, length of hospital stay, infection, and blood pressure. The C-index of 0.844 (0.798–0.896) indicated substantial variability and thus the model was adjusted appropriately. A score of 0.825 was achieved somewhere in the above interval. Examination of the decision curve estimated that herpes zoster nomogram was useful when the intervention was determined at the 16 percent of the herpes zoster infection potential threshold.

Conclusion

The herpes zoster nomogram combines age, weight, position of the rash, 2-hour plasma glucose, glycosuria, serum creatinine, length of the hospital stay, and hypertension. This calculator can be used to assess the individual herpes zoster risks in patients diagnosed with type 2 diabetes mellitus.