Machine learning risk score for prediction of gestational diabetes in early pregnancy in Tianjin, China

The early prediction of gestational diabetes mellitus by machine learning models

BACKGROUND

We aimed to determine the best-performing machine learning (ML)-based algorithm for predicting gestational diabetes mellitus (GDM) with sociodemographic and obstetrics features in the pre-conceptional period.

METHODS

We collected the data of pregnant women who were admitted to the obstetric clinic in the first trimester. The maternal age, body mass index, gravida, parity, previous birth weight, smoking status, the first-visit venous plasma glucose level, the family history of diabetes mellitus, and the results of an oral glucose tolerance test of the patients were evaluated. The women were categorized into groups based on having and not having a GDM diagnosis and also as being nulliparous or primiparous. 7 common ML algorithms were employed to construct the predictive model.

RESULTS

97 mothers were included in the study. 19 and 26 nulliparous were with and without GDM, respectively. 29 and 23 primiparous were with and without GDM, respectively. It was found that the greatest feature importance variables were the venous plasma glucose level, maternal BMI, and the family history of diabetes mellitus. The eXtreme Gradient Boosting (XGB) Classifier had the best predictive value for the two models with the accuracy of 66.7% and 72.7%, respectively.

DISCUSSION

The XGB classifier model constructed with maternal sociodemographic findings and the obstetric history could be used as an early prediction model for GDM especially in low-income countries.

A stepwise prediction and interpretation of gestational diabetes mellitus: Foster the practical application of machine learning in clinical decision

Background

Machine learning has shown to be an effective method for early prediction and intervention of Gestational diabetes mellitus (GDM), which greatly decreases GDM incidence, reduces maternal and infant complications and improves the prognosis. However, there is still much room for improvement in data quality, feature dimension, and accuracy. The contributions and mechanism explanations of clinical data at different pregnancy stages to the prediction accuracy are still lacking. More importantly, current models still face notable obstacles in practical applications due to the complex and diverse input features and difficulties in redeployment. As a result, a simple, practical but accurate enough model is urgently needed.

Design and methods

In this study, 2309 samples from two public hospitals in Shenzhen, China were collected for analysis. Different algorithms were systematically compared to build a robust and stepwise prediction system (level A to C) based on advanced machine learning, and models under different levels were interpreted.

Results

XGBoost reported the best performance with ACC of 0.922, 0.859 and 0.850, AUC of 0.974, 0.924 and 0.913 for the selected level A to C models in the test set, respectively. Tree-based feature importance and SHAP method successfully identified the commonly recognized risk factors, while indicated new inconsistent impact trends for GDM in different stages of pregnancy.

Conclusion

A stepwise prediction system was successfully established. A practical tool that enables a quick prediction of GDM was released at https://github.com/ifyoungnet/MedGDM.This study is expected to provide a more detailed profiling of GDM risk and lay the foundation for the application of the model in practice.

A perspective on genetic and polygenic risk scores-advances and limitations and overview of associated tools

Polygenetic Risk Scores are used to evaluate an individual's vulnerability to developing specific diseases or conditions based on their genetic composition, by taking into account numerous genetic variations. This article provides an overview of the concept of Polygenic Risk Scores (PRS). We elucidate the historical advancements of PRS, their advantages and shortcomings in comparison with other predictive methods, and discuss their conceptual limitations in light of the complexity of biological systems. Furthermore, we provide a survey of published tools for computing PRS and associated resources. The various tools and software packages are categorized based on their technical utility for users or prospective developers. Understanding the array of available tools and their limitations is crucial for accurately assessing and predicting disease risks, facilitating early interventions, and guiding personalized healthcare decisions. Additionally, we also identify potential new avenues for future bioinformatic analyzes and advancements related to PRS.

Identification of influence factors in overweight population through an interpretable risk model based on machine learning: a large retrospective cohort

BACKGROUND

The identification of associated overweight risk factors is crucial to future health risk predictions and behavioral interventions. Several consensus problems remain in machine learning, such as cross-validation, and the resulting model may suffer from overfitting or poor interpretability.

METHODS

This study employed nine commonly used machine learning methods to construct overweight risk models. The general community are the target of this study, and a total of 10,905 Chinese subjects from Ningde City in Fujian province, southeast China, participated. The best model was selected through appropriate verification and validation and was suitably explained.

RESULTS

The overweight risk models employing machine learning exhibited good performance. It was concluded that CatBoost, which is used in the construction of clinical risk models, may surpass previous machine learning methods. The visual display of the Shapley additive explanation value for the machine model variables accurately represented the influence of each variable in the model.

CONCLUSIONS

The construction of an overweight risk model using machine learning may currently be the best approach. Moreover, CatBoost may be the best machine learning method. Furthermore, combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Recent advancement in integrating artificial intelligence and information technology with real-world data for clinical decision-making in China: A scoping review

OBJECTIVE

Striking innovations and advancements have been achieved with the use of artificial intelligence and healthcare information technology being integrated into clinical real-world data. The current scoping review aimed to provide an overview of the current status of artificial intelligence-/information technology-based clinical decision support tools in China.

METHODS

PubMed/MEDLINE, Embase, China National Knowledge Internet, and Wanfang data were searched for both English and Chinese literature. The gray literature search was conducted for commercially available tools. Original studies that focused on clinical decision support tools driven by artificial intelligence or information technology in China and were published between 2010 and February 2022 were included. Information extracted from each article was further synthesized by themes based on three types of clinical decision-making.

RESULTS

A total of 37 peer-reviewed publications and 13 commercially available tools were included in the final analysis. Among them, 32.0% were developed for disease diagnosis, 54.0% for risk prediction and classification, and 14.0% for disease management. Chronic diseases were the most popular therapeutic areas of exploration, with particular emphasis on cardiovascular and cerebrovascular diseases. Single-center electronic medical records were the mainstream data sources leveraged to inform clinical decision-making, with internal validation being predominately used for model evaluation.

CONCLUSIONS

To effectively promote the extensive use of real-world data and drive a paradigm shift in clinical decision-making in China, multidisciplinary collaboration of key stakeholders is urgently needed.

Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features

Patients with parathyroid carcinoma (PC) are often diagnosed postoperatively, due to incomplete resection during the initial surgery, resulting in poor outcomes. The aim of our study was to investigate the pre-surgery indicators of PC and try to develop a predictive model for PC utilizing machine learning. Evaluation of pre-surgery neuropsychological function and confirmation of pathology were carried out in 133 patients with primary hyperparathyroidism in Beijing Chaoyang Hospital from December 2019 to January 2023. Patients were randomly divided into a training cohort (n = 93) and a validating cohort (n = 40). Analysis of the clinical dataset, two machine learning including the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression were utilized to develop the prediction model for PC. Logistic regression analysis was also conducted for comparison. Significant differences in elevated parathyroid hormone and decreased serum phosphorus in PC compared to (BP). The lower score of MMSE and MOCA was observed in PC and a cutoff of MMSE < 24 was the optimal threshold to stratify PC from BP (area under the curve AUC 0.699 vs 0.625). The predicted probability of PC by machine learning was similar to the observed probability in the test set, whereas the logistic model tended to overpredict the possibility of PC. The XGBoost model attained a higher AUC than the logistic algorithms and LASSO models. (0.835 vs 0.683 vs 0.607). Preoperative cognitive function may be a probable predictor for PC. The cognitive function-based prediction model based on the XGBoost algorithm outperformed LASSO and logistic regression, providing valuable preoperative assistance to surgeons in clinical decision-making for patients suspected PC.

Integrate prediction of machine learning for single ACoA rupture risk: a multicenter retrospective analysis

Background

Statistically, Anterior communicating aneurysm (ACoA) accounts for 30 to 35% of intracranial aneurysms. ACoA, once ruptured, will have an acute onset and cause severe neurological dysfunction and even death. Therefore, clinical analysis of risk factors related to ACoA and the establishment of prediction model are the benefits to the primary prevention of ACoA.

Methods

Among 1,436 cases of single ACoA patients, we screened 1,325 valid cases, classified risk factors of 1,124 cases in the ruptured group and 201 cases in the unruptured group, and assessed the risk factors, respectively, and predicted the risk of single ACoA rupture by using the logistic regression and the machine learning.

Results

In the ruptured group (84.8%) of 1,124 cases and the unruptured group (15.2%) of 201 cases, the multivariable logistic regression (MLR) model shows hemorrhagic stroke history (OR 95%CI, p:0.233 (0.120-0.454),<0.001) and the age stratification of 60-69 years (OR 95%CI, p:0.425 (0.271-0.668),<0.001) has a significant statistic difference. In the RandomForest (RF) model, hemorrhagic stroke history and age are the best predictive factors.

Conclusion

We combined the analysis of MLR, RF, and PCA models to conclude that hemorrhagic stroke history and gender affect single ACoA rupture. The RF model with web dynamic nomogram, allows for real-time personalized analysis based on different patients' conditions, which is a tremendous advantage for the primary prevention of single ACoA rupture.

Clinical trial registration

https://www.chictr.org.cn/showproj.html?proj=178501.

Development of machine learning models to predict gestational diabetes risk in the first half of pregnancy

BACKGROUND

Early prediction of Gestational Diabetes Mellitus (GDM) risk is of particular importance as it may enable more efficacious interventions and reduce cumulative injury to mother and fetus. The aim of this study is to develop machine learning (ML) models, for the early prediction of GDM using widely available variables, facilitating early intervention, and making possible to apply the prediction models in places where there is no access to more complex examinations.

METHODS

The dataset used in this study includes registries from 1,611 pregnancies. Twelve different ML models and their hyperparameters were optimized to achieve early and high prediction performance of GDM. A data augmentation method was used in training to improve prediction results. Three methods were used to select the most relevant variables for GDM prediction. After training, the models ranked with the highest Area under the Receiver Operating Characteristic Curve (AUCROC), were assessed on the validation set. Models with the best results were assessed in the test set as a measure of generalization performance.

RESULTS

Our method allows identifying many possible models for various levels of sensitivity and specificity. Four models achieved a high sensitivity of 0.82, a specificity in the range 0.72-0.74, accuracy between 0.73-0.75, and AUCROC of 0.81. These models required between 7 and 12 input variables. Another possible choice could be a model with sensitivity of 0.89 that requires just 5 variables reaching an accuracy of 0.65, a specificity of 0.62, and AUCROC of 0.82.

CONCLUSIONS

The principal findings of our study are: Early prediction of GDM within early stages of pregnancy using regular examinations/exams; the development and optimization of twelve different ML models and their hyperparameters to achieve the highest prediction performance; a novel data augmentation method is proposed to allow reaching excellent GDM prediction results with various models.

Clinical First-Trimester Prediction Models for Gestational Diabetes Mellitus: A Systematic Review and Meta-Analysis

BACKGROUND

Gestational diabetes mellitus (GDM) is a common pregnancy complication that negatively impacts the health of both the mother and child. Early prediction of the risk of GDM may permit prompt and effective interventions. This systematic review and meta-analysis aimed to summarize the study characteristics, methodological quality, and model performance of first-trimester prediction model studies for GDM.

METHODS

Five electronic databases, one clinical trial register, and gray literature were searched from the inception date to March 19, 2022. Studies developing or validating a first-trimester prediction model for GDM were included. Two reviewers independently extracted data according to an established checklist and assessed the risk of bias by the Prediction Model Risk of Bias Assessment Tool (PROBAST). We used a random-effects model to perform a quantitative meta-analysis of the predictive power of models that were externally validated at least three times.

RESULTS

We identified 43 model development studies, six model development and external validation studies, and five external validation-only studies. Body mass index, maternal age, and fasting plasma glucose were the most commonly included predictors across all models. Multiple estimates of performance measures were available for eight of the models. Summary estimates range from 0.68 to 0.78 (I² ranged from 0% to 97%).

CONCLUSION

Most studies were assessed as having a high overall risk of bias. Only eight prediction models for GDM have been externally validated at least three times. Future research needs to focus on updating and externally validating existing models.

A machine learning approach for early prediction of gestational diabetes mellitus using elemental contents in fingernails

The aim of this pilot study was to predict the risk of gestational diabetes mellitus (GDM) by the elemental content in fingernails and urine with machine learning analysis. Sixty seven pregnant women (34 control and 33 GDM patient) were included. Fingernails and urine were collected in the first and second trimesters, respectively. The concentrations of elements were determined by inductively coupled plasma-mass spectrometry. Logistic regression model was applied to estimate the adjusted odd ratios and 95% confidence intervals. The predictive performances of multiple machine learning algorithms were evaluated, and an ensemble model was built to predict the risk for GDM based on the elemental contents in the fingernails. Beryllium, selenium, tin and copper were positively associated with the risk of GDM while nickel and mercury showed opposite result. The trained ensemble model showed larger area under curve (AUC) of receiver operating characteristic curve (0.81) using fingernail Ni, Cu and Se concentrations. The model was validated by external data set with AUC = 0.71. In summary, the results of the present study highlight the potential of fingernails, as an alternative sample, together with machine learning in human biomonitoring studies.

Prediction model for gestational diabetes mellitus using the XG Boost machine learning algorithm

OBJECTIVE

To develop the extreme gradient boosting (XG Boost) machine learning (ML) model for predicting gestational diabetes mellitus (GDM) compared with a model using the traditional logistic regression (LR) method.

METHODS

A case-control study was carried out among pregnant women, who were assigned to either the training set (these women were recruited from August 2019 to November 2019) or the testing set (these women were recruited in August 2020). We applied the XG Boost ML model approach to identify the best set of predictors out of a set of 33 variables. The performance of the prediction model was determined by using the area under the receiver operating characteristic (ROC) curve (AUC) to assess discrimination, and the Hosmer-Lemeshow (HL) test and calibration plots to assess calibration. Decision curve analysis (DCA) was introduced to evaluate the clinical use of each of the models.

RESULTS

A total of 735 and 190 pregnant women were included in the training and testing sets, respectively. The XG Boost ML model, which included 20 predictors, resulted in an AUC of 0.946 and yielded a predictive accuracy of 0.875, whereas the model using a traditional LR included four predictors and presented an AUC of 0.752 and yielded a predictive accuracy of 0.786. The HL test and calibration plots show that the two models have good calibration. DCA indicated that treating only those women whom the XG Boost ML model predicts are at risk of GDM confers a net benefit compared with treating all women or treating none.

CONCLUSIONS

The established model using XG Boost ML showed better predictive ability than the traditional LR model in terms of discrimination. The calibration performance of both models was good.

Prevalence and Early Prediction of Diabetes Using Machine Learning in North Kashmir: A Case Study of District Bandipora

Diabetes is one of the biggest health problems that affect millions of people across the world. Uncontrolled diabetes can increase the risk of heart attack, cancer, kidney damage, blindness, and other illnesses. Researchers are motivated to create a Machine Learning methodology that can predict diabetes in the future. Exploiting Machine Learning Algorithms (MLA) is essential if healthcare professionals are able to identify diseases more effectively. In order to improve the medical diagnosis of diabetes this research explored and contrasts various MLA that can identify diabetes risk early. The research includes the analysis on real datasets such as a clinical dataset gathered from a doctor in the Indian district of Bandipora in the years April 2021–Feb2022. MLA are currently important in the healthcare sector due to their prediction abilities. Researchers are using MLA to improve disease prediction and reduce cost. In this Paper author developed a methodology using Machine Learning Algorithms for Diabetes Disease Risk Prediction in North Kashmir. Six MLA have been successfully used in the experimental study such as Random Forest (RF), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boost (GB), Decision Tree (DT), and Logistic Regression (LR). RF is the most accurate classifier with the uppermost accuracy rate of 98 percent followed by MLP (90.99%), SVM (92%), GBC (97%), DT (96%), and LR (69%), respectively, with the balanced data set. Lastly, this study enables us to effectively identify the prevalence and prediction of diabetes.

On AI Approaches for Promoting Maternal and Neonatal Health in Low Resource Settings: A Review

A significant challenge for hospitals and medical practitioners in low- and middle-income nations is the lack of sufficient health care facilities for timely medical diagnosis of chronic and deadly diseases. Particularly, maternal and neonatal morbidity due to various non-communicable and nutrition related diseases is a serious public health issue that leads to several deaths every year. These diseases affecting either mother or child can be hospital-acquired, contracted during pregnancy or delivery, postpartum and even during child growth and development. Many of these conditions are challenging to detect at their early stages, which puts the patient at risk of developing severe conditions over time. Therefore, there is a need for early screening, detection and diagnosis, which could reduce maternal and neonatal mortality. With the advent of Artificial Intelligence (AI), digital technologies have emerged as practical assistive tools in different healthcare sectors but are still in their nascent stages when applied to maternal and neonatal health. This review article presents an in-depth examination of digital solutions proposed for maternal and neonatal healthcare in low resource settings and discusses the open problems as well as future research directions.

Analytical Comparison of Risk Prediction Models for the Onset of Macrosomia Based on Three Statistical Methods

Background and Purpose. Fetal overgrowth can pose a serious threat to the safety of a mother and child. Early identification of high-risk pregnant women and timely pregnancy intervention and guidance are of great value in preventing the development of giant babies and improving adverse maternal and infant outcomes. The current clinical methods for predicting macrosomia mainly rely on obstetric examination and imaging, but their accuracy is controversial. And there is no accepted method for accurately predicting macrosomia. We investigated the risk factors influencing the occurrence of macrosomia and established a prediction model for the occurrence of macrosomia to provide a reference basis for interventions to prevent macrosomia. Method. A retrospective selection of 93 women who were hospitalized in our hospital from March 2019 to May 2022 with a singleton pregnancy and delivered at term with macrosomia were the study group. And 356 women who delivered a normal size baby during the same period were the control group. The variables that were associated with the onset of macrosomia were screened from maternal medical records. Logistic regression models, random forest, and CART decision tree models were developed using the screened variables as input variables and whether they were macrosomia as outcome variables, respectively. The performance of the three models was evaluated by accuracy, precision, recall, F1 score, and receiver operating characteristic curve (ROC). Result. The risk prediction models for the onset of macrosomia, logistic regression model, random forest model, and decision tree, were successfully developed, with accuracies of 0.904, 1.000, and 0.901 in the training set and 0.926, 0.582, and 0.852 in the validation set, respectively. The AUC in the training set were 0.898, 1.000, and 0.789, and in the validation set were 0.906, 0.913, and 0.731, respectively. In general, the logistic regression model has the highest diagnostic efficiency, followed by the random forest model. Conclusion. Logistic regression models have high application value in the assessment of predicting the risk of macrosomia, and it is suggested that the advantages of logistic regression models and random forest models should be combined in future studies and applications to make them work better in the prediction of the risk of macrosomia.

A Decision Support System for Diagnosing Diabetes Using Deep Neural Network

Background and Objective

According to the WHO, diabetes mellitus is a long-term condition marked by high blood sugar levels. The consequences might be far-reaching. According to current increases in mortality, diabetes has risen to number 10 among the leading causes of mortality worldwide. When used to predict diabetes using unbalanced datasets from testing, machine learning (ML) classifiers and established approaches for encoding categorical data have exhibited a broad variety of surprising outcomes. Early studies also made use of an artificial neural network to extract features without obtaining a grasp of the sequence information.

Methods

This study offers a deep learning-based decision support system (DSS), utilizing bidirectional long/short-term memory (BiLSTM), to accurately predict diabetic illness from patient data. In order to predict diabetes, the BiLSTM hybrid model was used after balancing the data set.

Results

Unlike earlier studies, this proposed model's trial findings were promising, with an accuracy of 93.07%, 93% precision, 92% recall, and a 92% F1-score.

Conclusions

Using a BILSTM model for classification outperforms current approaches in the diabetes detection domain.

Elevated serum triglyceride levels at first prenatal visit is associated with the development of gestational diabetes mellitus

AIMS

While several studies have indicated that maternal serum lipid profiles are associated with the development of gestational diabetes mellitus (GDM), the results have been inconsistent. This study aimed to explore the relationship between maternal lipids profiles at first prenatal visit and GDM and determine the optimal cut-off values of possible trimester-specific variables in predicting GDM.

MATERIALS AND METHODS

Clinical data of women with singleton pregnancies who delivered in Xinhua Hospital between January 2016 and January 2017 were collected from electronic databases. Multivariate logistic regression was used to determine the potential risk factors of GDM (specific to the trimester at first prenatal visit), including age, body mass index (BMI), and serum lipid profile and fasting plasma glucose (FPG) levels. The receiver operating characteristic (ROC) curve analysis was performed to determine the cut-off values of significant variables.

RESULTS

Among the 2191 pregnant women included, 315 (14.38%) were diagnosed with GDM. Of these, 880 (40.16%) had their first prenatal visit before 14 gestational weeks. Univariate and multivariate analyses showed that both FPG and triglyceride (TG) levels in the first and second trimesters were associated with a high risk of GDM (p < 0.05). The ROC curve showed that serum TG levels >1.235 mmol/L and >1.525 mmol/L in the first and second trimesters, respectively, were significantly associated with the development of GDM (p < 0.05).

CONCLUSIONS

TG levels at first prenatal visit is associated with GDM risk. Different TG cut-off values should be applied in the different trimesters of pregnancy for GDM screening.

Perspectives from metabolomics in the early diagnosis and prognosis of gestational diabetes mellitus

Gestational diabetes mellitus (GDM) is one of the most common metabolic disorders in pregnant women. The early detection of GDM provides an opportunity for the effective treatment of hyperglycemia in pregnancy, thus decreasing the risk of adverse perinatal outcomes for mothers and newborns. Metabolomics, an emerging technique, offers a novel point of view in understanding the onset and development of diseases and has been repeatedly used in various gestational periods in recent studies of GDM. Moreover, metabolomics provides varied opportunities in the different diagnoses of GDM from prediabetes or predisposition to diabetes, the diagnosis of GDM at a gestational age several weeks earlier than that used in the traditional method, and the assessment of prognosis considering the physiologic subtypes of GDM and clinical indexes. Longitudinal metabolomics truly facilitates the dynamic monitoring of metabolic alterations over the course of pregnancy. Herein, we review recent advancements in metabolomics and summarize evidence from studies on the application of metabolomics in GDM, highlighting the aspects of the diagnosis and differential diagnoses of GDM in an early stage. We also discuss future study directions concerning the physiologic subtypes, prognosis, and limitations of metabolomics.

An early model to predict the risk of gestational diabetes mellitus in the absence of blood examination indexes: application in primary health care centres

Background

Gestational diabetes mellitus (GDM) is one of the critical causes of adverse perinatal outcomes. A reliable estimate of GDM in early pregnancy would facilitate intervention plans for maternal and infant health care to prevent the risk of adverse perinatal outcomes. This study aims to build an early model to predict GDM in the first trimester for the primary health care centre.

Methods

Characteristics of pregnant women in the first trimester were collected from eastern China from 2017 to 2019. The univariate analysis was performed using SPSS 23.0 statistical software. Characteristics comparison was applied with Mann-Whitney U test for continuous variables and chi-square test for categorical variables. All analyses were two-sided with p < 0.05 indicating statistical significance. The train_test_split function in Python was used to split the data set into 70% for training and 30% for test. The Random Forest model and Logistic Regression model in Python were applied to model the training data set. The 10-fold cross-validation was used to assess the model’s performance by the areas under the ROC Curve, diagnostic accuracy, sensitivity, and specificity.

Results

A total of 1,139 pregnant women (186 with GDM) were included in the final data analysis. Significant differences were observed in age (Z=−2.693, p=0.007), pre-pregnancy BMI (Z=−5.502, p<0.001), abdomen circumference in the first trimester (Z=−6.069, p<0.001), gravidity (Z=−3.210, p=0.001), PCOS (χ²=101.024, p<0.001), irregular menstruation (χ²=6.578, p=0.010), and family history of diabetes (χ²=15.266, p<0.001) between participants with GDM or without GDM. The Random Forest model achieved a higher AUC than the Logistic Regression model (0.777±0.034 vs 0.755±0.032), and had a better discrimination ability of GDM from Non-GDMs (Sensitivity: 0.651±0.087 vs 0.683±0.084, Specificity: 0.813±0.075 vs 0.736±0.087).

Conclusions

This research developed a simple model to predict the risk of GDM using machine learning algorithm based on pre-pregnancy BMI, abdomen circumference in the first trimester, age, PCOS, gravidity, irregular menstruation, and family history of diabetes. The model was easy in operation, and all predictors were easily obtained in the first trimester in primary health care centres.

Nonalcoholic fatty liver disease and early prediction of gestational diabetes using machine learning methods

Background/Aims

To develop an early prediction model for gestational diabetes mellitus (GDM) using machine learning and to evaluate whether the inclusion of nonalcoholic fatty liver disease (NAFLD)-associated variables increases the performance of model.

Methods

This prospective cohort study evaluated pregnant women for NAFLD using ultrasound at 10–14 weeks and screened them for GDM at 24–28 weeks of gestation. The clinical variables before 14 weeks were used to develop prediction models for GDM (setting 1, conventional risk factors; setting 2, addition of new risk factors in recent guidelines; setting 3, addition of routine clinical variables; setting 4, addition of NALFD-associated variables, including the presence of NAFLD and laboratory results; and setting 5, top 11 variables identified from a stepwise variable selection method). The predictive models were constructed using machine learning methods, including logistic regression, random forest, support vector machine, and deep neural networks.

Results

Among 1,443 women, 86 (6.0%) were diagnosed with GDM. The highest performing prediction model among settings 1–4 was setting 4, which included both clinical and NAFLD-associated variables (area under the receiver operating characteristic curve [AUC] 0.563–0.697 in settings 1–3 vs. 0.740–0.781 in setting 4). Setting 5, with top 11 variables (which included NAFLD and hepatic steatosis index), showed similar predictive power to setting 4 (AUC 0.719–0.819 in setting 5, P=not significant between settings 4 and 5).

Conclusions

We developed an early prediction model for GDM using machine learning. The inclusion of NAFLD-associated variables significantly improved the performance of GDM prediction. (ClinicalTrials.gov Identifier: NCT02276144)

Comparing the bone mineral density among male patients with latent autoimmune diabetes and classical type 1 and type 2 diabetes, and exploring risk factors for osteoporosis

AIMS

This study aimed to compare the bone mineral densities (BMDs) among male patients with latent autoimmune diabetes in adults (LADA), classical type 1 diabetes (T1DM), and type 2 diabetes (T2DM), and to examine the risk factors for developing low BMD in these patients.

PATIENTS AND METHODS

Between January 2017 and October 2020, a total of 57, 67, and 223 male patients with LADA, classical T1DM, and T2DM, respectively, were recruited from the endocrinology department of Shanghai Tenth People's Hospital. Hormonal markers of bone metabolism, lipid profiles, uric acid, glycosylated hemoglobin A1c (HbA1c), and beta-cell function were measured using blood samples. BMD was measured at the lumbar spine, femoral neck, and right hip by dual-energy X-ray absorptiometry.

RESULTS

The mean BMD values from all three skeletal sites in male patients with LADA were comparable to those with classical T1DM but were much lower than those with T2DM. After adjusting for confounding factors, multiple linear regression analysis demonstrated that in all male patients with diabetes, body mass index (BMI), uric acid, and fasting C-peptide showed significant positive associations with BMD at all three skeletal sites; however, osteocalcin showed a negative association at all three sites.

CONCLUSIONS

Compared with male patients with T2DM, lower BMDs were observed in patients with LADA and T1DM. Low BMI, uric acid, C-peptide levels, and high osteocalcin levels are risk factors for developing low BMD in male patients with diabetes.

Machine Learning Prediction Models for Gestational Diabetes Mellitus: A meta- analysis (Preprint)

Background

Gestational diabetes mellitus (GDM) is a common endocrine metabolic disease, involving a carbohydrate intolerance of variable severity during pregnancy. The incidence of GDM-related complications and adverse pregnancy outcomes has declined, in part, due to early screening. Machine learning (ML) models are increasingly used to identify risk factors and enable the early prediction of GDM.

Objective

The aim of this study was to perform a meta-analysis and comparison of published prognostic models for predicting the risk of GDM and identify predictors applicable to the models.

Methods

Four reliable electronic databases were searched for studies that developed ML prediction models for GDM in the general population instead of among high-risk groups only. The novel Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias of the ML models. The Meta-DiSc software program (version 1.4) was used to perform the meta-analysis and determination of heterogeneity. To limit the influence of heterogeneity, we also performed sensitivity analyses, a meta-regression, and subgroup analysis.

Results

A total of 25 studies that included women older than 18 years without a history of vital disease were analyzed. The pooled area under the receiver operating characteristic curve (AUROC) for ML models predicting GDM was 0.8492; the pooled sensitivity was 0.69 (95% CI 0.68-0.69; P<.001; I²=99.6%) and the pooled specificity was 0.75 (95% CI 0.75-0.75; P<.001; I²=100%). As one of the most commonly employed ML methods, logistic regression achieved an overall pooled AUROC of 0.8151, while non–logistic regression models performed better, with an overall pooled AUROC of 0.8891. Additionally, maternal age, family history of diabetes, BMI, and fasting blood glucose were the four most commonly used features of models established by the various feature selection methods.

Conclusions

Compared to current screening strategies, ML methods are attractive for predicting GDM. To expand their use, the importance of quality assessments and unified diagnostic criteria should be further emphasized.

A Self-Care Prediction Model for Children with Disability Based on Genetic Algorithm and Extreme Gradient Boosting

Detecting self-care problems is one of important and challenging issues for occupational therapists, since it requires a complex and time-consuming process. Machine learning algorithms have been recently applied to overcome this issue. In this study, we propose a self-care prediction model called GA-XGBoost, which combines genetic algorithms (GAs) with extreme gradient boosting (XGBoost) for predicting self-care problems of children with disability. Selecting the feature subset affects the model performance; thus, we utilize GA to optimize finding the optimum feature subsets toward improving the model’s performance. To validate the effectiveness of GA-XGBoost, we present six experiments: comparing GA-XGBoost with other machine learning models and previous study results, a statistical significant test, impact analysis of feature selection and comparison with other feature selection methods, and sensitivity analysis of GA parameters. During the experiments, we use accuracy, precision, recall, and f1-score to measure the performance of the prediction models. The results show that GA-XGBoost obtains better performance than other prediction models and the previous study results. In addition, we design and develop a web-based self-care prediction to help therapist diagnose the self-care problems of children with disabilities. Therefore, appropriate treatment/therapy could be performed for each child to improve their therapeutic outcome.