Predicting Type 2 Diabetes Using Logistic Regression and Machine Learning Approaches

Secure and privacy-preserving automated machine learning operations into end-to-end integrated IoT-edge-artificial intelligence-blockchain monitoring system for diabetes mellitus prediction

Diabetes Mellitus, one of the leading causes of death worldwide, has no cure to date and can lead to severe health complications, such as retinopathy, limb amputation, cardiovascular diseases, and neuronal disease, if left untreated. Consequently, it becomes crucial to be able to monitor and predict the incidence of diabetes. Machine learning approaches have been proposed and evaluated in the literature for diabetes prediction. This paper proposes an IoT-edge-Artificial Intelligence (AI)-blockchain system for diabetes prediction based on risk factors. The proposed system is underpinned by blockchain to obtain a cohesive view of the risk factors data from patients across different hospitals and ensure security and privacy of the user's data. We provide a comparative analysis of different medical sensors, devices, and methods to measure and collect the risk factors values in the system. Numerical experiments and comparative analysis were carried out within our proposed system, using the most accurate random forest (RF) model, and the two most used state-of-the-art machine learning approaches, Logistic Regression (LR) and Support Vector Machine (SVM), using three real-life diabetes datasets. The results show that the proposed system predicts diabetes using RF with 4.57% more accuracy on average in comparison with the other models LR and SVM, with 2.87 times more execution time. Data balancing without feature selection does not show significant improvement. When using feature selection, the performance is improved by 1.14% for PIMA Indian and 0.02% for Sylhet datasets, while it is reduced by 0.89% for MIMIC III.

Establishment of prediction model for mortality risk of pancreatic cancer: a retrospective study

BACKGROUND AND AIM

Pancreatic cancer possesses a high prevalence and mortality rate among other cancers. Despite the low survival rate of this cancer type, the early prediction of this disease has a crucial role in decreasing the mortality rate and improving the prognosis. So, this study.

MATERIALS AND METHODS

In this retrospective study, we used 654 alive and dead PC cases to establish the prediction model for PC. The six chosen machine learning algorithms and prognostic factors were utilized to build the prediction models. The importance of the predictive factors was assessed using the relative importance of a high-performing algorithm.

RESULTS

The XG-Boost with AU-ROC of 0.933 (95% CI= [0.906-0.958]) and AU-ROC of 0.836 (95% CI= [0.789-0.865] in internal and external validation modes were considered as the best-performing model for predicting the mortality risk of PC. The factors, including tumor size, smoking, and chemotherapy, were considered the most influential for prediction.

CONCLUSION

The XG-Boost gained more performance efficiency in predicting the mortality risk of PC patients, so this model can promote the clinical solutions that doctors can achieve in healthcare environments to decrease the mortality risk of these patients.

Development and validation of a machine learning predictive model for perioperative myocardial injury in cardiac surgery with cardiopulmonary bypass

BACKGROUND

Perioperative myocardial injury (PMI) with different cut-off values has showed to be associated with different prognostic effect after cardiac surgery. Machine learning (ML) method has been widely used in perioperative risk predictions during cardiac surgery. However, the utilization of ML in PMI has not been studied yet. Therefore, we sought to develop and validate the performances of ML for PMI with different cut-off values in cardiac surgery with cardiopulmonary bypass (CPB).

METHODS

This was a second analysis of a multicenter clinical trial (OPTIMAL) and requirement for written informed consent was waived due to the retrospective design. Patients aged 18-70 undergoing elective cardiac surgery with CPB from December 2018 to April 2021 were enrolled in China. The models were developed using the data from Fuwai Hospital and externally validated by the other three cardiac centres. Traditional logistic regression (LR) and eleven ML models were constructed. The primary outcome was PMI, defined as the postoperative maximum cardiac Troponin I beyond different times of upper reference limit (40x, 70x, 100x, 130x) We measured the model performance by examining the area under the receiver operating characteristic curve (AUROC), precision-recall curve (AUPRC), and calibration brier score.

RESULTS

A total of 2983 eligible patients eventually participated in both the model development (n = 2420) and external validation (n = 563). The CatboostClassifier and RandomForestClassifier emerged as potential alternatives to the LR model for predicting PMI. The AUROC demonstrated an increase with each of the four cutoffs, peaking at 100x URL in the testing dataset and at 70x URL in the external validation dataset. However, it's worth noting that the AUPRC decreased with each cutoff increment. Additionally, the Brier loss score decreased as the cutoffs increased, reaching its lowest point at 0.16 with a 130x URL cutoff. Moreover, extended CPB time, aortic duration, elevated preoperative N-terminal brain sodium peptide, reduced preoperative neutrophil count, higher body mass index, and increased high-sensitivity C-reactive protein levels were identified as risk factors for PMI across all four cutoff values.

CONCLUSIONS

The CatboostClassifier and RandomForestClassifer algorithms could be an alternative for LR in prediction of PMI. Furthermore, preoperative higher N-terminal brain sodium peptide and lower high-sensitivity C-reactive protein were strong risk factor for PMI, the underlying mechanism require further investigation.

Construction of a 3-year risk prediction model for developing diabetes in patients with pre-diabetes

Introduction

To analyze the influencing factors for progression from newly diagnosed prediabetes (PreDM) to diabetes within 3 years and establish a prediction model to assess the 3-year risk of developing diabetes in patients with PreDM.

Methods

Subjects who were diagnosed with new-onset PreDM at the Physical Examination Center of the First Affiliated Hospital of Soochow University from October 1, 2015 to May 31, 2023 and completed the 3-year follow-up were selected as the study population. Data on gender, age, body mass index (BMI), waist circumference, etc. were collected. After 3 years of follow-up, subjects were divided into a diabetes group and a non-diabetes group. Baseline data between the two groups were compared. A prediction model based on logistic regression was established with nomogram drawn. The calibration was also depicted.

Results

Comparison between diabetes group and non-diabetes group: Differences in 24 indicators including gender, age, history of hypertension, fatty liver, BMI, waist circumference, systolic blood pressure, diastolic blood pressure, fasting blood glucose, HbA1c, etc. were statistically significant between the two groups (P<0.05). Differences in smoking, creatinine and platelet count were not statistically significant between the two groups (P>0.05). Logistic regression analysis showed that ageing, elevated BMI, male gender, high fasting blood glucose, increased LDL-C, fatty liver, liver dysfunction were risk factors for progression from PreDM to diabetes within 3 years (P<0.05), while HDL-C was a protective factor (P<0.05). The derived formula was: In(p/1-p)=0.181×age (40-54 years old)/0.973×age (55-74 years old)/1.868×age (≥75 years old)-0.192×gender (male)+0.151×blood glucose-0.538×BMI (24-28)-0.538×BMI (≥28)-0.109×HDL-C+0.021×LDL-C+0.365×fatty liver (yes)+0.444×liver dysfunction (yes)-10.038. The AUC of the model for predicting progression from PreDM to diabetes within 3 years was 0.787, indicating good predictive ability of the model.

Conclusions

The risk prediction model for developing diabetes within 3 years in patients with PreDM constructed based on 8 influencing factors including age, BMI, gender, fasting blood glucose, LDL-C, HDL-C, fatty liver and liver dysfunction showed good discrimination and calibration.

Evaluation of machine learning approach for surgical results of Ahmed valve implantation in patients with glaucoma

BACKGROUND

Ahmed valve implantation demonstrated an increasing proportion in glaucoma surgery, but predicting the successful maintenance of target intraocular pressure remains a challenging task. This study aimed to evaluate the performance of machine learning (ML) in predicting surgical outcomes after Ahmed valve implantation and to assess potential risk factors associated with surgical failure to contribute to improving the success rate.

METHODS

This study used preoperative data of patients who underwent Ahmed valve implantation from 2017 to 2021 at Ajou University Hospital. These datasets included demographic and ophthalmic parameters (dataset A), systemic medical records excluding psychiatric records (dataset B), and psychiatric medications (dataset C). Logistic regression, extreme gradient boosting (XGBoost), and support vector machines were first evaluated using only dataset A. The algorithm with the best performance was selected based on the area under the receiver operating characteristics curve (AUROC). Finally, three additional prediction models were developed using the best performance algorithm, incorporating combinations of multiple datasets to predict surgical outcomes at 1 year.

RESULTS

Among 153 eyes of 133 patients, 131 (85.6%) and 22 (14.4%) eyes were categorized as the success and failure groups, respectively. The XGBoost was shown as the best-performance model with an AUROC value of 0.684, using only dataset A. The final three further prediction models were developed based on the combination of multiple datasets using the XGBoost model. All datasets combinations demonstrated the best performances in terms of AUROC (dataset A + B: 0.782; A + C: 0.773; A + B + C: 0.801). Furthermore, advancing age was a risk factor associated with a higher surgical failure incidence.

CONCLUSIONS

ML provides some predictive value in predicting the outcomes of Ahmed valve implantation at 1 year. ML evaluation revealed advancing age as a common risk factor for surgical failure.

Machine Learning-Based Prediction of Helicobacter pylori Infection Study in Adults

BACKGROUND Helicobacter pylori has a high infection rate worldwide, and epidemiological study of H. pylori is important. Artificial intelligence has been widely used in the field of medical research and has become a hotspot in recent years. This paper proposed a prediction model for H. pylori infection based on machine learning in adults. MATERIAL AND METHODS Adult patients were selected as research participants, and information on 30 factors was collected. The chi-square test, mutual information, ReliefF, and information gain were used to screen the feature factors and establish 2 subsets. We constructed an H. pylori infection prediction model based on XGBoost and optimized the model using a grid search by analyzing the correlation between features. The performance of the model was assessed by comparing its accuracy, recall, precision, F1 score, and AUC with those of 4 other classical machine learning methods. RESULTS The model performed better on the part B subset than on the part A subset. Compared with the other 4 machine learning methods, the model had the highest accuracy, recall, F1 score, and AUC. SHAP was used to evaluate the importance of features in the model. It was found that H. pylori infection of family members, living in rural areas, poor washing hands before meals and after using the toilet were risk factors for H. pylori infection. CONCLUSIONS The model proposed in this paper is superior to other models in predicting H. pylori infection and can provide a scientific basis for identifying the population susceptible to H. pylori and preventing H. pylori infection.

Comparing the accuracy of four machine learning models in predicting type 2 diabetes onset within the Chinese population: a retrospective study

OBJECTIVE

To evaluate the effectiveness of machine learning (ML) models in predicting 5-year type 2 diabetes mellitus (T2DM) risk within the Chinese population by retrospectively analyzing annual health checkup records.

METHODS

We included 46,247 patients (32,372 and 13,875 in training and validation sets, respectively) from a national health checkup center database. Univariate and multivariate Cox analyses were performed to identify factors influencing T2DM risk. Extreme Gradient Boosting (XGBoost), support vector machine (SVM), logistic regression (LR), and random forest (RF) models were trained to predict 5-year T2DM risk. Model performances were analyzed using receiver operating characteristic (ROC) curves for discrimination and calibration plots for prediction accuracy.

RESULTS

Key variables included fasting plasma glucose, age, and sedentary time. The LR model showed good accuracy with respective areas under the ROC (AUCs) of 0.914 and 0.913 in training and validation sets; the RF model exhibited favorable AUCs of 0.998 and 0.838. In calibration analysis, the LR model displayed good fit for low-risk patients; the RF model exhibited satisfactory fit for low- and high-risk patients.

CONCLUSIONS

LR and RF models can effectively predict T2DM risk in the Chinese population. These models may help identify high-risk patients and guide interventions to prevent complications and disabilities.

Hybrid feature selection in a machine learning predictive model for perioperative myocardial injury in noncoronary cardiac surgery with cardiopulmonary bypass

BACKGROUND

Perioperative myocardial injury (PMI) is associated with increased mobility and mortality after noncoronary cardiac surgery. However, limited studies have developed a predictive model for PMI. Therefore, we used hybrid feature selection (FS) methods to establish a predictive model for PMI in noncoronary cardiac surgery with cardiopulmonary bypass (CPB).

METHODS

This was a single-center retrospective study conducted at the Fuwai Hospital in China. Patients aged 18-70 years who underwent elective noncoronary surgery with CPB at our institution from December 2018 to April 2021 were enrolled. The primary outcome was PMI, defined as the postoperative cardiac troponin I (cTnI) levels exceeding 220 times of upper reference limit (URL). Statistical analyses were conducted by Python (Python Software Foundation, version 3.9.7 and integrated development environment Jupyter Notebook 1.1.0) and SPSS software version 26.0 (IBM Corp., Armonk, New York, USA).

RESULTS

A total of 1130 patients were eventually eligible for this study. The incidence of PMI was 20.3% (229/1130) in the overall patients, 20.6% (163/791) in the training dataset, and 19.5% (66/339) in the testing dataset. The logistic regression model performed the best AUC of 0.6893 (95 CI%: 0.6371-0.7382) by the traditional selection method, and the random forest model performed the best AUC of 0.6937 (95 CI%: 0.6416-0.7423) by the union of Wrapper and Embedded method, and the CatBoost model performed the best AUC of 0.6828 (95 CI%: 0.6304-0.7320) by the union of Embedded and forward logistic regression technique, and the Naïve Bayes model achieved the best AUC with 0.7254 (95 CI%: 0.6746-0.7723) by forwarding logistic regression method. Moreover, the decision tree, KNeighborsClassifier, and support vector machine models performed the worse AUC in all selection forms. Furthermore, the SHapley Additive exPlanations plot showed that prolonged CPB, aortic clamp time, and preoperative low platelets count were strongly related to the PMI risk.

CONCLUSIONS

In total, four category feature selection methods were utilized, comprising five individual selection techniques and 15 combined methods. Notably, the combination of logistic regression and embedded methods demonstrated outstanding performance in predicting PMI risk. We also concluded that the machine learning model, including random forest, catboost, and Naive Bayes, were suitable candidates for establishing PMI predictive model. Nevertheless, additional investigation and validation are imperative for substantiating these finding.

Risk assessment of diabetes using the Indian Diabetes Risk Score among older adults: Secondary analysis from the Longitudinal Ageing Study in India

BACKGROUND

The Indian Diabetes Risk Score (IDRS) is a simple tool to assess the probability of an individual having type 2 diabetes (T2DM) but its applicability in community-dwelling older adults is lacking. This study aimed to estimate the risk of T2DM and its determinants among older adults without prior diabetes (DM) using the IDRS, while also assessing its sensitivity and specificity in individuals with a history of diabetes.

METHODS

We analyzed cross-sectional data from the Longitudinal Ageing Study in India (LASI) wave-1 (2017-18). IDRS was calculated amongst individuals aged ≥45 years considering waist circumference, physical activity, age and family history of DM. Risk was categorized as high (≥60), moderate (30-50), and low (<30).

RESULTS

Among 64541 individuals, 7.27 % (95 % CI: 6.78, 7.80) were at low risk, 61.80 % (95 % CI: 60.99, 62.61) at moderate risk, and 30.93 % (95 % CI: 30.19, 31.67) at high risk for T2DM. Adjusted analysis showed higher risk of T2DM among men, widowed/divorced, urban residents, minority religions, overweight, obese, and individuals with hypertension. ROC curve yielded an AUC of 0.67 (95 % CI: 0.66, 0.67, P < 0.001). The IDRS cutoff ≥50 had 73.69 % sensitivity and 51.40 % specificity for T2DM detection.

CONCLUSION

More than 9 in 10 older adults in India without history of DM have high-moderate risk of T2DM when assessed with the IDRS risk-prediction tool. However, the low specificity and moderate sensitivity of IDRS in existing DM cases constraints its practical utility as a decision tool for screening.

Correlation between Long-Term Exposure to Traffic Noise and Risk of Type 2 Diabetes Mellitus

OBJECTIVE

This study aimed to probe the correlation of long-term exposure to traffic noise with the risk of type 2 diabetes mellitus (T2DM).

METHODS

The data of 480 community residents collected from April 2017 to April 2018 were retrospectively analyzed. Exposure levels for traffic noise were defined using 24-h mean traffic noise. Logistic regression calculated the association between long-term exposure to traffic noise and the risk of T2DM.

RESULTS

Overall, 480 enrolled participants were divided into T2DM (n = 45) and non-T2DM (n = 435) groups. Participants with T2DM were older and more likely to be male, had higher BMI, and were frequent drinkers (P < 0.001). The T2DM group displayed higher exposure to traffic noise than the non-T2DM group (P < 0.001). According to quartiles of traffic noise, all participants were categorized into four groups: Q1 (<51.5 dB), Q2 (51.5-<53.9 dB), Q3 (53.9-<58.0 dB), and Q4 (≥58.0 dB). Prevalence of T2DM was 5.4% in Q1, 7.7% in Q2, 10.3% in Q3, and 14.1% in Q4 groups. Multifactor regression analysis showed that age, BMI, drinking history, and traffic noise exposure are risk factors for T2DM (P < 0.05), whereas sex does not seem to have a significant impact on T2DM (P > 0.05).

CONCLUSION

Long-term exposure to traffic noise may elevate the risk of T2DM. This suggests that long-term exposure to high levels of traffic noise can increase the incidence of diabetes mellitus, which deserves further consideration.

Integrated machine learning and deep learning for predicting diabetic nephropathy model construction, validation, and interpretability

OBJECTIVE

To construct a risk prediction model for assisted diagnosis of Diabetic Nephropathy (DN) using machine learning algorithms, and to validate it internally and externally.

METHODS

Firstly, the data was cleaned and enhanced, and was divided into training and test sets according to the 7:3 ratio. Then, the metrics related to DN were filtered by difference analysis, Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination (RFE), and Max-relevance and Min-redundancy (MRMR) algorithms. Ten machine learning models were constructed based on the key variables. The best model was filtered by Receiver Operating Characteristic (ROC), Precision-Recall (PR), Accuracy, Matthews Correlation Coefficient (MCC), and Kappa, and was internally and externally validated. Based on the best model, an online platform had been constructed.

RESULTS

15 key variables were selected, and among the 10 machine learning models, the Random Forest model achieved the best predictive performance. In the test set, the area under the ROC curve was 0.912, and in two external validation cohorts, the area under the ROC curve was 0.828 and 0.863, indicating excellent predictive and generalization abilities.

CONCLUSION

The model has a good predictive value and is expected to help in the early diagnosis and screening of clinical DN.

Nested genetic algorithm-based classifier selection and placement in multi-level ensemble framework for effective disease diagnosis

Effective disease diagnosis is a critical unmet need on a global scale. The intricacies of the numerous disease mechanisms and underlying symptoms make developing a model for early diagnosis and effective treatment extremely difficult. Machine learning (ML) can help to solve some of these issues. Recently, various ensemble-based ML models have benefited clinicians in early diagnosis. However, one of the most difficult challenges in multi-level ensemble approaches is the classifier selection and their placement in the ensemble framework as it improves the overall performance. Let m classifiers have to select from n classifiers there are ( n m ) ways. Again, these ( n m ) possibilities can be arranged in m ! ways. Finding the best m classifiers and their positions from total ( n m ) m ! ways is a challenging and hard problem. To address this challenge, a dynamic three-level ensemble framework is proposed. A nested Genetic Algorithm (GA) and ensemble-based fitness function are employed to optimize the classifier selection and their placement in a three-level ensemble framework. Our approach used eleven classifiers and chose seven classifiers by maximizing the fitness function. The proposed model experiments on 12 disease datasets. The proposed model outperformed in terms of accuracy, F1, and G-measure on the Chronic Kidney Disease (CKD) dataset is 0.987, 0.988, and 0.989, respectively. In terms of AUC on the Heart disease dataset (HDD) is 0.998 and in terms of recall on the Hypothyroid disease dataset (HyDD) is 0.988. In addition, the proposed model superiority is statically evaluated by Wilcoxon-Signed-Rank (WSR) test compared with other ensemble models, such as random forest (RF), bagging classifier (BC), XGBoost (XGB), and gradient boost classifier (GBC) with probability value p < 0.05 results shows all the traditional ensemble model differs with proposed model and also effective size evaluated with using the matched-pairs rank biserial correlation coefficient wc and statistical results shows effective size is large with RF and BC and effective size is medium with XGB and GBC. Proposed model has outperformed comparing with State-Of-The-Art (SOTA) ensemble and non-ensemble models. Further, the proposed model outperformed in terms of the ROC curve in the majority of the disease datasets. The results suggest the usage of the proposed model for disease diagnosis applications.

Machine learning based prediction of recurrence after curative resection for rectal cancer

PURPOSE

Patients with rectal cancer without distant metastases are typically treated with radical surgery. Post curative resection, several factors can affect tumor recurrence. This study aimed to analyze factors related to rectal cancer recurrence after curative resection using different machine learning techniques.

METHODS

Consecutive patients who underwent curative surgery for rectal cancer between 2004 and 2018 at Gil Medical Center were included. Patients with stage IV disease, colon cancer, anal cancer, other recurrent cancer, emergency surgery, or hereditary malignancies were excluded from the study. The Synthetic Minority Oversampling Technique with Tomek link (SMOTETomek) technique was used to compensate for data imbalance between recurrent and no-recurrent groups. Four machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), and Extreme gradient boosting (XGBoost), were used to identify significant factors. To overfit and improve the model performance, feature importance was calculated using the permutation importance technique.

RESULTS

A total of 3320 patients were included in the study. After exclusion, the total sample size of the study was 961 patients. The median follow-up period was 60.8 months (range:1.2-192.4). The recurrence rate during follow-up was 13.2% (n = 127). After applying the SMOTETomek method, the number of patients in both groups, recurrent and non-recurrent group were equalized to 667 patients. After analyzing for 16 variables, the top eight ranked variables {pathologic Tumor stage (pT), sex, concurrent chemoradiotherapy, pathologic Node stage (pN), age, postoperative chemotherapy, pathologic Tumor-Node-Metastasis stage (pTNM), and perineural invasion} were selected based on the order of permutational importance. The highest area under the curve (AUC) was for the SVM method (0.831). The sensitivity, specificity, and accuracy were found to be 0.692, 0.814, and 0.798, respectively. The lowest AUC was obtained for the XGBoost method (0.804), with a sensitivity, specificity, and accuracy of 0.308, 0.928, and 0.845, respectively. The variable with highest importance was pT as assessed through SVM, RF, and XGBoost (0.06, 0.12, and 0.13, respectively), whereas pTNM had the highest importance when assessed by LR (0.05).

CONCLUSIONS

In the current study, SVM showed the best AUC, and the most influential factor across all machine learning methods except LR was found to be pT. The rectal cancer patients who have a high pT stage during postoperative follow-up are need to be more close surveillance.

Optimizing diabetes classification with a machine learning-based framework

BACKGROUND

Diabetes is a metabolic disorder usually caused by insufficient secretion of insulin from the pancreas or insensitivity of cells to insulin, resulting in long-term elevated blood sugar levels in patients. Patients usually present with frequent urination, thirst, and hunger. If left untreated, it can lead to various complications that can affect essential organs and even endanger life. Therefore, developing an intelligent diagnosis framework for diabetes is necessary.

RESULT

This paper proposes a machine learning-based diabetes classification framework machine learning optimized GAN. The framework encompasses several methodological approaches to address the diverse challenges encountered during the analysis. These approaches encompass the implementation of the mean and median joint filling method for handling missing values, the application of the cap method for outlier processing, and the utilization of SMOTEENN to mitigate sample imbalance. Additionally, the framework incorporates the employment of the proposed Diabetes Classification Model based on Generative Adversarial Network and employs logistic regression for detailed feature analysis. The effectiveness of the framework is evaluated using both the PIMA dataset and the diabetes dataset obtained from the GEO database. The experimental findings showcase our model achieved exceptional results, including a binary classification accuracy of 96.27%, tertiary classification accuracy of 99.31%, precision and f1 score of 0.9698, recall of 0.9698, and an AUC of 0.9702.

CONCLUSION

The experimental results show that the framework proposed in this paper can accurately classify diabetes and provide new ideas for intelligent diagnosis of diabetes.

Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population

Background: Ischemic stroke is a significant global health issue, imposing substantial social and economic burdens. Carotid artery plaques (CAP) serve as an important risk factor for stroke, and early screening can effectively reduce stroke incidence. However, China lacks nationwide data on carotid artery plaques. Machine learning (ML) can offer an economically efficient screening method. This study aimed to develop ML models using routine health examinations and blood markers to predict the occurrence of carotid artery plaques. Methods: This study included data from 5,211 participants aged 18-70, encompassing health check-ups and biochemical indicators. Among them, 1,164 participants were diagnosed with carotid artery plaques through carotid ultrasound. We constructed six ML models by employing feature selection with elastic net regression, selecting 13 indicators. Model performance was evaluated using accuracy, sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), F1 score, kappa value, and Area Under the Curve (AUC) value. Feature importance was assessed by calculating the root mean square error (RMSE) loss after permutations for each variable in every model. Results: Among all six ML models, LightGBM achieved the highest accuracy at 91.8%. Feature importance analysis revealed that age, Low-Density Lipoprotein Cholesterol (LDL-c), and systolic blood pressure were important predictive factors in the models. Conclusion: LightGBM can effectively predict the occurrence of carotid artery plaques using demographic information, physical examination data and biochemistry data.

Diabetes mellitus early warning and factor analysis using ensemble Bayesian networks with SMOTE-ENN and Boruta

Diabetes mellitus (DM) has become the third chronic non-infectious disease affecting patients after tumor, cardiovascular and cerebrovascular diseases, becoming one of the major public health issues worldwide. Detection of early warning risk factors for DM is key to the prevention of DM, which has been the focus of some previous studies. Therefore, from the perspective of residents' self-management and prevention, this study constructed Bayesian networks (BNs) combining feature screening and multiple resampling techniques for DM monitoring data with a class imbalance in Shanxi Province, China, to detect risk factors in chronic disease monitoring programs and predict the risk of DM. First, univariate analysis and Boruta feature selection algorithm were employed to conduct the preliminary screening of all included risk factors. Then, three resampling techniques, SMOTE, Borderline-SMOTE (BL-SMOTE) and SMOTE-ENN, were adopted to deal with data imbalance. Finally, BNs developed by three algorithms (Tabu, Hill-climbing and MMHC) were constructed using the processed data to find the warning factors that strongly correlate with DM. The results showed that the accuracy of DM classification is significantly improved by the BNs constructed by processed data. In particular, the BNs combined with the SMOTE-ENN resampling improved the most, and the BNs constructed by the Tabu algorithm obtained the best classification performance compared with the hill-climbing and MMHC algorithms. The best-performing joint Boruta-SMOTE-ENN-Tabu model showed that the risk factors of DM included family history, age, central obesity, hyperlipidemia, salt reduction, occupation, heart rate, and BMI.

Household Wealth Gradient in Low Birthweight in India: A Cross-Sectional Analysis

A low birthweight is a common complication that can result from numerous physiological, environmental, and socioeconomic factors, and can put babies at an increased risk for health issues such as breathing difficulties, developmental delays, and even death in severe cases. In this analysis, I aim to assess the differences in the burden of low birthweight based on household wealth status in India using data from the latest National Family Health Survey (NFHS 2019-21). The sample population includes 161,596 mother-child dyads. A low birthweight is defined as a weight that is <2500 g at birth. I used descriptive and multivariate regression analyses in R studio to analyse the data. The findings show that 16.86% of the babies had a low birthweight. At the state level, the percentage of low birthweights ranges from 3.85% in Nagaland to 21.81% in Punjab. The mean birthweights range from 2759.68 g in the poorest, 2808.01 g in the poorer, 2838.17 g in the middle, 2855.06 g in the richer, and 2871.30 g in the richest wealth quintile households. The regression analysis indicates that higher wealth index quintiles have progressively lower risks of low birthweight, with the association being stronger in the rural areas. Compared with the poorest wealth quintile households, the risk ratio of low birthweight was 0.90 times lower for the poorer households and 0.74 times lower for the richest households. These findings indicate that household wealth condition is an important predictor of low birthweight by which low-income households are disproportionately affected. As wealth inequality continues to rise in India, health policymakers must take the necessary measures to support the vulnerable populations in order to improve maternal and infant health outcomes.

RFFE - Random Forest Fuzzy Entropy for the classification of Diabetes Mellitus

Diabetes is a category of metabolic disease commonly known as a chronic illness. It causes the body to generate less insulin and raises blood sugar levels, leading to various issues and disrupting the functioning of organs, including the retinal, kidney and nerves. To prevent this, people with chronic illnesses require lifetime access to treatment. As a result, early diabetes detection is essential and might save many lives. Diagnosis of people at high risk of developing diabetes is utilized for preventing the disease in various aspects. This article presents a chronic illness prediction prototype based on a person's risk feature data to provide an early prediction for diabetes with Fuzzy Entropy random vectors that regulate the development of each tree in the Random Forest. The proposed prototype consists of data imputation, data sampling, feature selection, and various techniques to predict the disease, such as Fuzzy Entropy, Synthetic Minority Oversampling Technique (SMOTE), Convolutional Neural Network (CNN) with Stochastic Gradient Descent with Momentum (SGDM), Support Vector Machines (SVM), Classification and Regression Tree (CART), K-Nearest Neighbor (KNN), and Naïve Bayes (NB). This study uses the existing Pima Indian Diabetes (PID) dataset for diabetic disease prediction. The predictions' true/false positive/negative rate is investigated using the confusion matrix and the receiver operating characteristic area under the curve (ROCAUC). Findings on a PID dataset are compared with machine learning algorithms revealing that the proposed Random Forest Fuzzy Entropy (RFFE) is a valuable approach for diabetes prediction, with an accuracy of 98 percent.

KFPredict: An ensemble learning prediction framework for diabetes based on fusion of key features

BACKGROUND AND OBJECTIVE

Diabetes is a disease that requires early detection and early treatment, and complications are likely to occur in late stages of the disease, threatening the life of patients. Therefore, in order to diagnose diabetic patients as early as possible, it is necessary to establish a model that can accurately predict diabetes.

METHODOLOGY

This paper proposes an ensemble learning framework: KFPredict, which combines multi-input models with key features and machine learning algorithms. We first propose a multi-input neural network model (KF_NN) that fuses key features and uses a decision tree-based selection recursive feature elimination algorithm and correlation coefficient method to screen out the key feature inputs and secondary feature inputs in the model. We then ensemble KF_NN with three machine learning algorithms (i.e., Support Vector Machine, Random Forest and K-Nearest Neighbors) for soft voting to form our predictive classifier for diabetes prediction.

RESULTS

Our framework demonstrates good prediction results on the test set with a sensitivity of 0.85, a specificity of 0.98, and an accuracy of 93.5%. Compared with the single prediction method KFPredict, the accuracy is up to 18.18% higher. Concurrently, we also compared KFPredict with the existing prediction methods. It still has good prediction performance, and the accuracy rate is improved by up to 14.93%.

CONCLUSION

This paper constructs a diabetes prediction framework that combines multi-input models with key features and machine learning algorithms. Taking tthe PIMA diabetes dataset as the test data, the experiment shows that the framework presents good prediction results.

Predicting the Onset of Diabetes with Machine Learning Methods

The number of people suffering from diabetes in Taiwan has continued to rise in recent years. According to the statistics of the International Diabetes Federation, about 537 million people worldwide (10.5% of the global population) suffer from diabetes, and it is estimated that 643 million people will develop the condition (11.3% of the total population) by 2030. If this trend continues, the number will jump to 783 million (12.2%) by 2045. At present, the number of people with diabetes in Taiwan has reached 2.18 million, with an average of one in ten people suffering from the disease. In addition, according to the Bureau of National Health Insurance in Taiwan, the prevalence rate of diabetes among adults in Taiwan has reached 5% and is increasing each year. Diabetes can cause acute and chronic complications that can be fatal. Meanwhile, chronic complications can result in a variety of disabilities or organ decline. If holistic treatments and preventions are not provided to diabetic patients, it will lead to the consumption of more medical resources and a rapid decline in the quality of life of society as a whole. In this study, based on the outpatient examination data of a Taipei Municipal medical center, 15,000 women aged between 20 and 80 were selected as the subjects. These women were patients who had gone to the medical center during 2018–2020 and 2021–2022 with or without the diagnosis of diabetes. This study investigated eight different characteristics of the subjects, including the number of pregnancies, plasma glucose level, diastolic blood pressure, sebum thickness, insulin level, body mass index, diabetes pedigree function, and age. After sorting out the complete data of the patients, this study used Microsoft Machine Learning Studio to train the models of various kinds of neural networks, and the prediction results were used to compare the predictive ability of the various parameters for diabetes. Finally, this study found that after comparing the models using two-class logistic regression as well as the two-class neural network, two-class decision jungle, or two-class boosted decision tree for prediction, the best model was the two-class boosted decision tree, as its area under the curve could reach a score of 0.991, which was better than other models.

Development and validation of a model that predicts the risk of diabetic retinopathy in type 2 diabetes mellitus patients

AIMS

Diabetic retinopathy is the leading cause of blindness in people with type 2 diabetes. To enable primary care physicians to identify high-risk type 2 diabetic patients with diabetic retinopathy at an early stage, we developed a nomogram model to predict the risk of developing diabetic retinopathy in the Xinjiang type 2 diabetic population.

METHODS

In a retrospective study, we collected data on 834 patients with type 2 diabetes through an electronic medical record system. Stepwise regression was used to filter variables. Logistic regression was applied to build a nomogram prediction model and further validated in the training set. The c-index, forest plot, calibration plot, and clinical decision curve analysis were used to comprehensively validate the model and evaluate its accuracy and clinical validity.

RESULTS

Four predictors were selected to establish the final model: hypertension, blood urea nitrogen, duration of diabetes, and diabetic peripheral neuropathy. The model displayed medium predictive power with a C-index of 0.781(95%CI:0.741-0.822) in the training set and 0.865(95%CI:0.807-0.923)in the validation set. The calibration curve of the DR probability shows that the predicted results of the nomogram are in good agreement with the actual results. Decision curve analysis demonstrated that the novel nomogram was clinically valuable.

CONCLUSIONS

The nomogram of the risk of developing diabetic nephropathy contains 4 characteristics. that can help primary care physicians quickly identify individuals at high risk of developing DR in patients with type 2 diabetes, to intervene as soon as possible.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.

Analysis of Risk Factors for Pneumonia Death in ICU Environment Based on Logistic Regression

Objective

To explore the risk and protect factors for death of pneumonia patients in intensive care unit (ICU), we conducted this logistic regression research.

Methods

We collected demographic and nursing care data for 80 patients form Wuhan fourth hospital, in which 40 patients were dead and the other 40 patients were alive. Difference analysis, Pearson's correlation matrix, and logistic regression were conducted to explore the risk and protective factors for living status of pneumonia patients in ICU.

Results

A total of 40 individuals were dead from pneumonia in ICU. The demographic and nursing information had no difference between death and living groups except age. After that, correlation analysis showed that there were correlations between living status, age, and marriage. Logistic regression showed that age (odds ratio (OR) = 0.94, P < 0.05) and no education (OR = 0.21, P < 0.05) may be harmful for pneumonia patients living status while high-quality nursing (OR = 2.72, P < 0.05) may be helpful for pneumonia patients living status.

Conclusion

High-quality care plays an important role in protecting the survival of patients with pneumonia, and old age and uneducated may be the risk factors for the death of patients with pneumonia.

Global Translation of Classification Models

The widespread and growing usage of machine learning models, particularly for critical areas such as law, predicate the need for global interpretability. Models that cannot be audited are vulnerable to biases inherited from the datasets that were used to develop them. Moreover, locally interpretable models are vulnerable to adversarial attacks. To address this issue, the present paper proposes a new methodology that can translate any existing machine learning model into a globally interpretable one. MTRE-PAN is a hybrid SVM-decision tree architecture that leverages the interpretability of linear hyperplanes by creating a set of polygons that delimit the decision boundaries of the target model. Moreover, the present paper introduces two new metrics: certain and boundary model parities. These metrics can be used to accurately evaluate the performance of the interpretable model near the decision boundaries. These metrics are used to compare MTRE-PAN to a previously proposed interpretable architecture called TRE-PAN. As in the case of TRE-PAN, MTRE-PAN aims at providing global interpretability. The comparisons are performed over target models developed using three benchmark datasets: Abalone, Census and Diabetes data. The results show that MTRE-PAN generates interpretable models that have a lower number of leaves and a higher agreement with the target models, especially around the most important regions in the feature space, namely the decision boundaries.

Type 2 diabetes epidemic and key risk factors in Qatar: a mathematical modeling analysis

INTRODUCTION

We aimed to characterize and forecast type 2 diabetes mellitus (T2DM) disease burden between 2021 and 2050 in Qatar where 89% of the population comprises expatriates from over 150 countries.

RESEARCH DESIGN AND METHODS

An age-structured mathematical model was used to forecast T2DM burden and the impact of key risk factors (obesity, smoking, and physical inactivity). The model was parametrized using data from T2DM natural history studies, Qatar's 2012 STEPwise survey, the Global Health Observatory, and the International Diabetes Federation Diabetes Atlas, among other data sources.

RESULTS

Between 2021 and 2050, T2DM prevalence increased from 7.0% to 14.0%, the number of people living with T2DM increased from 170 057 to 596 862, and the annual number of new T2DM cases increased from 25 007 to 45 155 among those 20-79 years of age living in Qatar. Obesity prevalence increased from 8.2% to 12.5%, smoking declined from 28.3% to 26.9%, and physical inactivity increased from 23.1% to 26.8%. The proportion of incident T2DM cases attributed to obesity increased from 21.9% to 29.9%, while the contribution of smoking and physical inactivity decreased from 7.1% to 6.0% and from 7.3% to 7.2%, respectively. The results showed substantial variability across various nationality groups residing in Qatar-for example, in Qataris and Egyptians, the T2DM burden was mainly due to obesity, while in other nationality groups, it appeared to be multifactorial.

CONCLUSIONS

T2DM prevalence and incidence in Qatar were forecasted to increase sharply by 2050, highlighting the rapidly growing need of healthcare resources to address the disease burden. T2DM epidemiology varied between nationality groups, stressing the need for prevention and treatment intervention strategies tailored to each nationality.

"I Had to Rediscover Our Healthy Food": An Indigenous Perspective on Coping with Type 2 Diabetes Mellitus

Type 2 Diabetes Mellitus (T2DM) is disproportionally prevalent among the Bedouin minority in Israel, with especially poor treatment outcomes compared to other indigenous groups. This study uses the perspective of the Bedouins themselves to explore the distinct challenges they face, as well as their coping strategies. The study is based on an interpretive interactionist analysis of 49 semi-structured interviews with Bedouin men and women. The findings of the analysis include three themes. First, physical inequality: the Bedouin community's way of coping is mediated by the transition to a semi-urban lifestyle under stressful conditions that include the experience of land dispossession and the rupture of caring relationships. Second, social inequality: they experience an inaccessibility to healthcare due to economic problems and a lack of suitable informational resources. Third, unique resources for coping with T2DM: interviewees use elements of local culture, such as religious practices or small enclaves of traditional lifestyles, to actively cope with T2DM. This study suggests that there is a need to expand the concept of active coping to include indigenous culture-based ways of coping (successfully) with chronic illness.

Adiposity and Long-Term Adiposity Change Are Associated with Incident Diabetes: A Prospective Cohort Study in Southwest China

In order to estimate the associations of different adiposity indicators and long-term adiposity changes with risk of incident type 2 diabetes (T2DM), we conducted a 10-year prospective cohort study of 7441 adults in Guizhou, China, from 2010 to 2020. Adiposity was measured at baseline and follow-up. Cox proportional hazard models were used to estimated hazard ratios (HRs) and 95% confidence intervals (95% CIs). A total of 764 new diabetes cases were identified over an average follow-up of 7.06 years. Adiposity indicators, body mass index (BMI), waist circumference (WC), waist-height ratio (WHtR), and long-term adiposity changes (both weight change and WC change) were significantly associated with an increased risk of T2DM (adjusted HRs: 1.16–1.48). Significant non-linear relationships were found between weight/WC change and incident T2DM. Compared with subjects with stable WC from baseline to follow-up visit, the subjects with WC gain ≥9 cm had a 1.61-fold greater risk of T2DM; those with WC loss had a 30% lower risk. Furthermore, the associations were stronger among participants aged 40 years or older, women, and Han Chinese. Preventing weight or WC gain and promoting maintenance of normal body weight or WC are important approaches for diabetes prevention, especially for the elderly, women, and Han Chinese.

Towards a Parsimonious Pathway Model of Modifiable and Mediating Risk Factors Leading to Diabetes Risk

Modifiable risk factors are of interest for chronic disease prevention. Few studies have assessed the system of modifiable and mediating pathways leading to diabetes mellitus. We aimed to develop a pathway model for Diabetes Risk with modifiable Lifestyle Risk factors as the start point and Physiological Load as the mediator. As there are no standardised risk thresholds for lifestyle behaviour, we derived a weighted composite for Lifestyle Risk. Physiological Load was based on an index using clinical thresholds. Sociodemographics are non-modifiable risk factors and were specified as covariates. We used structural equation modeling to test the model, first using 2014/2015 data from the Indonesian Family Life Survey. Next, we fitted a smaller model with longitudinal data (2007/2008 to 2014/2015), given limited earlier data. Both models showed the indirect effects of Lifestyle Risk on Diabetes Risk via the mediator of Physiological Load, whereas the direct effect was only supported in the cross-sectional analysis. Specifying Lifestyle Risk as an observable, composite variable incorporates the cumulative effect of risk behaviour and differentiates this study from previous studies assessing it as a latent construct. The parsimonious model groups the multifarious risk factors and illustrates modifiable pathways that could be applied in chronic disease prevention efforts.