Roles of Anxiety and Depression in Predicting Cardiovascular Disease Among Patients With Type 2 Diabetes Mellitus: A Machine Learning Approach

Predicting incident cardio-metabolic disease among persons with and without depressive and anxiety disorders: a machine learning approach

PURPOSE

There is a global increase of cardiovascular disease and diabetes (Cardio-Metabolic diseases: CMD). Suffering from depression or anxiety disorders increases the probability of developing CMD. In this study we tested a wide array of predictors for the onset of CMD with Machine Learning (ML), evaluating whether adding detailed psychiatric or biological variables increases predictive performance.

METHODS

We analysed data from the Netherlands Study of Depression and Anxiety, a longitudinal cohort study (N = 2071), using 368 predictors covering 4 domains (demographic, lifestyle & somatic, psychiatric, and biological markers). CMD onset (24% incidence) over a 9-year follow-up was defined using self-reported stroke, heart disease, diabetes with high fasting glucose levels and (antithrombotic, cardiovascular, or diabetes) medication use (ATC codes C01DA, C01-C05A-B, C07-C09A-B, C01DB, B01, A10A-X). Using different ML methods (Logistic regression, Support vector machine, Random forest, and XGBoost) we tested the predictive performance of single domains and domain combinations.

RESULTS

The classifiers performed similarly, therefore the simplest classifier (Logistic regression) was selected. The Area Under the Receiver Operator Characteristic Curve (AUC-ROC) achieved by singe domains ranged from 0.569 to 0.649. The combination of demographics, lifestyle & somatic indicators and psychiatric variables performed best (AUC-ROC = 0.669), but did not significantly outperform demographics. Age and hypertension contributed most to prediction; detailed psychiatric variables added relatively little.

CONCLUSION

In this longitudinal study, ML classifiers were not able to accurately predict 9-year CMD onset in a sample enriched of subjects with psychopathology. Detailed psychiatric/biological information did not substantially increase predictive performance.

Estimating cardiovascular mortality in patients with hypertension using machine learning: The role of depression classification based on lifestyle and physical activity

PURPOSE

This study aims to harness machine learning techniques, particularly the Random Survival Forest (RSF) model, to assess the impact of depression on cardiovascular disease (CVD) mortality among hypertensive patients. A key objective is to elucidate the interplay between mental health, lifestyle, and physical activity while comparing the effectiveness of the RSF model against the traditional Cox proportional hazards model in predicting CVD mortality.

METHODS

Data from the National Health and Nutrition Examination Survey (NHANES) spanning 2007 to 2014 were used for comprehensive depression screening. The Patient Health Questionnaire-9 (PHQ-9) was employed to categorize depression severity levels among participants. The final cohort included 9271 participants, selected after excluding those with incomplete data. Participants were followed up for a median of 7.1 years, and cardiovascular mortality was assessed up to December 31, 2019. We employed the RSF model to predict cardiovascular mortality with high effectiveness and precision. And to ensure comparability, we developed the traditional Cox proportional hazards model using the same set of predictors.

RESULTS

RSF model outperformed the Cox proportional hazards model in predicting cardiovascular mortality among hypertensive patients with varying depression levels. The RSF model's integrated area under the curve (iAUC) scores were 0.842, 0.893, and 0.760 for none, mild, and severe depression, respectively, surpassing the Cox model's scores of 0.826, 0.805, and 0.746.

CONCLUSION

The RSF model provides a more accurate prediction of CVD mortality among hypertensive patients with varying degrees of depression, offering a valuable tool for personalized patient care. Its ability to stratify patients into risk categories can assist healthcare professionals in making informed decisions, underscoring the potential of machine learning in public health and clinical settings. This model demonstrates particular utility in settings where detailed, patient-specific risk assessments are critical for managing long-term health outcomes. Future research should focus on external validation and integration of more diverse variables to enhance predictive power.

Refining PREVENT prediction models for 10-year risk of cardiovascular disease using measures of anxiety and depression

BACKGROUND

Anxiety and depression are associated with cardiovascular disease (CVD). We aimed to investigate whether adding measures of anxiety and depression to the American Heart Association Predicting Risk of Cardiovascular Disease Events (PREVENT) predictors improves the prediction of CVD risk.

METHODS

We developed and internally validated risk prediction models using 60% and 40% of the cohort data from the UK Biobank, respectively. Mental health predictors included baseline depressive symptom score and self-reported and record-based history of anxiety and depression diagnoses before the baseline. We identified CVD events using hospital admission and death certificate data over a 10-year period from baseline. We determined incremental predictive values by adding the mental health predictors to the PREVENT predictors using Harrell's C-indices, sensitivity, specificity, and net reclassification improvement indices. We used a threshold of 10-year risk of incident CVD of greater than 5%.

RESULTS

Of the 502 366 UK Biobank participants, we included 195 489 in the derivation set and 130 326 in the validation set. In the validation set, the inclusion of all mental health measures, except self-reported anxiety, produced a very modest increase in the C-index and specificity while sensitivity remained unchanged. Among these mental health predictors, depressive symptom score produced the greatest improvements in both C-index (difference of 0.005, 95% confidence interval 0.004-0.006) and specificity (difference of 0.89%). Depressive symptom score showed similar small improvements in female and male validation sets.

INTERPRETATION

Our findings suggest that the inclusion of measures of depression and anxiety in PREVENT would have little additional effect on the risk classification of CVD at the population level and may not be worthwhile.

Overcoming Missing Data: Accurately Predicting Cardiovascular Risk in Type 2 Diabetes, A Systematic Review

Understanding is limited regarding strategies for addressing missing value when developing and validating models to predict cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM). This study aimed to investigate the presence of and approaches to missing data in these prediction models. The MEDLINE electronic database was systematically searched for English-language studies from inception to June 30, 2024. The percentages of missing values, missingness mechanisms, and missing data handling strategies in the included studies were extracted and summarized. This study included 51 articles published between 2001 and 2024, involving 19 studies that focused solely on prediction model development, and 16 and 16 studies that incorporated internal and external validation, respectively. Most articles reported missing data in the development (n = 40/51) and external validation (n = 12/16) stages. Furthermore, the missing data were addressed in 74.5% of development studies and 68.8% of validation studies. Imputation emerged as the predominant method employed for both development (27/40) and validation (7/12) purposes, followed by deletion (17/40 and 4/12, respectively). During the model development phase, the number of studies reported missing data increased from 9 out of 15 before 2016 to 31 out of 36 in 2016 and subsequent years. Although missing values have received much attention in CVD risk prediction models in patients with T2DM, most studies lack adequate reporting on the methodologies used for addressing the missing data. Enhancing the quality assurance of prediction models necessitates heightened clarity and the utilization of suitable methodologies to handle missing data effectively.

Transforming the cardiometabolic disease landscape: Multimodal AI-powered approaches in prevention and management

The rise of artificial intelligence (AI) has revolutionized various scientific fields, particularly in medicine, where it has enabled the modeling of complex relationships from massive datasets. Initially, AI algorithms focused on improved interpretation of diagnostic studies such as chest X-rays and electrocardiograms in addition to predicting patient outcomes and future disease onset. However, AI has evolved with the introduction of transformer models, allowing analysis of the diverse, multimodal data sources existing in medicine today. Multimodal AI holds great promise in more accurate disease risk assessment and stratification as well as optimizing the key driving factors in cardiometabolic disease: blood pressure, sleep, stress, glucose control, weight, nutrition, and physical activity. In this article we outline the current state of medical AI in cardiometabolic disease, highlighting the potential of multimodal AI to augment personalized prevention and treatment strategies in cardiometabolic disease.

Which risk factor best predicts coronary artery disease using artificial neural network method?

BACKGROUND

Coronary artery disease (CAD) is recognized as the leading cause of death worldwide. This study analyses CAD risk factors using an artificial neural network (ANN) to predict CAD.

METHODS

The research data were obtained from a multi-center study, namely the Iran-premature coronary artery disease (I-PAD). The current study used the medical records of 415 patients with CAD hospitalized in Razi Hospital, Birjand, Iran, between May 2016 and June 2019. A total of 43 variables that affect CAD were selected, and the relevant data was extracted. Once the data were cleaned and normalized, they were imported into SPSS (V26) for analysis. The present study used the ANN technique.

RESULTS

The study revealed that 48% of the study population had a history of CAD, including 9.4% with premature CAD and 38.8% with CAD. The variables of age, sex, occupation, smoking, opium use, pesticide exposure, anxiety, sexual activity, and high fasting blood sugar were found to be significantly different among the three groups of CAD, premature CAD, and non-CAD individuals. The neural network achieved success with five hidden fitted layers and an accuracy of 81% in non-CAD diagnosis, 79% in premature diagnosis, and 78% in CAD diagnosis. Anxiety, acceptance, eduction and gender were the four most important factors in the ANN model.

CONCLUSIONS

The current study shows that anxiety is a high-prevalence risk factor for CAD in the hospitalized population. There is a need to implement measures to increase awareness about the psychological factors that can be managed in individuals at high risk for future CAD.

Predicting coronary heart disease in Chinese diabetics using machine learning

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.

Improving diabetes disease patients classification using stacking ensemble method with PIMA and local healthcare data

Diabetes mellitus, a chronic metabolic disorder, continues to be a major public health issue around the world. It is estimated that one in every two diabetics is undiagnosed. Early diagnosis and management of diabetes can also prevent or delay the onset of complications. With the help of a variety of machine learning and deep learning models, stacking algorithms, and other techniques, our study's goal is to detect diseases early. In this study, we propose two stacking-based models for diabetes disease classification using a combination of the PIMA Indian diabetes dataset, simulated data, and additional data collected from a local healthcare facility. We use both the classical and deep neural network stacking ensemble methods to combine the predictions of multiple classification models and improve classification accuracy and robustness. In the evaluation protocol, we used both the train-test and cross-validation (CV) techniques to validate our proposed model. The highest accuracy is obtained by stacking ensemble with three NN architectures, resulting in an accuracy of 95.50 %, precision of 94 %, recall of 97 %, and f1-score of 96 % using 5-fold CV on simulation study. The stacked accuracy obtained from ML algorithms for the Pima Indian Diabetes dataset is 75.03 % using the train-test split protocol, while the accuracy obtained from the CV protocol is 77.10 % on the stacked model. The range of performance scores that outperformed the CV protocol 2.23 %-12 %. Our proposed method achieves a high accuracy range from 92 % to 95 %, precision, recall, and F1-score ranges from 88 % to 96 % using classical and deep neural network (NN)-based stacking method on the primary dataset. The proposed dataset and ensemble method could be useful in the early detection and treatment of diabetes, as well as in the advancement of machine learning and data analysis techniques in the healthcare industry.

Deep neural network for prediction of diet quality among doctors and nurses in North China during the COVID-19 pandemic

Objective

The COVID-19 pandemic has placed unprecedented pressure on front-line healthcare workers, leading to poor health status, especially diet quality. This study aimed to develop a diet quality prediction model and determine the predictive effects of personality traits, socioeconomic status, lifestyles, and individual and working conditions on diet quality among doctors and nurses during the COVID-19 pandemic.

Methods

A total of 5,013 doctors and nurses from thirty-nine COVID-19 designated hospitals provided valid responses in north China in 2022. Participants' data related to social-demographic characteristics, lifestyles, sleep quality, personality traits, burnout, work-related conflicts, and diet quality were collected with questionnaires. Deep Neural Network (DNN) was applied to develop a diet quality prediction model among doctors and nurses during the COVID-19 pandemic.

Results

The mean score of diet quality was 46.14 ± 15.08; specifically, the mean scores for variety, adequacy, moderation, and overall balance were 14.33 ± 3.65, 17.99 ± 5.73, 9.41 ± 7.33, and 4.41 ± 2.98, respectively. The current study developed a DNN model with a 21-30-28-1 network framework for diet quality prediction. The DNN model achieved high prediction efficacy, and values of R2, MAE, MSE, and RMSE were 0.928, 0.048, 0.004, and 0.065, respectively. Among doctors and nurses in north China, the top five predictors in the diet quality prediction model were BMI, poor sleep quality, work-family conflict, negative emotional eating, and nutrition knowledge.

Conclusion

During the COVID-19 pandemic, poor diet quality is prevalent among doctors and nurses in north China. Machine learning models can provide an automated identification mechanism for the prediction of diet quality. This study suggests that integrated interventions can be a promising approach to improving diet quality among doctors and nurses, particularly weight management, sleep quality improvement, work-family balance, decreased emotional eating, and increased nutrition knowledge.

Using Machine Learning for the Risk Factors Classification of Glycemic Control in Type 2 Diabetes Mellitus

Several risk factors are related to glycemic control in patients with type 2 diabetes mellitus (T2DM), including demographics, medical conditions, negative emotions, lipid profiles, and heart rate variability (HRV; to present cardiac autonomic activity). The interactions between these risk factors remain unclear. This study aimed to use machine learning methods of artificial intelligence to explore the relationships between various risk factors and glycemic control in T2DM patients. The study utilized a database from Lin et al. (2022) that included 647 T2DM patients. Regression tree analysis was conducted to identify the interactions among risk factors that contribute to glycated hemoglobin (HbA1c) values, and various machine learning methods were compared for their accuracy in classifying T2DM patients. The results of the regression tree analysis revealed that high depression scores may be a risk factor in one subgroup but not in others. When comparing different machine learning classification methods, the random forest algorithm emerged as the best-performing method with a small set of features. Specifically, the random forest algorithm achieved 84% accuracy, 95% area under the curve (AUC), 77% sensitivity, and 91% specificity. Using machine learning methods can provide significant value in accurately classifying patients with T2DM when considering depression as a risk factor.

Machine-learning prediction of BMI change among doctors and nurses in North China during the COVID-19 pandemic

Objective

The COVID-19 pandemic has become a major public health concern over the past 3 years, leading to adverse effects on front-line healthcare workers. This study aimed to develop a Body Mass Index (BMI) change prediction model among doctors and nurses in North China during the COVID-19 pandemic, and further identified the predicting effects of lifestyles, sleep quality, work-related conditions, and personality traits on BMI change.

Methods

The present study was a cross-sectional study conducted in North China, during May-August 2022. A total of 5,400 doctors and nurses were randomly recruited from 39 COVID-19 designated hospitals and 5,271 participants provided valid responses. Participants' data related to social-demographics, dietary behavior, lifestyle, sleep, personality, and work-related conflicts were collected with questionnaires. Deep Neural Network (DNN) was applied to develop a BMI change prediction model among doctors and nurses during the COVID-19 pandemic.

Results

Of participants, only 2,216 (42.0%) individuals kept a stable BMI. Results showed that personality traits, dietary behaviors, lifestyles, sleep quality, burnout, and work-related conditions had effects on the BMI change among doctors and nurses. The prediction model for BMI change was developed with a 33-26-20-1 network framework. The DNN model achieved high prediction efficacy, and values of R ², MAE, MSE, and RMSE for the model were 0.940, 0.027, 0.002, and 0.038, respectively. Among doctors and nurses, the top five predictors in the BMI change prediction model were unbalanced nutritional diet, poor sleep quality, work-family conflict, lack of exercise, and soft drinks consumption.

Conclusion

During the COVID-19 pandemic, BMI change was highly prevalent among doctors and nurses in North China. Machine learning models can provide an automated identification mechanism for the prediction of BMI change. Personality traits, dietary behaviors, lifestyles, sleep quality, burnout, and work-related conditions have contributed to the BMI change prediction. Integrated treatment measures should be taken in the management of weight and BMI by policymakers, hospital administrators, and healthcare workers.

Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review

Prediction model has been the focus of studies since the last century in the diagnosis and prognosis of various diseases. With the advancement in computational technology, machine learning (ML) has become the widely used tool to develop a prediction model. This review is to investigate the current development of prediction model for the risk of cardiovascular disease (CVD) among type 2 diabetes (T2DM) patients using machine learning. A systematic search on Scopus and Web of Science (WoS) was conducted to look for relevant articles based on the research question. The risk of bias (ROB) for all articles were assessed based on the Prediction model Risk of Bias Assessment Tool (PROBAST) statement. Neural network with 76.6% precision, 88.06% sensitivity, and area under the curve (AUC) of 0.91 was found to be the most reliable algorithm in developing prediction model for cardiovascular disease among type 2 diabetes patients. The overall concern of applicability of all included studies is low. While two out of 10 studies were shown to have high ROB, another studies ROB are unknown due to the lack of information. The adherence to reporting standards was conducted based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) standard where the overall score is 53.75%. It is highly recommended that future model development should adhere to the PROBAST and TRIPOD assessment to reduce the risk of bias and ensure its applicability in clinical settings. Potential lipid peroxidation marker is also recommended in future cardiovascular disease prediction model to improve overall model applicability.

Neuropsychiatric Symptoms and Commonly Used Biomarkers of Alzheimer's Disease: A Literature Review from a Machine Learning Perspective

There is a growing interest in the application of machine learning (ML) in Alzheimer's disease (AD) research. However, neuropsychiatric symptoms (NPS), frequent in subjects with AD, mild cognitive impairment (MCI), and other related dementias have not been analyzed sufficiently using ML methods. To portray the landscape and potential of ML research in AD and NPS studies, we present a comprehensive literature review of existing ML approaches and commonly studied AD biomarkers. We conducted PubMed searches with keywords related to NPS, AD biomarkers, machine learning, and cognition. We included a total of 38 articles in this review after excluding some irrelevant studies from the search results and including 6 articles based on a snowball search from the bibliography of the relevant studies. We found a limited number of studies focused on NPS with or without AD biomarkers. In contrast, multiple statistical machine learning and deep learning methods have been used to build predictive diagnostic models using commonly known AD biomarkers. These mainly included multiple imaging biomarkers, cognitive scores, and various omics biomarkers. Deep learning approaches that combine these biomarkers or multi-modality datasets typically outperform single-modality datasets. We conclude ML may be leveraged to untangle the complex relationships of NPS and AD biomarkers with cognition. This may potentially help to predict the progression of MCI or dementia and develop more targeted early intervention approaches based on NPS.

Prediction of suicidal ideation among Chinese college students based on radial basis function neural network

Background

Suicide is one of the leading causes of death for college students. The predictors of suicidal ideation among college students are inconsistent and few studies have systematically investigated psychological symptoms of college students to predict suicide. Therefore, this study aims to develop a suicidal ideation prediction model and explore important predictors of suicidal ideation among college students in China.

Methods

We recruited 1,500 college students of Sichuan University and followed up for 4 years. Demographic information, behavioral and psychological information of the participants were collected using computer-based questionnaires. The Radial Basis Function Neural Network (RBFNN) method was used to develop three suicidal ideation risk prediction models and to identify important predictive factors for suicidal ideation among college students.

Results

The incidence of suicidal ideation among college students in the last 12 months ranged from 3.00 to 4.07%. The prediction accuracies of all the three models were over 91.7%. The area under curve scores were up to 0.96. Previous suicidal ideation and poor subjective sleep quality were the most robust predictors. Poor self-rated mental health has also been identified to be an important predictor. Paranoid symptom, internet addiction, poor self-rated physical health, poor self-rated overall health, emotional abuse, low average annual household income per person and heavy study pressure were potential predictors for suicidal ideation.

Conclusions

The study suggested that the RBFNN method was accurate in predicting suicidal ideation. And students who have ever had previous suicidal ideation and poor sleep quality should be paid consistent attention to.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Anxiety Levels Predict Bone Mineral Density in Postmenopausal Women Undergoing Oral Bisphosphonates: A Two-Year Follow-Up

Clinical psychological factors may predict medical diseases. Anxiety level has been associated with osteoporosis, but its role on bone mineral density (BMD) change is still unknown. This study aimed to investigate the association between anxiety levels and both adherence and treatment response to oral bisphosphonates (BPs) in postmenopausal osteoporosis. BMD and anxiety levels were evaluated trough dual-energy X-ray absorptiometry and the Hamilton Anxiety Rating Scale (HAM-A), respectively. Participants received weekly medication with alendronate or risedronate and were grouped according to the HAM-A scores into tertiles (HAM-A 3 > HAM-A 2 > HAM-A 1). After 24 months, BMD changes were different among the HAM-A tertiles. The median lumbar BMD change was significantly greater in both the HAM-A 2 and HAM-A 3 in comparison with the HAM-A 1. The same trend was observed for femoral BMD change. Adherence to BPs was >75% in 68% of patients in the HAM-A 1, 79% of patients in the HAM-A 2, and 89% of patients in the HAM-A 3 (p = 0.0014). After correcting for age, body mass index, depressive symptoms, and the 10-yr. probability of osteoporotic fractures, anxiety levels independently predicted lumbar BMD change (β = 0.3417, SE 0.145, p = 0.02). In conclusion, women with higher anxiety levels reported greater BMD improvement, highlighting that anxiety was associated with adherence and response to osteoporosis medical treatment, although further research on this topic is needed.