Machine learning models for prediction of co-occurrence of diabetes and cardiovascular diseases: a retrospective cohort study

Optimized classification of diabetes using dynamic waterwheel plant optimization algorithm

The classification of chronic diseases has been a prominent research focus in public health, extensively leveraging machine learning algorithms. One of these chronic diseases that has significant rates of occurrence all around the world is diabetes, which is a disease by itself. Many academics are working to construct robust machine-learning algorithms for accurate categorization, given the prevalence of this chronic disease. A revolutionary methodology that can accurately categorize diabetic disease is the focus of this study, which aims to provide new methods. The proposed technique in this work is based on developing a novel feature selection method, DWWPA, which stands for dynamic waterwheel plant algorithm. The DWWPA algorithm is utilized in the process of optimizing the K-nearest neighbors (KNN) model in order to improve the accuracy of its classification. In the feature selection process, a binary representation of this method is called binary DWWPA (bDWWPA). Several different machine learning models and optimization techniques are compared to the strategy that has been presented. When categorizing diabetes cases in the dataset, the findings demonstrate the superiority and success of the proposed method. Furthermore, several different statistical analysis techniques, such as Analyses of variance (ANOVA) and Wilcoxon signed-rank test, are carried out to investigate the statistical difference and importance of the suggested strategy in contrast to the other ways at the same level of competition. The conclusions of these tests were consistent with what was anticipated they would be. Based on the suggested feature selection and the optimization of the KNN model, the proposed method has an accuracy of 98.9% when taken as an entire. The suggested method was useful in accurately classifying diabetic disease, as evidenced by the fact that it achieved a higher level of accuracy than the contemporary approaches.

Machine learning applications in preventive healthcare: A systematic literature review on predictive analytics of disease comorbidity from multiple perspectives

Artificial intelligence is constantly revolutionizing biomedical research and healthcare management. Disease comorbidity is a major threat to the quality of life for susceptible groups, especially middle-aged and elderly patients. The presence of multiple chronic diseases makes precision diagnosis challenging to realize and imposes a heavy burden on the healthcare system and economy. Given an enormous amount of accumulated health data, machine learning techniques show their capability in handling this puzzle. The present study conducts a review to uncover current research efforts in applying these methods to understanding comorbidity mechanisms and making clinical predictions considering these complex patterns. A descriptive metadata analysis of 791 unique publications aims to capture the overall research progression between January 2012 and June 2023. To delve into comorbidity-focused research, 61 of these scientific papers are systematically assessed. Four predictive analytics of tasks are detected: disease comorbidity data extraction, clustering, network, and risk prediction. It is observed that some machine learning-driven applications address inherent data deficiencies in healthcare datasets and provide a model interpretation that identifies significant risk factors of comorbidity development. Based on insights, both technical and practical, gained from relevant literature, this study intends to guide future interests in comorbidity research and draw conclusions about chronic disease prevention and diagnosis with managerial implications.

Radiomics of pericoronary adipose tissue on computed tomography angiography predicts coronary heart disease in patients with type 2 diabetes mellitus

BACKGROUND

Diabetes is a common chronic metabolic disease. The progression of the disease promotes vascular inflammation and the formation of atherosclerosis, leading to cardiovascular disease. The coronary artery perivascular adipose tissue attenuation index based on CCTA is a new noninvasive imaging biomarker that reflects the spatial changes in perivascular adipose tissue attenuation in CCTA images and the inflammation around the coronary arteries. In this study, a radiomics approach is proposed to extract a large number of image features from CCTA in a high-throughput manner and combined with clinical diagnostic data to explore the predictive ability of vascular perivascular adipose imaging data based on CCTA for coronary heart disease in diabetic patients.

METHODS

R language was used for statistical analysis to screen the variables with significant differences. A presegmentation model was used for CCTA vessel segmentation, and the pericoronary adipose region was screened out. PyRadiomics was used to calculate the radiomics features of pericoronary adipose tissue, and SVM, DT and RF were used to model and analyze the clinical data and radiomics data. Model performance was evaluated using indicators such as PPV, FPR, AAC, and ROC.

RESULTS

The results indicate that there are significant differences in age, blood pressure, and some biochemical indicators between diabetes patients with and without coronary heart disease. Among 1037 calculated radiomic parameters, 18.3% showed significant differences in imaging omics features. Three modeling methods were used to analyze different combinations of clinical information, internal vascular radiomics information and pericoronary vascular fat radiomics information. The results showed that the dataset of full data had the highest ACC values under different machine learning models. The support vector machine method showed the best specificity, sensitivity, and accuracy for this dataset.

CONCLUSIONS

In this study, the clinical data and pericoronary radiomics data of CCTA were fused to predict the occurrence of coronary heart disease in diabetic patients. This provides information for the early detection of coronary heart disease in patients with diabetes and allows for timely intervention and treatment.

Quercetin and Kaempferol as Multi-Targeting Antidiabetic Agents against Mouse Model of Chemically Induced Type 2 Diabetes

Diabetes, a multifactorial metabolic disorder, demands the discovery of multi-targeting drugs with minimal side effects. This study investigated the multi-targeting antidiabetic potential of quercetin and kaempferol. The druggability and binding affinities of both compounds towards multiple antidiabetic targets were explored using pharmacokinetic and docking software (AutoDock Vina 1.1.2). Our findings showed that quercetin and kaempferol obey Lipinski's rule of five and exhibit desirable ADMET (absorption, distribution, metabolism excretion, and toxicity) profiles. Both compounds showed higher binding affinities towards C-reactive protein (CRP), interleukin-1 (IL-1), dipeptidyl peptidase-4 (DPP-IV), peroxisome proliferator-activated receptor gamma (PPARG), protein tyrosine phosphatase (PTP), and sodium-glucose co-transporter-1 (SGLT-1) compared to metformin (the positive control). Both quercetin and kaempferol inhibited α-amylase activity (in vitro) up to 20.30 ± 0.49 and 37.43 ± 0.42%, respectively. Their oral supplementation significantly reduced blood glucose levels (p < 0.001), improved lipid profile (p < 0.001), and enhanced total antioxidant status (p < 0.01) in streptozotocin-nicotinamide (STZ-NA)-induced diabetic mice. Additionally, both compounds significantly inhibited the proliferation of Huh-7 and HepG2 (cancer cells) (p < 0.0001) with no effect on the viability of Vero cell line (non-cancer). In conclusion, quercetin and kaempferol demonstrated higher binding affinities towards multiple targets than metformin. In vitro and in vivo antidiabetic potential along with the anticancer activities of both compounds suggest promise for further development in diabetes management. The combination of both drugs did not show a synergistic effect, possibly due to their same target on the receptors.

Burden of Hypertensive Heart Disease and High Systolic Blood Pressure in Australia from 1990 to 2019: Results From the Global Burden of Diseases Study

BACKGROUND

There is a dearth of comprehensive studies examining the burden and trends of hypertensive heart disease (HHD) and high systolic blood pressure (SBP) among the Australian population. We aimed to explore the burden of HHD and high SBP, and how they changed over time from 1990 to 2019 in Australia.

METHODS

We analysed data from the Global Burden of Disease study in Australia. We assessed the prevalence, mortality, disability-adjusted life-years (DALY), years lived with disability (YLD) and years of life lost (YLL) attributable to HHD and high SBP. Data were presented as point estimates with 95% uncertainty intervals (UI). We compared the burden of HHD and high SBP in Australia with World Bank defined high-income countries and six other comparator countries with similar sociodemographic characteristics and economies.

RESULTS

From 1990 to 2019, the burden of HHD and high SBP in Australia reduced. Age standardised prevalence rate of HHD was 119.3 cases per 100,000 people (95% UI 86.6-161.0) in 1990, compared to 80.1 cases (95% UI 57.4-108.1) in 2019. Deaths due to HDD were 3.4 cases per 100,000 population (95% UI 2.6-3.8) in 1990, compared to 2.5 (95% UI 1.9-3.0) in 2019. HHD contributed to 57.2 (95% UI 46.6-64.7) DALYs per 100,000 population in 1990 compared to 38.4 (95% UI 32.0-45.2) in 2019. Death rates per 100,000 population attributable to high SBP declined significantly over time for both sexes from 1990 (155.6 cases; 95% UI 131.2-177.0) to approximately one third in 2019 (53.8 cases; 95% UI 43.4-64.4). Compared to six other countries in 2019, the prevalence of HHD was highest in the USA (274.3%) and lowest in the UK (52.6%), with Australia displaying the third highest prevalence. Australia ranked second in term of lowest rates of deaths and third for lowest DALYs respectively due to high SBP. From 1990-2019, Australia ranked third best for reductions in deaths and DALYs due to HHD and first for reductions in deaths and DALYs due to high SBP.

CONCLUSION

Over the past three decades, the burden of HHD in Australia has reduced, but its prevalence remains relatively high. The contribution of high SBP to deaths, DALYs and YLLs also reduced over the three decades.

Predicting Cardiovascular Disease Mortality: Leveraging Machine Learning for Comprehensive Assessment of Health and Nutrition Variables

Cardiovascular disease (CVD) is one of the primary causes of death around the world. This study aimed to identify risk factors associated with CVD mortality using data from the National Health and Nutrition Examination Survey (NHANES). We created three models focusing on dietary data, non-diet-related health data, and a combination of both. Machine learning (ML) models, particularly the random forest algorithm, demonstrated robust consistency across health, nutrition, and mixed categories in predicting death from CVD. Shapley additive explanation (SHAP) values showed age, systolic blood pressure, and several other health factors as crucial variables, while fiber, calcium, and vitamin E, among others, were significant nutritional variables. Our research emphasizes the importance of comprehensive health evaluation and dietary intake in predicting CVD mortality. The inclusion of nutrition variables improved the performance of our models, underscoring the utility of dietary intake in ML-based data analysis. Further investigation using large datasets with recurring dietary recalls is necessary to enhance the effectiveness and interpretability of such models.

An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database

Heart disease is a significant global cause of mortality, and predicting it through clinical data analysis poses challenges. Machine learning (ML) has emerged as a valuable tool for diagnosing and predicting heart disease by analyzing healthcare data. Previous studies have extensively employed ML techniques in medical research for heart disease prediction. In this study, eight ML classifiers were utilized to identify crucial features that enhance the accuracy of heart disease prediction. Various combinations of features and well-known classification algorithms were employed to develop the prediction model. Neural network models, such as Naïve Bayes and Radial Basis Functions, were implemented, achieving accuracies of 94.78% and 90.78% respectively in heart disease prediction. Among the state-of-the-art methods for cardiovascular problem prediction, Learning Vector Quantization exhibited the highest accuracy rate of 98.7%. The motivation behind predicting Cardiovascular Heart Disease lies in its potential to save lives, improves health outcomes, and allocates healthcare resources efficiently. The key contributions encompass early intervention, personalized medicine, technological advancements, the impact on public health, and ongoing research, all of which collectively work toward reducing the burden of CHD on both individual patients and society as a whole.

Use of Multiple Fluid Biomarkers for Predicting the Co-occurrence of Diabetes and Hypertension Using Machine Learning Approaches

The co-existence of diabetes and hypertension can complicate and affect the management of these diseases. The early detection of these comorbidities can help in developing personalized preventive treatments and thereby, reduce the healthcare burden. The inclusion of readily available fluid biomarkers from different body fluids can be used as diagnostic tools and can facilitate in the designing of treatment strategies. In this work, an attempt has been made using multiple fluid biomarkers to differentiate diabetic from diabetic and hypertensive comorbid (DHC) condition. The fluid biomarkers are obtained from a publicly available dataset for diabetic (N=105) and DHC (N=57) conditions. The features, such as systolic blood pressure, fasting blood glucose, diastolic blood pressure, and total cholesterol are extracted and statistically analyzed. Data balancing technique namely synthetic minority oversampling technique is applied on the minority class to balance the dataset. Machine learning techniques namely, linear discriminant analysis, random forest, K-nearest neighbor, and linear support vector machine are used to perform the classification between the two groups. The results show that systolic blood pressure, diastolic blood pressure, and total cholesterol are elevated in the comorbid condition. These features also exhibit a statistical significance (p<0.001) between the two groups. This study also addresses the data imbalance issue, which is resolved by using an oversampling technique to mitigate the bias resulting from imbalanced data. The LDA classifier achieves a maximum accuracy of 61.2% in distinguishing between the two conditions. Machine learning based approaches may help in the prediction of comorbid conditions. This can act as a guideline for future studies on the progression of diseases and the identification of fluid biomarkers.

Prediction of disease comorbidity using explainable artificial intelligence and machine learning techniques: A systematic review

OBJECTIVE

Disease comorbidity is a major challenge in healthcare affecting the patient's quality of life and costs. AI-based prediction of comorbidities can overcome this issue by improving precision medicine and providing holistic care. The objective of this systematic literature review was to identify and summarise existing machine learning (ML) methods for comorbidity prediction and evaluate the interpretability and explainability of the models.

MATERIALS AND METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was used to identify articles in three databases: Ovid Medline, Web of Science and PubMed. The literature search covered a broad range of terms for the prediction of disease comorbidity and ML, including traditional predictive modelling.

RESULTS

Of 829 unique articles, 58 full-text papers were assessed for eligibility. A final set of 22 articles with 61 ML models was included in this review. Of the identified ML models, 33 models achieved relatively high accuracy (80-95%) and AUC (0.80-0.89). Overall, 72% of studies had high or unclear concerns regarding the risk of bias.

DISCUSSION

This systematic review is the first to examine the use of ML and explainable artificial intelligence (XAI) methods for comorbidity prediction. The chosen studies focused on a limited scope of comorbidities ranging from 1 to 34 (mean = 6), and no novel comorbidities were found due to limited phenotypic and genetic data. The lack of standard evaluation for XAI hinders fair comparisons.

CONCLUSION

A broad range of ML methods has been used to predict the comorbidities of various disorders. With further development of explainable ML capacity in the field of comorbidity prediction, there is a significant possibility of identifying unmet health needs by highlighting comorbidities in patient groups that were not previously recognised to be at risk for particular comorbidities.

The burden of type 2 diabetes in Australia during the period 1990-2019: Findings from the global burden of disease study

AIMS

To describe morbidity and mortality trends of type 2 diabetes in Australia, from 1990 to 2019, compared with similar sociodemographic index (SDI) countries.

METHODS

Australia-specific Global Burden of Diseases data were used to estimate age-standardised, age-specific, and sex-specific rates for prevalence, years lived with disability (YLDs), years of life lost (YLLs), disability-adjusted life years (DALYs), and deaths due to type 2 diabetes between 1990 and 2019. Australian data were compared with 14 similar SDI countries.

RESULTS

Type 2 diabetes increased in Australia between 1990 and 2019. The age-standardised prevalence increased from 1,985 [95% Confidence Interval (CI): 1,786.7-2195.3] per 100,000 population, to 3,429 [95% CI 3,053.3-3,853.7]. Cases tripled, from 379,532 [342,465-419,475] to 1,307,261 [1,165,522-1,461,180]. The age-standardised death rates doubled, from 2,098 [1,953-2,203] per 100,000, to 4,122 [3,617-4,512]. DALYs doubled, from 70,348 [59,187-83,500] to 169,763 [129,792-216,150], with increases seen in YLDs and YLLs. Men displayed higher rates. Compared to similar SDI countries, Australia ranked 4th in terms of burden for type 2 diabetes.

CONCLUSIONS

The burden of type 2 diabetes in Australia has increased considerably over three decades. There is an urgent need to prioritise resource allocation for prevention programs, screening initiatives to facilitate early detection, and effective and accessible management strategies for the large proportion of the population impacted by type 2 diabetes.

Effectively Predicting the Presence of Coronary Heart Disease Using Machine Learning Classifiers

Coronary heart disease is one of the major causes of deaths around the globe. Predicating a heart disease is one of the most challenging tasks in the field of clinical data analysis. Machine learning (ML) is useful in diagnostic assistance in terms of decision making and prediction on the basis of the data produced by healthcare sector globally. We have also perceived ML techniques employed in the medical field of disease prediction. In this regard, numerous research studies have been shown on heart disease prediction using an ML classifier. In this paper, we used eleven ML classifiers to identify key features, which improved the predictability of heart disease. To introduce the prediction model, various feature combinations and well-known classification algorithms were used. We achieved 95% accuracy with gradient boosted trees and multilayer perceptron in the heart disease prediction model. The Random Forest gives a better performance level in heart disease prediction, with an accuracy level of 96%.

Consensus on Recommended Functions of a Smart Home System to Improve Self-Management Behaviors in People With Heart Failure: A Modified Delphi Approach

Background

Smart home systems could enhance clinical and self-management of chronic heart failure by supporting health monitoring and remote support, but evidence to guide the design of smart home system functionalities is lacking.

Objective

To identify consensus-based recommendations for functions of a smart home system that could augment clinical and self-management for people living with chronic heart failure in the community.

Methods

Healthcare professionals caring for people living with chronic heart failure participated in a two-round modified Delphi survey and a consensus workshop. Thirty survey items spanning eight chronic health failure categories were derived from international guidelines for the management of heart failure. In survey Round 1, participants rated the importance of all items using a 9-point Liket scale and suggested new functions to support people with chronic heart failure in their homes using a smart home system. The Likert scale scores ranged from 0 (not important) to 9 (very important) and scores were categorized into three groups: 1-3 = not important, 4-6 = important, and 7-9 = very important. Consensus agreement was defined a priori as ≥70% of respondents rating a score of ≥7 and ≤ 15% rating a score ≤ 3. In survey Round 2, panel members re-rated items where consensus was not reached, and rated the new items proposed in earlier round. Panel members were invited to an online consensus workshop to discuss items that had not reached consensus after Round 2 and agree on a set of recommendations for a smart home system.

Results

In Round 1, 15 experts agreed 24/30 items were "very important", and suggested six new items. In Round 2, experts agreed 2/6 original items and 6/6 new items were "very important". During the consensus workshop, experts endorsed 2/4 remaining items. Finally, the expert panel recommended 34 items as "very important" for a smart home system including, healthy eating, body weight and fluid intake, physical activity and sedentary behavior, heart failure symptoms, tobacco cessation and alcohol reduction, medication adherence, physiological monitoring, interaction with healthcare professionals, and mental health among others.

Conclusion

A panel of healthcare professional experts recommended 34-item core functions in smart home systems designed to support people with chronic heart failure for self-management and clinical support. Results of this study will help researchers to co-design and protyping solutions with consumers and healthcare providers to achieve these core functions to improve self-management and clinical outcomes in people with chronic heart failure.

Prediction of cardiac autonomic neuropathy using a machine learning model in patients with diabetes

Background

Cardiac autonomic neuropathy (CAN) is a diabetes-related complication with increasing prevalence and remains challenging to detect in clinical settings. Machine learning (ML) approaches have the potential to predict CAN using clinical data. In this study, we aimed to develop and evaluate the performance of an ML model to predict early CAN occurrence in patients with diabetes.

Methods

We used the diabetes complications screening research initiative data set containing 200 CAN-related tests on more than 2000 participants with type 2 diabetes in Australia. Data were collected on peripheral nerve functions, Ewing's tests, blood biochemistry, demographics, and medical history. The ML model was validated using 10-fold cross-validation, of which 90% were used in training the model and the remaining 10% was used in evaluating the performance of the model. Predictive accuracy was assessed by area under the receiver operating curve, and sensitivity, specificity, positive predictive value, and negative predictive value.

Results

Of the 237 patients included, 105 were diagnosed with an early stage of CAN while the remaining 132 were healthy. The ML model showed outstanding performance for CAN prediction with receiver operating characteristic curve of 0.962 [95% confidence interval (CI) = 0.939-0.984], 87.34% accuracy, and 87.12% sensitivity. There was a significant and positive association between the ML model and CAN occurrence (p < 0.001).

Conclusion

Our ML model has the potential to detect CAN at an early stage using Ewing's tests. This model might be useful for healthcare providers for predicting the occurrence of CAN in patients with diabetes, monitoring the progression, and providing timely intervention.