Machine learning in precision diabetes care and cardiovascular risk prediction

Oikonomou, Evangelos K.; Khera, Rohan

doi:10.1186/s12933-023-01985-3

Cited by 20 publications

(11 citation statements)

References 138 publications

(146 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies utilizing logistical regression and classification trees have predicted that fasting blood glucose, BMI, and age are the main predictors of developing diabetes and observed population health risk assessment for diabetes onset [25][26][27]. It has also been used to predict associated complications [28,29]. However, there remains a gap in the literature when it comes to analyzing outcomes and readmission with the use of machine and deep learning.…”

Section: Introductionmentioning

confidence: 99%

Cardiovascular Health Management in Diabetic Patients with Machine-Learning-Driven Predictions and Interventions

Jose,

Syed,

Thomas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The advancement of machine learning in healthcare offers significant potential for enhancing disease prediction and management. This study harnesses the PyCaret library—a Python-based machine learning toolkit—to construct and refine predictive models for diagnosing diabetes mellitus and forecasting hospital readmission rates. By analyzing a rich dataset featuring a variety of clinical and demographic variables, we endeavored to identify patients at heightened risk for diabetes complications leading to readmissions. Our methodology incorporates an evaluation of numerous machine learning algorithms, emphasizing their predictive accuracy and generalizability to improve patient care. We scrutinized the predictive strength of each model concerning crucial metrics like accuracy, precision, recall, and the area under the curve, underlining the imperative to eliminate false diagnostics in the field. Special attention is given to the use of the light gradient boosting machine classifier among other advanced modeling techniques, which emerge as particularly effective in terms of the Kappa statistic and Matthews correlation coefficient, suggesting robustness in prediction. The paper discusses the implications of diabetes management, underscoring interventions like lifestyle changes and pharmacological treatments to avert long-term complications. Through exploring the intersection of machine learning and health informatics, the study reveals pivotal insights into algorithmic predictions of diabetes readmission. It also emphasizes the necessity for further research and development to fully incorporate machine learning into modern diabetes care to prompt timely interventions and achieve better overall health outcomes. The outcome of this research is a testament to the transformative impact of automated machine learning in the realm of healthcare analytics.

show abstract

Section: Introductionmentioning

confidence: 99%

Cardiovascular Health Management in Diabetic Patients with Machine-Learning-Driven Predictions and Interventions

Jose,

Syed,

Thomas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A recent review [9] has highlighted that artificial intelligence (AI) and machine learning are catalyzing a transformative shift in medicine, offering data-driven, personalized approaches for addressing diabetes and its associated cardiovascular risk. Research has revealed that the utilization of AI and data-driven techniques in managing patients with diabetes who face heightened cardiovascular risks shows great promise.…”

Section: Introductionmentioning

confidence: 99%

“…Research has revealed that the utilization of AI and data-driven techniques in managing patients with diabetes who face heightened cardiovascular risks shows great promise. These approaches can be harnessed to develop predictive models aimed at personalized care, encompassing diagnosis, prognosis, phenotyping, and treatment of both diabetes and its cardiovascular complications [9]. .…”

Section: Introductionmentioning

confidence: 99%

Dental Pathology Reveal Bidirectional Link between Diabetes and Cardiovascular Risk: Multi-Way Array Analysis

Pham

2024

Preprint

View full text Add to dashboard Cite

Background: Understanding the relationship between diabetes and cardiovascular risk is paramount for achieving holistic and effective healthcare. Diabetes, a complex metabolic disorder, is intricately linked to an increased susceptibility to cardiovascular diseases, making it imperative to unravel the nuanced interplay between these two health parameters. Cardiovascular risk in individuals with diabetes is often heightened due to various factors, including endothelial dysfunction, inflammation, and metabolic disturbances. Insights into this intricate relationship can empower healthcare professionals to adopt a proactive stance, offering timely interventions and personalized care strategies. Methods: This study leverages a publicly available dataset comprising 212 patients from Dutch hospitals to investigate the intricate connections among patient characteristics, dental pathology, and cardiovascular risk factors. Utilizing tensor decomposition in data science and visual representation, this study explored the bidirectional relationship between diabetes and coronary artery calcification. A multi-way array analysis integrated patient characteristics and dental conditions to construct tensor models for three categories: without diabetes, with diabetes, and with coronary artery calcification. Furthermore, com-1 plementary nonlinear dynamics, visual analyses, and machine learning were utilized to further enrich the investigation. Results: Patterns across the three categories were discovered through PARAFAC tensor decomposition factors, incorporating both patient characteristics and dental conditions. The k-NN search, examining the similarity among tensor coefficients derived from the 3-way arrays within the three categories, highlighted a bidirectional link between diabetes and cardiovascular risk. Additionally, the utilization of fuzzy recurrence plots and entropy measures enabled the quantification of distinctive patterns among subjects without diabetes , those with diabetes, and individuals experiencing coronary artery calcification. Conclusion: The reciprocal interaction between diabetes and CAC tertiles 2 and 3 becomes apparent, underscoring the necessity for a broader analytical perspective. The incorporation of patient characteristics and dental health in the 3-way array analysis reveals latent patterns, enhancing current understanding with nuanced insights. Dental conditions emerge as pivotal indicators, providing a more detailed viewpoint on the intricacy between diabetes and cardiovascular risk.

show abstract

“…Diabetes has also been studied using machine learning [7][8][9]. Oikonomou et al [10] provide a comprehensive overview of how machine learning has been applied to precision diabetes care, particularly in cardiovascular risk prediction among diabetic patients. Their work underscores the significant potential of machine learning in transforming diabetes care by leveraging large datasets to identify risk factors and predict outcomes with high accuracy.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Data Missingness on Machine Learning Predictions of Uncontrolled Diabetes Using All of Us Data

Jabbar,

Washington

2024

BioMedInformatics

View full text Add to dashboard Cite

Electronic Health Records (EHR) provide a vast amount of patient data that are relevant to predicting clinical outcomes. The inherent presence of missing values poses challenges to building performant machine learning models. This paper aims to investigate the effect of various imputation methods on the National Institutes of Health’s All of Us dataset, a dataset containing a high degree of data missingness. We apply several imputation techniques such as mean substitution, constant filling, and multiple imputation on the same dataset for the task of diabetes prediction. We find that imputing values causes heteroskedastic performance for machine learning models with increased data missingness. That is, the more missing values a patient has for their tests, the higher variance there is on a diabetes model AUROC, F1, precision, recall, and accuracy scores. This highlights a critical challenge in using EHR data for predictive modeling. This work highlights the need for future research to develop methodologies to mitigate the effects of missing data and heteroskedasticity in EHR-based predictive models.

show abstract

Machine learning in precision diabetes care and cardiovascular risk prediction

Cited by 20 publications

References 138 publications

Cardiovascular Health Management in Diabetic Patients with Machine-Learning-Driven Predictions and Interventions

Cardiovascular Health Management in Diabetic Patients with Machine-Learning-Driven Predictions and Interventions

Dental Pathology Reveal Bidirectional Link between Diabetes and Cardiovascular Risk: Multi-Way Array Analysis

The Effect of Data Missingness on Machine Learning Predictions of Uncontrolled Diabetes Using All of Us Data

Contact Info

Product

Resources

About