Search

Background: In the age of big data, linked social and administrative health data in combination with machine learning (ML) is being increasingly used to improve prediction in chronic disease, e.g., cardiovascular diseases (CVD). In this study we aimed to apply ML methods on extensive national-level health and social administrative datasets to assess the utility of these for predicting future diabetes complications, including by ethnicity. Methods: Five ML models were used to predict CVD events among all people with known diabetes in the population of New Zealand, utilizing nationwide individual-level administrative data. Results: The Xgboost ML model had the best predictive power for predicting CVD events three years into the future among the population with diabetes (N = 145,600). The optimization procedure also found limited improvement in prediction by ethnicity (using area under the receiver operating curve, [AUC]). The results indicated no trade-off between model predictive performance and equity gap of prediction by ethnicity (that is improving model prediction and reducing performance gaps by ethnicity can be achieved simultaneously). The list of variables of importance was different among different models/ethnic groups, for example: age, deprivation (neighborhood-level), having had a hospitalization event, and the number of years living with diabetes. Discussion and conclusions: We provide further evidence that ML with administrative health data can be used for meaningful future prediction of health outcomes. As such, it could be utilized to inform health planning and healthcare resource allocation for diabetes management and the prevention of CVD events. Our results may suggest limited scope for developing prediction models by ethnic group and that the major ways to reduce inequitable health outcomes is probably via improved delivery of prevention and management to those groups with diabetes at highest need. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration. [ABSTRACT FROM AUTHOR]

Primary care has the potential to be transformed by artificial intelligence (AI) and, in particular, machine learning (ML). This review summarizes the potential of ML and its subsets in influencing two domains of primary care: pre-operative care and screening. ML can be utilized in preoperative treatment to forecast postoperative results and assist physicians in selecting surgical interventions. Clinicians can modify their strategy to reduce risk and enhance outcomes using ML algorithms to examine patient data and discover factors that increase the risk of worsened health outcomes. ML can also enhance the precision and effectiveness of screening tests. Healthcare professionals can identify diseases at an early and curable stage by using ML models to examine medical pictures, diagnostic modalities, and spot patterns that may suggest disease or anomalies. Before the onset of symptoms, ML can be used to identify people at an increased risk of developing specific disorders or diseases. ML algorithms can assess patient data such as medical history, genetics, and lifestyle factors to identify those at higher risk. This enables targeted interventions such as lifestyle adjustments or early screening. In general, using ML in primary care offers the potential to enhance patient outcomes, reduce healthcare costs, and boost productivity. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) and heart failure (HF) are the first and most frequent comorbidities associated with mortality risks in early-stage type 2 diabetes mellitus (T2DM). However, efficient screening and risk assessment strategies for identifying T2DM patients at high risk of developing CKD and/or HF (CKD/HF) remains to be established. This study aimed to generate a novel machine learning (ML) model to predict the risk of developing CKD/HF in early-stage T2DM patients. The models were derived from a retrospective cohort of 217,054 T2DM patients without a history of cardiovascular and renal diseases extracted from a Japanese claims database. Among algorithms used for the ML, extreme gradient boosting exhibited the best performance for CKD/HF diagnosis and hospitalization after internal validation and was further validated using another dataset including 16,822 patients. In the external validation, 5-years prediction area under the receiver operating characteristic curves for CKD/HF diagnosis and hospitalization were 0.718 and 0.837, respectively. In Kaplan–Meier curves analysis, patients predicted to be at high risk showed significant increase in CKD/HF diagnosis and hospitalization compared with those at low risk. Thus, the developed model predicted the risk of developing CKD/HF in T2DM patients with reasonable probability in the external validation cohort. Clinical approach identifying T2DM at high risk of developing CKD/HF using ML models may contribute to improved prognosis by promoting early diagnosis and intervention. [ABSTRACT FROM AUTHOR]

Gestational diabetes mellitus (GDM) increases the risk of early-onset type 2 diabetes, which further exacerbates the risk of developing diabetic complications such as kidney, circulatory, and neurological complications. Yet, existing models have solely focused on the prediction of type 2 diabetes, and not of its complications, which are arguably the most clinically relevant outcomes. Our aim was to develop a prediction model for type 2 diabetic complications in patients with GDM. Using provincial administrative data from Quebec, Canada, we developed a model to predict type 2 diabetic complications within 10 years among 90,143 women with GDM. The model was internally validated and assessed for discrimination, calibration, and risk stratification accuracy. The incidence of diabetic complications was 3.8 (95% confidence interval (CI) 3.4–4.3) per 10,000 person-years. The final prediction model included maternal age, socioeconomic deprivation, substance use disorder, gestational age at delivery, severe maternal morbidity, previous pregnancy complications, and hypertensive disorders of pregnancy. The model had good discrimination [area under the curve (AUROC) 0.72 (95% CI 0.69–0.74)] and calibration (slope ≥ 0.9) to predict diabetic complications. In the highest category of the risk stratification table, the positive likelihood ratio was 8.68 (95% CI 4.14–18.23), thereby showing a moderate ability to identify women at highest risk of developing type 2 diabetic complications. Our model predicts the risk of type 2 diabetic complications with moderate accuracy and, once externally validated, may prove to be a useful tool in the management of women after GDM. [ABSTRACT FROM AUTHOR]

The utilization of artificial intelligence (AI) in diabetes care has focused on early intervention and treatment management. Notably, usage has expanded to predict an individual's risk for developing type 2 diabetes. A scoping review of 40 studies by Mohsen et al. shows that while most studies used unimodal AI models, multimodal approaches were superior because they integrate multiple types of data. However, creating multimodal models and determining model performance are challenging tasks given the multi-factored nature of diabetes. For both unimodal and multimodal models, there are also concerns of bias with the lack of external validations and representation of race, age, and gender in training data. The barriers in data quality and evaluation standardization are ripe areas for developing new technologies, especially for entrepreneurs and innovators. Collaboration amongst providers, entrepreneurs, and researchers must be prioritized to ensure that AI in diabetes care is providing quality and equitable patient care. [ABSTRACT FROM AUTHOR]

Diabetes Mellitus is a severe, chronic disease that occurs when blood glucose levels rise above certain limits. Over the last years, machine and deep learning techniques have been used to predict diabetes and its complications. However, researchers and developers still face two main challenges when building type 2 diabetes predictive models. First, there is considerable heterogeneity in previous studies regarding techniques used, making it challenging to identify the optimal one. Second, there is a lack of transparency about the features used in the models, which reduces their interpretability. This systematic review aimed at providing answers to the above challenges. The review followed the PRISMA methodology primarily, enriched with the one proposed by Keele and Durham Universities. Ninety studies were included, and the type of model, complementary techniques, dataset, and performance parameters reported were extracted. Eighteen different types of models were compared, with tree-based algorithms showing top performances. Deep Neural Networks proved suboptimal, despite their ability to deal with big and dirty data. Balancing data and feature selection techniques proved helpful to increase the model's efficiency. Models trained on tidy datasets achieved almost perfect models. [ABSTRACT FROM AUTHOR]