Reverse Engineering and Evaluation of Prediction Models for Progression to Type 2 Diabetes: An Application of Machine Learning Using Electronic Health Records. | LitMetric
Background: Application of novel machine learning approaches to electronic health record (EHR) data could provide valuable insights into disease processes. We utilized this approach to build predictive models for progression to prediabetes and type 2 diabetes (T2D).
Methods: Using a novel analytical platform (Reverse Engineering and Forward Simulation [REFS]), we built prediction model ensembles for progression to prediabetes or T2D from an aggregated EHR data sample. REFS relies on a Bayesian scoring algorithm to explore a wide model space, and outputs a distribution of risk estimates from an ensemble of prediction models. We retrospectively followed 24 331 adults for transitions to prediabetes or T2D, 2007-2012. Accuracy of prediction models was assessed using an area under the curve (AUC) statistic, and validated in an independent data set.
Results: Our primary ensemble of models accurately predicted progression to T2D (AUC = 0.76), and was validated out of sample (AUC = 0.78). Models of progression to T2D consisted primarily of established risk factors (blood glucose, blood pressure, triglycerides, hypertension, lipid disorders, socioeconomic factors), whereas models of progression to prediabetes included novel factors (high-density lipoprotein, alanine aminotransferase, C-reactive protein, body temperature; AUC = 0.70).
Conclusions: We constructed accurate prediction models from EHR data using a hypothesis-free machine learning approach. Identification of established risk factors for T2D serves as proof of concept for this analytical approach, while novel factors selected by REFS represent emerging areas of T2D research. This methodology has potentially valuable downstream applications to personalized medicine and clinical research.
Background: Delirium is common in hospitalized patients and correlated with increased morbidity and mortality. Despite this, delirium is underdiagnosed, and many institutions do not have sufficient resources to consistently apply effective screening and prevention.
Objective: To develop a machine learning algorithm to identify patients at highest risk of delirium in the hospital each day in an automated fashion based on data available in the electronic medical record, reducing the barrier to large-scale delirium screening.
Ceratapion basicorne (Illiger) (Coleoptera: Apionidae), a weevil native to Europe and western Asia, shows promise for enhancing the control of yellow starthistle (Centaurea solstitialis L.), an invasive annual forb in the western United States. However, a paucity of data on this biocontrol agent's environmental constraints has made it difficult to assess the suitability of potential release locations.
Chromatin is a dynamic polymer in constant motion. These motions are heterogeneous between cells and within individual cell nuclei and are profoundly altered in response to DNA damage. The shifts in chromatin motions following genomic insults depend on the temporal and physical scales considered.
Objective: We have shown that men aged 50 years+ at high risk of type 2 diabetes treated with testosterone together with a lifestyle program reduced the risk of type 2 diabetes at two years by 40% compared to a lifestyle program alone. To develop a personalized approach to treatment, we aimed to explore a prognostic model for incident type 2 diabetes at two years and investigate biomarkers predictive of the testosterone effect.
Design: Model development in 783 men with impaired glucose tolerance but not type 2 diabetes from T4DM; a multicenter, 2-year trial of Testosterone vs placebo.
Colorectal cancer (CRC) is a significant contributor to cancer-related mortality, emphasizing the need for advanced biomarkers to guide treatment. As part of an international consortium, we previously categorized CRCs into four consensus molecular subtypes (CMS1-CMS4), showing promise for outcome prediction. To facilitate clinical integration of CMS classification in settings where formalin-fixed paraffin-embedded (FFPE) samples are routinely used, we developed NanoCMSer, a NanoString-based CMS classifier using 55 genes.
