Automating and improving cardiovascular disease prediction using Machine learning and EMR data features from a regional healthcare system.

BACKGROUND: The ACC/AHA Pooled Cohort Equations (PCE) Risk Calculator is widely used in the US for primary prevention of atherosclerotic cardiovascular disease (ASCVD), but may under- or over-estimate risk in some populations. We therefore designed an automated, population-specific ASCVD risk calculator using machine-learning (ML) methods and electronic medical record (EMR) data, and compared its predictive power with that of the PCE calculator. METHODS AND FINDINGS: We collected data from 101,110 unique EMRs of living patients from January 1, 2009 to April 30, 2020. ML techniques were applied to patient datasets that included either only cross-sectional (CS) features, or CS combined with longitudinal (LT) features derived from vital statistics and laboratory values. We compared the utility of the models using a proposed new cost measure (Screened Cases Percentage @ Sensitivity level). All ML models tested achieved better predictive power than the PCE risk calculator. The random forest ML technique (RF) applied on the combination of CS and LT features (RF-LTC) produced the best area under curve (AUC) score of 0.902 (95% confidence interval (CI), 0.895-0.910). To detect 90% of all positive ASCVD cases, the best ML model required screening only 43% of patients, while the PCE risk calculator required screening 69% of patients. CONCLUSIONS: Prediction models built using ML techniques improved ASCVD prediction and reduced the number of screenings required to predict ASCVD when compared with the PCE calculator, alone. Combining LT and CS features in the ML models significantly improved ASCVD prediction compared with using CS features, alone.

Improving Familial Hypercholesterolemia Diagnosis Using an EMR-based Hybrid Diagnostic Model.

CONTEXT: Familial hypercholesterolemia (FH) confers a greatly increased risk for premature cardiovascular disease, but remains very underdiagnosed and undertreated in primary care populations. OBJECTIVE: We assessed whether using a hybrid model consisting of 2 existing FH diagnostic criteria coupled with electronic medical record (EMR) data would accurately identify patients with FH in a Midwest US metropolitan healthcare system. METHODS: We conducted a retrospective, records-based, cross-sectional study using datasets from unique EMRs of living patients. Using Structured Query Language to identify components of 2 currently approved FH diagnostic criteria, we created a hybrid model to identify individuals with FH. RESULTS: Of 264 264 records analyzed, between 794 and 1571 patients were identified as having FH based on the hybrid diagnostic model, with a prevalence of 1:300 to 1:160. These patients had a higher prevalence of premature coronary artery disease (CAD) (38-58%) than the general population (1.8%) and higher than those having a high CAD risk but no FH (10%). Although most patients were receiving lipid-lowering therapies (LLTs), only 50% were receiving guideline-recommended high-intensity LLT. CONCLUSION: Using the hybrid model, we identified FH with a higher clinical and genetic detection rate than using standard diagnostic criteria individually. Statin and other LLT use were suboptimal and below guideline recommendations. Because FH underdiagnosis and undertreatment are due partially to the challenges of implementing existing diagnostic criteria in a primary care setting, this hybrid model potentially can improve FH diagnosis and subsequent early access to appropriate treatment.

Lower-Intensity Statins Contributing to Gaps in Care for Patients With Primary Severe Hypercholesterolemia.

Background Although severe hypercholesterolemia confers a 5-fold increased long-term risk for coronary artery disease, treatment guidelines may not be fully implemented, leading to underdiagnosis and suboptimal treatment. To further understand the clinical features and gaps in treatment approaches, we analyzed electronic medical record data from a midwestern US multidisciplinary healthcare system, between 2009 and 2020. Methods and Results We retrospectively assessed the prevalence, clinical presentation, and treatment characteristics of individuals currently treated with statin therapy having a low-density lipoprotein cholesterol (LDL-C) value that is either (1) an actual maximum electronic medical record-documented LDL-C ≥190 mg/dL (group 1, n=7542) or (2) an estimated pretreatment LDL-C ≥190 mg/dL (group 2, n=7710). Comorbidities and prescribed lipid-lowering therapies were assessed. Statistical analyses identified differences among individuals within and between groups. Of records analyzed (n=266 282), 7% met the definition for primary severe hypercholesterolemia. Group 1 had more comorbidities than group 2. More individuals in both groups were treated by primary care providers (49.8%-53.0%, 32.6%-36.4%) than by specialty providers (4.1%-5.5%, 2.1%-3.3%). High-intensity lipid-lowering therapy was prescribed less frequently for group 2 than for group 1, but moderate-intensity statins were prescribed more frequently for group 2 (65%) than for group 1 (52%). Conclusions Two percent of patients in our study population being treated with low- or moderate-intensity statins have an estimated LDL-C ≥190 mg/dL (indicating severe hypercholesterolemia), but receive less aggressive treatment than patients with a maximum measured LDL-C ≥190 mg/dL.

Prevalence and Characteristics of Patients With Primary Severe Hypercholesterolemia in a Multidisciplinary Healthcare System.

Severe hypercholesterolemia (SH) includes individuals with LDL-C ≥ 190 mg/dl, regardless of cause. These individuals have a fivefold increased long-term risk for coronary artery disease. Although systematic SH screening can trigger early treatment, current treatment guidelines may not be fully implemented or followed by patients. To further understand this treatment gap, we used electronic health record data to retrospectively assess SH prevalence, characteristics, and treatment in a midwest US healthcare system, between 2009 and 2020. Comorbidities, tobacco exposure, and prescribed lipid-lowering therapies were assessed. Statistical analyses were conducted to identify differences between individuals with primary SH (LDL-C ≥ 190 mg/dl, group 1) and those without primary SH (LDL-C < 190 mg/dl, group 2). Of 265,220 records analyzed, 7.4% met the definition for primary SH. These group 1 cases had more comorbidities than group 2 cases, including premature coronary artery disease (5.8% vs 2.7%). Results showed most individuals in group 1 were treated by primary care providers (43.2% to 45.7%), than by specialty providers (2.5% to 3.3%), and these primary care providers prescribed mainly moderate-intensity statins. Seventy-seven percent of group 1 individuals were treated with a statin, 27% were treated with a high-intensity statin, and 4% were treated with ezetimibe. Fewer young patients (< 40 years) were treated with statins (50% to 58.3%) than older patients (74.0% to 76.3%). Although use of general statins, high-intensity statins, and ezetimibe was higher in individuals with SH than those without SH, treatment remains below guideline recommendations, especially in younger individuals.

Translating U-500R Randomized Clinical Trial Evidence to the Practice Setting: A Diabetes Educator/Expert Prescriber Team Approach.

Purpose The purpose of this article is to provide recommendations to the diabetes educator/expert prescriber team for the use of human regular U-500 insulin (U-500R) in patients with severely insulin-resistant type 2 diabetes, including its initiation and titration, by utilizing dosing charts and teaching materials translated from a recent U-500R clinical trial. Conclusions Clinically relevant recommendations and teaching materials for the optimal use and management of U-500R in clinical practice are provided based on the efficacy and safety results of and lessons learned from the U-500R clinical trial by Hood et al, current standards of practice, and the authors' clinical expertise. This trial was the first robustly powered, randomized, titration-to-target trial to compare twice-daily and three-times-daily U-500R dosing regimens. Modifications were made to the initiation and titration dosing algorithms used in this trial to simplify dosing strategies for the clinical setting and align with current glycemic targets recommended by the American Diabetes Association. Leveraging the expertise, resources, and patient interactions of the diabetes educator who can provide diabetes self-management education and support in collaboration with the multidisciplinary diabetes team is strongly recommended to ensure patients treated with U-500R receive the timely and comprehensive care required to safely and effectively use this highly concentrated insulin.

Obesity and type 2 diabetes mellitus in South Dakota: focused insight into prevalence, physiology and treatment.

Type 2 diabetes mellitus is one of the significant comorbidities of obesity. This review addresses the prevalence of obesity and diabetes mellitus nationally and in South Dakota. It elaborates on some of the mechanisms of association of obesity with diabetes mellitus, including effects related to adipokines, lipotoxicity, vitamin D deficiency and apolipoprotein C1. This review addresses the prevention and treatment of diabetes mellitus in the obese population through life style changes, medications and/or surgery. Future directions in the management of diabetes are explored in the obese population.

Value of hemoglobin A1c in diagnosing diabetes mellitus within a chronic disease management system illustrated by the receiver operating characteristic curve.

OBJECTIVE: To develop a receiver operating characteristic (ROC) curve of glycosylated hemoglobin (HbA1c) for diagnosing diabetes mellitus within a chronic disease management system. METHODS: A case-control study including medical records from January 1, 1997, to December 31, 2005, was conducted at the Sioux Falls Veterans Affairs Medical Center. Medical records for the case group (patients with diabetes) were selected based on 1 of 3 criteria: International Classification of Diseases, Ninth Revision, Clinical Modification or Current Procedural Terminology codes specific for type 1 and type 2 diabetes; patients' use of medications (oral hypoglycemic agents, antidiabetes agents, or insulin); or results from random blood or plasma glucose tests (at least 2 measurements of blood glucose > or = 200 mg/dL). Records for the control group were selected based on patients having HbA1c measured, but not meeting the above diagnostic criteria for diabetes during the study period. Records for cases and controls were randomly frequency-matched, one-to-one. The control group was randomly divided into 5 sets of an equal number of records. Five sets of an equal number of cases were then randomly selected from the total number of cases. Each test data set included 1 case group and 1 control group, resulting in 5 independent data sets. RESULTS: In total, 5040 patient records met the case definition in the diabetes registry. Records of 15 patients who were prescribed metformin only, but did not meet any other case criteria, were reviewed and excluded after determining the patients were not diabetic. The control group consisted of 5 sets of 616 records each (totaling 3080 records), and the case group consisted of 5 sets of 616 records each (totaling 3080 records). Thus, each of the 5 independent data sets of 1 case group and 1 control group contained 1232 records. The case group was predominantly composed of white men (mean age, 69 years; mean body mass index, 31 kg/m2). Demographic data were similar for control patients. The ROC curve revealed that a HbA1c > or = 6.3% (mean + 1 SD) offered the most accurate cutoff value for diagnosing type 2 diabetes mellitus, with the following statistical values: C statistic, 0.78; sensitivity, 70%; specificity, 85%; and positive likelihood ratio, 4.6 (95% confidence interval, 4.2-5.0). CONCLUSION: A HbA1c value > or = 6.3% may be a useful benchmark for diagnosing diabetes mellitus within a chronic disease management system and may be a useful tool for monitoring high-risk populations.

Osteodystrophy in celiac disease: ultimate complications and possible treatment.

Hypovitaminosis D and its consequences are significant complications in the course of untreated celiac disease (CD). We report a case that illustrates the natural evolution of osteomalacia in an adult patient with untreated CD and his response to vitamin D supplementation. In patients with complicated CD and hypovitaminosis D, vitamin D-2 replacement in high enough doses is important to improving functional performance and for the treatment of osteomalacia.