Some patients with type 2 diabetes may benefit from intensive glycaemic and blood pressure control: A post-hoc machine learning analysis of ACCORD trial data.

AIM: The action to control cardiovascular risk in diabetes (ACCORD) trial showed a neutral average treatment effect of intensive blood glucose and blood pressure (BP) controls in preventing major adverse cardiovascular events (MACE) in individuals with type 2 diabetes. Yet, treatment effects across patient subgroups have not been well understood. We aimed to identify patient subgroups that might benefit from intensive glucose or BP controls for preventing MACE. MATERIALS AND METHODS: As a post-hoc analysis of the ACCORD trial, we included 10 251 individuals with type 2 diabetes. We applied causal forest and causal tree models to identify participant characteristics that modify the efficacy of intensive glucose or BP controls from 68 candidate variables (demographics, comorbidities, medications and biomarkers) at the baseline. The exposure was (a) intensive versus standard glucose control [glycated haemoglobin (HbA1c) <6.0% vs. 7.0%-7.9%], and (b) intensive versus standard BP control (systolic BP <120 vs. <140 mmHg). The primary outcome was MACE. RESULTS: Compared with standard glucose control, intensive one reduced MACE in those with baseline HbA1c <8.5% [relative risk (RR): 0.79, 95% confidence interval (CI): 0.67-0.93] and those with estimated glomerular filtration rate ≥106 ml/min/1.73 m2 (RR: 0.74, 95% CI: 0.55-0.99). Intensive BP control reduced MACE in those with normal high-density lipoprotein levels (women >55 mg/dl, men >45 mg/dl; RR: 0.51, 95% CI: 0.34-0.74). Risk reductions were not significant in other patient subgroups. CONCLUSIONS: Our findings suggest heterogeneous treatment effects of intensive glucose and BP control and could provide biomarkers for future clinical trials to identify more precise HbA1c and BP treatment goals for individualized medicine.

Associations Between Postdischarge Care and Cognitive Impairment-Related Hospital Readmissions for Ketoacidosis and Severe Hypoglycemia in Adults With Diabetes.

OBJECTIVE: Patients with severe hypoglycemia (SH) or diabetic ketoacidosis (DKA) experience high hospital readmission after being discharged. Cognitive impairment (CI) may further increase the risk, especially in those experiencing an interruption of medical care after discharge. This study examined the effect modification role of postdischarge care (PDC) on CI-associated readmission risk among U.S. adults with diabetes initially admitted for DKA or SH. RESEARCH DESIGN AND METHODS: We used the Nationwide Readmissions Database (NRD) (2016-2018) to identify individuals hospitalized with a diagnosis of DKA or SH. Multivariate Cox regression was used to compare the all-cause readmission risk at 30 days between those with and without CI identified during the initial hospitalization. We assessed the CI-associated readmission risk in the patients with and without PDC, an effect modifier with the CI status. RESULTS: We identified 23,775 SH patients (53.3% women, mean age 65.9 ± 15.3 years) and 140,490 DKA patients (45.8% women, mean age 40.3 ± 15.4 years), and 2,675 (11.2%) and 1,261 (0.9%), respectively, had a CI diagnosis during their index hospitalization. For SH and DKA patients discharged without PDC, CI was associated with a higher readmission risk of 23% (adjusted hazard ratio [aHR] 1.23, 95% confidence interval 1.08-1.40) and 35% (aHR 1.35, 95% confidence interval 1.08-1.70), respectively. However, when patients were discharged with PDC, we found PDC was an effect modifier to mitigate CI-associated readmission risk for both SH and DKA patients (P < 0.05 for all). CONCLUSIONS: Our results suggest that PDC can potentially mitigate the excessive readmission risk associated with CI, emphasizing the importance of postdischarge continuity of care for medically complex patients with comorbid diabetes and CI.

5-Year simulation of diabetes-related complications in people treated with tirzepatide or semaglutide versus insulin glargine.

AIM: This study compared the 5-year incidence rate of macrovascular and microvascular complications for tirzepatide, semaglutide and insulin glargine in individuals with type 2 diabetes, using the Building, Relating, Assessing, and Validating Outcomes (BRAVO) diabetes simulation model. RESEARCH DESIGN AND METHODS: This study was a 5-year SURPASS-2 trial extrapolation, with an insulin glargine arm added as an additional comparator. The 1-year treatment effects of tirzepatide (5, 10 or 15 mg), semaglutide (1 mg) and insulin glargine on glycated haemoglobin, systolic blood pressure, low-density lipoprotein and body weights were obtained from the SUSTAIN-4 and SURPASS-2 trials. We used the BRAVO model to predict 5-year complications for each study arm under two scenarios: the 1-year treatment effects persisted (optimistic) or diminished to none in 5 years (conservative). RESULTS: When compared with insulin glargine, we projected a 5-year risk reduction in cardiovascular adverse events [rate ratio (RR) 0.64, 95% confidence interval (CI) 0.61-0.67] and microvascular composite (RR 0.67, 95% CI 0.64-0.70) with 15 mg tirzepatide, and 5-year risk reduction in cardiovascular adverse events (RR 0.75, 95% CI 0.72-0.79) and microvascular composite (RR 0.79, 95% CI 0.76-0.82) with semaglutide (1 mg) under an optimistic scenario. Lower doses of tirzepatide also had similar, albeit smaller benefits. Treatment effects for tirzepatide and semaglutide were smaller but still significantly higher than insulin glargine under a conservative scenario. The 5-year risk reduction in diabetes-related complication events and mortality for the 15 mg tirzepatide compared with insulin glargine ranged from 49% to 10% under an optimistic scenario, which was reduced by 17%-33% when a conservative scenario was assumed. CONCLUSION: With the use of the BRAVO diabetes model, tirzepatide and semaglutide exhibited potential to reduce the risk of macrovascular and microvascular complications among individuals with type 2 diabetes, compared with insulin glargine in a 5-year window. Based on the current modelling assumptions, tirzepatide (15 mg) may potentially outperform semaglutide (1 mg). While the BRAVO model offered insights, the long-term cardiovascular benefit of tirzepatide should be further validated in a prospective clinical trial.

A Natural Language Processing Algorithm for Classifying Suicidal Behaviors in Alzheimer's Disease and Related Dementia Patients: Development and Validation Using Electronic Health Records Data.

This study aimed to develop a natural language processing algorithm (NLP) using machine learning (ML) and Deep Learning (DL) techniques to identify and classify documentation of suicidal behaviors in patients with Alzheimer's disease and related dementia (ADRD). We utilized MIMIC-III and MIMIC-IV datasets and identified ADRD patients and subsequently those with suicide ideation using relevant International Classification of Diseases (ICD) codes. We used cosine similarity with ScAN (Suicide Attempt and Ideation Events Dataset) to calculate semantic similarity scores of ScAN with extracted notes from MIMIC for the clinical notes. The notes were sorted based on these scores, and manual review and categorization into eight suicidal behavior categories were performed. The data were further analyzed using conventional ML and DL models, with manual annotation as a reference. The tested classifiers achieved classification results close to human performance with up to 98% precision and 98% recall of suicidal ideation in the ADRD patient population. Our NLP model effectively reproduced human annotation of suicidal ideation within the MIMIC dataset. These results establish a foundation for identifying and categorizing documentation related to suicidal ideation within ADRD population, contributing to the advancement of NLP techniques in healthcare for extracting and classifying clinical concepts, particularly focusing on suicidal ideation among patients with ADRD. Our study showcased the capability of a robust NLP algorithm to accurately identify and classify documentation of suicidal behaviors in ADRD patients.

Use of a Statistical Adaptive Treatment Strategy Approach for Emulating Randomized Controlled Trials Using Observational Data: The Example of Blood-Pressure Control Strategies for the Prevention of Cardiovascular Events Among Individuals With Hypertension at High Cardiovascular Risk.

Statistical approaches to adaptive treatment strategies (ATS) can be used to mimic the sequential decision-making inherently found in clinical practice. To illustrate the use of a statistical ATS approach, we emulated a target trial of different blood pressure (BP) control plans for the prevention of cardiovascular events among individuals with hypertension at high cardiovascular risk, inspired by the Systolic Blood Pressure Intervention Trial (SPRINT). We included 103,708 patients with hypertension and a "QRISK3" estimated 10-year risk of cardiovascular disease of ≥20% who initiated an antihypertensive drug between 1998 and 2018. Dynamic marginal structural models estimated the comparative effects of treating patients with intensive (target BP: 130/80 mm Hg), standard (140/90 mm Hg), and conservative (150/90 mm Hg) BP control strategies. The adjusted hazard ratios (HRs) for the intensive versus standard strategy were 0.96 (95% confidence interval (CI): 0.92, 1.00) for major adverse cardiovascular events and 0.93 (95% CI: 0.88, 0.97) for death from cardiovascular causes. For the conservative versus standard strategy, they were 1.06 (95% CI: 1.02, 1.10) and 1.08 (95% CI: 1.03, 1.13), respectively. These results are largely compatible with SPRINT. ATS can be used to emulate randomized controlled trials of complex treatment strategies in an observational setting and represents an alternative approach for situations where randomized controlled trials are not feasible.

Projected Impact of the Medicare Part D Senior Savings Model on Diabetes-Related Health and Economic Outcomes Among Insulin Users Covered by Medicare.

OBJECTIVE: The Medicare Part D Senior Savings Model (SSM) took effect on 1 January 2021. In this study we estimated the number of beneficiaries who would benefit from SSM and the long-term health and economic consequences of implementing this new policy. RESEARCH DESIGN AND METHODS: Data for Medicare beneficiaries with diabetes treated with insulin were extracted from the 2018 Medical Expenditure Panel Survey. A validated diabetes microsimulation model estimated health and economic impacts of the new policy for the 5-year initial implementation period and a 20-year extended policy horizon. Costs were estimated from a health system perspective. RESULTS: Of 4.2 million eligible Medicare beneficiaries, 1.6 million (38.3%) would benefit from the policy, and out-of-pocket (OOP) costs per year per beneficiary would decrease by 61% or $500 on average. Compared with non-White subgroups, the White population subgroups would have a higher proportion of SSM enrollees (29.6% vs. 43.7%) and a higher annual OOP cost reduction (reduction of $424 vs. $531). Among the SSM enrollees, one-third (605,125) were predicted to have improved insulin adherence due to lower cost sharing and improved health outcomes. In 5 years, the SSM would 1) avert 2,014 strokes, 935 heart attacks, 315 heart failure cases, and 344 end-stage renal disease cases; 2) gain 3,220 life-years and 3,381 quality-adjusted life-years (QALY); and 3) increase insulin cost and total medical cost by $3.5 billion and $2.8 billion. In 20 years, the number of avoided clinical outcomes, number of life-years and QALY gained, and the total and insulin cost would be larger. CONCLUSIONS: The Medicare SSM may reduce the OOP costs for approximately one-third of the Medicare beneficiaries treated with insulin, improving health outcomes via increased insulin adherence. However, the SSM will also increase overall Medicare spending for insulin and overall medical costs, which may impact future premiums and benefits. Our findings can inform policy makers about the potential impact of the new Medicare SSM.

Identifying asthma patients at high risk of exacerbation in a routine visit: A machine learning model.

BACKGROUND: Tools capable of predicting the risk of asthma exacerbations can facilitate asthma management in clinical practice. However, existing tools require additional data from patients beyond electronic medical records. OBJECTIVE: To predict asthma exacerbation in an upcoming year using electronically accessible data conditional on past adherence to asthma medications. METHODS: This retrospective cohort study included patients with ≥1 hospitalization or ≥2 medical claims for asthma within 2 consecutive years between 2002 and 2015 in Quebec administrative databases. Cohort entry (CE) was defined as the date of the first asthma-related ambulatory visit on or after meeting the operational definition of asthma. Adherence to each controller medication and use of each rescue medication was measured in the year prior to CE. Elastic-net regularized logistic regression was applied. RESULTS: Among 98,823 patients, the mean age was 55.9 years and 36.2% were men. The area under the curve for prediction was 0.708. In the model, the use of long-acting anticholinergic or long-acting ß2-agonists in the year prior to CE increased the odds of exacerbation by 24% and 21%, respectively. Among patients who received rescue medication, low and high adherence to controller medications increased the odds by 2%-5% compared with patients with medium adherence. Patients with a predicted risk of ≥0.20 were more likely to develop future exacerbation. CONCLUSION: This risk prediction indicated that asthma-related medication use increased the risk of asthma exacerbation. A potential U-shaped relationship between adherence to controller medications and the risk of exacerbation was identified among users of rescue medications.

Prescription Patterns for the Use of Antihypertensive Drugs for Primary Prevention Among Patients With Hypertension in the United Kingdom.

BACKGROUND: Several antihypertensive drugs are available for the primary prevention of cardiovascular disease (CVD). However, existing evidence on prescription patterns was primarily generated among patients at high CVD risk with short-term follow-up, and failed to capture impacts of time and patient characteristics. Our objective was therefore to describe longitudinal prescription patterns for antihypertensive drugs for the primary prevention of CVD among patients with arterial hypertension in the United Kingdom. METHODS: This population-based cohort study used data from the Clinical Practice Research Datalink, included 660,545 patients with hypertension who initiated an antihypertensive drug between 1998 and 2018. Antihypertensive treatments were measured by drug class and described overall and in subgroups, focusing on first-line therapy (first antihypertensive drug(s) recorded after a diagnosis of hypertension) and second-line therapy (antihypertensive drug(s) prescribed as part of a treatment change following first-line therapy). RESULTS: Angiotensin-converting enzyme (ACE) inhibitors (29.0%), thiazide diuretics (22.1%), and calcium-channel blockers (CCBs) (21.0%) were the most prescribed first-line therapies. ACE inhibitors have been increasingly prescribed as first-line therapy since 2001. Men were more likely to be prescribed ACE inhibitors than women (43.5% vs. 32.1%; difference: 11.4%; 95% confidence interval [CI], 11.0%-11.8%), and Black patients were more likely to be prescribed CCBs than White patients (63.6% vs. 37.0%; difference: 26.6%; 95% CI, 24.8%-28.4%). CONCLUSIONS: Antihypertensive prescription patterns for the primary prevention of CVD among patients with hypertension are consistent with treatment guidelines that were in place during the study period, providing reassurance regarding the use of evidence-based prescribing.

Predictors of Asthma Control and Exacerbations: A Real-World Study.

BACKGROUND: Achieving optimal asthma control and minimizing the risk of exacerbation are the main goals of asthma treatment. OBJECTIVE: This study aimed to assess the predictors of poor asthma control and asthma exacerbations within a population of moderate to severe asthmatic patients treated in a tertiary-care center. METHODS: We conducted a cohort study assessing 738 patients enrolled in the Quebec registry in respiratory health (RESP) with a diagnosis of asthma confirmed by a respirologist and treated in a tertiary care center from April 2010 to March 2016. Sociodemographic and clinical data, including Asthma Control Questionnaire score, were collected at enrollment in the registry (ie, cohort entry) and patients were followed for a 2-year period thereafter. The information regarding exacerbations that occurred during follow-up was collected in administrative databases (Régie d l'assurance médicale du Québec [RAMQ], Maintenance et exploitation des données pour l'étude de la clientèle hospitalière [MED-ECHO], and medication data registry [reMed]). RESULTS: We assessed 738 subjects (64% women). Psychological distress (odds ratio [OR] 1.91; 95% confidence interval [95% CI] 1.21-3.02), smoking (OR 3.72; 95% CI 1.72-8.05]), and poor lung function, forced expiratory volume in 1 second less than 50% (OR 4.1; 95% CI 1.48-11.34]) appeared as significant factors associated with uncontrolled asthma. Occurrence of previous asthma exacerbations (hazard ratio [HR] 6.25; 95% CI 4.01-9.75]), poor asthma control (HR 1.60; 95% CI 1.07-2.38]), forced expiratory volume in 1 second between 50% and 80% (HR 2.25; 95% CI 1.58-3.34]), and older age (HR 2.26; 95% CI 1.37-3.74]) were associated with asthma exacerbations. Adherence to asthma treatment was very low in patients with (44.4% ± 34.4%) and without asthma exacerbations (37.5% ± 33.0%). CONCLUSIONS: Psychological distress and current smoking are modifiable factors that need to be addressed in tailored behavioral interventions to improve asthma control. Asthma exacerbations are mostly associated with the intrinsic severity of the disease.

Real-world evidence in pain research: a review of data sources.

Outcomes research studies use clinical and administrative data generated in the course of patient care or from patient surveys to examine the effectiveness of treatments. Health care providers need to understand the limitations and strengths of the real-world data sources used in outcomes studies to meaningfully use the results. This paper describes five types of databases commonly used in the United States for outcomes research studies, discusses their strengths and limitations, and provides examples of each within the context of pain treatment. The databases specifically discussed are generated from (1) electronic medical records, which are created from patient-provider interactions; (2) administrative claims, which are generated from providers' and patients' transactions with payers; (3) integrated health systems, which are generated by systems that provide both clinical care and insurance benefits and typically represent a combination of electronic medical record and claims data; (4) national surveys, which provide patient-reported responses about their health and behaviors; and (5) patient registries, which are developed to track patients with a given disease or exposure over time for specified purposes, such as population management, safety monitoring, or research.

Cost implications of formulary decisions on oral anticoagulants in nonvalvular atrial fibrillation.

BACKGROUND: Nonvalvular atrial fibrillation (AF) is a major public health issue. The major complication of AF is an increased risk of stroke. Warfarin, long used for stroke prophylaxis in AF patients, has a narrow therapeutic window and numerous food and drug interactions necessitating regular laboratory monitoring. New oral anticoagulants (e.g., dabigatran, rivaroxaban, apixaban) may meet the need for predictable anticoagulation with fixed, unmonitored dosing. OBJECTIVE: To review costs of monitoring, bleeding, and stroke in AF patients to analyze costs of anticoagulants for stroke prophylaxis in AF patients. METHODS: A literature search on the costs of treating AF used PubMed/MEDLINE databases (to April 2012) focusing on studies in the United States. Key words or MeSH terms were used, such as "observational studies," "oral anticoagulants," "warfarin," "cost of bleeding," "cost of stroke," and "cost of INR monitoring." RESULTS: The literature focused mainly on short-term, in-hospital expenditures and less on long-term care costs. Annual overall costs per patient for treating AF in the United States ranged from $18,454 to $38,270. Annual incremental costs of treating AF ranged from $8,705 to $16,311. Annual inpatient costs ranged from $7,841 to $22,582 per patient. Annual costs of anticoagulation monitoring ranged from $291 to $943 per patient. Intracranial hemorrhage and major gastrointestinal bleeding with oral anticoagulants were uncommon but expensive: 1-year costs ranged from $7,584 to $193,804. Annual direct costs of stroke in AF patients ranged from $23,143 to $37,620 (incremental cost of $7,824 to $8,232 vs. AF patients without stroke). CONCLUSIONS: AF-associated direct costs are high and can be broken into costs of warfarin monitoring and direct costs of managing consequences of anticoagulant therapy-stroke and bleeding.

Application of electronic medical record data for health outcomes research: a review of recent literature.

Electronic medical records (EMRs) have become a common source of data for outcomes research. This review discusses trends in EMR data use for outcomes research as well as strengths and limitations, and likely future developments to help optimize value and use of EMR data for outcomes research. EMR-based studies reporting treatment outcomes published between 2007 and 2012 were predominantly from the USA and Europe. There has been a substantial increase in the number of EMR-based outcomes studies published from 2007-2008 (n = 28) to 2010-2011 (n = 55). Many studies evaluated biometric and laboratory test outcomes in common chronic conditions. However, researchers are expanding the scope of evaluated diseases and outcomes using advanced techniques, such as natural language processing and linking EMRs to other patient-level data to overcome issues with missing data or data that cannot be accessed using standard queries. These advances will help to expand the scope and sophistication of outcomes research in the coming years.

A cost-utility analysis of pregabalin versus duloxetine for the treatment of painful diabetic neuropathy.

The objective of the current study was to determine the cost-utility of pregabalin versus duloxetine for treating painful diabetic neuropathy (PDN) using a decision tree analysis. Literature searches identified clinical trials and real-world studies reporting the efficacy, tolerability, safety, adherence, opioid usage, health care utilization, and costs of pregabalin and duloxetine. The proportions of patients reported in the included studies were used to determine probabilities in the decision tree model. The base-case model included the Food and Drug Administration (FDA)-approved doses of pregabalin (300 mg/day) and duloxetine (60 mg/day), whereas "real-world" sensitivity analyses explored the effects over a range of doses (pregabalin 75-600 mg/day, duloxetine 20-120 mg/day). A 6-month time horizon and a US third-party payer perspective were chosen for the study. Outcomes from the model were expressed as cost per quality-adjusted life-year (QALY). In the base-case model, duloxetine cost less and was more effective than pregabalin (incremental cost -$187, incremental effectiveness 0.011 QALYs). Results from two real-world sensitivity analyses indicated that duloxetine cost $16,300 and $20,667 more per additional QALY than pregabalin. Using a decision tree model that incorporated both clinical trial and real-world data, duloxetine was a more cost-effective option than pregabalin in the treatment of PDN from the perspective of third-party payers.