Identifying treatment heterogeneity in atrial fibrillation using a novel causal machine learning method.

BACKGROUND: Lifelong oral anticoagulation is recommended in patients with atrial fibrillation (AF) to prevent stroke. Over the last decade, multiple new oral anticoagulants (OACs) have expanded the number of treatment options for these patients. While population-level effectiveness of OACs has been compared, it is unclear if there is variability in benefit and risk across patient subgroups. METHODS: We analyzed claims and medical data for 34,569 patients who initiated a nonvitamin K antagonist oral anticoagulant (non-vitamin K antagonist oral anticoagulant (NOAC); apixaban, dabigatran, and rivaroxaban) or warfarin for nonvalvular AF between 08/01/2010 and 11/29/2017 from the OptumLabs Data Warehouse. A machine learning (ML) method was applied to match different OAC groups on several baseline variables including, age, sex, race, renal function, and CHA2DS2 -VASC score. A causal ML method was then used to discover patient subgroups characterizing the head-to-head treatment effects of the OACs on a primary composite outcome of ischemic stroke, intracranial hemorrhage, and all-cause mortality. RESULTS: The mean age, number of females and white race in the entire cohort of 34,569 patients were 71.2 (SD, 10.7) years, 14,916 (43.1%), and 25,051 (72.5%) respectively. During a mean follow-up of 8.3 (SD, 9.0) months, 2,110 (6.1%) of patients experienced the composite outcome, of whom 1,675 (4.8%) died. The causal ML method identified 5 subgroups with variables favoring apixaban over dabigatran; 2 subgroups favoring apixaban over rivaroxaban; 1 subgroup favoring dabigatran over rivaroxaban; and 1 subgroup favoring rivaroxaban over dabigatran in terms of risk reduction of the primary endpoint. No subgroup favored warfarin and most dabigatran vs warfarin users favored neither drug. The variables that most influenced favoring one subgroup over another included Age, history of ischemic stroke, thromboembolism, estimated glomerular filtration rate, Race, and myocardial infarction. CONCLUSIONS: Among patients with AF treated with a NOAC or warfarin, a causal ML method identified patient subgroups with differences in outcomes associated with OAC use. The findings suggest that the effects of OACs are heterogeneous across subgroups of AF patients, which could help personalize the choice of OAC. Future prospective studies are needed to better understand the clinical impact of the subgroups with respect to OAC selection.

Changes in Kidney Function After Diagnosis of Advanced Heart Failure.

BACKGROUND: Kidney function and its association with outcomes in patients with advanced heart failure (HF) has not been well-defined. METHODS AND RESULTS: We conducted a retrospective cohort study comprising all adult residents of Olmsted County, Minnesota, with HF who developed advanced HF from 2007 to 2017. Patients were grouped by estimated glomerular filtration rate (eGFR) at advanced HF diagnosis using the 2021 Chronic Kidney Disease Epidemiology Collaboration equation. A linear mixed effects model was fitted to assess the relationship between development of advanced HF and longitudinal eGFR trajectory. A total of 936 patients with advanced HF (mean age 77 years, 55% male, 93.7% White) were included. Twenty-two percent of these patients had an eGFR of <30 at advanced HF diagnosis, 22% had an eGFR of 30-44, 23% had an eGFR of 45-59, and 32% had an eGFR of ≥60 mL/min/1.73 m2. The eGFR decreased faster after advanced HF (7.6% vs 10.9% annual decline before vs after advanced HF), with greater decreases after advanced HF in those with diabetes and preserved ejection fraction. An eGFR of <30 mL/min/1.73 m2 was associated with worse survival after advanced HF compared with an eGFR of ≥60 mL/min/1.73 m2 (adjusted hazard ratio 1.30, 95% confidence interval 1.07-1.57). CONCLUSIONS: eGFR deteriorated faster after patients developed advanced HF. An eGFR of <30 mL/min/1.73 m2 at advanced HF diagnosis was associated with higher mortality.

A prediction model for asthma exacerbations after stopping asthma biologics.

BACKGROUND: Little is known regarding the prediction of the risks of asthma exacerbation after stopping asthma biologics. OBJECTIVE: To develop and validate a predictive model for the risk of asthma exacerbations after stopping asthma biologics using machine learning models. METHODS: We identified 3057 people with asthma who stopped asthma biologics in the OptumLabs Database Warehouse and considered a wide range of demographic and clinical risk factors to predict subsequent outcomes. The primary outcome used to assess success after stopping was having no exacerbations in the 6 months after stopping the biologic. Elastic-net logistic regression (GLMnet), random forest, and gradient boosting machine models were used with 10-fold cross-validation within a development (80%) cohort and validation cohort (20%). RESULTS: The mean age of the total cohort was 47.1 (SD, 17.1) years, 1859 (60.8%) were women, 2261 (74.0%) were White, and 1475 (48.3%) were in the Southern region of the United States. The elastic-net logistic regression model yielded an area under the curve (AUC) of 0.75 (95% confidence interval [CI], 0.71-0.78) in the development and an AUC of 0.72 in the validation cohort. The random forest model yielded an AUC of 0.75 (95% CI, 0.68-0.79) in the development cohort and an AUC of 0.72 in the validation cohort. The gradient boosting machine model yielded an AUC of 0.76 (95% CI, 0.72-0.80) in the development cohort and an AUC of 0.74 in the validation cohort. CONCLUSION: Outcomes after stopping asthma biologics can be predicted with moderate accuracy using machine learning methods.

Using ensemble of ensemble machine learning methods to predict outcomes of cardiac resynchronization.

INTRODUCTION: The efficacy of cardiac resynchronization therapy (CRT) has been widely studied in the medical literature; however, about 30% of candidates fail to respond to this treatment strategy. Smart computational approaches based on clinical data can help expose hidden patterns useful for identifying CRT responders. METHODS: We retrospectively analyzed the electronic health records of 1664 patients who underwent CRT procedures from January 1, 2002 to December 31, 2017. An ensemble of ensemble (EoE) machine learning (ML) system composed of a supervised and an unsupervised ML layers was developed to generate a prediction model for CRT response. RESULTS: We compared the performance of EoE against traditional ML methods and the state-of-the-art convolutional neural network (CNN) model trained on raw electrocardiographic (ECG) waveforms. We observed that the models exhibited improvement in performance as more features were incrementally used for training. Using the most comprehensive set of predictors, the performance of the EoE model in terms of the area under the receiver operating characteristic curve and F1-score were 0.76 and 0.73, respectively. Direct application of the CNN model on the raw ECG waveforms did not generate promising results. CONCLUSION: The proposed CRT risk calculator effectively discriminates which heart failure (HF) patient is likely to respond to CRT significantly better than using clinical guidelines and traditional ML methods, thus suggesting that the tool can enhanced care management of HF patients by helping to identify high-risk patients.

Risk of Gastrointestinal Bleeding Increases With Combinations of Antithrombotic Agents and Patient Age.

BACKGROUND & AIMS: The safety of different antithrombotic strategies for patients with 1 or more indication for antithrombotic drugs has not been determined. We investigated the risk and time frame for gastrointestinal bleeding (GIB) in patients prescribed different antithrombotic regimens. We proposed that risk would increase over time and with combination regimens, especially among elderly patients. METHODS: We performed a retrospective analysis of nationwide claims data from privately insured and Medicare Advantage enrollees who received anticoagulant and/or antiplatelet agents from October 1, 2010, through May 31, 2017. Patients were stratified by their prescriptions (anticoagulant alone, antiplatelet alone, or a combination) and by their primary diagnosis (atrial fibrillation, ischemic heart disease, or venous thromboembolism). The 1-year GIB risk was estimated using parametric time-to-event survival models and expressed as annualized risk and number needed to harm (NNH). RESULTS: Our final analysis included 311,211 patients (mean ages, 67 years for monotherapy and 69.8 years for combination antithrombotic therapy). There was no significant difference in the proportion of patients with bleeding after anticoagulant or antiplatelet monotherapy (∼3.5%/year). Combination antithrombotic therapy increased GIB risk compared with anticoagulant (NNH, 29) or antiplatelet (NNH, 31) monotherapy, regardless of the patients' diagnosis or time point analyzed. Advancing age was associated with increasing 1-year probability of GIB. Patients prescribed combination therapy were at the greatest risk for GIB, especially after the age of 75 years (GIB occurred in 10%-17.5% of patients/y). CONCLUSIONS: In an analysis of nationwide insurance and Medicare claims data, we found GIB to occur in a higher proportion of patients prescribed combinations of anticoagulant and antiplatelet agents compared with monotherapy. Among all drug exposure categories and cardiovascular conditions, the risk of GIB increased with age, especially among patients older than 75 years.

Association of Use of an Intravascular Microaxial Left Ventricular Assist Device vs Intra-aortic Balloon Pump With In-Hospital Mortality and Major Bleeding Among Patients With Acute Myocardial Infarction Complicated by Cardiogenic Shock.

Importance: Acute myocardial infarction (AMI) complicated by cardiogenic shock is associated with substantial morbidity and mortality. Although intravascular microaxial left ventricular assist devices (LVADs) provide greater hemodynamic support as compared with intra-aortic balloon pumps (IABPs), little is known about clinical outcomes associated with intravascular microaxial LVAD use in clinical practice. Objective: To examine outcomes among patients undergoing percutaneous coronary intervention (PCI) for AMI complicated by cardiogenic shock treated with mechanical circulatory support (MCS) devices. Design, Setting, and Participants: A propensity-matched registry-based retrospective cohort study of patients with AMI complicated by cardiogenic shock undergoing PCI between October 1, 2015, and December 31, 2017, who were included in data from hospitals participating in the CathPCI and the Chest Pain-MI registries, both part of the American College of Cardiology's National Cardiovascular Data Registry. Patients receiving an intravascular microaxial LVAD were matched with those receiving IABP on demographics, clinical history, presentation, infarct location, coronary anatomy, and clinical laboratory data, with final follow-up through December 31, 2017. Exposures: Hemodynamic support, categorized as intravascular microaxial LVAD use only, IABP only, other (such as use of a percutaneous extracorporeal ventricular assist system, extracorporeal membrane oxygenation, or a combination of MCS device use), or medical therapy only. Main Outcomes and Measures: The primary outcomes were in-hospital mortality and in-hospital major bleeding. Results: Among 28 304 patients undergoing PCI for AMI complicated by cardiogenic shock, the mean (SD) age was 65.0 (12.6) years, 67.0% were men, 81.3% had an ST-elevation myocardial infarction, and 43.3% had cardiac arrest. Over the study period among patients with AMI, an intravascular microaxial LVAD was used in 6.2% of patients, and IABP was used in 29.9%. Among 1680 propensity-matched pairs, there was a significantly higher risk of in-hospital death associated with use of an intravascular microaxial LVAD (45.0%) vs with an IABP (34.1% [absolute risk difference, 10.9 percentage points {95% CI, 7.6-14.2}; P < .001) and also higher risk of in-hospital major bleeding (intravascular microaxial LVAD [31.3%] vs IABP [16.0%]; absolute risk difference, 15.4 percentage points [95% CI, 12.5-18.2]; P < .001). These associations were consistent regardless of whether patients received a device before or after initiation of PCI. Conclusions and Relevance: Among patients undergoing PCI for AMI complicated by cardiogenic shock from 2015 to 2017, use of an intravascular microaxial LVAD compared with IABP was associated with higher adjusted risk of in-hospital death and major bleeding complications, although study interpretation is limited by the observational design. Further research may be needed to understand optimal device choice for these patients.

Mixed effect machine learning: A framework for predicting longitudinal change in hemoglobin A1c.

Accurate and reliable prediction of clinical progression over time has the potential to improve the outcomes of chronic disease. The classical approach to analyzing longitudinal data is to use (generalized) linear mixed-effect models (GLMM). However, linear parametric models are predicated on assumptions, which are often difficult to verify. In contrast, data-driven machine learning methods can be applied to derive insight from the raw data without a priori assumptions. However, the underlying theory of most machine learning algorithms assume that the data is independent and identically distributed, making them inefficient for longitudinal supervised learning. In this study, we formulate an analytic framework, which integrates the random-effects structure of GLMM into non-linear machine learning models capable of exploiting temporal heterogeneous effects, sparse and varying-length patient characteristics inherent in longitudinal data. We applied the derived mixed-effect machine learning (MEml) framework to predict longitudinal change in glycemic control measured by hemoglobin A1c (HbA1c) among well controlled adults with type 2 diabetes. Results show that MEml is competitive with traditional GLMM, but substantially outperformed standard machine learning models that do not account for random-effects. Specifically, the accuracy of MEml in predicting glycemic change at the 1st, 2nd, 3rd, and 4th clinical visits in advanced was 1.04, 1.08, 1.11, and 1.14 times that of the gradient boosted model respectively, with similar results for the other methods. To further demonstrate the general applicability of MEml, a series of experiments were performed using real publicly available and synthetic data sets for accuracy and robustness. These experiments reinforced the superiority of MEml over the other methods. Overall, results from this study highlight the importance of modeling random-effects in machine learning approaches based on longitudinal data. Our MEml method is highly resistant to correlated data, readily accounts for random-effects, and predicts change of a longitudinal clinical outcome in real-world clinical settings with high accuracy.

Trajectories of Glycemic Change in a National Cohort of Adults With Previously Controlled Type 2 Diabetes.

BACKGROUND: Individualized diabetes management would benefit from prospectively identifying well-controlled patients at risk of losing glycemic control. OBJECTIVES: To identify patterns of hemoglobin A1c (HbA1c) change among patients with stable controlled diabetes. RESEARCH DESIGN: Cohort study using OptumLabs Data Warehouse, 2001-2013. We develop and apply a machine learning framework that uses a Bayesian estimation of the mixture of generalized linear mixed effect models to discover glycemic trajectories, and a random forest feature contribution method to identify patient characteristics predictive of their future glycemic trajectories. SUBJECTS: The study cohort consisted of 27,005 US adults with type 2 diabetes, age 18 years and older, and stable index HbA1c <7.0%. MEASURES: HbA1c values during 24 months of observation. RESULTS: We compared models with k=1, 2, 3, 4, 5 trajectories and baseline variables including patient age, sex, race/ethnicity, comorbidities, medications, and HbA1c. The k=3 model had the best fit, reflecting 3 distinct trajectories of glycemic change: (T1) rapidly deteriorating HbA1c among 302 (1.1%) youngest (mean, 55.2 y) patients with lowest mean baseline HbA1c, 6.05%; (T2) gradually deteriorating HbA1c among 902 (3.3%) patients (mean, 56.5 y) with highest mean baseline HbA1c, 6.53%; and (T3) stable glycemic control among 25,800 (95.5%) oldest (mean, 58.5 y) patients with mean baseline HbA1c 6.21%. After 24 months, HbA1c rose to 8.75% in T1 and 8.40% in T2, but remained stable at 6.56% in T3. CONCLUSIONS: Patients with controlled type 2 diabetes follow 3 distinct trajectories of glycemic control. This novel application of advanced analytic methods can facilitate individualized and population diabetes care by proactively identifying high risk patients.

Emergency department risk model: timely identification of patients for outpatient care coordination.

OBJECTIVE: Major depressive disorder (MDD) is linked to a 61% increased risk of emergency department (ED) visits and frequent ED usage. Collaborative care management (CoCM) models target MDD treatment in primary care, but how best to prioritize patients for CoCM to prevent frequent ED utilization remains unclear. This study aimed to develop and validate a risk identification model to proactively detect patients with MDD in CoCM at high risk of frequent (≥ 3) ED visits. STUDY DESIGN: This retrospective cohort study utilized electronic health records from Mayo Clinic's primary care system to develop and validate a machine learning-based risk identification model. The model predicts the likelihood of frequent ED visits among patients with MDD within a 12-month period. METHODS: Data were collected from Mayo Clinic's primary care system between May 1, 2006, and December 19, 2018. Risk identification models were developed and validated using machine learning classifiers to estimate frequent ED visit risks over 12 months. The Shapley Additive Explanations model identified variables driving frequent ED visits. RESULTS: The patient population had a mean (SD) age of 39.78 (16.66) years, with 30.3% being male and 6.1% experiencing frequent ED visits. The best-performing algorithm (elastic-net logistic regression) achieved an area under the curve of 0.79 (95% CI, 0.74-0.84), a sensitivity of 0.71 (95% CI, 0.57-0.82), and a specificity of 0.76 (95% CI, 0.64-0.85) in the development data set. In the validation data set, the best-performing algorithm (random forest) achieved an area under the curve of 0.79, a sensitivity of 0.83, and a specificity of 0.61. Significant variables included male gender, prior frequent ED visits, high Patient Health Questionnaire-9 score, low education level, unemployment, and use of multiple medications. CONCLUSIONS: The risk identification model has potential for clinical application in triaging primary care patients with MDD in CoCM, aiming to reduce future ED utilization.

Longitudinal trajectories of glycemic control among U.S. Adults with newly diagnosed diabetes.

AIMS: To identify longitudinal trajectories of glycemic control among adults with newly diagnosed diabetes, overall and by diabetes type. METHODS: We analyzed claims data from OptumLabs® Data Warehouse for 119,952 adults newly diagnosed diabetes between 2005 and 2018. We applied a novel Mixed Effects Machine Learning model to identify longitudinal trajectories of hemoglobin A1c (HbA1c) over 3 years of follow-up and used multinomial regression to characterize factors associated with each trajectory. RESULTS: The study population was comprised of 119,952 adults with newly diagnosed diabetes, including 696 (0.58%) with type 1 diabetes. Among patients with type 1 diabetes, 52.6% were diagnosed at very high HbA1c, partially improved, but never achieved control; 32.5% were diagnosed at low HbA1c and deteriorated over time; and 14.9% had stable low HbA1c. Among patients with type 2 diabetes, 67.7% had stable low HbA1c, 14.4% were diagnosed at very high HbA1c, partially improved, but never achieved control; 10.0% were diagnosed at moderately high HbA1c and deteriorated over time; and 4.9% were diagnosed at moderately high HbA1c and improved over time. CONCLUSIONS: Claims data identified distinct longitudinal trajectories of HbA1c after diabetes diagnosis, which can be used to anticipate challenges and individualize care plans to improve glycemic control.

Clinical Phenotyping with an Outcomes-driven Mixture of Experts for Patient Matching and Risk Estimation.

Observational medical data present unique opportunities for analysis of medical outcomes and treatment decision making. However, because these datasets do not contain the strict pairing of randomized control trials, matching techniques are to draw comparisons among patients. A key limitation to such techniques is verification that the variables used to model treatment decision making are also relevant in identifying the risk of major adverse events. This article explores a deep mixture of experts approach to jointly learn how to match patients and model the risk of major adverse events in patients. Although trained with information regarding treatment and outcomes, after training, the proposed model is decomposable into a network that clusters patients into phenotypes from information available before treatment. This model is validated on a dataset of patients with acute myocardial infarction complicated by cardiogenic shock. The mixture of experts approach can predict the outcome of mortality with an area under the receiver operating characteristic curve of 0.85 ± 0.01 while jointly discovering five potential phenotypes of interest. The technique and interpretation allow for identifying clinically relevant phenotypes that may be used both for outcomes modeling as well as potentially evaluating individualized treatment effects.

Identifying Patients With Advanced Heart Failure Using Administrative Data.

Objective: To develop algorithms to identify patients with advanced heart failure (HF) that can be applied to administrative data. Patients and Methods: In a population-based cohort of all residents of Olmsted County, Minnesota, with greater than or equal to 1 HF billing code 2007-2017 (n=8657), we identified all patients with advanced HF (n=847) by applying the gold standard European Society of Cardiology advanced HF criteria via manual medical review by an HF cardiologist. The advanced HF index date was the date the patient first met all European Society of Cardiology criteria. We subsequently developed candidate algorithms to identify advanced HF using administrative data (billing codes and prescriptions relevant to HF or comorbidities that affect HF outcomes), applied them to the HF cohort, and assessed their ability to identify patients with advanced HF on or after their advanced HF index date. Results: A single hospitalization for HF or ventricular arrhythmias identified all patients with advanced HF (sensitivity, 100%); however, the positive predictive value (PPV) was low (36.4%). More stringent definitions, including additional hospitalizations and/or other signs of advanced HF (hyponatremia, acute kidney injury, hypotension, or high-dose diuretic use), decreased the sensitivity but improved the specificity and PPV. For example, 2 hospitalizations plus 1 sign of advanced HF had a sensitivity of 72.7%, specificity of 89.8%, and PPV of 60.5%. Negative predictive values were high for all algorithms evaluated. Conclusion: Algorithms using administrative data can identify patients with advanced HF with reasonable performance.

Introduction to Machine Learning in Obstetrics and Gynecology.

In the digital age of the 21st century, we have witnessed an explosion in data matched by remarkable progress in the field of computer science and engineering, with the development of powerful and portable artificial intelligence-powered technologies. At the same time, global connectivity powered by mobile technology has led to an increasing number of connected users and connected devices. In just the past 5 years, the convergence of these technologies in obstetrics and gynecology has resulted in the development of innovative artificial intelligence-powered digital health devices that allow easy and accurate patient risk stratification for an array of conditions spanning early pregnancy, labor and delivery, and care of the newborn. Yet, breakthroughs in artificial intelligence and other new and emerging technologies currently have a slow adoption rate in medicine, despite the availability of large data sets that include individual electronic health records spanning years of care, genomics, and the microbiome. As a result, patient interactions with health care remain burdened by antiquated processes that are inefficient and inconvenient. A few health care institutions have recognized these gaps and, with an influx of venture capital investments, are now making in-roads in medical practice with digital products driven by artificial intelligence algorithms. In this article, we trace the history, applications, and ethical challenges of the artificial intelligence that will be at the forefront of digitally transforming obstetrics and gynecology and medical practice in general.

Impact of labor characteristics on maternal and neonatal outcomes of labor: A machine-learning model.

INTRODUCTION: Since Friedman's seminal publication on laboring women, numerous publications have sought to define normal labor progress. However, there is paucity of data on contemporary labor cervicometry incorporating both maternal and neonatal outcomes. The objective of this study is to establish intrapartum prediction models of unfavorable labor outcomes using machine-learning algorithms. MATERIALS AND METHODS: Consortium on Safe Labor is a large database consisting of pregnancy and labor characteristics from 12 medical centers in the United States. Outcomes, including maternal and neonatal outcomes, were retrospectively collected. We defined primary outcome as the composite of following unfavorable outcomes: cesarean delivery in active labor, postpartum hemorrhage, intra-amniotic infection, shoulder dystocia, neonatal morbidity, and mortality. Clinical and obstetric parameters at admission and during labor progression were used to build machine-learning risk-prediction models based on the gradient boosting algorithm. RESULTS: Of 228,438 delivery episodes, 66,586 were eligible for this study. Mean maternal age was 26.95 ± 6.48 years, mean parity was 0.92 ± 1.23, and mean gestational age was 39.35 ± 1.13 weeks. Unfavorable labor outcome was reported in 14,439 (21.68%) deliveries. Starting at a cervical dilation of 4 cm, the area under receiver operating characteristics curve (AUC) of prediction models increased from 0.75 (95% confidence interval, 0.75-0.75) to 0.89 (95% confidence interval, 0.89-0.90) at a dilation of 10 cm. Baseline labor risk score was above 35% in patients with unfavorable outcomes compared to women with favorable outcomes, whose score was below 25%. CONCLUSION: Labor risk score is a machine-learning-based score that provides individualized and dynamic alternatives to conventional labor charts. It predicts composite of adverse birth, maternal, and neonatal outcomes as labor progresses. Therefore, it can be deployed in clinical practice to monitor labor progress in real time and support clinical decisions.

Screening for idiopathic pulmonary fibrosis using comorbidity signatures in electronic health records.

Idiopathic pulmonary fibrosis (IPF) is a lethal fibrosing interstitial lung disease with a mean survival time of less than 5 years. Nonspecific presentation, a lack of effective early screening tools, unclear pathobiology of early-stage IPF and the need for invasive and expensive procedures for diagnostic confirmation hinder early diagnosis. In this study, we introduce a new screening tool for IPF in primary care settings that requires no new laboratory tests and does not require recognition of early symptoms. Using subtle comorbidity signatures identified from the history of medical encounters of individuals, we developed an algorithm, called the zero-burden comorbidity risk score for IPF (ZCoR-IPF), to predict the future risk of an IPF diagnosis. ZCoR-IPF was trained on a national insurance claims database and validated on three independent databases, comprising a total of 2,983,215 participants, with 54,247 positive cases. The algorithm achieved positive likelihood ratios greater than 30 at a specificity of 0.99 across different cohorts, for both sexes, and for participants with different risk states and history of confounding diseases. The area under the receiver-operating characteristic curve for ZCoR-IPF in predicting IPF exceeded 0.88 and was approximately 0.84 at 1 and 4 years before a conventional diagnosis, respectively. Thus, if adopted, ZCoR-IPF can potentially enable earlier diagnosis of IPF and improve outcomes of disease-modifying therapies and other interventions.

Estimation of manual wheelchair-based activities in the free-living environment using a neural network model with inertial body-worn sensors.

Shoulder pain is common in manual wheelchair (MWC) users. Overuse is thought to be a major cause, but little is known about exposure to activities of daily living (ADLs). The study goal was to develop a method to estimate three conditions in the field: (1) non-propulsion activity, (2) MWC propulsion, and (3) static time using an inertial measurement unit (IMU). Upper arm IMU data were collected as ten MWC users performed lab-based MWC-related ADLs. A neural network model was developed to classify data as non-propulsion activity, propulsion, or static, and validated for the lab-based data collection by video comparison. Six of the participants' free-living IMU data were collected and the lab-based model was applied to estimate daily non-propulsion activity, propulsion, and static time. The neural network model yielded lab-based validity measures ≥0.87 for differentiating non-propulsion activity, propulsion, and static time. A quasi-validation of one participant's field-based data yielded validity measures ≥0.66 for identifying propulsion. Participants' estimated mean daily non-propulsion activity, propulsion, and static time ranged from 158 to 409, 13 to 25, and 367 to 609 min, respectively. The preliminary results suggest the model may be able to accurately identify MWC users' field-based activities. The inclusion of field-based IMU data in the model could further improve field-based classification.

Comparative Effectiveness of Machine Learning Approaches for Predicting Gastrointestinal Bleeds in Patients Receiving Antithrombotic Treatment.

Importance: Anticipating the risk of gastrointestinal bleeding (GIB) when initiating antithrombotic treatment (oral antiplatelets or anticoagulants) is limited by existing risk prediction models. Machine learning algorithms may result in superior predictive models to aid in clinical decision-making. Objective: To compare the performance of 3 machine learning approaches with the commonly used HAS-BLED (hypertension, abnormal kidney and liver function, stroke, bleeding, labile international normalized ratio, older age, and drug or alcohol use) risk score in predicting antithrombotic-related GIB. Design, Setting, and Participants: This retrospective cross-sectional study used data from the OptumLabs Data Warehouse, which contains medical and pharmacy claims on privately insured patients and Medicare Advantage enrollees in the US. The study cohort included patients 18 years or older with a history of atrial fibrillation, ischemic heart disease, or venous thromboembolism who were prescribed oral anticoagulant and/or thienopyridine antiplatelet agents between January 1, 2016, and December 31, 2019. Exposures: A cohort of patients prescribed oral anticoagulant and thienopyridine antiplatelet agents was divided into development and validation cohorts based on date of index prescription. The development cohort was used to train 3 machine learning models to predict GIB at 6 and 12 months: regularized Cox proportional hazards regression (RegCox), random survival forests (RSF), and extreme gradient boosting (XGBoost). Main Outcomes and Measures: The performance of the models for predicting GIB in the validation cohort, evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, and prediction density plots. Relative importance scores were used to identify the variables that were most influential in the top-performing machine learning model. Results: In the entire study cohort of 306 463 patients, 166 177 (54.2%) were male, 193 648 (63.2%) were White, the mean (SD) age was 69.0 (12.6) years, and 12 322 (4.0%) had experienced a GIB. In the validation data set, the HAS-BLED model had an AUC of 0.60 for predicting GIB at 6 months and 0.59 at 12 months. The RegCox model performed the best in the validation set, with an AUC of 0.67 at 6 months and 0.66 at 12 months. XGBoost was similar, with AUCs of 0.67 at 6 months and 0.66 at 12 months, whereas for RSF, AUCs were 0.62 at 6 months and 0.60 at 12 months. The variables with the highest importance scores in the RegCox model were prior GI bleed (importance score, 0.72); atrial fibrillation, ischemic heart disease, and venous thromboembolism combined (importance score, 0.38); and use of gastroprotective agents (importance score, 0.32). Conclusions and Relevance: In this cross-sectional study, the machine learning models examined showed similar performance in identifying patients at high risk for GIB after being prescribed antithrombotic agents. Two models (RegCox and XGBoost) performed modestly better than the HAS-BLED score. A prospective evaluation of the RegCox model compared with HAS-BLED may provide a better understanding of the clinical impact of improved performance.

Use of Mechanical Circulatory Support Devices Among Patients With Acute Myocardial Infarction Complicated by Cardiogenic Shock.

Importance: Mechanical circulatory support (MCS) devices, including intravascular microaxial left ventricular assist devices (LVADs) and intra-aortic balloon pumps (IABPs), are used in patients who undergo percutaneous coronary intervention (PCI) for acute myocardial infarction (AMI) complicated by cardiogenic shock despite limited evidence of their clinical benefit. Objective: To examine trends in the use of MCS devices among patients who underwent PCI for AMI with cardiogenic shock, hospital-level use variation, and factors associated with use. Design, Setting, and Participants: This cross-sectional study used the CathPCI and Chest Pain-MI Registries of the American College of Cardiology National Cardiovascular Data Registry. Patients who underwent PCI for AMI complicated by cardiogenic shock between October 1, 2015, and December 31, 2017, were identified from both registries. Data were analyzed from October 2018 to August 2020. Exposures: Therapies to provide hemodynamic support were categorized as intravascular microaxial LVAD, IABP, TandemHeart, extracorporeal membrane oxygenation, LVAD, other devices, combined IABP and intravascular microaxial LVAD, combined IABP and other device (defined as TandemHeart, extracorporeal membrane oxygenation, LVAD, or another MCS device), or medical therapy only. Main Outcomes and Measures: Use of MCS devices overall and specific MCS devices, including intravascular microaxial LVAD, at both patient and hospital levels and variables associated with use. Results: Among the 28 304 patients included in the study, the mean (SD) age was 65.4 (12.6) years and 18 968 were men (67.0%). The overall MCS device use was constant from the fourth quarter of 2015 to the fourth quarter of 2017, although use of intravascular microaxial LVADs significantly increased (from 4.1% to 9.8%; P < .001), whereas use of IABPs significantly decreased (from 34.8% to 30.0%; P < .001). A significant hospital-level variation in MCS device use was found. The median (interquartile range [IQR]) proportion of patients who received MCS devices was 42% (30%-54%), and the median proportion of patients who received intravascular microaxial LVADs was 1% (0%-10%). In multivariable analyses, cardiac arrest at first medical contact or during hospitalization (odds ratio [OR], 1.82; 95% CI, 1.58-2.09) and severe left main and/or proximal left anterior descending coronary artery stenosis (OR, 1.36; 95% CI, 1.20-1.54) were patient characteristics that were associated with higher odds of receiving intravascular microaxial LVADs only compared with IABPs only. Conclusions and Relevance: This study found that, among patients who underwent PCI for AMI complicated by cardiogenic shock, overall use of MCS devices was constant, and a 2.5-fold increase in intravascular microaxial LVAD use was found along with a corresponding decrease in IABP use and a significant hospital-level variation in MCS device use. These trends were observed despite limited clinical trial evidence of improved outcomes associated with device use.

Longitudinal cohorts for harnessing the electronic health record for disease prediction in a US population.

PURPOSE: The depth and breadth of clinical data within electronic health record (EHR) systems paired with innovative machine learning methods can be leveraged to identify novel risk factors for complex diseases. However, analysing the EHR is challenging due to complexity and quality of the data. Therefore, we developed large electronic population-based cohorts with comprehensive harmonised and processed EHR data. PARTICIPANTS: All individuals 30 years of age or older who resided in Olmsted County, Minnesota on 1 January 2006 were identified for the discovery cohort. Algorithms to define a variety of patient characteristics were developed and validated, thus building a comprehensive risk profile for each patient. Patients are followed for incident diseases and ageing-related outcomes. Using the same methods, an independent validation cohort was assembled by identifying all individuals 30 years of age or older who resided in the largely rural 26-county area of southern Minnesota and western Wisconsin on 1 January 2013. FINDINGS TO DATE: For the discovery cohort, 76 255 individuals (median age 49; 53% women) were identified from which a total of 9 644 221 laboratory results; 9 513 840 diagnosis codes; 10 924 291 procedure codes; 1 277 231 outpatient drug prescriptions; 966 136 heart rate measurements and 1 159 836 blood pressure (BP) measurements were retrieved during the baseline time period. The most prevalent conditions in this cohort were hyperlipidaemia, hypertension and arthritis. For the validation cohort, 333 460 individuals (median age 54; 52% women) were identified and to date, a total of 19 926 750 diagnosis codes, 10 527 444 heart rate measurements and 7 356 344 BP measurements were retrieved during baseline. FUTURE PLANS: Using advanced machine learning approaches, these electronic cohorts will be used to identify novel sex-specific risk factors for complex diseases. These approaches will allow us to address several challenges with the use of EHR.

Quality over quantity: skeletal loading intensity plays a key role in understanding the relationship between physical activity and bone density in postmenopausal women.

OBJECTIVE: Increasing physical activity (PA) is regularly cited as a modifiable target to improve health outcomes and quality of life in the aging population, especially postmenopausal women who exhibit low bone mineral density (BMD) and high fracture risk. In this cross-sectional study, we aimed to quantify real-world PA and its association with BMD in postmenopausal women. METHODS: Seventy postmenopausal women, aged 46 to 79 years, received a dual-energy X-ray absorptiometry scan measuring total hip BMD and wore bilateral triaxial accelerometers on the ankles for 7 days to measure PA in their free-living environment. Custom step detection and peak vertical ground reaction force estimation algorithms, sensitive to both quantity and intensity of PA, were used to calculate a daily bone density index (BDI) for each participant. Multiple regression was used to quantify the relationship between total hip BMD, age, step counts, and mean BDI over the span of 7 days of data collection. RESULTS: All participants completed the full 7 days of PA monitoring, totaling more than 7 million detected steps. Participants averaged 14,485 ±â€Š4,334 steps daily with mean peak vertical ground reaction force stepping loads of 675 ±â€Š121 N during daily living. Across the population, total hip BMD was found to be significantly correlated with objective estimates of mean BDI (r = 0.44), as well as participant age (r = 0.285). CONCLUSION: Despite having higher-than-expected PA, the low stepping loads observed in this cohort, along with half of the participants having low BMD measures, underscores the need for PA intensity to be considered in the management of postmenopausal bone health.