Network enrichment significance testing in brain-phenotype association studies.

Functional networks often guide our interpretation of spatial maps of brain-phenotype associations. However, methods for assessing enrichment of associations within networks of interest have varied in terms of both scientific rigor and underlying assumptions. While some approaches have relied on subjective interpretations, others have made unrealistic assumptions about spatial properties of imaging data, leading to inflated false positive rates. We seek to address this gap in existing methodology by borrowing insight from a method widely used in genetics research for testing enrichment of associations between a set of genes and a phenotype of interest. We propose network enrichment significance testing (NEST), a flexible framework for testing the specificity of brain-phenotype associations to functional networks or other sub-regions of the brain. We apply NEST to study enrichment of associations with structural and functional brain imaging data from a large-scale neurodevelopmental cohort study.

University of Pennsylvania Telehealth Research Center of Excellence.

Drawing from insights from communication science and behavioral economics, the University of Pennsylvania Telehealth Research Center of Excellence (Penn TRACE) is designing and testing telehealth strategies with the potential to transform access to care, care quality, outcomes, health equity, and health-care efficiency across the cancer care continuum, with an emphasis on understanding mechanisms of action. Penn TRACE uses lung cancer care as an exemplar model for telehealth across the care continuum, from screening to treatment to survivorship. We bring together a diverse and interdisciplinary team of international experts and incorporate rapid-cycle approaches and mixed methods evaluation in all center projects. Our initiatives include a pragmatic sequential multiple assignment randomized trial to compare the effectiveness of telehealth strategies to increase shared decision-making for lung cancer screening and 2 pilot projects to test the effectiveness of telehealth to improve cancer care, identify multilevel mechanisms of action, and lay the foundation for future pragmatic trials. Penn TRACE aims to produce new fundamental knowledge and advance telehealth science in cancer care at Penn and nationally.

Behavioral Interventions to Improve Breast Cancer Screening Outreach: Two Randomized Clinical Trials.

Importance: Despite public health efforts, breast cancer screening rates remain below national goals. Objective: To evaluate whether bulk ordering, text messaging, and clinician endorsement increase breast cancer screening rates. Design, Setting, and Participants: Two concurrent, pragmatic, randomized clinical trials, each with a 2-by-2 factorial design, were conducted between October 25, 2021, and April 25, 2022, in 2 primary care regions of an academic health system. The trials included women aged 40 to 74 years with at least 1 primary care visit in the past 2 years who were eligible for breast cancer screening. Interventions: Patients in trial A were randomized in a 1:1 ratio to receive a signed bulk order for mammogram or no order; in a factorial design, patients were concurrently randomized in a 1:1 ratio to receive or not receive text message reminders. Patients in trial B were randomized in a 1:1 ratio to receive a message signed by their primary care clinician (clinician endorsement) or from the organization (standard messaging); in a factorial design, patients were concurrently randomized in a 1:1 ratio to receive or not receive text message reminders. Main Outcomes and Measures: The primary outcome was the proportion of patients who completed a screening mammogram within 3 months. Results: Among 24 632 patients included, the mean (SD) age was 60.4 (7.5) years. In trial A, at 3 months, 15.4% (95% CI, 14.6%-16.1%) of patients in the bulk order arm and 12.7% (95% CI, 12.1%-13.4%) in the no order arm completed a mammogram, showing a significant increase (absolute difference, 2.7%; 95% CI, 1.6%-3.6%; P < .001). In the text messaging comparison arms, 15.1% (95% CI, 14.3%-15.8%) of patients receiving a text message completed a mammogram compared with 13.0% (95% CI, 12.4%-13.7%) of those in the no text messaging arm, a significant increase (absolute difference of 2.1%; 95% CI, 1.0%-3.0%; P < .001). In trial B, at 3 months, 12.5% (95% CI, 11.3%-13.7%) of patients in the clinician endorsement arm completed a mammogram compared with 11.4% (95% CI, 10.3%-12.5%) of those in the standard messaging arm, which was not significant (absolute difference, 1.1%; 95% CI, -0.5% to 2.7%; P = .18). In the text messaging comparison arms, 13.2% (95% CI, 12.0%-14.4%) of patients receiving a text message completed a mammogram compared with 10.7% (95% CI, 9.7%-11.8%) of those in the no text messaging arm, a significant increase (absolute difference, 2.5%; 95% CI, 0.8%-4.0%; P = .003). Conclusions and Relevance: These findings show that text messaging women after initial breast cancer screening outreach via either electronic portal or mailings, as well as bulk ordering with or without text messaging, can increase mammogram completion rates. Trial Registration: ClinicalTrials.gov Identifier: NCT05089903.

Association of Electronic Self-Scheduling and Screening Mammogram Completion.

INTRODUCTION: The purpose of this study was to evaluate if an electronic health record (EHR) self-scheduling function was associated with changes in mammogram completion for primary care patients who were eligible for a screening mammogram using U.S. Preventive Service Task Force recommendations. METHODS: This was a retrospective cohort study (September 1, 2014-August 31, 2019, analyses completed in 2022) using a difference-in-differences design to examine mammogram completion before versus after the implementation of self-scheduling. The difference-in-differences estimate was the interaction between time (pre-versus post-implementation) and group (active EHR patient portal versus inactive EHR patient portal). The primary outcome was mammogram completion among all eligible patients, with completion defined as receiving a mammogram within 6 months post-visit. The secondary outcome was mammogram completion among patients who received a clinician order during their visit. RESULTS: The primary analysis included 35,257 patient visits. The overall mammogram completion rate in the pre-period was 22.2% and 49.7% in the post-period. EHR self-scheduling was significantly associated with increased mammogram completion among those with an active EHR portal, relative to patients with an inactive portal (adjusted difference 13.2 percentage points [95% CI 10.6-15.8]). For patients who received a clinician mammogram order at their eligible visit, self-scheduling was significantly associated with increased mammogram completion among patients with an active EHR portal account (adjusted difference 14.7 percentage points, [95% CI 10.9-18.5]). CONCLUSIONS: EHR-based self-scheduling was associated with a significant increase in mammogram completion among primary care patients. Self-scheduling can be a low-cost, scalable function for increasing preventive cancer screenings.

Algorithmic Fairness of Machine Learning Models for Alzheimer Disease Progression.

Importance: Predictive models using machine learning techniques have potential to improve early detection and management of Alzheimer disease (AD). However, these models potentially have biases and may perpetuate or exacerbate existing disparities. Objective: To characterize the algorithmic fairness of longitudinal prediction models for AD progression. Design, Setting, and Participants: This prognostic study investigated the algorithmic fairness of logistic regression, support vector machines, and recurrent neural networks for predicting progression to mild cognitive impairment (MCI) and AD using data from participants in the Alzheimer Disease Neuroimaging Initiative evaluated at 57 sites in the US and Canada. Participants aged 54 to 91 years who contributed data on at least 2 visits between September 2005 and May 2017 were included. Data were analyzed in October 2022. Exposures: Fairness was quantified across sex, ethnicity, and race groups. Neuropsychological test scores, anatomical features from T1 magnetic resonance imaging, measures extracted from positron emission tomography, and cerebrospinal fluid biomarkers were included as predictors. Main Outcomes and Measures: Outcome measures quantified fairness of prediction models (logistic regression [LR], support vector machine [SVM], and recurrent neural network [RNN] models), including equal opportunity, equalized odds, and demographic parity. Specifically, if the model exhibited equal sensitivity for all groups, it aligned with the principle of equal opportunity, indicating fairness in predictive performance. Results: A total of 1730 participants in the cohort (mean [SD] age, 73.81 [6.92] years; 776 females [44.9%]; 69 Hispanic [4.0%] and 1661 non-Hispanic [96.0%]; 29 Asian [1.7%], 77 Black [4.5%], 1599 White [92.4%], and 25 other race [1.4%]) were included. Sensitivity for predicting progression to MCI and AD was lower for Hispanic participants compared with non-Hispanic participants; the difference (SD) in true positive rate ranged from 20.9% (5.5%) for the RNN model to 27.8% (9.8%) for the SVM model in MCI and 24.1% (5.4%) for the RNN model to 48.2% (17.3%) for the LR model in AD. Sensitivity was similarly lower for Black and Asian participants compared with non-Hispanic White participants; for example, the difference (SD) in AD true positive rate was 14.5% (51.6%) in the LR model, 12.3% (35.1%) in the SVM model, and 28.4% (16.8%) in the RNN model for Black vs White participants, and the difference (SD) in MCI true positive rate was 25.6% (13.1%) in the LR model, 24.3% (13.1%) in the SVM model, and 6.8% (18.7%) in the RNN model for Asian vs White participants. Models generally satisfied metrics of fairness with respect to sex, with no significant differences by group, except for cognitively normal (CN)-MCI and MCI-AD transitions (eg, an absolute increase [SD] in the true positive rate of CN-MCI transitions of 10.3% [27.8%] for the LR model). Conclusions and Relevance: In this study, models were accurate in aggregate but failed to satisfy fairness metrics. These findings suggest that fairness should be considered in the development and use of machine learning models for AD progression.

Network Enrichment Significance Testing in Brain-Phenotype Association Studies.

Functional networks often guide our interpretation of spatial maps of brain-phenotype associations. However, methods for assessing enrichment of associations within networks of interest have varied in terms of both scientific rigor and underlying assumptions. While some approaches have relied on subjective interpretations, others have made unrealistic assumptions about the spatial structure of imaging data, leading to inflated false positive rates. We seek to address this gap in existing methodology by borrowing insight from a method widely used in genomics research for testing enrichment of associations between a set of genes and a phenotype of interest. We propose Network Enrichment Significance Testing (NEST), a flexible framework for testing the specificity of brain-phenotype associations to functional networks or other sub-regions of the brain. We apply NEST to study phenotype associations with structural and functional brain imaging data from a large-scale neurodevelopmental cohort study.

Developmental Correlates of Accelerated Molar Eruption in Early Childhood.

Background: Adversity has been linked to accelerated maturation. Molar eruption is a simple and scalable way to identify early maturation, but its developmental correlates remain unexplored. Thus, we examined whether accelerated maturation as indexed by molar eruption is associated with children's mental health or cognitive skills. Methods: Molar eruption was evaluated from T2-weighted magnetic resonance imaging in 117 children (63 female; ages 4-7 years). Parents reported on child mental health with the Child Behavior Checklist. Children completed standardized assessments of fluid reasoning, working memory, processing speed, crystallized knowledge, and math performance. Relationships between molar eruption and developmental outcomes were examined using linear models, with age, gender, and stress risk as covariates. Results: Earlier molar eruption was positively associated with children's externalizing symptoms (false discovery rate-corrected p [pFDR] = .027) but not internalizing symptoms, and the relationship with externalizing symptoms did not hold when controlling for stress risk. Earlier molar eruption was negatively associated with fluid reasoning (pFDR < .001), working memory (pFDR = .033), and crystallized knowledge (pFDR = .001). The association between molar eruption and both reasoning and crystallized knowledge held when controlling for stress risk. Molar eruption also partially mediated associations between stress risk and both reasoning (proportion mediated = 0.273, p = .004) and crystallized knowledge (proportion mediated = 0.126, p = .016). Conclusions: Accelerated maturation, as reflected in early molar eruption, may have consequences for cognitive development, perhaps because it constrains brain plasticity. Knowing the pace of a child's maturation may provide insight into the impact of a child's stress history on their cognitive development.

Public Views on Medicaid Work Requirements and Mandatory Premiums in Kentucky.

Importance: Federal and state policymakers continue to pursue work requirements and premiums as conditions of Medicaid participation. Opinion polling should distinguish between general policy preferences and specific views on quotas, penalties, and other elements. Objective: To identify views of adults in Kentucky regarding the design of Medicaid work requirements and premiums. Design, Setting, and Participant: A cross-sectional survey was conducted via telephone and the internet from June 27 through July 11, 2019, of 1203 Kentucky residents 9 months before the state intended to implement Medicaid work requirements and mandatory premiums. Statistical analysis was performed from October 2019 to August 2023. Main Outcomes and Measures: Agreement, disagreement, or neutral views on policy components were the main outcomes. Recruitment for the survey used statewide random-digit dialing and an internet panel to recruit residents aged 18 years or older. Findings were weighted to reflect state demographics. Of 39 110 landlines called, 209 reached an eligible person (of whom 150 participated), 8654 were of unknown eligibility, and 30 247 were ineligible. Of 55 305 cell phone lines called, 617 reached an eligible person (of whom 451 participated), 29 951 were of unknown eligibility, and 24 737 were ineligible. Internet recruitment (602 participants) used a panel of adult Kentucky residents maintained by an external data collector. Results: Percentages were weighted to resemble the adult population of Kentucky residents. Of the participants in the study, 52% (95% CI, 48%-55%) were women, 80% (95% CI, 77%-82%) were younger than 65 years, 41% (95% CI, 38%-45%) were enrolled in Medicaid, 36% (95% CI, 32%-39%) were Republican voters, 32% (95% CI, 29%-36%) were Democratic voters, 14% (95% CI, 11%-16%) were members of racial and ethnic minority groups (including but not limited to American Indian or Alaska Native, Asian, Black, Hispanic or Latinx, and Native Hawaiian or Pacific Islander), and 48% (95% CI, 44%-52%) were employed. Most participants supported work requirements generally (69% [95% CI, 66%-72%]) but did not support terminating benefits due to noncompliance (43% [95% CI, 39%-46%]) or requiring quotas of 20 or more hours per week (34% [95% CI, 31%-38%]). Support for monthly premiums (34% [95% CI, 31%-38%]) and exclusion penalties for premium nonpayment (22% [95% CI, 19%-25%]) was limited. Medicaid enrollees were significantly less supportive of these policies than nonenrollees. For instance, regarding work requirements, agreement was lower (64% [95% CI, 59%-69%] vs 72% [95% CI, 68%-77%]) and disagreement higher (26% [95% CI, 21%-31%] vs 20% [95% CI, 16%-24%]) among current Medicaid enrollees compared with nonenrollees (P = .04). Among Medicaid enrollees, some beliefs about work requirements varied significantly by employment status but not by political affiliation. Among nonenrollees, beliefs about work requirements, premiums, and Medicaid varied significantly by political affiliation but not by employment. Conclusions and Relevance: This study suggests that even when public constituencies express general support for Medicaid work requirements or premiums, they may oppose central design features, such as quotas and termination of benefits. Program participants may also hold significantly different beliefs than nonparticipants, which should be understood before policies are changed.

ReMiND: Recovery of Missing Neuroimaging using Diffusion Models with Application to Alzheimer's Disease.

Objective: Missing data is a significant challenge in medical research. In longitudinal studies of Alzheimer's disease (AD) where structural magnetic resonance imaging (MRI) is collected from individuals at multiple time points, participants may miss a study visit or drop out. Additionally, technical issues such as participant motion in the scanner may result in unusable imaging data at designated visits. Such missing data may hinder the development of high-quality imaging-based biomarkers. Furthermore, when imaging data are unavailable in clinical practice, patients may not benefit from effective application of biomarkers for disease diagnosis and monitoring. Methods: To address the problem of missing MRI data in studies of AD, we introduced a novel 3D diffusion model specifically designed for imputing missing structural MRI (Recovery of Missing Neuroimaging using Diffusion models (ReMiND)). The model generates a whole-brain image conditional on a single structural MRI observed at a past visit or conditional on one past and one future observed structural MRI relative to the missing observation. Results: Experimental results show that our method can generate high-quality individual 3D structural MRI with high similarity to ground truth, observed images. Additionally, images generated using ReMiND exhibit relatively lower error rates and more accurately estimated rates of atrophy over time in important anatomical brain regions compared with two alternative imputation approaches: forward filling and image generation using variational autoencoders. Conclusion: Our 3D diffusion model can impute missing structural MRI data at a single designated visit and outperforms alternative methods for imputing whole-brain images that are missing from longitudinal trajectories.

Estimation and evaluation of individualized treatment rules following multiple imputation.

An individualized treatment rule (ITR) is a function that inputs patient-level information and outputs a recommended treatment. An important focus of precision medicine is to develop optimal ITRs that maximize a population-level distributional summary. However, guidance for estimating and evaluating optimal ITRs in the presence of missing data is limited. Our work is motivated by the Social Incentives to Encourage Physical Activity and Understand Predictors (STEP UP) study. Participants were randomized to a control or one of three interventions designed to increase physical activity and were given wearable devices to record daily steps as a measure of physical activity. Many participants were missing at least one daily step count during the study period. In the primary analysis of the STEP UP trial, multiple imputation (MI) was used to address missingness in daily step counts. Despite ubiquitous use of MI in practice, it has been given relatively little attention in the context of personalized medicine. We fill this gap by describing two frameworks for estimation and evaluation of an optimal ITR following MI and assessing their performance using simulated data. One framework relies on splitting the data into independent training and testing sets for estimation and evaluation, respectively. The other framework estimates an optimal ITR using the full data and constructs an m $$ m $$ -out-of- n $$ n $$ bootstrap confidence interval to evaluate its performance. Finally, we provide an illustrative analysis to estimate and evaluate an optimal ITR from the STEP UP data with a focus on practical considerations such as choosing the number of imputations.

Evaluating equity in performance of an electronic health record-based 6-month mortality risk model to trigger palliative care consultation: a retrospective model validation analysis.

OBJECTIVE: Evaluate predictive performance of an electronic health record (EHR)-based, inpatient 6-month mortality risk model developed to trigger palliative care consultation among patient groups stratified by age, race, ethnicity, insurance and socioeconomic status (SES), which may vary due to social forces (eg, racism) that shape health, healthcare and health data. DESIGN: Retrospective evaluation of prediction model. SETTING: Three urban hospitals within a single health system. PARTICIPANTS: All patients ≥18 years admitted between 1 January and 31 December 2017, excluding observation, obstetric, rehabilitation and hospice (n=58 464 encounters, 41 327 patients). MAIN OUTCOME MEASURES: General performance metrics (c-statistic, integrated calibration index (ICI), Brier Score) and additional measures relevant to health equity (accuracy, false positive rate (FPR), false negative rate (FNR)). RESULTS: For black versus non-Hispanic white patients, the model's accuracy was higher (0.051, 95% CI 0.044 to 0.059), FPR lower (-0.060, 95% CI -0.067 to -0.052) and FNR higher (0.049, 95% CI 0.023 to 0.078). A similar pattern was observed among patients who were Hispanic, younger, with Medicaid/missing insurance, or living in low SES zip codes. No consistent differences emerged in c-statistic, ICI or Brier Score. Younger age had the second-largest effect size in the mortality prediction model, and there were large standardised group differences in age (eg, 0.32 for non-Hispanic white versus black patients), suggesting age may contribute to systematic differences in the predicted probabilities between groups. CONCLUSIONS: An EHR-based mortality risk model was less likely to identify some marginalised patients as potentially benefiting from palliative care, with younger age pinpointed as a possible mechanism. Evaluating predictive performance is a critical preliminary step in addressing algorithmic inequities in healthcare, which must also include evaluating clinical impact, and governance and regulatory structures for oversight, monitoring and accountability.

Multivariate Residualization in Medical Imaging Analysis.

Nuisance variables in medical imaging research are common, complicating association and prediction studies based on image data. Medical image data are typically high dimensional, often consisting of many highly correlated features. As a result, computationally efficient and robust methods to address nuisance variables are difficult to implement. By-region univariate residualization is commonly used to remove the influence of nuisance variables, as are various extensions. However, these methods neglect multivariate properties and may fail to fully remove influence related to the joint distribution of these regions. Some methods, such as functional regression and others, do consider multivariate properties when controlling for nuisance variables. However, the utility of these methods is limited for data with many image regions due to computational and model complexity. We develop a multivariate residualization method to estimate the association between the image and nuisance variable using a machine learning algorithm and then compute the orthogonal projection of each subject's image data onto this space. We illustrate this method's performance in a set of simulation studies and apply it to data from the Alzheimer's Disease Neuroimaging Initiative (ADNI).

Performance of Multiple Imputation Using Modern Machine Learning Methods in Electronic Health Records Data.

BACKGROUND: Missing data are common in studies using electronic health records (EHRs)-derived data. Missingness in EHR data is related to healthcare utilization patterns, resulting in complex and potentially missing not at random missingness mechanisms. Prior research has suggested that machine learning-based multiple imputation methods may outperform traditional methods and may perform well even in settings of missing not at random missingness. METHODS: We used plasmode simulations based on a nationwide EHR-derived de-identified database for patients with metastatic urothelial carcinoma to compare the performance of multiple imputation using chained equations, random forests, and denoising autoencoders in terms of bias and precision of hazard ratio estimates under varying proportions of observations with missing values and missingness mechanisms (missing completely at random, missing at random, and missing not at random). RESULTS: Multiple imputation by chained equations and random forest methods had low bias and similar standard errors for parameter estimates under missingness completely at random. Under missingness at random, denoising autoencoders had higher bias than multiple imputation by chained equations and random forests. Contrary to results of prior studies of denoising autoencoders, all methods exhibited substantial bias under missingness not at random, with bias increasing in direct proportion to the amount of missing data. CONCLUSIONS: We found no advantage of denoising autoencoders for multiple imputation in the setting of an epidemiologic study conducted using EHR data. Results suggested that denoising autoencoders may overfit the data leading to poor confounder control. Use of more flexible imputation approaches does not mitigate bias induced by missingness not at random and can produce estimates with spurious precision.

Penalized decomposition using residuals (PeDecURe) for feature extraction in the presence of nuisance variables.

Neuroimaging data are an increasingly important part of etiological studies of neurological and psychiatric disorders. However, mitigating the influence of nuisance variables, including confounders, remains a challenge in image analysis. In studies of Alzheimer's disease, for example, an imbalance in disease rates by age and sex may make it difficult to distinguish between structural patterns in the brain (as measured by neuroimaging scans) attributable to disease progression and those characteristic of typical human aging or sex differences. Concerningly, when not properly accounted for, nuisance variables pose threats to the generalizability and interpretability of findings from these studies. Motivated by this critical issue, in this work, we examine the impact of nuisance variables on feature extraction methods and propose Penalized Decomposition Using Residuals (PeDecURe), a new method for obtaining nuisance variable-adjusted features. PeDecURe estimates primary directions of variation which maximize covariance between partially residualized imaging features and a variable of interest (e.g., Alzheimer's diagnosis) while simultaneously mitigating the influence of nuisance variation through a penalty on the covariance between partially residualized imaging features and those variables. Using features derived using PeDecURe's first direction of variation, we train a highly accurate and generalizable predictive model, as evidenced by its robustness in testing samples with different underlying nuisance variable distributions. We compare PeDecURe to commonly used decomposition methods (principal component analysis (PCA) and partial least squares) as well as a confounder-adjusted variation of PCA. We find that features derived from PeDecURe offer greater accuracy and generalizability and lower correlations with nuisance variables compared with the other methods. While PeDecURe is primarily motivated by challenges that arise in the analysis of neuroimaging data, it is broadly applicable to data sets with highly correlated features, where novel methods to handle nuisance variables are warranted.

Performance of Physician Groups and Hospitals Participating in Bundled Payments Among Medicare Beneficiaries.

Importance: Hospital participation in bundled payment initiatives has been associated with financial savings and stable quality of care. However, how physician group practices (PGPs) perform in bundled payments compared with hospitals remains unknown. Objectives: To evaluate the association of PGP participation in the Bundled Payments for Care Improvement (BPCI) initiative with episode outcomes and to compare these with outcomes for participating hospitals. Design, Settings, and Participants: This cohort study with a difference-in-differences analysis used 2011 to 2018 Medicare claims data to compare the association of BPCI participation with episode outcomes for PGPs vs hospitals providing medical and surgical care to Medicare beneficiaries. Data analyses were conducted from January 1, 2020, to May 31, 2022. Exposures: Hospitalization for any of the 10 highest-volume episodes (5 medical and 5 surgical) included in the BPCI initiative for Medicare patients of participating PGPs and hospitals. Main Outcomes and Measures: The primary outcome was 90-day total episode spending. Secondary outcomes were 90-day readmissions and mortality. Results: The total sample comprised data from 1 288 781 Medicare beneficiaries, of whom 696 710 (mean [SD] age, 76.2 [10.8] years; 432 429 [59.7%] women; 619 655 [85.5%] White individuals) received care through 379 BPCI-participating hospitals and 1441 propensity-matched non-BPCI-participating hospitals, and 592 071 (mean [SD] age, 75.4 [10.9] years; 527 574 [86.6%] women; 360 835 [59.3%] White individuals) received care from 6405 physicians in BPCI-participating PGPs and 24 758 propensity-matched physicians in non-BPCI-participating PGPs. For PGPs, BPCI participation was associated with greater reductions in episode spending for surgical (difference, -$1368; 95% CI, -$1648 to -$1088) but not for medical episodes (difference, -$101; 95% CI, -$410 to $206). Hospital participation in BPCI was associated with greater reductions in episode spending for both surgical (-$1010; 95% CI, -$1345 to -$675) and medical (-$763; 95% CI, -$1139 to -$386) episodes. Conclusions and Relevance: This cohort study and difference-in-differences analysis of PGPs and hospital participation in BPCI found that bundled payments were associated with cost savings for surgical episodes for PGPs, and savings for both surgical and medical episodes for hospitals. Policy makers should consider the comparative performance of participant types when designing and evaluating bundled payment models.

Bayesian Spatial Binary Regression for Label Fusion in Structural Neuroimaging.

Alzheimer's disease is a neurodegenerative condition that accelerates cognitive decline relative to normal aging. It is of critical scientific importance to gain a better understanding of early disease mechanisms in the brain to facilitate effective, targeted therapies. The volume of the hippocampus is often used in diagnosis and monitoring of the disease. Measuring this volume via neuroimaging is difficult since each hippocampus must either be manually identified or automatically delineated, a task referred to as segmentation. Automatic hippocampal segmentation often involves mapping a previously manually segmented image to a new brain image and propagating the labels to obtain an estimate of where each hippocampus is located in the new image. A more recent approach to this problem is to propagate labels from multiple manually segmented atlases and combine the results using a process known as label fusion. To date, most label fusion algorithms employ voting procedures with voting weights assigned directly or estimated via optimization. We propose using a fully Bayesian spatial regression model for label fusion that facilitates direct incorporation of covariate information while making accessible the entire posterior distribution. Our results suggest that incorporating tissue classification (e.g, gray matter) into the label fusion procedure can greatly improve segmentation when relatively homogeneous, healthy brains are used as atlases for diseased brains. The fully Bayesian approach also produces meaningful uncertainty measures about hippocampal volumes, information which can be leveraged to detect significant, scientifically meaningful differences between healthy and diseased populations, improving the potential for early detection and tracking of the disease.

Equitable implementation of S.A.F.E. Firearm: A multi-method pilot study.

Attention to health equity is critical in the implementation of firearm safety efforts. We present our operationalization of equity-oriented recommendations in preparation for launch of a hybrid effectiveness-implementation trial focused on firearm safety promotion in pediatric primary care as a universal suicide prevention strategy. In Step 1 of our process, pre-trial engagement with clinican partners and literature review alerted us that delivery of a firearm safety program may vary by patients' medical complexity, race, and ethnicity. In Step 2, we selected the Health Equity Implementation Framework to inform our understanding of contextual determinants (i.e., barriers and facilitators). In Step 3, we leveraged an implementation pilot across 5 pediatric primary care clinics in 2 health system sites to study signals of inequities. Eligible well-child visits for 694 patients and 47 clinicians were included. Our results suggested that medical complexity was not associated with program delivery. We did see potential signals of inequities by race and ethnicity but must interpret with caution. Though we did not initially plan to examine differences by sex assigned at birth, we discovered that clinicians may be more likely to deliver the program to parents of male than female patients. Seven qualitative interviews with clinicians provided additional context. In Step 4, we interrogated equity considerations (e.g., why and how do these inequities exist). In Step 5, we will develop a plan to probe potential inequities related to race, ethnicity, and sex in the fully powered trial. Our process highlights that prospective, rigorous, exploratory work is vital for equity-informed implementation trials.

Voxel-wise intermodal coupling analysis of two or more modalities using local covariance decomposition.

When individual subjects are imaged with multiple modalities, biological information is present not only within each modality, but also between modalities - that is, in how modalities covary at the voxel level. Previous studies have shown that local covariance structures between modalities, or intermodal coupling (IMCo), can be summarized for two modalities, and that two-modality IMCo reveals otherwise undiscovered patterns in neurodevelopment and certain diseases. However, previous IMCo methods are based on the slopes of local weighted linear regression lines, which are inherently asymmetric and limited to the two-modality setting. Here, we present a generalization of IMCo estimation which uses local covariance decompositions to define a symmetric, voxel-wise coupling coefficient that is valid for two or more modalities. We use this method to study coupling between cerebral blood flow, amplitude of low frequency fluctuations, and local connectivity in 803 subjects ages 8 through 22. We demonstrate that coupling is spatially heterogeneous, varies with respect to age and sex in neurodevelopment, and reveals patterns that are not present in individual modalities. As availability of multi-modal data continues to increase, principal-component-based IMCo (pIMCo) offers a powerful approach for summarizing relationships between multiple aspects of brain structure and function. An R package for estimating pIMCo is available at: https://github.com/hufengling/pIMCo.

Developmental coupling of cerebral blood flow and fMRI fluctuations in youth.

The functions of the human brain are metabolically expensive and reliant on coupling between cerebral blood flow (CBF) and neural activity, yet how this coupling evolves over development remains unexplored. Here, we examine the relationship between CBF, measured by arterial spin labeling, and the amplitude of low-frequency fluctuations (ALFF) from resting-state magnetic resonance imaging across a sample of 831 children (478 females, aged 8-22 years) from the Philadelphia Neurodevelopmental Cohort. We first use locally weighted regressions on the cortical surface to quantify CBF-ALFF coupling. We relate coupling to age, sex, and executive functioning with generalized additive models and assess network enrichment via spin testing. We demonstrate regionally specific changes in coupling over age and show that variations in coupling are related to biological sex and executive function. Our results highlight the importance of CBF-ALFF coupling throughout development; we discuss its potential as a future target for the study of neuropsychiatric diseases.

Effect of Transcutaneous Magnetic Stimulation in Patients With Ventricular Tachycardia Storm: A Randomized Clinical Trial.

IMPORTANCE: Autonomic neuromodulation provides therapeutic benefit in ventricular tachycardia (VT) storm. Transcutaneous magnetic stimulation (TcMS) can noninvasively and nondestructively modulate a patient's nervous system activity and may reduce VT burden in patients with VT storm. OBJECTIVE: To evaluate the safety and efficacy of TcMS of the left stellate ganglion for patients with VT storm. DESIGN, SETTING, AND PARTICIPANTS: This double-blind, sham-controlled randomized clinical trial took place at a single tertiary referral center between August 2019 and July 2021. The study included 26 adult patients with 3 or more episodes of VT in 24 hours. INTERVENTIONS: Patients were randomly assigned to receive a single session of either TcMS that targeted the left stellate ganglion (n = 14) or sham stimulation (n = 12). MAIN OUTCOMES AND MEASURES: The primary outcome was freedom from VT in the 24-hour period following randomization. Key secondary outcomes included safety of TcMS on cardiac implantable electronic devices, as well as burden of VT in the 72-hour period following randomization. RESULTS: Among 26 patients (mean [SD] age, 64 [13] years; 20 [77%] male), a mean (SD) of 12.7 (10.3) episodes of VT occurred within the 24 hours preceding randomization. Patients had recurrent VT despite taking a mean (SD) of 2.0 (0.6) antiarrhythmic drugs (AADs), and 11 patients (42%) required mechanical hemodynamic support at the time of randomization. In the 24-hour period after randomization, VT recurred in 4 of 14 patients (29% [SD 47%]) in the TcMS group vs 7 of 12 patients (58% [SD 51%]) in the sham group (P = .20). In the 72-hour period after randomization, patients in the TcMS group had a mean (SD) of 4.5 (7.2) episodes of VT vs 10.7 (13.8) in the sham group (incidence rate ratio, 0.42; P < .001). Patients in the TcMS group were taking fewer AADs 24 hours after randomization compared with baseline (mean [SD], 0.9 [0.8] vs 1.8 [0.4]; P = .001), whereas there was no difference in the number of AADs taken for the sham group (mean [SD], 2.3 [0.8] vs 1.9 [0.5]; P = .20). None of the 7 patients in the TcMS group with a cardiac implantable electronic device had clinically significant effects on device function. CONCLUSIONS AND RELEVANCE: In this randomized clinical trial, findings support the potential for TcMS to safely reduce the burden of VT in the setting of VT storm in patients with and without cardiac implantable electronic devices and inform the design of future trials to further investigate this novel treatment approach. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT04043312.