Differential expression is a key application of imaging spatial transcriptomics, moving analysis beyond cell type localization to examining cell state responses to microenvironments. However, spatial data poses new challenges to differential expression: segmentation errors cause bias in fold-change estimates, and correlation among neighboring cells leads standard models to inflate statistical significance. We find that ignoring these issues can result in considerable false discoveries that greatly outnumber true findings. We present a suite of solutions to these fundamental challenges, and implement them in the R package smiDE.

Somatic hypermutation (SHM) is the diversity-generating process in antibody affinity maturation. Probabilistic models of SHM are needed for analyzing rare mutations, understanding the selective forces guiding affinity maturation, and understanding the underlying biochemical process. High-throughput data offers the potential to develop and fit models of SHM on relevant data sets. In this article, we model SHM using modern frameworks. We are motivated by recent work suggesting the importance of a wider context for SHM; however, assigning an independent rate to each k-mer leads to an exponential proliferation of parameters. Thus, using convolutions on 3-mer embeddings, we develop ‘thrifty’ models of SHM of various sizes; these can have fewer free parameters than a 5-mer model and yet have a significantly wider context. These offer a slight performance improvement over a 5-mer model, and other modern model elaborations worsen performance. We also find that a per-site effect is not necessary to explain SHM patterns given nucleotide context. Also, the two current methods for fitting an SHM model—on out-of-frame sequence data and on synonymous mutations—produce significantly different results, and augmenting out-of-frame data with synonymous mutations does not aid out-of-sample performance.

Somatic hypermutation (SHM) is a critical enzyme-mediated process of the adaptive immune response in which antibodies acquire mutations to enhance antigen binding. Despite abundant research elucidating the biochemical basis of SHM, and substantial sequence data available for parameterization, previous computational models of SHM have not been explicitly mechanistic. In this paper we bridge this gap by developing a probabilistic latent variable model encapsulating a sequence of interacting steps, thus formulating the biochemical underpinnings of SHM in a mathematical framework. However, fitting this latent variable model is challenging. To navigate this complexity, we employ an approximate Bayesian computation strategy integrated with neural networks. We are able to estimate almost all of the parameters of the model to good accuracy but find that the parameters involving the boundaries of the nucleotide stripping process are slightly more challenging, given the type of data available.

Group sequential designs in clinical trials allow for interim efficacy and futility monitoring. Adjustment for baseline covariates can increase power and precision of estimated effects. However, inconsistently applying covariate adjustment throughout the stages of a group sequential trial can result in inflation of type I error, biased point estimates, and anti-conservative confidence intervals. We propose methods for performing correct interim monitoring, estimation, and inference in this setting that avoid these issues. We focus on two-arm trials with simple, balanced randomization and continuous outcomes. We study the performance of our boundary, estimation, and inference adjustments in simulation studies. We end with recommendations about the application of covariate adjustment in group sequential designs.

In Bayesian data analysis, it is often important to evaluate quantiles of the posterior distribution of a parameter of interest (e.g., to form posterior intervals). In multi-dimensional problems, when non-conjugate priors are used, this is often difficult generally requiring either an analytic or sampling-based approximation, such as Markov chain Monte-Carlo (MCMC), Approximate Bayesian computation (ABC) or variational inference. We discuss a general approach that reframes this as a multi-task learning problem and uses recurrent deep neural networks (RNNs) to approximately evaluate posterior quantiles. As RNNs carry information along a sequence, this application is particularly useful in time-series. An advantage of this risk-minimization approach is that we do not need to sample from the posterior or calculate the likelihood. We illustrate the proposed approach in several examples.

Differential expression is a key application of imaging spatial transcriptomics, moving analysis beyond cell type localization to examining cell state responses to microenvironments. However, spatial data poses new challenges to differential expression: segmentation errors cause bias in fold-change estimates, and correlation among neighboring cells leads standard models to inflate statistical significance. We find that ignoring these issues can result in considerable false discoveries that greatly outnumber true findings. We present a suite of solutions to these fundamental challenges, and implement them in the R package smiDE. ### Competing Interest Statement The authors have declared no competing interest.

Development of new therapeutics for a rare disease such as cystic fibrosis is hindered by challenges in accruing enough patients for clinical trials. Use of external controls from well-matched historical trials can reduce prospective trial sizes, and this approach has supported regulatory approval of new interventions for other rare diseases. Here we consider 3 statistical methods that incorporate external controls into a hypothetical clinical trial of a new treatment to reduce pulmonary exacerbations in cystic fibrosis patients: (1) inverse probability weighting, (2) bayesian modeling with propensity-score-based power priors, and (3) hierarchical bayesian modeling with commensurate priors. We compare the methods via simulation study and in a real clinical-trial data setting. Simulations showed that bias in the treatment effect was less than 4% using any of the methods, with type I error (or in the bayesian cases, posterior probability of the null hypothesis) usually less than 5%. Inverse probability weighting was sensitive to similarity in prevalence of the covariates between historical and prospective trial populations. The commensurate prior method performed best with real clinical trial data. Using external controls to reduce trial size in future clinical trials holds promise and can advance the therapeutic pipeline for rare diseases. This article is part of a Special Collection on Pharmacoepidemiology.

The conditional survival function of a time-to-event outcome subject to censoring and truncation is a common target of estimation in survival analysis. This parameter may be of scientific interest and also often appears as a nuisance in nonparametric and semiparametric problems. In addition to classical parametric and semiparametric methods (e.g., based on the Cox proportional hazards model), flexible machine learning approaches have been developed to estimate the conditional survival function. However, many of these methods are either implicitly or explicitly targeted toward risk stratification rather than overall survival function estimation. Others apply only to discrete-time settings or require inverse probability of censoring weights, which can be as difficult to estimate as the outcome survival function itself. Here, we employ a decomposition of the conditional survival function in terms of observable regression models in which censoring and truncation play no role. This allows application of an array of flexible regression and classification methods rather than only approaches that explicitly handle the complexities inherent to survival data. We outline estimation procedures based on this decomposition, empirically assess their performance, and demonstrate their use on data from an HIV vaccine trial. Supplementary materials for this article are available online.

Given a collection of features available for inclusion in a predictive model, it may be of interest to quantify the relative importance of a subset of features for the prediction task at hand. For example, in HIV vaccine trials, participant baseline characteristics are used to predict the probability of HIV acquisition over the intended follow-up period, and investigators may wish to understand how much certain types of predictors, such as behavioural factors, contribute to overall predictiveness. Time-to-event outcomes such as time to HIV acquisition are often subject to right censoring, and existing methods for assessing variable importance are typically not intended to be used in this setting. We describe a broad class of algorithm-agnostic variable importance measures for prediction in the context of survival data. We propose a nonparametric efficient estimation procedure that incorporates flexible learning of nuisance parameters, yields asymptotically valid inference and enjoys double robustness. We assess the performance of our proposed procedure via numerical simulations and analyse data from the HVTN 702 vaccine trial to inform enrolment strategies for future HIV vaccine trials.

Software as a Medical Device (SaMD) has been transforming medical practices by improving patient care with more precise and timely information. The key capabilities of SaMD are often enabled by Artificial Intelligence (AI) algorithms. However, notable challenges have been observed in building robust algorithms in SaMD development and evaluation, where it is not unusual for algorithms to show strong performance in the development phase but poor performance when deployed in pivotal validation study. With rapid development in medical research, data from new trials or the real world are very likely to differ from legacy data used for training in many important aspects. Added caution is thus needed to account for such potential differences. In this paper, we will discuss the pitfalls of using conventional cross- validation methods in SaMD algorithm development and its magnitude of overestimation of model performance when heterogeneity is anticipated. To mitigate against overestimation bias performance assessment, we propose a leave-one-set-out (LOSO) cross validation method and discuss best practices in design of the independent validation pivotal study.

One challenge of training deep neural networks with gigapixel whole-slide images (WSIs) in computational pathology is the lack of annotation at pixel level or regional level due to the high cost and time-consuming labeling effort. Multiple instance learning (MIL) and its attention-based versions are typical weakly supervised learning methods, which allow us to use slide-level labels directly, without the need for pixel or region labels, thus reducing the cost of annotation. However, training a deep neural network with thousands of image regions (patches) per slide is computationally expensive, and it needs a lot of time for convergence. This paper proposes a fast adaptive attention-based deep MIL approach. This approach adaptively selects image regions that are highly predictive of outcome and ignores image regions with little or no information. We empirically show that our proposed approach outperforms the random sampling approach while it is faster than the standard attention-based MIL method (which uses all image regions for training).

We construct non-linear machine learning (ML) prediction models for systolic and diastolic blood pressure (SBP, DBP) using demographic and clinical variables and polygenic risk scores (PRSs). We developed a two-model ensemble, consisting of a baseline model, where prediction is based on demographic and clinical variables only, and a genetic model, where we also include PRSs. We evaluate the use of a linear versus a non-linear model at both the baseline and the genetic model levels and assess the improvement in performance when incorporating multiple PRSs. We report the ensemble model's performance as percentage variance explained (PVE) on a held-out test dataset. A non-linear baseline model improved the PVEs from 28.1 to 30.1% (SBP) and 14.3% to 17.4% (DBP) compared with a linear baseline model. Including seven PRSs in the genetic model computed based on the largest available GWAS of SBP/DBP improved the genetic model PVE from 4.8 to 5.1% (SBP) and 4.7 to 5% (DBP) compared to using a single PRS. Adding additional 14 PRSs computed based on two independent GWASs further increased the genetic model PVE to 6.3% (SBP) and 5.7% (DBP). PVE differed across self-reported race/ethnicity groups, with primarily all non-White groups benefitting from the inclusion of additional PRSs. In summary, non-linear ML models improves BP prediction in models incorporating diverse populations.

Objectives Designing cancer screening trials for multi-cancer early detection (MCED) tests presents a significant methodology challenge, as natural histories of cell-free DNA-shedding cancers are not yet known. A microsimulation model was developed to project the performance and utility of an MCED test in cancer screening trials. Methods Individual natural history of preclinical progression through cancer stages for 23 cancer classes was simulated by a stage-transition model under a broad range of cancer latency parameters. Cancer incidences and stage distributions at clinical presentation in simulated trials were set to match the data from Surveillance, Epidemiology, and End Results program. One or multiple rounds of annual screening using a targeted methylation-based MCED test (Galleri Ⓡ ) was conducted to detect preclinical cancers. Mortality benefit of early detection was simulated by a stage-shift model. Results In simulated trials, accounting for healthy volunteer effect and varying test sensitivity, positive predictive value in the prevalence screening round reached 48% to 61% in 6 natural history scenarios. After 3 rounds of annual screening, the cumulative proportions of stage I/II cancers increased by approximately 9% to 14%, the incidence of stage IV cancers was reduced by 37% to 46%, the reduction of stages III and IV cancer incidences was 9% to 24%, and the reduction of mortality reached 13% to 16%. Greater reductions of late-stage cancers and cancer mortality were achieved by five rounds of MCED screening. Conclusions Simulation results guide trial design and suggest that adding this MCED test to routine screening in the United States may shift cancer detection to earlier stages, and potentially save lives.

BACKGROUND: The majority of out-of-hospital cardiac arrests (OHCAs) occur among individuals in the general population, for whom there is no established strategy to identify risk. In this study, we assess the use of electronic health record (EHR) data to identify OHCA in the general population and define salient factors contributing to OHCA risk. METHODS: The analytical cohort included 2366 individuals with OHCA and 23 660 age- and sex-matched controls receiving health care at the University of Washington. Comorbidities, electrocardiographic measures, vital signs, and medication prescription were abstracted from the EHR. The primary outcome was OHCA. Secondary outcomes included shockable and nonshockable OHCA. Model performance including area under the receiver operating characteristic curve and positive predictive value were assessed and adjusted for observed rate of OHCA across the health system. RESULTS: There were significant differences in demographic characteristics, vital signs, electrocardiographic measures, comorbidities, and medication distribution between individuals with OHCA and controls. In external validation, discrimination in machine learning models (area under the receiver operating characteristic curve 0.80–0.85) was superior to a baseline model with conventional cardiovascular risk factors (area under the receiver operating characteristic curve 0.66). At a specificity threshold of 99%, correcting for baseline OHCA incidence across the health system, positive predictive value was 2.5% to 3.1% in machine learning models compared with 0.8% for the baseline model. Longer corrected QT interval, substance abuse disorder, fluid and electrolyte disorder, alcohol abuse, and higher heart rate were identified as salient predictors of OHCA risk across all machine learning models. Established cardiovascular risk factors retained predictive importance for shockable OHCA, but demographic characteristics (minority race, single marital status) and noncardiovascular comorbidities (substance abuse disorder) also contributed to risk prediction. For nonshockable OHCA, a range of salient predictors, including comorbidities, habits, vital signs, demographic characteristics, and electrocardiographic measures, were identified. CONCLUSIONS: In a population-based case–control study, machine learning models incorporating readily available EHR data showed reasonable discrimination and risk enrichment for OHCA in the general population. Salient factors associated with OCHA risk were myriad across the cardiovascular and noncardiovascular spectrum. Public health and tailored strategies for OHCA prediction and prevention will require incorporation of this complexity.

BackgroundIn 2017, the US Food and Drug Administration initiated expansion of drug labels for the treatment of cystic fibrosis (CF) to include CF transmembrane conductance regulator (CFTR) gene variants based on in vitro functional studies. This study aims to identify CFTR variants that result in increased chloride (Cl−) transport function by the CFTR protein after treatment with the CFTR modulator combination elexacaftor/tezacaftor/ivacaftor (ELX/TEZ/IVA). These data may benefit people with CF (pwCF) who are not currently eligible for modulator therapies.MethodsPlasmid DNA encoding 655 CFTR variants and wild-type (WT) CFTR were transfected into Fisher Rat Thyroid cells that do not natively express CFTR. After 24 h of incubation with control or TEZ and ELX, and acute addition of IVA, CFTR function was assessed using the transepithelial current clamp conductance assay. Each variant's forskolin/cAMP-induced baseline Cl− transport activity, responsiveness to IVA alone, and responsiveness to the TEZ/ELX/IVA combination were measured in three different laboratories. Western blots were conducted to evaluate CFTR protein maturation and complement the functional data.Results and conclusions253 variants not currently approved for CFTR modulator therapy showed low baseline activity (<10 % of normal CFTR Cl− transport activity). For 152 of these variants, treatment with ELX/TEZ/IVA improved the Cl− transport activity by ≥10 % of normal CFTR function, which is suggestive of clinical benefit. ELX/TEZ/IVA increased CFTR function by ≥10 percentage points for an additional 140 unapproved variants with ≥10 % but <50 % of normal CFTR function at baseline. These findings significantly expand the number of rare CFTR variants for which ELX/TEZ/IVA treatment should result in clinical benefit.

Abstract Introduction: Breast cancer (BC) treatment has known cardiotoxic effects. While increased risk of death from cardiovascular disease (CVD) after BC has been demonstrated in select racial/ethnic minorities, less is known about the association of social determinants of health (SDH) variables on death from CVD after BC treatment. Methods: Using data from the Women’s Health Initiative, we examined factors associated with increased risk of death from CVD after BC diagnosis among 8,728 women (n=7,433 non-Hispanic White (NHW); n=706 non-Hispanic, Black (NHB); n=288 Hispanic, n=271 non-Hispanic Asian; n=30 missing racial information) . Cox proportional hazard model was used to analyze the relationship between survival outcomes (death due to BC, death due to CVD, and adjudicated CVD after BC) and race/ethnicity and income. Income level was stratified into less than $35,000, $35,000-$74,999, and greater than or equal to $75,000. Results: Income level less than $35,000 was associated with a significantly increased risk of death due to CVD after BC (HR=1.57; 95% CI: 1.34, 1.84) compared to income between $35,000 and $74,999. Income greater than $75,000 was associated with a significantly less risk of death due to CVD after BC (HR=0.56; 95% CI: 0.45, 0.71). A higher cumulative incidence of death from BC and death from CVD was associated with the lowest income bracket. Furthermore, death from CVD surpassed death from BC around 13 years after BC diagnosis for income levels less than $35,000 and at 20 years after BC diagnosis for those with income levels between $35,000 and $74.999. However, for the highest income bracket of greater than $75,000, death from CVD never surpassed cumulative incidence of death from BC. Hispanic women were less likely to have death due to CVD after BC compared to NHW women (HR=0.10; 95% CI:0.49,0.77). No significant difference in death from CVD was seen between NHW and NHB women. Among NHW women, those with income less than $35,000 had higher likelihood of death from CVD (HR=1.58; 95% CI: 1.34, 1.84), compared to those with income between $35,000 and $74,999. NHW women with greater than $75,000 had a less likely chance of dying compared to those with income between $35,000 and $74,999 (HR=0.61; 95% CI 0.49, 0.77). A difference in death due to CVD across income levels was not observed among NHB women. However, among Hispanic women with less than $35,000 annual income, a 10- fold increased risk of death from CVD was observed compared to Hispanic women with annual income $35,000-$74,999 (HR=10.41; 95% CI 1.43, 75.57). Conclusion: In the WHI, income level was strongly associated with increased risk of death from CVD after BC, especially among NHW and Hispanic women, but not among NHB women. Clinical trials investigating therapies with potential cardiotoxic effects must include patients with diverse income levels to prevent potentially exacerbating BC disparities. Citation Format: Veronica Jones, Yongzhe Wang, Alexi Vasbinder, Noah Simon, Kerryn Reding. Income level associated with death from cardiovascular disease after breast cancer in the Women’s Health Initiative [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr B014.

AbstractBackgroundIn 2017, the US Food and Drug Administration initiated expansion of drug labels for the treatment of cystic fibrosis (CF) to include CF transmembrane conductance regulator (CFTR) gene variants based onin vitrofunctional studies. This study aims to identifyCFTRvariants that result in increased chloride (Cl-) transport function by the CFTR protein after treatment with the CFTR-modulator combination elexacaftor/tezacaftor/ivacaftor (ELX/TEZ/IVA). These data may benefit people with CF (pwCF) who are not currently eligible for modulator therapies.MethodsPlasmid DNA encoding 655 CFTR variants and wild-type (WT)CFTRwere transfected into Fisher Rat Thyroid cells that do not natively express CFTR. After 24 hours of incubation with control or TEZ and ELX, and acute addition of IVA, CFTR function was assessed using the transepithelial current clamp conductance assay. Each variant’s baseline activity, responsiveness to IVA alone, and responsiveness to the TEZ/ELX/IVA combination were measured in three different laboratories. Western blots were conducted to evaluate CFTR protein maturation and complement the functional data.Results and Conclusions253 variants not currently approved for CFTR modulator therapy showed low baseline activity (<10% of normal CFTR Cl-transport activity). For 152 of these variants, treatment with ELX/TEZ/IVA improved the Cl-transport activity by ≥10% of normal CFTR function, which is suggestive of clinical benefit. ELX/TEZ/IVA increased CFTR function by ≥10 percentage points for an additional 140 unapproved variants with ≥10% but <50% of normal CFTR function at baseline. These findings significantly expand the number of rare CFTR variants for which ELX/TEZ/IVA treatment should result in clinical benefit.