PURPOSE:Prediction models can contribute to disparities in care by performing unequally across demographic groups. While fairness-aware methods have been explored for binary outcomes, applications to survival analysis remain limited. This study compares two fairness-aware deep learning survival models to mitigate racial disparities in predicting survival after radical prostatectomy for prostate cancer. METHODS:We used the National Cancer Database to train deep Cox proportional hazards models for overall survival. Two fairness-aware approaches, Fair Deep Cox Proportional Hazards Model (Fair DCPH) and Group Distributionally Robust Optimization Deep Cox Proportional Hazards Model (GroupDRO DCPH), were compared against a standard Deep Cox model (Baseline). Model fairness was assessed via cross-group and within-group concordance indices (C-index). RESULTS:Among 418,968 included patients, 78.5% were White, with smaller proportions of Black (13.2%), Hispanic (4.5%), Asian (1.9%), and Other (2.0%) patients. The baseline DCPH model achieved a cross-group C-index of 0.699 for White patients but showed reduced performance for Black (0.678) and Hispanic (0.689) patients. Fairness-aware models improved cross-group C-indices; for Black patients, cross-group C-index increased to 0.692 (Fair DCPH) and 0.696 (GroupDRO DCPH); for Hispanic patients, to 0.693 and 0.697, respectively. Cross-group C-index also improved in the Asian subgroup, where the C-index rose from 0.696 (Baseline DCPH) to 0.702 (Fair DCPH) and 0.707 (GroupDRO DCPH), with minimal performance loss observed for White patients. CONCLUSION:We benchmark two fairness-aware survival models that address racial disparities in post-prostatectomy survival prediction. These methods can be extended to other time-to-event models to ensure equitable care supported by fair prediction models.

Semi-supervised learning (SSL) uses unlabeled data to improve the performance of machine learning models when labeled data is scarce. However, its real-world applications often face the label distribution mismatch problem, in which the unlabeled dataset includes instances whose ground-truth labels are absent from the labeled training dataset. Recent studies, referred to as safe SSL, have addressed this issue by using both classification and out-of-distribution (OOD) detection. However, the existing methods may suffer from overconfidence in deep neural networks, leading to increased SSL errors because of high confidence in incorrect pseudo-labels or OOD detection. To address this, we propose a novel method, CaliMatch, which calibrates both the classifier and the OOD detector to foster safe SSL. CaliMatch presents adaptive label smoothing and temperature scaling, which eliminates the need to manually tune the smoothing degree for effective calibration. We give a theoretical justification for why improving the calibration of both the classifier and the OOD detector is crucial in safe SSL. Extensive evaluations on CIFAR-10, CIFAR-100, SVHN, TinyImageNet, and ImageNet demonstrate that CaliMatch outperforms the existing methods in safe SSL tasks.

Introduction Predictive models are increasingly being used as clinical decision-support tools for the diagnosis and risk stratification of prostate cancer patients. While machine learning and artificial intelligence methods have the potential to develop precise prediction models, recent research has shown that data-driven predictive models often retain systematic biases present in the underlying data and can propagate inequalities via their predictions. This issue is particularly concerning in prostate cancer, where algorithmic bias can exacerbate known existing disparities in care for vulnerable populations, including racial minorities. In this study, we examined the potential for racial bias in machine learning prediction models for prostate cancer survival and compared bias-mitigation strategies to reduce model bias. Methods We utilized the National Cancer Database (NCDB) to identify patients diagnosed with localized prostate cancer between 2004 and 2022. Demographic information, clinical data, and disease-specific factors were extracted for these patients. We categorized patients into National Institute of Health (NIH) subgroups: ‘Non-Hispanic White’, ‘Non-Hispanic Black’, ‘Hispanic’, and ‘Asian’. The dataset was divided into training and testing sets in a 70%/30% split based on these subgroups. A deep Cox proportional hazard model was trained to predict the risk of prostate cancer development. We evaluated model performance to predict death at 5 years in the overall test set and its subgroups based on NIH race categories. Model performance was evaluated in the test sets with balanced accuracy and C-index. The primary metric for assessing prediction disparity was the equalized odds ratio (eOR). We compared three bias mitigation techniques to encourage prediction parity: threshold optimizer, Fair Cox proportional hazard model, and distributionally robust (DRO) Cox proportional hazard model. Results We identified 361,883 patients that met the inclusion criteria, comprising 290,805 (80.3%) non-Hispanic white (NHW), 47,710 (13.2%) non-Hispanic black (NHB), 16,405 (4.5%) Hispanic, and 6,963 (2%) Asian patients. The deep Cox model had a balanced accuracy of 0.591 (95% CI 0.581-0.601) and an overall C-index of 0.667 (95% CI 0.653-0.681). This model performed best for Asian patients (balanced accuracy 0.616; 95% CI 0.584-0.648) and worst for NHW patients (C-index 0.0.588; 95% CI 0.0.580-0.0.597) ; the equalized odds ratio (eOR) of this model was 0.681 (95% CI 0.663-0.699) indicating a prediction disparity across racial and ethnic groups. Applying a threshold optimizer significantly (p-value < 10-5) improved the eOR to 0.797 (95% CI 0.779-0.815) with a balanced accuracy of 0.597 (95% CI 0.582-0.612), indicating no loss in predictive performance. Detailed results are illustrated in Figure 1. The fair Cox proportional hazard model achieved a balanced accuracy of 0.611 (95% CI 0.606-0.616) and an eOR of 0.798 (95% CI 0.771-0.823), while the DRO CoxPH model demonstrated a balanced accuracy of 0.629 (95% CI 0.624-0.634) and an eOR of 0.799 (95% CI 0.779-0.815). Conclusions We developed machine learning models to predict prostate cancer survival and observed that a naïve model exhibited prediction disparities, with certain racial groups experiencing inferior performance compared to others. By applying bias mitigation techniques, we were able to reduce these disparities and achieve improved prediction parity without compromising overall performance. Our study underscores the importance of examining prediction disparities in risk models and employing bias mitigation strategies to enhance model equity in healthcare applications.

Time series are often irregularly sampled with uneven time intervals. In multivariate cases, such irregularities may lead to misaligned observations across variables and varying observation counts, making it difficult to extract intrinsic patterns and degrading the classification performance of deep learning models. In this study, we propose an adaptive time encoding approach to address the challenge of irregular sampling in multivariate time-series classification. Our approach generates latent representations at learnable reference points that capture missingness patterns in irregular sequences, enhancing classification performance. We also introduce consistency regularization techniques to incorporate intricate temporal and intervariable information into the learned representations. Extensive experiments demonstrate that our method achieves state-of-the-art performance with high computational efficiency in irregular multivariate time-series classification tasks.

Current domain adaptation methods under missingness shift are restricted to Missing At Random (MAR) missingness mechanisms. However, in many real-world examples, the MAR assumption may be too restrictive. When covariates are Missing Not At Random (MNAR) in both source and target data, the common covariate shift solutions, including importance weighting, are not directly applicable. We show that under reasonable assumptions, the problem of MNAR missingness shift can be reduced to an imputation problem. This allows us to leverage recent methodological developments in both the traditional statistics and machine/deep-learning literature for MNAR imputation to develop a novel domain adaptation procedure for MNAR missingness shift. We further show that our proposed procedure can be extended to handle simultaneous MNAR missingness and covariate shifts. We apply our procedure to Electronic Health Record (EHR) data from two hospitals in south and northeast regions of the US. In this setting we expect different hospital networks and regions to serve different populations and to have different procedures, practices, and software for inputting and recording data, causing simultaneous missingness and covariate shifts.

IntroductionQuantitative, multiplexed imaging is revealing complex spatial relationships between phenotypically diverse tumor infiltrating leukocyte populations and their prognostic implications. The underlying mechanisms and tissue structures that determine leukocyte distribution within and around tumor nests, however, remain poorly understood. While presumed players in metastatic dissemination, new preclinical data demonstrates that blood and lymphatic vessels (lymphovasculature) also dictate leukocyte trafficking within tumor microenvironments and thereby impact anti-tumor immunity. Here we interrogate these relationships in primary human cutaneous melanoma. MethodsWe established a quantitative, multiplexed imaging platform to simultaneously detect immune infiltrates and tumor-associated vessels in formalin-fixed paraffin embedded patient samples. We performed a discovery, retrospective analysis of 28 treatment-naïve, primary cutaneous melanomas. ResultsHere we find that the lymphvasculature and immune infiltrate is heterogenous across patients in treatment naïve, primary melanoma. We categorized five lymphovascular subtypes that differ by functionality and morphology and mapped their localization in and around primary tumors. Interestingly, the localization of specific vessel subtypes, but not overall vessel density, significantly associated with the presence of lymphoid aggregates, regional progression, and intratumoral T cell infiltrates. DiscussionWe describe a quantitative platform to enable simultaneous lymphovascular and immune infiltrate analysis and map their spatial relationships in primary melanoma. Our data indicate that tumor-associated vessels exist in different states and that their localization may determine potential for metastasis or immune infiltration. This platform will support future efforts to map tumor-associated lymphovascular evolution across stage, assess its prognostic value, and stratify patients for adjuvant therapy.

This study addresses unsupervised anomaly detection using one-class classification, which constructs a decision boundary to determine if a new instance belongs to the target class. Existing one-class classification methods often fail in real-world scenarios due to their sensitivity to noise and inability to handle complex structures. We propose a proximity-based density description with a regularized reconstruction algorithm to overcome these limitations. Our method defines density-descriptive coefficients to reconstruct initial density and derives optimal coefficients by minimizing reconstruction error subject to sparsity and smoothness constraints. The sparsity constraint reduces noise effects, while the smoothness constraint encourages a flexible decision boundary. We evaluate our algorithm on benchmark datasets and compare it to existing methods, demonstrating superior performance.

Objectives We introduce a widely applicable model-based approach for estimating individual-level Social Determinants of Health (SDoH) and evaluate its effectiveness using the All of Us Research Program.Materials and Methods Our approach utilizes aggregated SDoH datasets to estimate individual-level SDoH, demonstrated with examples of no high school diploma (NOHSDP) and no health insurance (UNINSUR) variables. Models are estimated using American Community Survey data and applied to derive individual-level estimates for All of Us participants. We assess concordance between model-based SDoH estimates and self-reported SDoHs in All of Us and examine associations with undiagnosed hypertension and diabetes.Results Compared to self-reported SDoHs, the area under the curve for NOHSDP is 0.727 (95% CI, 0.724-0.730) and for UNINSUR is 0.730 (95% CI, 0.727-0.733) among the 329 074 All of Us participants, both significantly higher than aggregated SDoHs. The association between model-based NOHSDP and undiagnosed hypertension is concordant with those estimated using self-reported NOHSDP, with a correlation coefficient of 0.649. Similarly, the association between model-based NOHSDP and undiagnosed diabetes is concordant with those estimated using self-reported NOHSDP, with a correlation coefficient of 0.900.Discussion and Conclusion The model-based SDoH estimation method offers a scalable and easily standardized approach for estimating individual-level SDoHs. Using the All of Us dataset, we demonstrate reasonable concordance between model-based SDoH estimates and self-reported SDoHs, along with consistent associations with health outcomes. Our findings also underscore the critical role of geographic contexts in SDoH estimation and in evaluating the association between SDoHs and health outcomes.

Background Prediction models based on machine learning (ML) methods are being increasingly developed and adopted in health care. However, these models may be prone to bias and considered unfair if they demonstrate variable performance in population subgroups. An unfair model is of particular concern in bladder cancer, where disparities have been identified in sex and racial subgroups. Objective This study aims (1) to develop a ML model to predict survival after radical cystectomy for bladder cancer and evaluate for potential model bias in sex and racial subgroups; and (2) to compare algorithm unfairness mitigation techniques to improve model fairness. Methods We trained and compared various ML classification algorithms to predict 5-year survival after radical cystectomy using the National Cancer Database. The primary model performance metric was the F1-score. The primary metric for model fairness was the equalized odds ratio (eOR). We compared 3 algorithm unfairness mitigation techniques to improve eOR. Results We identified 16,481 patients; 23.1% (n=3800) were female, and 91.5% (n=15,080) were “White,” 5% (n=832) were “Black,” 2.3% (n=373) were “Hispanic,” and 1.2% (n=196) were “Asian.” The 5-year mortality rate was 75% (n=12,290). The best naive model was extreme gradient boosting (XGBoost), which had an F1-score of 0.860 and eOR of 0.619. All unfairness mitigation techniques increased the eOR, with correlation remover showing the highest increase and resulting in a final eOR of 0.750. This mitigated model had F1-scores of 0.86, 0.904, and 0.824 in the full, Black male, and Asian female test sets, respectively. Conclusions The ML model predicting survival after radical cystectomy exhibited bias across sex and racial subgroups. By using algorithm unfairness mitigation techniques, we improved algorithmic fairness as measured by the eOR. Our study highlights the role of not only evaluating for model bias but also actively mitigating such disparities to ensure equitable health care delivery. We also deployed the first web-based fair ML model for predicting survival after radical cystectomy.

The domain generalization (DG) setup considers the problem where models are trained on data sampled from multiple domains and evaluated on test domains unseen during training. In this paper, we formulate DG as a sample selection problem where each domain is sampled from a common underlying population through non-random sampling probabilities that correlate with both the features and the outcome. Under this setting, the fundamental iid assumption of the empirical risk minimization (ERM) is violated, so it often performs worse on test domains whose non-random sampling probabilities differ from the domains in the training dataset. We propose a Selection-Guided DG (SGDG) framework to learn the selection probability of each domain and the joint distribution of the outcome and domain selection variables. The proposed SGDG is domain generalizable as it intends to minimize the risk under the population distribution. We theoretically proved that, under certain regular conditions, SGDG can achieve smaller risk than ERM. Furthermore, we present a class of parametric SGDG (HeckmanDG) estimators applicable to continuous, binary, and multinomial outcomes. We also demonstrated its efficacy empirically through simulations and experiments on a set of benchmark datasets comparing with other well-known DG methods.

In data collection for predictive modeling, under-representation of certain groups, based on gender, race/ethnicity, or age, may yield less-accurate predictions for these groups. Recently, this issue of fairness in predictions has attracted significant attention, as data-driven models are increasingly utilized to perform crucial decision-making tasks. Existing methods to achieve fairness in the machine learning literature typically build a single prediction model in a manner that encourages fair prediction performance for all groups. These approaches have two major limitations: i) fairness is often achieved by compromising accuracy for some groups; ii) the underlying relationship between dependent and independent variables may not be the same across groups. We propose a Joint Fairness Model (JFM) approach for logistic regression models for binary outcomes that estimates group-specific classifiers using a joint modeling objective function that incorporates fairness criteria for prediction. We introduce an Accelerated Smoothing Proximal Gradient Algorithm to solve the convex objective function, and present the key asymptotic properties of the JFM estimates. Through simulations, we demonstrate the efficacy of the JFM in achieving good prediction performance and across-group parity, in comparison with the single fairness model, group-separate model, and group-ignorant model, especially when the minority group's sample size is small. Finally, we demonstrate the utility of the JFM method in a real-world example to obtain fair risk predictions for under-represented older patients diagnosed with coronavirus disease 2019 (COVID-19).

In the semiconductor manufacturing processes, a wafer bin map (WBM) represents electrical test results. In WBMs, defective dies often form specific local patterns; such patterns are usually caused by failure from specific processes or equipment. Thus, identifying the local patterns is crucial for finding the processes or equipment responsible for the fault. Various statistical and machine learning methods have been developed for WBM classification; however, most of the existing studies considered single WBMs. This study proposes an explainable neural network for multiple WBMs classification, named a hierarchical spatial-test attention network. Our method has a hierarchical structure that reflects the characteristics of multiple WBMs. The method has two levels of attention mechanisms to the spatial and test levels, allowing the model to attend to more and less important parts when classifying WBMs. Furthermore, we propose a spatial attention probability conveyance mechanism and test-level attention entropy penalty to improve the classification performance and interpretability of the proposed method. We applied our method on a real-world multiple WBMs dataset to demonstrate the usefulness and applicability of our method. The results confirmed that the proposed method could accurately classify defect patterns while correctly identifying defect patterns’ test and location.

BACKGROUND:Morbidity and death due to coronavirus disease 2019 (COVID-19) experienced by older adults in nursing homes have been well described, but COVID-19's impact on community-living older adults is less studied. Similarly, the previous ambulatory care experience of such patients has rarely been considered in studies of COVID-19 risks and outcomes. METHODS:To investigate the relationship of advanced age (65+), on risk factors associated with COVID-19 outcomes in community-living elders, we identified an electronic health records cohort of older patients aged 65+ with laboratory-confirmed COVID-19 with and without an ambulatory care visit in the past 24 months (n = 47,219) in the New York City (NYC) academic medical institutions and the NYC public hospital system from January 2020 to February 2021. The main outcomes are COVID-19 hospitalization; severe outcomes/Intensive care unit (ICU), intubation, dialysis, stroke, in-hospital death), and in-hospital death. The exposures include demographic characteristics, and those with ambulatory records, comorbidities, frailty, and laboratory results. RESULTS:The 31,770 patients with an ambulatory history had a median age of 74 years; were 47.4% male, 24.3% non-Hispanic white, 23.3% non-Hispanic black, and 18.4% Hispanic. With increasing age, the odds ratios and attributable fractions of sex, race-ethnicity, comorbidities, and biomarkers decreased except for dementia and frailty (Hospital Frailty Risk Score). Patients without ambulatory care histories, compared to those with, had significantly higher adjusted rates of COVID-19 hospitalization and severe outcomes, with strongest effect in the oldest group. CONCLUSIONS:In this cohort of community-dwelling older adults, we provided evidence of age-specific risk factors for COVID-19 hospitalization and severe outcomes. Future research should explore the impact of frailty and dementia in severe COVID-19 outcomes in community-living older adults, and the role of engagement in ambulatory care in mitigating severe disease.

The widespread availability of high-dimensional electronic healthcare record (EHR) datasets has led to significant interest in using such data to derive clinical insights and make risk predictions. More specifically, techniques from machine learning are being increasingly applied to the problem of dynamic survival analysis, where updated time-to-event risk predictions are learned as a function of the full covariate trajectory from EHR datasets. EHR data presents unique challenges in the context of dynamic survival analysis, involving a variety of decisions about data representation, modeling, interpretability, and clinically meaningful evaluation. In this paper we propose a new approach to dynamic survival analysis which addresses some of these challenges. Our modeling approach is based on learning a global parametric distribution to represent population characteristics and then dynamically locating individuals on the time-axis of this distribution conditioned on their histories. For evaluation we also propose a new version of the dynamic C-Index for clinically meaningful evaluation of dynamic survival models. To validate our approach we conduct dynamic risk prediction on three real-world datasets, involving COVID-19 severe outcomes, cardiovascular disease (CVD) onset, and primary biliary cirrhosis (PBC) time-to-transplant. We find that our proposed modeling approach is competitive with other well-known statistical and machine learning approaches for dynamic risk prediction, while offering potential advantages in terms of interepretability of predictions at the individual level.

Multichannel signal data collected from multiple sensors are widely used to monitor the status of various mechanical systems. Recently, deep neural networks have been success-fully applied to multichannel signal data analysis because of their capability to learn dis-criminative features with minimum feature engineering. However, the latest deep neural networks for multichannel signal analysis lack explainability, which is essential for post hoc analysis in various fields. In this study, we propose an explainable neural network for the multichannel signal classification task. The proposed method is equipped with two levels of attention mechanisms -at the segment and channel levels- encouraging the model to focus on important parts in discriminating the status of a system. The derived attention probabilities facilitate interpretation of network behavior and thus can support post hoc analysis. To demonstrate the practicality and applicability of the proposed method, we conducted experiments on both simulated and real-world automobile data. The results confirmed that the proposed method is capable of accurately classifying mul-tichannel signals and correctly identifying the critical segments and channels. (c) 2021 Elsevier Inc. All rights reserved. With recent advances in sensor technology regarding hardware and software for data storage and wireless communication, the use of multiple sensors of monitoring of various systems based on multiple sensors has become more prevalent than ever. Signals collected from the sensors can be used to describe states or to detect system malfunctions of a system. Examples include human activity recognition [1], automobile statement recognition [2], and monitoring construction equipment monitoring [3]. Various methods have been considered for analyzing complex multivariate time series data obtained from multiple sen

We propose a new method for variable subset selection and regression coefficient estimation in linear regression models that incorporates a graph structure of the predictor variables. The proposed method is based on the cardinality constraint that controls the number of selected variables and the graph structured subset constraint that encourages the predictor variables adjacent in the graph to be simultaneously selected or eliminated from the model. Moreover, we develop an efficient discrete projected gradient descent method to handle the NP-hardness of the problem originating from the discrete constraints. Numerical experiments on simulated and real-world data are conducted to demonstrate the usefulness and applicability of the proposed method by comparing it with existing graph regularization methods in terms of the predictive accuracy and variable selection performance. The results confirm that the proposed method outperforms the existing methods. (C) 2020 Elsevier Inc. All rights reserved.

•A new graph-based clustering method using node cutting was proposed.•We present theoretical results that guarantee the robustness in selecting nodes.•The optimal cluster number can be determined by adjusting a sparsity parameter.•Comparison studies show that the proposed method outperformed existing methods.

This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality.