MOTIVATION: Clustering patients into subgroups based on their microbial compositions can greatly enhance our understanding of the role of microbes in human health and disease etiology. Distance-based clustering methods, such as partitioning around medoids (PAM), are popular due to their computational efficiency and absence of distributional assumptions. However, the performance of these methods can be suboptimal when true cluster memberships are driven by differences in the abundance of only a few microbes, a situation known as the sparse signal scenario. RESULTS: We demonstrate that classical multidimensional scaling (MDS), a widely used dimensionality reduction technique, effectively denoises microbiome data and enhances the clustering performance of distance-based methods. We propose a two-step procedure that first applies MDS to project high-dimensional microbiome data into a low-dimensional space, followed by distance-based clustering using the low-dimensional data. Our extensive simulations demonstrate that our procedure offers superior performance compared to directly conducting distance-based clustering under the sparse signal scenario. The advantage of our procedure is further showcased in several real data applications. AVAILABILITY AND IMPLEMENTATION: The R package MDSMClust is available at https://github.com/wxy929/MDS-project.

Estimating individualized treatment rules (ITRs) is fundamental in causal inference, particularly for precision medicine applications. Traditional ITR estimation methods rely on inverse probability weighting (IPW) to address confounding factors and $L_{1}$-penalization for simplicity and interpretability. However, IPW can introduce statistical bias without precise propensity score modeling, while $L_1$-penalization makes the objective non-smooth, leading to computational bias and requiring subgradient methods. In this paper, we propose a unified ITR estimation framework formulated as a constrained, weighted, and smooth convex optimization problem. The optimal ITR can be robustly and effectively computed by projected gradient descent. Our comprehensive theoretical analysis reveals that weights that balance the spectrum of a `weighted design matrix' improve both the optimization and likelihood landscapes, yielding improved computational and statistical estimation guarantees. In particular, this is achieved by distributional covariate balancing weights, which are model-free alternatives to IPW. Extensive simulations and applications demonstrate that our framework achieves significant gains in both robustness and effectiveness for ITR learning against existing methods.

OBJECTIVE: The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. MATERIALS AND METHODS: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. RESULTS: Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. DISCUSSION: The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. CONCLUSIONS: Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations.

OBJECTIVE: This study aims to develop machine learning models that provide both accurate and equitable predictions of 2-year stroke risk for patients with atrial fibrillation across diverse racial groups. MATERIALS AND METHODS: Our study utilized structured electronic health records (EHR) data from the All of Us Research Program. Machine learning models (LightGBM) were utilized to capture the relations between stroke risks and the predictors used by the widely recognized CHADS2 and CHA2DS2-VASc scores. We mitigated the racial disparity by creating a representative tuning set, customizing tuning criteria, and setting binary thresholds separately for subgroups. We constructed a hold-out test set that not only supports temporal validation but also includes a larger proportion of Black/African Americans for fairness validation. RESULTS: Compared to the original CHADS2 and CHA2DS2-VASc scores, significant improvements were achieved by modeling their predictors using machine learning models (Area Under the Receiver Operating Characteristic curve from near 0.70 to above 0.80). Furthermore, applying our disparity mitigation strategies can effectively enhance model fairness compared to the conventional cross-validation approach. DISCUSSION: Modeling CHADS2 and CHA2DS2-VASc risk factors with LightGBM and our disparity mitigation strategies achieved decent discriminative performance and excellent fairness performance. In addition, this approach can provide a complete interpretation of each predictor. These highlight its potential utility in clinical practice. CONCLUSIONS: Our research presents a practical example of addressing clinical challenges through the All of Us Research Program data. The disparity mitigation framework we proposed is adaptable across various models and data modalities, demonstrating broad potential in clinical informatics.

OBJECTIVE: Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question. MATERIALS AND METHODS: Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system. RESULTS: The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort. DISCUSSION: Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data. CONCLUSION: This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

Objective: This study creates linear and generalized additive models (GAMs) of video-recorded two-dimensional hand motion (synonymously referred to as hand movements or hand kinematics) to predict expert-rated performance along a series of surgical motion scales. Background: Surgical performance assessments are costly and time consuming. Automatically quantifying hand motion may offload some burden of surgical coaching and intervention by automatically collecting features of psychomotor performance. Methods: Five experts rated anonymized video clips of benchtop suturing and tying tasks (n = 219) along four visual-analog (0-10) performance scales: fluidity of motion, motion economy, tissue handling, and hand coordination. Custom software tracked both participant hands across successive video frames and populated a robust feature set to train a series of predictive models to reproduce the expert ratings. Results: A GAM (which accounts for nonlinear effects) predicted fluidity of motion ratings with slope = 0.71, intercept = 1.98, and R2= 0.77 for clinicians of different experience levels. Fluidity of motion and motion economy models outperformed those created to predict hand coordination and tissue handling ratings. Conclusions: Hand motion tracking may not address all contextual features of surgical tasks. Future work will explore how well simulation-based models extrapolate to more dynamic settings of the operating room.

Motivation: : Association analysis of microbiome composition with disease-related outcomes provides invaluable knowledge towards understanding the roles of microbes in the underlying disease mechanisms. Proper analysis of sparse compositional microbiome data is challenging. Existing methods rely on strong assumptions on the data structure and fail to pinpoint the associated microbial communities. Results: : We develop a general framework to: (i) perform robust association tests for the microbial community that exhibits arbitrary inter-taxa dependencies; (ii) localize lineages on the taxonomic tree that are associated with covariates (e.g. disease status); and (iii) assess the overall association of the whole microbial community with the covariates. Unlike existing methods for microbiome association analysis, our framework does not make any distributional assumptions on the microbiome data; it allows for the adjustment of confounding variables and accommodates excessive zero observations; and it incorporates taxonomic information. We perform extensive simulation studies under a wide-range of scenarios to evaluate the new methods and demonstrate substantial power gain over existing methods. The advantages of the proposed framework are further demonstrated with real datasets from two microbiome studies. The relevant R package miLineage is publicly available. Availability and Implementation: : miLineage package, manual and tutorial are available at https://medschool.vanderbilt.edu/tang-lab/software/miLineage . Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

OBJECTIVE: Predictive analytics create opportunities to incorporate personalized risk estimates into clinical decision support. Models must be well calibrated to support decision-making, yet calibration deteriorates over time. This study explored the influence of modeling methods on performance drift and connected observed drift with data shifts in the patient population. MATERIALS AND METHODS: Using 2003 admissions to Department of Veterans Affairs hospitals nationwide, we developed 7 parallel models for hospital-acquired acute kidney injury using common regression and machine learning methods, validating each over 9 subsequent years. RESULTS: Discrimination was maintained for all models. Calibration declined as all models increasingly overpredicted risk. However, the random forest and neural network models maintained calibration across ranges of probability, capturing more admissions than did the regression models. The magnitude of overprediction increased over time for the regression models while remaining stable and small for the machine learning models. Changes in the rate of acute kidney injury were strongly linked to increasing overprediction, while changes in predictor-outcome associations corresponded with diverging patterns of calibration drift across methods. CONCLUSIONS: Efficient and effective updating protocols will be essential for maintaining accuracy of, user confidence in, and safety of personalized risk predictions to support decision-making. Model updating protocols should be tailored to account for variations in calibration drift across methods and respond to periods of rapid performance drift rather than be limited to regularly scheduled annual or biannual intervals.

MOTIVATION: Recent advances in sequencing technology have made it possible to obtain high-throughput data on the composition of microbial communities and to study the effects of dysbiosis on the human host. Analysis of pairwise intersample distances quantifies the association between the microbiome diversity and covariates of interest (e.g. environmental factors, clinical outcomes, treatment groups). In the design of these analyses, multiple choices for distance metrics are available. Most distance-based methods, however, use a single distance and are underpowered if the distance is poorly chosen. In addition, distance-based tests cannot flexibly handle confounding variables, which can result in excessive false-positive findings. RESULTS: We derive presence-weighted UniFrac to complement the existing UniFrac distances for more powerful detection of the variation in species richness. We develop PERMANOVA-S, a new distance-based method that tests the association of microbiome composition with any covariates of interest. PERMANOVA-S improves the commonly-used Permutation Multivariate Analysis of Variance (PERMANOVA) test by allowing flexible confounder adjustments and ensembling multiple distances. We conducted extensive simulation studies to evaluate the performance of different distances under various patterns of association. Our simulation studies demonstrate that the power of the test relies on how well the selected distance captures the nature of the association. The PERMANOVA-S unified test combines multiple distances and achieves good power regardless of the patterns of the underlying association. We demonstrate the usefulness of our approach by reanalyzing several real microbiome datasets. AVAILABILITY AND IMPLEMENTATION: miProfile software is freely available at https://medschool.vanderbilt.edu/tang-lab/software/miProfile CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.