MOTIVATION: Large-scale bioinformatics analyses increasingly require collaboration across multiple cohorts and institutions, yet existing workflows often rely on data co-localization, which is slow, difficult to scale, and raises privacy concerns. We present a privacy-preserving federated analytics framework that enables secure statistical analysis across distributed datasets without transferring raw data, by performing all computations on encrypted data via cryptographic methods. RESULTS: We evaluate the framework by validating polygenic risk scores and conducting meta-analyses on two real-world cohorts. The proposed solution achieves over 99.9% accuracy relative to plaintext analyses, while maintaining scalable runtime performance with increasing data size and number of participating sites. These results demonstrate the feasibility of secure federated analytics for practical bioinformatics applications involving sensitive data.

Deep learning models are increasingly used for making predictions based on clinical time-series data, but model generalization remains a challenge. Continual learning approaches, which preserve representations while learning new distributions, are suitable for addressing this challenge. We propose Continual Bayesian Long Short Term Memory (C-BLSTM), a continual learning algorithm based on the Bayesian LSTM model for domain incremental learning. C-BLSTM continually learns a sequence of tasks by combining architectural pruning, variational inference-based regularization, and coreset replay strategies. In extensive experiments on two public electronic medical record datasets for mortality prediction, we show that C-BLSTM outperforms many state-of-the-art continual learning approaches. Further, we apply the C-BLSTM to two real-world clinical time series datasets for prediction of readmission risk in patients with heart failure and glycated haemoglobin outcomes in patients with type 2 diabetes. First, we show that these datasets exhibit domain incremental characteristics with significant drifts in their marginal distributions and moderate drifts in their conditional distributions. Then, we demonstrate that the C-BLSTM improves generalization in five diverse real-world scenarios spanning temporal, site, device, case mix, and ethnicity shifts, both in terms of performance and reliability of predictions.

There is increasing interest in data-driven approaches for recommending optimal treatment strategies in many chronic disease management and critical care applications. Reinforcement learning methods are well-suited to this sequential decision-making problem, but must be trained and evaluated exclusively on retrospective medical record datasets as direct online exploration is unsafe and infeasible. Despite this requirement, the vast majority of treatment optimization studies use off-policy RL methods (e.g., Double Deep Q Networks (DDQN) or its variants) that are known to perform poorly in purely offline settings. Recent advances in offline RL, such as Conservative Q-Learning (CQL), offer a suitable alternative. But there remain challenges in adapting these approaches to real-world applications where suboptimal examples dominate the retrospective dataset and strict safety constraints need to be satisfied. In this work, we introduce a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training. We perform extensive experiments on two real-world tasks for diabetes and sepsis treatment optimization to compare performance of the proposed approach against prominent off-policy and offline RL baselines (DDQN and CQL). Across a range of principled and clinically relevant metrics, we show that our proposed approach enables substantial improvements in expected health outcomes and in consistency with relevant practice and safety guidelines.

Accurate disease diagnosis requires objective assessment of clinical image quality. Automated image quality assessment (IQA) could enhance screening and diagnosis workflows. However, development of generalizable quality assessment tools requires large labeled clinical image datasets from different sites. Obtaining these datasets is often infeasible; and quality indicators may vary with acquisition settings due to domain shift. We introduce a minimally-supervised image quality assessment (MIQA) approach that can learn effectively with small datasets and limited labels in class-imbalanced domain shift scenarios. We formulate the IQA task as an anomaly detection problem, and use a small number of target domain images to identify a compact subset of source domain data for better representation of acceptable quality features. For this compact source domain dataset, we extract features with a pre-trained CNN, perform adaptive feature selection, and develop a one-class classifier to detect poor quality images. We evaluate our approach on two ophthalmology datasets, and show substantial AUC gains and improved cross-site generalizability over competitive baselines. Our approach has implications for improved image quality audit in many clinical settings.

While high-resolution pathology images lend themselves well to 'data hungry' deep learning algorithms, obtaining exhaustive annotations on these images for learning is a major challenge. In this article, we propose a self-supervised convolutional neural network (CNN) framework to leverage unlabeled data for learning generalizable and domain invariant representations in pathology images. Our proposed framework, termed as Self-Path, employs multi-task learning where the main task is tissue classification and pretext tasks are a variety of self-supervised tasks with labels inherent to the input images. We introduce novel pathology-specific self-supervision tasks that leverage contextual, multi-resolution and semantic features in pathology images for semi-supervised learning and domain adaptation. We investigate the effectiveness of Self-Path on 3 different pathology datasets. Our results show that Self-Path with the pathology-specific pretext tasks achieves state-of-the-art performance for semi-supervised learning when small amounts of labeled data are available. Further, we show that Self-Path improves domain adaptation for histopathology image classification when there is no labeled data available for the target domain. This approach can potentially be employed for other applications in computational pathology, where annotation budget is often limited or large amount of unlabeled image data is available.

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data. Compared to the state-of-the-art methods, our approach does not require label embed-dings as part of the input and therefore lends itself nicely to a wide range of model architectures. In addition, our architecture computes contextual distances between words and labels to avoid adding contextual windows, thus reducing memory footprint. We validate the approach on established spoken dialogue datasets and show that it can achieve state-of-the-art performance with much fewer trainable parameters.

A common feature in biological neuromuscular systems is the redundancy in joint actuation. Understanding how these redundancies are resolved in typical joint movements has been a long-standing problem in biomechanics, neuroscience and prosthetics. Many empirical studies have uncovered neural, mechanical and energetic aspects of how humans resolve these degrees of freedom to actuate leg joints for common tasks like walking. However, a unifying theoretical framework that explains the many independent empirical observations and predicts individual muscle and tendon contributions to joint actuation is yet to be established. Here we develop a computational framework to address how the ankle joint actuation problem is resolved by the neuromuscular system in walking. Our framework is founded upon the proposal that a consideration of both neural control and leg muscle-tendon morphology is critical to obtain predictive, mechanistic insight into individual muscle and tendon contributions to joint actuation. We examine kinetic, kinematic and electromyographic data from healthy walking subjects to find that human leg muscle-tendon morphology and neural activations enable a metabolically optimal realization of biological ankle mechanics in walking. This optimal realization (a) corresponds to independent empirical observations of operation and performance of the soleus and gastrocnemius muscles, (b) gives rise to an efficient load-sharing amongst ankle muscle-tendon units and (c) causes soleus and gastrocnemius muscle fibers to take on distinct mechanical roles of force generation and power production at the end of stance phase in walking. The framework outlined here suggests that the dynamical interplay between leg structure and neural control may be key to the high walking economy of humans, and has implications as a means to obtain insight into empirically inaccessible features of individual muscle and tendons in biomechanical tasks.