Search

Polygenic risk scores (PRSs) can significantly enhance breast cancer risk prediction when combined with clinical risk factor data. While many studies have explored the value-add of PRSs, little is known about the potential impact of gene-by-gene or gene-by-environment interactions towards enhancing the risk discrimination capabilities of multi-modal models combining PRSs with clinical data. In this study, we integrated data on 318 individual genotype variants along with clinical data in a neural network to explore whether gene-by-gene (i.e., between individual variants) and/or gene-by-environment (between clinical risk factors and variants) interactions could be leveraged jointly during training to improve breast cancer risk prediction performance. We benchmarked our approach against a baseline model combining traditional univariate PRSs with clinical data in a logistic regression model and ran an interpretability analysis to identify feature interactions. While our model did not demonstrate improved performance over the baseline, we discovered 248 (<1%) statistically significant gene-by-gene and gene-by-environment interactions out of the ~53.6k possible feature pairs, the most contributory of which included rs6001930 (MKL1) and rs889312 (MAP3K1), with age and menopause being the most heavily interacting non-genetic risk factors. We also modeled the significant interactions as a network of highly connected features, suggesting that potential higher-order interactions are captured by the model. Although gene-by-environment (or gene-by-gene) interactions did not enhance breast cancer risk prediction performance in neural networks, our study provides evidence that these interactions can be leveraged by these models to inform their predictions. This study represents the first application of neural networks to screen for interactions impacting breast cancer risk using real-world data.

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propose MedAdapter, a unified post-hoc adapter for test-time adaptation of LLMs towards biomedical applications. Instead of fine-tuning the entire LLM, MedAdapter effectively adapts the original model by fine-tuning only a small BERT-sized adapter to rank candidate solutions generated by LLMs. Experiments demonstrate that MedAdapter effectively adapts both white-box and black-box LLMs in biomedical reasoning, achieving average performance improvements of 25.48% and 11.31%, respectively, without requiring extensive computational resources or sharing data with third parties. MedAdapter also yields superior performance when combined with train-time adaptation, highlighting a flexible and complementary solution to existing adaptation methods. Faced with the challenges of balancing model performance, computational resources, and data privacy, MedAdapter provides an efficient, privacy-preserving, cost-effective, and transparent solution for adapting LLMs to the biomedical domain., Comment: Work in Progress

Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BMRetriever also exhibits strong parameter efficiency, with the 410M variant outperforming baselines up to 11.7 times larger, and the 2B variant matching the performance of models with over 5B parameters. The training data and model checkpoints are released at \url{https://huggingface.co/BMRetriever} to ensure transparency, reproducibility, and application to new domains., Comment: Work in progress. The model and data will be uploaded to \url{https://github.com/ritaranx/BMRetriever}

We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs). RAM-EHR first collects multiple knowledge sources, converts them into text format, and uses dense retrieval to obtain information related to medical concepts. This strategy addresses the difficulties associated with complex names for the concepts. RAM-EHR then augments the local EHR predictive model co-trained with consistency regularization to capture complementary information from patient visits and summarized knowledge. Experiments on two EHR datasets show the efficacy of RAM-EHR over previous knowledge-enhanced baselines (3.4% gain in AUROC and 7.2% gain in AUPR), emphasizing the effectiveness of the summarized knowledge from RAM-EHR for clinical prediction tasks. The code will be published at \url{https://github.com/ritaranx/RAM-EHR}., Comment: ACL 2024 (Oral)

Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving. We propose EHRAgent, an LLM agent empowered with a code interface, to autonomously generate and execute code for multi-tabular reasoning within electronic health records (EHRs). First, we formulate an EHR question-answering task into a tool-use planning process, efficiently decomposing a complicated task into a sequence of manageable actions. By integrating interactive coding and execution feedback, EHRAgent learns from error messages and improves the originally generated code through iterations. Furthermore, we enhance the LLM agent by incorporating long-term memory, which allows EHRAgent to effectively select and build upon the most relevant successful cases from past experiences. Experiments on three real-world multi-tabular EHR datasets show that EHRAgent outperforms the strongest baseline by up to 29.6% in success rate. EHRAgent leverages the emerging few-shot learning capabilities of LLMs, enabling autonomous code generation and execution to tackle complex clinical tasks with minimal demonstrations., Comment: Work in Progress

In the context of surgery, robots can provide substantial assistance by performing small, repetitive tasks such as suturing, needle exchange, and tissue retraction, thereby enabling surgeons to concentrate on more complex aspects of the procedure. However, existing surgical task learning mainly pertains to rigid body interactions, whereas the advancement towards more sophisticated surgical robots necessitates the manipulation of soft bodies. Previous work focused on tissue phantoms for soft tissue task learning, which can be expensive and can be an entry barrier to research. Simulation environments present a safe and efficient way to learn surgical tasks before their application to actual tissue. In this study, we create a Robot Operating System (ROS)-compatible physics simulation environment with support for both rigid and soft body interactions within surgical tasks. Furthermore, we investigate the soft tissue interactions facilitated by the patient-side manipulator of the DaVinci surgical robot. Leveraging the pybullet physics engine, we simulate kinematics and establish anchor points to guide the robotic arm when manipulating soft tissue. Using demonstration-guided reinforcement learning (RL) algorithms, we investigate their performance in comparison to traditional reinforcement learning algorithms. Our in silico trials demonstrate a proof-of-concept for autonomous surgical soft tissue retraction. The results corroborate the feasibility of learning soft body manipulation through the application of reinforcement learning agents. This work lays the foundation for future research into the development and refinement of surgical robots capable of managing both rigid and soft tissue interactions. Code is available at https://github.com/amritpal-001/tissue_retract., Comment: 10 Pages, 5 figures, MICCAI 2023 conference (AECAI workshop)

Despite the myriad peer-reviewed papers demonstrating novel Artificial Intelligence (AI)-based solutions to COVID-19 challenges during the pandemic, few have made significant clinical impact. The impact of artificial intelligence during the COVID-19 pandemic was greatly limited by lack of model transparency. This systematic review examines the use of Explainable Artificial Intelligence (XAI) during the pandemic and how its use could overcome barriers to real-world success. We find that successful use of XAI can improve model performance, instill trust in the end-user, and provide the value needed to affect user decision-making. We introduce the reader to common XAI techniques, their utility, and specific examples of their application. Evaluation of XAI results is also discussed as an important step to maximize the value of AI-based clinical decision support systems. We illustrate the classical, modern, and potential future trends of XAI to elucidate the evolution of novel XAI techniques. Finally, we provide a checklist of suggestions during the experimental design process supported by recent publications. Common challenges during the implementation of AI solutions are also addressed with specific examples of potential solutions. We hope this review may serve as a guide to improve the clinical impact of future AI-based solutions., Comment: 23 pages, 13 figures, submitting to IEEE

Each year there are nearly 57 million deaths around the world, with over 2.7 million in the United States. Timely, accurate and complete death reporting is critical in public health, as institutions and government agencies rely on death reports to analyze vital statistics and to formulate responses to communicable diseases. Inaccurate death reporting may result in potential misdirection of public health policies. Determining the causes of death is, nevertheless, challenging even for experienced physicians. To facilitate physicians in accurately reporting causes of death, we present an advanced AI approach to determine a chronically ordered sequence of clinical conditions that lead to death, based on decedent's last hospital discharge record. The sequence of clinical codes on the death report is named as causal chain of death, coded in the tenth revision of International Statistical Classification of Diseases (ICD-10); in line with the ICD-9-CM Official Guidelines for Coding and Reporting, the priority-ordered clinical conditions on the discharge record are coded in ICD-9. We identify three challenges in proposing the causal chain of death: two versions of coding system in clinical codes, medical domain knowledge conflict, and data interoperability. To overcome the first challenge in this sequence-to-sequence problem, we apply neural machine translation models to generate target sequence. Along with three accuracy metrics, we evaluate the quality of generated sequences with the BLEU (BiLingual Evaluation Understudy) score and achieve 16.04 out of 100. To address the second challenge, we incorporate expert-verified medical domain knowledge as constraint in generating output sequence to exclude infeasible causal chains. Lastly, we demonstrate the usability of our work in a Fast Healthcare Interoperability Resources (FHIR) interface to address the third challenge., Comment: 11 pages, 8 figures, 8 tables. Updates: (1) Added Section II: Recent Work (2) Added three accuracy evaluation criteria (3) Re-run experiments of OpenNMT and updated the results and discussion in Section VI: Results and Discussion (4) Finished FHIR mobile app and updated Section VII: FHIR Interface (5) Revised Section VIII: Conclusion accordingly

Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols, treatment preference and etc. As the result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using three large-scale Chest X-ray datasets: first, we assessed the dataset bias using vanilla training baseline; second, we proposed a novel multi-source domain generalization model by (a) designing a new bias-regularized loss function; and (b) synthesizing new data for domain augmentation. We showed that our model significantly outperformed the baseline and other approaches on data from unseen domain in terms of accuracy and various bias measures, without retraining or finetuning. Our method is generally applicable to other biomedical data, providing new algorithms for training models robust to bias for big data analysis and applications. Demo training code is publicly available., Comment: 9 pages, 5 figures

Multiple cause-of-death data provides a valuable source of information that can be used to enhance health standards by predicting health related trajectories in societies with large populations. These data are often available in large quantities across U.S. states and require Big Data techniques to uncover complex hidden patterns. We design two different classes of models suitable for large-scale analysis of mortality data, a Hadoop-based ensemble of random forests trained over N-grams, and the DeepDeath, a deep classifier based on the recurrent neural network (RNN). We apply both classes to the mortality data provided by the National Center for Health Statistics and show that while both perform significantly better than the random classifier, the deep model that utilizes long short-term memory networks (LSTMs), surpasses the N-gram based models and is capable of learning the temporal aspect of the data without a need for building ad-hoc, expert-driven features.

The interaction between proteins and DNA is a key driving force in a significant number of biological processes such as transcriptional regulation, repair, recombination, splicing, and DNA modification. The identification of DNA-binding sites and the specificity of target proteins in binding to these regions are two important steps in understanding the mechanisms of these biological activities. A number of high-throughput technologies have recently emerged that try to quantify the affinity between proteins and DNA motifs. Despite their success, these technologies have their own limitations and fall short in precise characterization of motifs, and as a result, require further downstream analysis to extract useful and interpretable information from a haystack of noisy and inaccurate data. Here we propose MotifMark, a new algorithm based on graph theory and machine learning, that can find binding sites on candidate probes and rank their specificity in regard to the underlying transcription factor. We developed a pipeline to analyze experimental data derived from compact universal protein binding microarrays and benchmarked it against two of the most accurate motif search methods. Our results indicate that MotifMark can be a viable alternative technique for prediction of motif from protein binding microarrays and possibly other related high-throughput techniques.

Transcription factors (TFs) are macromolecules that bind to \textit{cis}-regulatory specific sub-regions of DNA promoters and initiate transcription. Finding the exact location of these binding sites (aka motifs) is important in a variety of domains such as drug design and development. To address this need, several \textit{in vivo} and \textit{in vitro} techniques have been developed so far that try to characterize and predict the binding specificity of a protein to different DNA loci. The major problem with these techniques is that they are not accurate enough in prediction of the binding affinity and characterization of the corresponding motifs. As a result, downstream analysis is required to uncover the locations where proteins of interest bind. Here, we propose DeeperBind, a long short term recurrent convolutional network for prediction of protein binding specificities with respect to DNA probes. DeeperBind can model the positional dynamics of probe sequences and hence reckons with the contributions made by individual sub-regions in DNA sequences, in an effective way. Moreover, it can be trained and tested on datasets containing varying-length sequences. We apply our pipeline to the datasets derived from protein binding microarrays (PBMs), an in-vitro high-throughput technology for quantification of protein-DNA binding preferences, and present promising results. To the best of our knowledge, this is the most accurate pipeline that can predict binding specificities of DNA sequences from the data produced by high-throughput technologies through utilization of the power of deep learning for feature generation and positional dynamics modeling., Comment: in 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Cancer survival prediction is an active area of research that can help prevent unnecessary therapies and improve patient's quality of life. Gene expression profiling is being widely used in cancer studies to discover informative biomarkers that aid predict different clinical endpoint prediction. We use multiple modalities of data derived from RNA deep-sequencing (RNA-seq) to predict survival of cancer patients. Despite the wealth of information available in expression profiles of cancer tumors, fulfilling the aforementioned objective remains a big challenge, for the most part, due to the paucity of data samples compared to the high dimension of the expression profiles. As such, analysis of transcriptomic data modalities calls for state-of-the-art big-data analytics techniques that can maximally use all the available data to discover the relevant information hidden within a significant amount of noise. In this paper, we propose a pipeline that predicts cancer patients' survival by exploiting the structure of the input (manifold learning) and by leveraging the unlabeled samples using Laplacian support vector machines, a graph-based semi supervised learning (GSSL) paradigm. We show that under certain circumstances, no single modality per se will result in the best accuracy and by fusing different models together via a stacked generalization strategy, we may boost the accuracy synergistically. We apply our approach to two cancer datasets and present promising results. We maintain that a similar pipeline can be used for predictive tasks where labeled samples are expensive to acquire., Comment: in 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Prediction of survival for cancer patients is an open area of research. However, many of these studies focus on datasets with a large number of patients. We present a novel method that is specifically designed to address the challenge of data scarcity, which is often the case for cancer datasets. Our method is able to use unlabeled data to improve classification by adopting a semi-supervised training approach to learn an ensemble classifier. The results of applying our method to three cancer datasets show the promise of semi-supervised learning for prediction of cancer survival.