Nikhil Patel

Gregory Kell, Angus Roberts, Serge Umansky et al.

Clinical question answering systems have the potential to provide clinicians with relevant and timely answers to their questions. Nonetheless, despite the advances that have been made, adoption of these systems in clinical settings has been slow. One issue is a lack of question-answering datasets which reflect the real-world needs of health professionals. In this work, we present RealMedQA, a dataset of realistic clinical questions generated by humans and an LLM. We describe the process for generating and verifying the QA pairs and assess several QA models on BioASQ and RealMedQA to assess the relative difficulty of matching answers to questions. We show that the LLM is more cost-efficient for generating "ideal" QA pairs. Additionally, we achieve a lower lexical similarity between questions and answers than BioASQ which provides an additional challenge to the top two QA models, as per the results. We release our code and our dataset publicly to encourage further research.

Zelong Liu, Andrew Tieu, Nikhil Patel et al.

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present VIsualization and Segmentation Masked AutoEncoder (VIS-MAE), novel model weights specifically designed for medical imaging. Specifically, VIS-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET,X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VIS-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications. In addition, VIS-MAE has improved label efficiency as it can achieve similar performance to other models with a reduced amount of labeled training data (50% or 80%) compared to other pre-trained weights. VIS-MAE represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload. The source code of this work is available at https://github.com/lzl199704/VIS-MAE.

Jingting Yao, Artan Kaso, Nikhil Patel et al.

Current magnetic resonance imaging (MRI) requires the subject to remain stationary to limit motion artifacts and avoid unwanted field-induced brain stimulation. However, imaging during large-scale motion could enable studies in which motion itself is central. One example is the study of brain networks involved in vestibular function, which senses head motion. Here, we demonstrate Moving MRI (mMRI), a system that enables imaging during large-scale motion by moving the subject and scanner together to minimize relative motion. We implemented a proof-of-concept platform using a compact, cryogen-free superconducting magnet mounted on a pneumatically actuated tilt mechanism that moves the magnet, gradients, and RF coil as a unit during scanning. Phantom and in vivo rat brain scans were acquired during repetitive tilting. We characterized artifacts arising from tilt-induced field shifts and residual subject-scanner motion, and partially reduced these effects. mMRI enables imaging during large-scale movement and may broaden access to naturalistic vestibular paradigms while providing a foundation for future human systems.

Alexander Zhou, Zelong Liu, Andrew Tieu et al.

In this retrospective study, we annotated 44 structures on two datasets: an internal dataset of 1,518 MRI sequences from 843 patients at the Mount Sinai Health System, and an external dataset of 397 MRI sequences from 263 patients for benchmarking. The internal dataset trained the nnU-Net model MRAnnotator, which demonstrated strong generalizability on the external dataset. MRAnnotator outperformed existing models such as TotalSegmentator MRI and MRSegmentator on both datasets, achieving an overall average Dice score of 0.878 on the internal dataset and 0.875 on the external set. Model weights are available on GitHub, and the external test set can be shared upon request.

Yue Dong, Han Li, Shen Li et al.

Large-scale recommendation systems are pivotal to process an immense volume of daily user interactions, requiring the effective modeling of high cardinality and heterogeneous features to ensure accurate predictions. In prior work, we introduced Hierarchical Sequential Transducers (HSTU), an attention-based architecture for modeling high cardinality, non-stationary streaming recommendation data, providing good scaling law in the generative recommender framework (GR). Recent studies and experiments demonstrate that attending to longer user history sequences yields significant metric improvements. However, scaling sequence length is activation-heavy, necessitating parallelism solutions to effectively shard activation memory. In transformer-based LLMs, context parallelism (CP) is a commonly used technique that distributes computation along the sequence-length dimension across multiple GPUs, effectively reducing memory usage from attention activations. In contrast, production ranking models typically utilize jagged input tensors to represent user interaction features, introducing unique CP implementation challenges. In this work, we introduce context parallelism with jagged tensor support for HSTU attention, establishing foundational capabilities for scaling up sequence dimensions. Our approach enables a 5.3x increase in supported user interaction sequence length, while achieving a 1.55x scaling factor when combined with Distributed Data Parallelism (DDP).

Megan Gu, Chloe Qianhui Zhao, Claire Liu et al. · cmu

Our study introduces an automated system leveraging large language models (LLMs) to assess the effectiveness of five key tutoring strategies: 1. giving effective praise, 2. reacting to errors, 3. determining what students know, 4. helping students manage inequity, and 5. responding to negative self-talk. Using a public dataset from the Teacher-Student Chatroom Corpus, our system classifies each tutoring strategy as either being employed as desired or undesired. Our study utilizes GPT-3.5 with few-shot prompting to assess the use of these strategies and analyze tutoring dialogues. The results show that for the five tutoring strategies, True Negative Rates (TNR) range from 0.655 to 0.738, and Recall ranges from 0.327 to 0.432, indicating that the model is effective at excluding incorrect classifications but struggles to consistently identify the correct strategy. The strategy \textit{helping students manage inequity} showed the highest performance with a TNR of 0.738 and Recall of 0.432. The study highlights the potential of LLMs in tutoring strategy analysis and outlines directions for future improvements, including incorporating more advanced models for more nuanced feedback.

Gregory Kell, Angus Roberts, Serge Umansky et al.

Objective: Question answering (QA) systems have the potential to improve the quality of clinical care by providing health professionals with the latest and most relevant evidence. However, QA systems have not been widely adopted. This systematic review aims to characterize current medical QA systems, assess their suitability for healthcare, and identify areas of improvement. Materials and methods: We searched PubMed, IEEE Xplore, ACM Digital Library, ACL Anthology and forward and backward citations on 7th February 2023. We included peer-reviewed journal and conference papers describing the design and evaluation of biomedical QA systems. Two reviewers screened titles, abstracts, and full-text articles. We conducted a narrative synthesis and risk of bias assessment for each study. We assessed the utility of biomedical QA systems. Results: We included 79 studies and identified themes, including question realism, answer reliability, answer utility, clinical specialism, systems, usability, and evaluation methods. Clinicians' questions used to train and evaluate QA systems were restricted to certain sources, types and complexity levels. No system communicated confidence levels in the answers or sources. Many studies suffered from high risks of bias and applicability concerns. Only 8 studies completely satisfied any criterion for clinical utility, and only 7 reported user evaluations. Most systems were built with limited input from clinicians. Discussion: While machine learning methods have led to increased accuracy, most studies imperfectly reflected real-world healthcare information needs. Key research priorities include developing more realistic healthcare QA datasets and considering the reliability of answer sources, rather than merely focusing on accuracy.

Nikhil Patel, James Hale, Kanika Jindal et al.

We propose to take on the problem ofWord Sense Disambiguation (WSD). In language, words of the same form can take different meanings depending on context. While humans easily infer the meaning or gloss of such words by their context, machines stumble on this task.As such, we intend to replicated and expand upon the results of Huang et al.GlossBERT, a model which they design to disambiguate these words (Huang et al.,2019). Specifically, we propose the following augmentations: data-set tweaking(alpha hyper-parameter), ensemble methods, and replacement of BERT with BART andALBERT. The following GitHub repository contains all code used in this report, which extends on the code made available by Huang et al.

Hyundong Cho, Basel Shbita, Kartik Shenoy et al.

We present Viola, an open-domain dialogue system for spoken conversation that uses a topic-agnostic dialogue manager based on a simple generate-and-rank approach. Leveraging recent advances of generative dialogue systems powered by large language models, Viola fetches a batch of response candidates from various neural dialogue models trained with different datasets and knowledge-grounding inputs. Additional responses originating from template-based generators are also considered, depending on the user's input and detected entities. The hand-crafted generators build on a dynamic knowledge graph injected with rich content that is crawled from the web and automatically processed on a daily basis. Viola's response ranker is a fine-tuned polyencoder that chooses the best response given the dialogue history. While dedicated annotations for the polyencoder alone can indirectly steer it away from choosing problematic responses, we add rule-based safety nets to detect neural degeneration and a dedicated classifier to filter out offensive content. We analyze conversations that Viola took part in for the Alexa Prize Socialbot Grand Challenge 4 and discuss the strengths and weaknesses of our approach. Lastly, we suggest future work with a focus on curating conversation data specifcially for socialbots that will contribute towards a more robust data-driven socialbot.