Ramakanth Kavuluru

Yuhang Jiang, Ramakanth Kavuluru

Combination drug therapies are treatment regimens that involve two or more drugs, administered more commonly for patients with cancer, HIV, malaria, or tuberculosis. Currently there are over 350K articles in PubMed that use the "combination drug therapy" MeSH heading with at least 10K articles published per year over the past two decades. Extracting combination therapies from scientific literature inherently constitutes an $n$-ary relation extraction problem. Unlike in the general $n$-ary setting where $n$ is fixed (e.g., drug-gene-mutation relations where $n=3$), extracting combination therapies is a special setting where $n \geq 2$ is dynamic, depending on each instance. Recently, Tiktinsky et al. (NAACL 2022) introduced a first of its kind dataset, CombDrugExt, for extracting such therapies from literature. Here, we use a sequence-to-sequence style end-to-end extraction method to achieve an F1-Score of $66.7\%$ on the CombDrugExt test set for positive (or effective) combinations. This is an absolute $\approx 5\%$ F1-score improvement even over the prior best relation classification score with spotted drug entities (hence, not end-to-end). Thus our effort introduces a state-of-the-art first model for end-to-end extraction that is already superior to the best prior non end-to-end model for this task. Our model seamlessly extracts all drug entities and relations in a single pass and is highly suitable for dynamic $n$-ary extraction scenarios.

Shashank Gupta, Xuguang Ai, Ramakanth Kavuluru

End-to-end relation extraction (E2ERE) is an important and realistic application of natural language processing (NLP) in biomedicine. In this paper, we aim to compare three prevailing paradigms for E2ERE using a complex dataset focused on rare diseases involving discontinuous and nested entities. We use the RareDis information extraction dataset to evaluate three competing approaches (for E2ERE): NER $\rightarrow$ RE pipelines, joint sequence to sequence models, and generative pre-trained transformer (GPT) models. We use comparable state-of-the-art models and best practices for each of these approaches and conduct error analyses to assess their failure modes. Our findings reveal that pipeline models are still the best, while sequence-to-sequence models are not far behind; GPT models with eight times as many parameters are worse than even sequence-to-sequence models and lose to pipeline models by over 10 F1 points. Partial matches and discontinuous entities caused many NER errors contributing to lower overall E2E performances. We also verify these findings on a second E2ERE dataset for chemical-protein interactions. Although generative LM-based methods are more suitable for zero-shot settings, when training data is available, our results show that it is better to work with more conventional models trained and tailored for E2ERE. More innovative methods are needed to marry the best of the both worlds from smaller encoder-decoder pipeline models and the larger GPT models to improve E2ERE. As of now, we see that well designed pipeline models offer substantial performance gains at a lower cost and carbon footprint for E2ERE. Our contribution is also the first to conduct E2ERE for the RareDis dataset.

Xuguang Ai, Ramakanth Kavuluru

End-to-end relation extraction (E2ERE) is an important task in information extraction, more so for biomedicine as scientific literature continues to grow exponentially. E2ERE typically involves identifying entities (or named entity recognition (NER)) and associated relations, while most RE tasks simply assume that the entities are provided upfront and end up performing relation classification. E2ERE is inherently more difficult than RE alone given the potential snowball effect of errors from NER leading to more errors in RE. A complex dataset in biomedical E2ERE is the ChemProt dataset (BioCreative VI, 2017) that identifies relations between chemical compounds and genes/proteins in scientific literature. ChemProt is included in all recent biomedical natural language processing benchmarks including BLUE, BLURB, and BigBio. However, its treatment in these benchmarks and in other separate efforts is typically not end-to-end, with few exceptions. In this effort, we employ a span-based pipeline approach to produce a new state-of-the-art E2ERE performance on the ChemProt dataset, resulting in $> 4\%$ improvement in F1-score over the prior best effort. Our results indicate that a straightforward fine-grained tokenization scheme helps span-based approaches excel in E2ERE, especially with regards to handling complex named entities. Our error analysis also identifies a few key failure modes in E2ERE for ChemProt.

Yuhang Jiang, Ramakanth Kavuluru

As COVID-19 ravages the world, social media analytics could augment traditional surveys in assessing how the pandemic evolves and capturing consumer chatter that could help healthcare agencies in addressing it. This typically involves mining disclosure events that mention testing positive for the disease or discussions surrounding perceptions and beliefs in preventative or treatment options. The 2020 shared task on COVID-19 event extraction (conducted as part of the W-NUT workshop during the EMNLP conference) introduced a new Twitter dataset for benchmarking event extraction from COVID-19 tweets. In this paper, we cast the problem of event extraction as extractive question answering using recent advances in continuous prompting in language models. On the shared task test dataset, our approach leads to over 5% absolute micro-averaged F1-score improvement over prior best results, across all COVID-19 event slots. Our ablation study shows that continuous prompts have a major impact on the eventual performance.

Md Sultan Al Nahian, Ramakanth Kavuluru

Extractive question answering over clinical text is a crucial need to help deal with the deluge of clinical text generated in hospitals. While encoder models (e.g., BERT) have been popular for this reading comprehension task, recently encoder-decoder models (e.g., T5) are on the rise. There is also the emergence of preference optimization techniques to align decoder-only LLMs with human preferences. In this paper, we combine encoder-decoder models with the direct preference optimization (DPO) method to improve over prior state of the art for the RadQA radiology question answering task by 12-15 F1 points. To the best of our knowledge, this effort is the first to show that DPO method also works for reading comprehension via novel heuristics to generate preference data without human inputs.

Aviv Brokman, Xuguang Ai, Yuhang Jiang et al.

Objective: Zero-shot methodology promises to cut down on costs of dataset annotation and domain expertise needed to make use of NLP. Generative large language models trained to align with human goals have achieved high zero-shot performance across a wide variety of tasks. As of yet, it is unclear how well these models perform on biomedical relation extraction (RE). To address this knowledge gap, we explore patterns in the performance of OpenAI LLMs across a diverse sampling of RE tasks. Methods: We use OpenAI GPT-4-turbo and OpenAI's reasoning models o1 and GPT-OSS to conduct end-to-end RE experiments on seven datasets. We use the JSON generation capabilities of GPT models to generate structured output in two ways: (1) by defining an explicit schema describing the structure of relations, and (2) using a setting that infers the structure from the prompt language. Results: Our work is the first to study and compare the performance of the GPT-4, o1 and GPT-OSS for the end-to-end zero-shot biomedical RE task across a broad array of datasets. We found the zero-shot performances to be proximal to that of fine-tuned methods. The limitations of this approach are that it performs poorly on instances containing many relations and errs on the boundaries of textual mentions. Conclusion: LLMs exhibit promising zero-shot capabilities in complex biomedical RE tasks, offering competitive performance with reduced dataset curation costs and NLP modeling needs but with increased perpetual compute costs. Addressing the limitations we identify could further boost reliability. The code, data, and prompts for all our experiments are publicly available for additional benchmarking by the community: https://github.com/bionlproc/ZeroShotRE

Jiho Noh, Ramakanth Kavuluru

Biomedical word embeddings are usually pre-trained on free text corpora with neural methods that capture local and global distributional properties. They are leveraged in downstream tasks using various neural architectures that are designed to optimize task-specific objectives that might further tune such embeddings. Since 2018, however, there is a marked shift from these static embeddings to contextual embeddings motivated by language models (e.g., ELMo, transformers such as BERT, and ULMFiT). These dynamic embeddings have the added benefit of being able to distinguish homonyms and acronyms given their context. However, static embeddings are still relevant in low resource settings (e.g., smart devices, IoT elements) and to study lexical semantics from a computational linguistics perspective. In this paper, we jointly learn word and concept embeddings by first using the skip-gram method and further fine-tuning them with correlational information manifesting in co-occurring Medical Subject Heading (MeSH) concepts in biomedical citations. This fine-tuning is accomplished with the BERT transformer architecture in the two-sentence input mode with a classification objective that captures MeSH pair co-occurrence. In essence, we repurpose a transformer architecture (typically used to generate dynamic embeddings) to improve static embeddings using concept correlations. We conduct evaluations of these tuned static embeddings using multiple datasets for word relatedness developed by previous efforts. Without selectively culling concepts and terms (as was pursued by previous efforts), we believe we offer the most exhaustive evaluation of static embeddings to date with clear performance improvements across the board. We provide our code and embeddings for public use for downstream applications and research endeavors: https://github.com/bionlproc/BERT-CRel-Embeddings

Jiho Noh, Ramakanth Kavuluru

Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to be incorporated. In this paper, we present a document reranking approach that combines neural query-document matching and text summarization toward such retrieval scenarios. Our architecture builds on the basic BERT model with three specific components for reranking: (a). document-query matching (b). keyword extraction and (c). facet-conditioned abstractive summarization. The outcomes of (b) and (c) are used to essentially transform a candidate document into a concise summary that can be compared with the query at hand to compute a relevance score. Component (a) directly generates a matching score of a candidate document for a query. The full architecture benefits from the complementary potential of document-query matching and the novel document transformation approach based on summarization along PM facets. Evaluations using NIST's TREC-PM track datasets (2017--2019) show that our model achieves state-of-the-art performance. To foster reproducibility, our code is made available here: https://github.com/bionlproc/text-summ-for-doc-retrieval.

Aviv Brokman, Ramakanth Kavuluru

Cutting edge techniques developed in the general NLP domain are often subsequently applied to the high-value, data-rich biomedical domain. The past few years have seen generative language models (LMs), instruction finetuning, and few-shot learning become foci of NLP research. As such, generative LMs pretrained on biomedical corpora have proliferated and biomedical instruction finetuning has been attempted as well, all with the hope that domain specificity improves performance on downstream tasks. Given the nontrivial effort in training such models, we investigate what, if any, benefits they have in the key biomedical NLP task of relation extraction. Specifically, we address two questions: (1) Do LMs trained on biomedical corpora outperform those trained on general domain corpora? (2) Do models instruction finetuned on biomedical datasets outperform those finetuned on assorted datasets or those simply pretrained? We tackle these questions using existing LMs, testing across four datasets. In a surprising result, general-domain models typically outperformed biomedical-domain models. However, biomedical instruction finetuning improved performance to a similar degree as general instruction finetuning, despite having orders of magnitude fewer instructions. Our findings suggest it may be more fruitful to focus research effort on larger-scale biomedical instruction finetuning of general LMs over building domain-specific biomedical LMs

Motasem S Obeidat, Md Sultan Al Nahian, Ramakanth Kavuluru

Recognizing spans of biomedical concepts and their types (e.g., drug or gene) in free text, often called biomedical named entity recognition (NER), is a basic component of information extraction (IE) pipelines. Without a strong NER component, other applications, such as knowledge discovery and information retrieval, are not practical. State-of-the-art in NER shifted from traditional ML models to deep neural networks with transformer-based encoder models (e.g., BERT) emerging as the current standard. However, decoder models (also called large language models or LLMs) are gaining traction in IE. But LLM-driven NER often ignores positional information due to the generative nature of decoder models. Furthermore, they are computationally very expensive (both in inference time and hardware needs). Hence, it is worth exploring if they actually excel at biomedical NER and assess any associated trade-offs (performance vs efficiency). This is exactly what we do in this effort employing the same BIO entity tagging scheme (that retains positional information) using five different datasets with varying proportions of longer entities. Our results show that the LLMs chosen (Mistral and Llama: 8B range) often outperform best encoder models (BERT-(un)cased, BiomedBERT, and DeBERTav3: 300M range) by 2-8% in F-scores except for one dataset, where they equal encoder performance. This gain is more prominent among longer entities of length >= 3 tokens. However, LLMs are one to two orders of magnitude more expensive at inference time and may need cost prohibitive hardware. Thus, when performance differences are small or real time user feedback is needed, encoder models might still be more suitable than LLMs.

Monika Jain, Raghava Mutharaju, Kuldeep Singh et al.

Relation extraction (RE) is a well-known NLP application often treated as a sentence- or document-level task. However, a handful of recent efforts explore it across documents or in the cross-document setting (CrossDocRE). This is distinct from the single document case because different documents often focus on disparate themes, while text within a document tends to have a single goal. Linking findings from disparate documents to identify new relationships is at the core of the popular literature-based knowledge discovery paradigm in biomedicine and other domains. Current CrossDocRE efforts do not consider domain knowledge, which are often assumed to be known to the reader when documents are authored. Here, we propose a novel approach, KXDocRE, that embed domain knowledge of entities with input text for cross-document RE. Our proposed framework has three main benefits over baselines: 1) it incorporates domain knowledge of entities along with documents' text; 2) it offers interpretability by producing explanatory text for predicted relations between entities 3) it improves performance over the prior methods.

Yuhang Jiang, Ramakanth Kavuluru

Relation extraction (RE) is a standard information extraction task playing a major role in downstream applications such as knowledge discovery and question answering. Although decoder-only large language models are excelling in generative tasks, smaller encoder models are still the go to architecture for RE. In this paper, we revisit fine-tuning such smaller models using a novel dual-encoder architecture with a joint contrastive and cross-entropy loss. Unlike previous methods that employ a fixed linear layer for predicate representations, our approach uses a second encoder to compute instance-specific predicate representations by infusing them with real entity spans from corresponding input instances. We conducted experiments on two biomedical RE datasets and two general domain datasets. Our approach achieved F1 score improvements ranging from 1% to 2% over state-of-the-art methods with a simple but elegant formulation. Ablation studies justify the importance of various components built into the proposed architecture.

Md Sultan Al Nahian, Chris Delcher, Daniel Harris et al.

The ability to predict drug overdose risk from a patient's medical records is crucial for timely intervention and prevention. Traditional machine learning models have shown promise in analyzing longitudinal medical records for this task. However, recent advancements in large language models (LLMs) offer an opportunity to enhance prediction performance by leveraging their ability to process long textual data and their inherent prior knowledge across diverse tasks. In this study, we assess the effectiveness of Open AI's GPT-4o LLM in predicting drug overdose events using patients' longitudinal insurance claims records. We evaluate its performance in both fine-tuned and zero-shot settings, comparing them to strong traditional machine learning methods as baselines. Our results show that LLMs not only outperform traditional models in certain settings but can also predict overdose risk in a zero-shot setting without task-specific training. These findings highlight the potential of LLMs in clinical decision support, particularly for drug overdose risk prediction.

Patrick J. Ward, April M. Young, Svetla Slavova et al.

Surveillance of drug overdose deaths relies on death certificates for identification of the substances that caused death. Drugs and drug classes can be identified through the International Classification of Diseases, 10th Revision (ICD-10) codes present on death certificates. However, ICD-10 codes do not always provide high levels of specificity in drug identification. To achieve more fine-grained identification of substances on a death certificate, the free-text cause of death section, completed by the medical certifier, must be analyzed. Current methods for analyzing free-text death certificates rely solely on look-up tables for identifying specific substances, which must be frequently updated and maintained. To improve identification of drugs on death certificates, a deep learning named-entity recognition model was developed, which achieved an F1-score of 99.13%. This model can identify new drug misspellings and novel substances that are not present on current surveillance look-up tables, enhancing the surveillance of drug overdose deaths.

Sijia Liu, Andrew Wen, Liwei Wang et al.

While we pay attention to the latest advances in clinical natural language processing (NLP), we can notice some resistance in the clinical and translational research community to adopt NLP models due to limited transparency, interpretability, and usability. In this study, we proposed an open natural language processing development framework. We evaluated it through the implementation of NLP algorithms for the National COVID Cohort Collaborative (N3C). Based on the interests in information extraction from COVID-19 related clinical notes, our work includes 1) an open data annotation process using COVID-19 signs and symptoms as the use case, 2) a community-driven ruleset composing platform, and 3) a synthetic text data generation workflow to generate texts for information extraction tasks without involving human subjects. The corpora were derived from texts from three different institutions (Mayo Clinic, University of Kentucky, University of Minnesota). The gold standard annotations were tested with a single institution's (Mayo) ruleset. This resulted in performances of 0.876, 0.706, and 0.694 in F-scores for Mayo, Minnesota, and Kentucky test datasets, respectively. The study as a consortium effort of the N3C NLP subgroup demonstrates the feasibility of creating a federated NLP algorithm development and benchmarking platform to enhance multi-institution clinical NLP study and adoption. Although we use COVID-19 as a use case in this effort, our framework is general enough to be applied to other domains of interest in clinical NLP.

Sajjad Fouladvand, Jeffery Talbert, Linda P. Dwoskin et al.

Opioid Use Disorder (OUD) is a public health crisis costing the US billions of dollars annually in healthcare, lost workplace productivity, and crime. Analyzing longitudinal healthcare data is critical in addressing many real-world problems in healthcare. Leveraging the real-world longitudinal healthcare data, we propose a novel multi-stream transformer model called MUPOD for OUD identification. MUPOD is designed to simultaneously analyze multiple types of healthcare data streams, such as medications and diagnoses, by attending to segments within and across these data streams. Our model tested on the data from 392,492 patients with long-term back pain problems showed significantly better performance than the traditional models and recently developed deep learning models.

Gongbo Liang, Connor Greenwell, Yu Zhang et al.

A key challenge in training neural networks for a given medical imaging task is often the difficulty of obtaining a sufficient number of manually labeled examples. In contrast, textual imaging reports, which are often readily available in medical records, contain rich but unstructured interpretations written by experts as part of standard clinical practice. We propose using these textual reports as a form of weak supervision to improve the image interpretation performance of a neural network without requiring additional manually labeled examples. We use an image-text matching task to train a feature extractor and then fine-tune it in a transfer learning setting for a supervised task using a small labeled dataset. The end result is a neural network that automatically interprets imagery without requiring textual reports during inference. This approach can be applied to any task for which text-image pairs are readily available. We evaluate our method on three classification tasks and find consistent performance improvements, reducing the need for labeled data by 67%-98%.

Tung Tran, Ramakanth Kavuluru, Halil Kilicoglu

Preventable adverse events as a result of medical errors present a growing concern in the healthcare system. As drug-drug interactions (DDIs) may lead to preventable adverse events, being able to extract DDIs from drug labels into a machine-processable form is an important step toward effective dissemination of drug safety information. In this study, we tackle the problem of jointly extracting drugs and their interactions, including interaction outcome, from drug labels. Our deep learning approach entails composing various intermediate representations including sequence and graph based context, where the latter is derived using graph convolutions (GC) with a novel attention-based gating mechanism (holistically called GCA). These representations are then composed in meaningful ways to handle all subtasks jointly. To overcome scarcity in training data, we additionally propose transfer learning by pre-training on related DDI data. Our model is trained and evaluated on the 2018 TAC DDI corpus. Our GCA model in conjunction with transfer learning performs at 39.20% F1 and 26.09% F1 on entity recognition (ER) and relation extraction (RE) respectively on the first official test set and at 45.30% F1 and 27.87% F1 on ER and RE respectively on the second official test set corresponding to an improvement over our prior best results by up to 6 absolute F1 points. After controlling for available training data, our model exhibits state-of-the-art performance by improving over the next comparable best outcome by roughly three F1 points in ER and 1.5 F1 points in RE evaluation across two official test sets.

Tung Tran, Ramakanth Kavuluru, Halil Kilicoglu

Preventable adverse drug reactions as a result of medical errors present a growing concern in modern medicine. As drug-drug interactions (DDIs) may cause adverse reactions, being able to extracting DDIs from drug labels into machine-readable form is an important effort in effectively deploying drug safety information. The DDI track of TAC 2018 introduces two large hand-annotated test sets for the task of extracting DDIs from structured product labels with linkage to standard terminologies. Herein, we describe our approach to tackling tasks one and two of the DDI track, which corresponds to named entity recognition (NER) and sentence-level relation extraction respectively. Namely, our approach resembles a multi-task learning framework designed to jointly model various sub-tasks including NER and interaction type and outcome prediction. On NER, our system ranked second (among eight teams) at 33.00% and 38.25% F1 on Test Sets 1 and 2 respectively. On relation extraction, our system ranked second (among four teams) at 21.59% and 23.55% on Test Sets 1 and 2 respectively.

Tung Tran, Ramakanth Kavuluru

Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model. Several recent efforts, under the theme of end-to-end RE, seek to exploit inter-task correlations by modeling both NER and RE tasks jointly. Earlier work in this area commonly reduces the task to a table-filling problem wherein an additional expensive decoding step involving beam search is applied to obtain globally consistent cell labels. In efforts that do not employ table-filling, global optimization in the form of CRFs with Viterbi decoding for the NER component is still necessary for competitive performance. We introduce a novel neural architecture utilizing the table structure, based on repeated applications of 2D convolutions for pooling local dependency and metric-based features, that improves on the state-of-the-art without the need for global optimization. We validate our model on the ADE and CoNLL04 datasets for end-to-end RE and demonstrate $\approx 1\%$ gain (in F-score) over prior best results with training and testing times that are seven to ten times faster --- the latter highly advantageous for time-sensitive end user applications.

Yifan Peng, Anthony Rios, Ramakanth Kavuluru et al.

Text mining the relations between chemicals and proteins is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical-protein relations in running text (PubMed abstracts). This manuscript describes our submission, which is an ensemble of three systems, including a Support Vector Machine, a Convolutional Neural Network, and a Recurrent Neural Network. Their output is combined using a decision based on majority voting or stacking. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an f-score of 0.6410, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature. Our submission achieved the highest performance in the task during the 2017 challenge.

A. K. M. Sabbir, Antonio Jimeno Yepes, Ramakanth Kavuluru

Biomedical word sense disambiguation (WSD) is an important intermediate task in many natural language processing applications such as named entity recognition, syntactic parsing, and relation extraction. In this paper, we employ knowledge-based approaches that also exploit recent advances in neural word/concept embeddings to improve over the state-of-the-art in biomedical WSD using the MSH WSD dataset as the test set. Our methods involve weak supervision - we do not use any hand-labeled examples for WSD to build our prediction models; however, we employ an existing well known named entity recognition and concept mapping program, MetaMap, to obtain our concept vectors. Over the MSH WSD dataset, our linear time (in terms of numbers of senses and words in the test instance) method achieves an accuracy of 92.24% which is an absolute 3% improvement over the best known results obtained via unsupervised or knowledge-based means. A more expensive approach that we developed relies on a nearest neighbor framework and achieves an accuracy of 94.34%. Employing dense vector representations learned from unlabeled free text has been shown to benefit many language processing tasks recently and our efforts show that biomedical WSD is no exception to this trend. For a complex and rapidly evolving domain such as biomedicine, building labeled datasets for larger sets of ambiguous terms may be impractical. Here, we show that weak supervision that leverages recent advances in representation learning can rival supervised approaches in biomedical WSD. However, external knowledge bases (here sense inventories) play a key role in the improvements achieved.