Timothy A. Miller

Yanjun Gao, Dmitriy Dligach, Timothy Miller et al. · harvard

Automatically summarizing patients' main problems from daily progress notes using natural language processing methods helps to battle against information and cognitive overload in hospital settings and potentially assists providers with computerized diagnostic decision support. Problem list summarization requires a model to understand, abstract, and generate clinical documentation. In this work, we propose a new NLP task that aims to generate a list of problems in a patient's daily care plan using input from the provider's progress notes during hospitalization. We investigate the performance of T5 and BART, two state-of-the-art seq2seq transformer architectures, in solving this problem. We provide a corpus built on top of progress notes from publicly available electronic health record progress notes in the Medical Information Mart for Intensive Care (MIMIC)-III. T5 and BART are trained on general domain text, and we experiment with a data augmentation method and a domain adaptation pre-training method to increase exposure to medical vocabulary and knowledge. Evaluation methods include ROUGE, BERTScore, cosine similarity on sentence embedding, and F-score on medical concepts. Results show that T5 with domain adaptive pre-training achieves significant performance gains compared to a rule-based system and general domain pre-trained language models, indicating a promising direction for tackling the problem summarization task.

Yanjun Gao, Dmitriy Dligach, Timothy Miller et al. · harvard

Applying methods in natural language processing on electronic health records (EHR) data is a growing field. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there is a paucity of annotated corpus built to model clinical diagnostic thinking, a process involving text understanding, domain knowledge abstraction and reasoning. This work introduces a hierarchical annotation schema with three stages to address clinical text understanding, clinical reasoning, and summarization. We created an annotated corpus based on an extensive collection of publicly available daily progress notes, a type of EHR documentation that is collected in time series in a problem-oriented format. The conventional format for a progress note follows a Subjective, Objective, Assessment and Plan heading (SOAP). We also define a new suite of tasks, Progress Note Understanding, with three tasks utilizing the three annotation stages. The novel suite of tasks was designed to train and evaluate future NLP models for clinical text understanding, clinical knowledge representation, inference, and summarization.

Yanjun Gao, Dmitriy Dligach, Timothy Miller et al. · harvard

The BioNLP Workshop 2023 initiated the launch of a shared task on Problem List Summarization (ProbSum) in January 2023. The aim of this shared task is to attract future research efforts in building NLP models for real-world diagnostic decision support applications, where a system generating relevant and accurate diagnoses will augment the healthcare providers decision-making process and improve the quality of care for patients. The goal for participants is to develop models that generated a list of diagnoses and problems using input from the daily care notes collected from the hospitalization of critically ill patients. Eight teams submitted their final systems to the shared task leaderboard. In this paper, we describe the tasks, datasets, evaluation metrics, and baseline systems. Additionally, the techniques and results of the evaluation of the different approaches tried by the participating teams are summarized.

Brihat Sharma, Yanjun Gao, Timothy Miller et al. · harvard

Generative artificial intelligence (AI) is a promising direction for augmenting clinical diagnostic decision support and reducing diagnostic errors, a leading contributor to medical errors. To further the development of clinical AI systems, the Diagnostic Reasoning Benchmark (DR.BENCH) was introduced as a comprehensive generative AI framework, comprised of six tasks representing key components in clinical reasoning. We present a comparative analysis of in-domain versus out-of-domain language models as well as multi-task versus single task training with a focus on the problem summarization task in DR.BENCH (Gao et al., 2023). We demonstrate that a multi-task, clinically trained language model outperforms its general domain counterpart by a large margin, establishing a new state-of-the-art performance, with a ROUGE-L score of 28.55. This research underscores the value of domain-specific training for optimizing clinical diagnostic reasoning tasks.

Weipeng Zhou, Danielle Bitterman, Majid Afshar et al.

Large language models (LLMs) like ChatGPT have excited scientists across fields; in medicine, one source of excitement is the potential applications of LLMs trained on electronic health record (EHR) data. But there are tough questions we must first answer if health care institutions are interested in having LLMs trained on their own data; should they train an LLM from scratch or fine-tune it from an open-source model? For healthcare institutions with a predefined budget, what are the biggest LLMs they can afford? In this study, we take steps towards answering these questions with an analysis on dataset sizes, model sizes, and costs for LLM training using EHR data. This analysis provides a framework for thinking about these questions in terms of data scale, compute scale, and training budgets.

Yanjun Gao, Ruizhe Li, Emma Croxford et al.

Electronic Health Records (EHRs) and routine documentation practices play a vital role in patients' daily care, providing a holistic record of health, diagnoses, and treatment. However, complex and verbose EHR narratives overload healthcare providers, risking diagnostic inaccuracies. While Large Language Models (LLMs) have showcased their potential in diverse language tasks, their application in the healthcare arena needs to ensure the minimization of diagnostic errors and the prevention of patient harm. In this paper, we outline an innovative approach for augmenting the proficiency of LLMs in the realm of automated diagnosis generation, achieved through the incorporation of a medical knowledge graph (KG) and a novel graph model: Dr.Knows, inspired by the clinical diagnostic reasoning process. We derive the KG from the National Library of Medicine's Unified Medical Language System (UMLS), a robust repository of biomedical knowledge. Our method negates the need for pre-training and instead leverages the KG as an auxiliary instrument aiding in the interpretation and summarization of complex medical concepts. Using real-world hospital datasets, our experimental results demonstrate that the proposed approach of combining LLMs with KG has the potential to improve the accuracy of automated diagnosis generation. More importantly, our approach offers an explainable diagnostic pathway, edging us closer to the realization of AI-augmented diagnostic decision support systems.

Shan Chen, Marco Guevara, Shalini Moningi et al.

Documentation burden is a major contributor to clinician burnout, which is rising nationally and is an urgent threat to our ability to care for patients. Artificial intelligence (AI) chatbots, such as ChatGPT, could reduce clinician burden by assisting with documentation. Although many hospitals are actively integrating such systems into electronic medical record systems, AI chatbots utility and impact on clinical decision-making have not been studied for this intended use. We are the first to examine the utility of large language models in assisting clinicians draft responses to patient questions. In our two-stage cross-sectional study, 6 oncologists responded to 100 realistic synthetic cancer patient scenarios and portal messages developed to reflect common medical situations, first manually, then with AI assistance. We find AI-assisted responses were longer, less readable, but provided acceptable drafts without edits 58% of time. AI assistance improved efficiency 77% of time, with low harm risk (82% safe). However, 7.7% unedited AI responses could severely harm. In 31% cases, physicians thought AI drafts were human-written. AI assistance led to more patient education recommendations, fewer clinical actions than manual responses. Results show promise for AI to improve clinician efficiency and patient care through assisting documentation, if used judiciously. Monitoring model outputs and human-AI interaction remains crucial for safe implementation.

Yanjun Gao, Skatje Myers, Shan Chen et al.

The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially numerical data pivotal in clinical contexts, into LLM paradigms has not been thoroughly explored. In this study, we examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record (EHR) data. We compare the performance of these embeddings with that of raw numerical EHR data when used as feature inputs to traditional machine learning (ML) algorithms that excel at tabular data learning, such as eXtreme Gradient Boosting. We focus on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluating their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Furthermore, we examine prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. Although findings suggest the raw data features still prevails in medical ML tasks, zero-shot LLM embeddings demonstrate competitive results, suggesting a promising avenue for future research in medical applications.

Yanjun Gao, Skatje Myers, Shan Chen et al.

Large language models (LLMs) are being explored for diagnostic decision support, yet their ability to estimate pre-test probabilities, vital for clinical decision-making, remains limited. This study evaluates two LLMs, Mistral-7B and Llama3-70B, using structured electronic health record data on three diagnosis tasks. We examined three current methods of extracting LLM probability estimations and revealed their limitations. We aim to highlight the need for improved techniques in LLM confidence estimation.

Skatje Myers, Dmitriy Dligach, Timothy A. Miller et al.

Electronic health records (EHRs) are long, noisy, and often redundant, posing a major challenge for the clinicians who must navigate them. Large language models (LLMs) offer a promising solution for extracting and reasoning over this unstructured text, but the length of clinical notes often exceeds even state-of-the-art models' extended context windows. Retrieval-augmented generation (RAG) offers an alternative by retrieving task-relevant passages from across the entire EHR, potentially reducing the amount of required input tokens. In this work, we propose three clinical tasks designed to be replicable across health systems with minimal effort: 1) extracting imaging procedures, 2) generating timelines of antibiotic use, and 3) identifying key diagnoses. Using EHRs from actual hospitalized patients, we test three state-of-the-art LLMs with varying amounts of provided context, using either targeted text retrieval or the most recent clinical notes. We find that RAG closely matches or exceeds the performance of using recent notes, and approaches the performance of using the models' full context while requiring drastically fewer input tokens. Our results suggest that RAG remains a competitive and efficient approach even as newer models become capable of handling increasingly longer amounts of text.

Shan Chen, Jack Gallifant, Marco Guevara et al.

Generative models have been showing potential for producing data in mass. This study explores the enhancement of clinical natural language processing performance by utilizing synthetic data generated from advanced language models. Promising results show feasible applications in such a high-stakes domain.

Wonjin Yoon, Ian Bulovic, Timothy A. Miller · harvard

Large language models perform surprisingly well on many zero-shot classification tasks, but are difficult to fairly compare to supervised classifiers due to the lack of a modifiable decision boundary. In this work, we propose and evaluate a method that converts binary classification tasks into pairwise comparison tasks, obtaining relative rankings from LLMs. Repeated pairwise comparisons can be used to score instances using the Elo rating system (used in chess and other competitions), inducing a confidence ordering over instances in a dataset. We evaluate scheduling algorithms for their ability to minimize comparisons, and show that our proposed algorithm leads to improved classification performance, while also providing more information than traditional zero-shot classification.

Yuqi Si, Jingcheng Du, Zhao Li et al.

Patient representation learning refers to learning a dense mathematical representation of a patient that encodes meaningful information from Electronic Health Records (EHRs). This is generally performed using advanced deep learning methods. This study presents a systematic review of this field and provides both qualitative and quantitative analyses from a methodological perspective. We identified studies developing patient representations from EHRs with deep learning methods from MEDLINE, EMBASE, Scopus, the Association for Computing Machinery (ACM) Digital Library, and Institute of Electrical and Electronics Engineers (IEEE) Xplore Digital Library. After screening 363 articles, 49 papers were included for a comprehensive data collection. We noticed a typical workflow starting with feeding raw data, applying deep learning models, and ending with clinical outcome predictions as evaluations of the learned representations. Specifically, learning representations from structured EHR data was dominant (37 out of 49 studies). Recurrent Neural Networks were widely applied as the deep learning architecture (LSTM: 13 studies, GRU: 11 studies). Disease prediction was the most common application and evaluation (31 studies). Benchmark datasets were mostly unavailable (28 studies) due to privacy concerns of EHR data, and code availability was assured in 20 studies. We show the importance and feasibility of learning comprehensive representations of patient EHR data through a systematic review. Advances in patient representation learning techniques will be essential for powering patient-level EHR analyses. Future work will still be devoted to leveraging the richness and potential of available EHR data. Knowledge distillation and advanced learning techniques will be exploited to assist the capability of learning patient representation further.

Dianbo Liu, Tim Miller

Large scale contextual representation models, such as BERT, have significantly advanced natural language processing (NLP) in recently years. However, in certain area like healthcare, accessing diverse large scale text data from multiple institutions is extremely challenging due to privacy and regulatory reasons. In this article, we show that it is possible to both pretrain and fine tune BERT models in a federated manner using clinical texts from different silos without moving the data.

Dianbo Liu, Dmitriy Dligach, Timothy Miller

A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from different hospitals or clinics without moving the data, and demonstrate its performance using obesity and comorbities phenotyping as medical task. This approach not only improves the quality of a specific clinical task but also facilitates knowledge progression in the whole healthcare system, which is an essential part of learning health system. To the best of our knowledge, this is the first application of federated machine learning in clinical NLP.

Timothy A Miller

Unsupervised domain adaptation (UDA) is the task of modifying a statistical model trained on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target domain. Existing state-of-the-art UDA approaches use neural networks to learn representations that can predict the values of subset of important features called "pivot features." In this work, we show that it is possible to improve on these methods by jointly training the representation learner with the task learner, and examine the importance of existing pivot selection methods.

Dianbo Liu, Timothy Miller, Raheel Sayeed et al.

Electronic health record (EHR) data is collected by individual institutions and often stored across locations in silos. Getting access to these data is difficult and slow due to security, privacy, regulatory, and operational issues. We show, using ICU data from 58 different hospitals, that machine learning models to predict patient mortality can be trained efficiently without moving health data out of their silos using a distributed machine learning strategy. We propose a new method, called Federated-Autonomous Deep Learning (FADL) that trains part of the model using all data sources in a distributed manner and other parts using data from specific data sources. We observed that FADL outperforms traditional federated learning strategy and conclude that balance between global and local training is an important factor to consider when design distributed machine learning methods , especially in healthcare.

Lifeng Jin, Finale Doshi-Velez, Timothy Miller et al.

There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016; Jin et al., 2018). Modern depth-bounded grammar inducers have been shown to be more accurate than early unbounded PCFG inducers, but this technique has never been compared against unbounded induction within the same system, in part because most previous depth-bounding models are built around sequence models, the complexity of which grows exponentially with the maximum allowed depth. The present work instead applies depth bounds within a chart-based Bayesian PCFG inducer (Johnson et al., 2007b), where bounding can be switched on and off, and then samples trees with and without bounding. Results show that depth-bounding is indeed significantly effective in limiting the search space of the inducer and thereby increasing the accuracy of the resulting parsing model. Moreover, parsing results on English, Chinese and German show that this bounded model with a new inference technique is able to produce parse trees more accurately than or competitively with state-of-the-art constituency-based grammar induction models.

Dmitriy Dligach, Timothy Miller

Mining electronic health records for patients who satisfy a set of predefined criteria is known in medical informatics as phenotyping. Phenotyping has numerous applications such as outcome prediction, clinical trial recruitment, and retrospective studies. Supervised machine learning for phenotyping typically relies on sparse patient representations such as bag-of-words. We consider an alternative that involves learning patient representations. We develop a neural network model for learning patient representations and show that the learned representations are general enough to obtain state-of-the-art performance on a standard comorbidity detection task.

Lifeng Jin, Finale Doshi-Velez, Timothy Miller et al.

There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech and newswire text exceed or are competitive with those of other models when evaluated on parse accuracy. Moreover, gram- mars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.