The extraction of critical patient information from Electronic Health Records (EHRs) poses significant challenges due to the complexity and unstructured nature of the data. Traditional machine learning approaches often fail to capture pertinent details efficiently, making it difficult for clinicians to utilize these tools effectively in patient care. This paper introduces a novel approach to extracting the OPQRST assessment from EHRs by leveraging the capabilities of Large Language Models (LLMs). We propose to reframe the task from sequence labeling to text generation, enabling the models to provide reasoning steps that mimic a physician's cognitive processes. This approach enhances interpretability and adapts to the limited availability of labeled data in healthcare settings. Furthermore, we address the challenge of evaluating the accuracy of machine-generated text in clinical contexts by proposing a modification to traditional Named Entity Recognition (NER) metrics. This includes the integration of semantic similarity measures, such as the BERT Score, to assess the alignment between generated text and the clinical intent of the original records. Our contributions demonstrate a significant advancement in the use of AI in healthcare, offering a scalable solution that improves the accuracy and usability of information extraction from EHRs, thereby aiding clinicians in making more informed decisions and enhancing patient care outcomes.

Current machine learning approaches to medical diagnosis often rely on correlational patterns between symptoms and diseases, risking misdiagnoses when symptoms are ambiguous or common across multiple conditions. In this work, we move beyond correlation to investigate the causal influence of key symptoms-specifically "chest pain" on diagnostic predictions. Leveraging the CausaLM framework, we generate counterfactual text representations in which target concepts are effectively "forgotten" enabling a principled estimation of the causal effect of that concept on a model's predicted disease distribution. By employing Textual Representation-based Average Treatment Effect (TReATE), we quantify how the presence or absence of a symptom shapes the model's diagnostic outcomes, and contrast these findings against correlation-based baselines such as CONEXP. Our results offer deeper insight into the decision-making behavior of clinical NLP models and have the potential to inform more trustworthy, interpretable, and causally-grounded decision support tools in medical practice.

In medicine, machine learning (ML) datasets are often built using the International Classification of Diseases (ICD) codes. As new models are being developed, there is a need for larger datasets. However, ICD codes are intended for billing. We aim to determine how suitable ICD codes are for creating datasets to train ML models. We focused on a rare and common disease using the All of Us database. First, we compared the patient cohort created using ICD codes for Valley fever (coccidioidomycosis, CM) with that identified via serological confirmation. Second, we compared two similarly created patient cohorts for myocardial infarction (MI) patients. We identified significant discrepancies between these two groups, and the patient overlap was small. The CM cohort had 811 patients in the ICD-10 group, 619 patients in the positive-serology group, and 24 with both. The MI cohort had 14,875 patients in the ICD-10 group, 23,598 in the MI laboratory-confirmed group, and 6,531 in both. Demographics, rates of disease symptoms, and other clinical data varied across our case study cohorts.

Recent breakthroughs in large language models (LLMs) have led to their rapid dissemination and widespread use. One early application has been to medicine, where LLMs have been investigated to streamline clinical workflows and facilitate clinical analysis and decision-making. However, a leading barrier to the deployment of Artificial Intelligence (AI) and in particular LLMs has been concern for embedded gender and racial biases. Here, we evaluate whether a leading LLM, ChatGPT 3.5, exhibits gender and racial bias in clinical management of acute coronary syndrome (ACS). We find that specifying patients as female, African American, or Hispanic resulted in a decrease in guideline recommended medical management, diagnosis, and symptom management of ACS. Most notably, the largest disparities were seen in the recommendation of coronary angiography or stress testing for the diagnosis and further intervention of ACS and recommendation of high intensity statins. These disparities correlate with biases that have been observed clinically and have been implicated in the differential gender and racial morbidity and mortality outcomes of ACS and coronary artery disease. Furthermore, we find that the largest disparities are seen during unstable angina, where fewer explicit clinical guidelines exist. Finally, we find that through asking ChatGPT 3.5 to explain its reasoning prior to providing an answer, we are able to improve clinical accuracy and mitigate instances of gender and racial biases. This is among the first studies to demonstrate that the gender and racial biases that LLMs exhibit do in fact affect clinical management. Additionally, we demonstrate that existing strategies that improve LLM performance not only improve LLM performance in clinical management, but can also be used to mitigate gender and racial biases.

Information extraction systems often produce hundreds to thousands of strings on a specific topic. We present a method that facilitates better consumption of these strings, in an exploratory setting in which a user wants to both get a broad overview of what's available, and a chance to dive deeper on some aspects. The system works by grouping similar items together and arranging the remaining items into a hierarchical navigable DAG structure. We apply the method to medical information extraction.

Heart attacks could soon be diagnosed with better speed and accuracy than ever before thanks to a new AI tool. Researchers have developed an algorithm which they say could reduce pressure on A&E and reassure patients suffering from chest pain. A new study suggests that compared to current testing methods, their algorithm was able to rule out a heart attack in more than double the number of patients with an accuracy of 99.6 per cent. The team, from the University of Edinburgh, said this ability to quickly rule out a heart attack could greatly reduce hospital admissions and rapidly identify patients that are safe to go home. The current gold standard for diagnosing a heart attack involves measuring levels of the protein troponin in the blood.

A new machine learning system is better at predicting the likelihood of patients with cardiovascular problems dying within ten years than healthcare professionals' methods, according to a study presented at the EuroEcho 2021, a scientific meeting of the European Society Cardiology. Unlike traditional methods based solely on clinical data, the new machine learning system also includes results from imaging scans on the heart, measured by stress cardiovascular magnetic resonance (CMR). During this exam, patients receive a drug that mimics the effect of exercise on the heart and then undergo imaging using a magnetic resonance imaging scanner. Assessing the risk of death is commonly done in these patients. Usually, doctors use a limited amount of clinical information, including age, sex, smoking, blood pressure, and cholesterol levels.

Anginal symptoms can connote increased cardiac risk and a need for change in cardiovascular management. This study evaluated the potential to extract these symptoms from physician notes using the Bidirectional Encoder from Transformers language model fine-tuned on a domain-specific corpus. The history of present illness section of 459 expert annotated primary care physician notes from consecutive patients referred for cardiac testing without known atherosclerotic cardiovascular disease were included. Notes were annotated for positive and negative mentions of chest pain and shortness of breath characterization. The results demonstrate high sensitivity and specificity for the detection of chest pain or discomfort, substernal chest pain, shortness of breath, and dyspnea on exertion. Small sample size limited extracting factors related to provocation and palliation of chest pain. This study provides a promising starting point for the natural language processing of physician notes to characterize clinically actionable anginal symptoms. Introduction Angina pectoris is a constellation of symptoms that portends inadequate oxygenation of cardiac muscle due to either a decrease in coronary blood supply, an increase in myocardial oxygen demand, or both.

In this post, I will test the effectiveness of machine learning in the medical field especially in classifying whether or not a person has heart disease. AS well, I will guide you through building some classifiers from the scikit-learn library then, we will highlight the best accuracy. According to the World health organization, 17.9 million deaths caused by Cardiovascular diseases each year. Our objective here is help doctors diagnose heart disease faster, and also inform patient who are at high risk. Through this post we will try to solve these important questions: 1- Who are more likely to have heart disease?

Following each patient visit, physicians must draft detailed clinical summaries called SOAP notes. Moreover, with electronic health records, these notes must be digitized. For all the benefits of this documentation the process remains onerous, contributing to increasing physician burnout. In a parallel development, patients increasingly record audio from their visits (with consent), often through dedicated apps. In this paper, we present the first study to evaluate complete pipelines for leveraging these transcripts to train machine learning model to generate these notes. We first describe a unique dataset of patient visit records, consisting of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence. We decompose the problem into extractive and abstractive subtasks, exploring a spectrum of approaches according to how much they demand from each component. Our best performing method first (i) extracts noteworthy utterances via multi-label classification assigns them to summary section(s); (ii) clusters noteworthy utterances on a per-section basis; and (iii) generates the summary sentences by conditioning on the corresponding cluster and the subsection of the SOAP sentence to be generated. Compared to an end-to-end approach that generates the full SOAP note from the full conversation, our approach improves by 7 ROUGE-1 points. Oracle experiments indicate that fixing our generative capabilities, improvements in extraction alone could provide (up to) a further 9 ROUGE point gain.