An official website of the United States government
Background and Objectives: Sepsis is a leading cause of mortality in intensive care units (ICUs). The development of a robust prognostic model utilizing patients’ clinical data could significantly enhance clinicians’ ability to make informed treatment decisions, potentially improving outcomes for septic patients. This study aims to create a novel machine-learning framework for constructing prognostic tools capable of predicting patient survival or mortality outcome. Methods: A novel dataset is created using concatenated triples of static data, temporal data, and clinical outcomes to expand data size. This structured input trains five machine learning classifiers (KNN, Logistic Regression, SVM, RF, and XGBoost) with advanced feature engineering. Models are evaluated on an independent cohort using AUROC and a new metric, 𝛾, which incorporates the F1 score, to assess discriminative power and generalizability. Results: We developed five prognostic models using the concatenated triple dataset with 10 dynamic features from patient medical records. Our analysis shows that the Extreme Gradient Boosting (XGBoost) model (AUROC = 0.777, F1 score = 0.694) and the Random Forest (RF) model (AUROC = 0.769, F1 score = 0.647), when paired with an ensemble under-sampling strategy, outperform other models. The RF model improves AUROC by 6.66% and reduces overfitting by 54.96%, while the XGBoost model shows a 0.52% increase in AUROC and a 77.72% reduction in overfitting. These results highlight our framework’s ability to enhance predictive accuracy and generalizability, particularly in sepsis prognosis. Conclusion: This study presents a novel modeling framework for predicting treatment outcomes in septic patients, designed for small, imbalanced, and high-dimensional datasets. By using temporal feature encoding, advanced sampling, and dimension reduction techniques, our approach enhances standard classifier performance. The resulting models show improved accuracy with limited data, offering valuable prognostic tools for sepsis management. This framework demonstrates the potential of machine learning in small medical datasets.
more »
« less
This content will become publicly available on December 1, 2026
Development and prospective implementation of a large language model based system for early sepsis prediction
Sepsis is a dysregulated host response to infection with high mortality and morbidity. Early detection and intervention have been shown to improve patient outcomes, but existing computational models relying on structured electronic health record data often miss contextual information from unstructured clinical notes. This study introduces COMPOSER-LLM, an open-source large language model (LLM) integrated with the COMPOSER model to enhance early sepsis prediction. For high-uncertainty predictions, the LLM extracts additional context to assess sepsis-mimics, improving accuracy. Evaluated on 2500 patient encounters, COMPOSER-LLM achieved a sensitivity of 72.1%, positive predictive value of 52.9%, F-1 score of 61.0%, and 0.0087 false alarms per patient hour, outperforming the standalone COMPOSER model. Prospective validation yielded similar results. Manual chart review found 62% of false positives had bacterial infections, demonstrating potential clinical utility. Our findings suggest that integrating LLMs with traditional models can enhance predictive performance by leveraging unstructured data, representing a significant advance in healthcare analytics.
more »
« less
- Award ID(s):
- 2405974
- PAR ID:
- 10627054
- Publisher / Repository:
- Springer Nature
- Date Published:
- Journal Name:
- npj Digital Medicine
- Volume:
- 8
- Issue:
- 1
- ISSN:
- 2398-6352
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Luo, Ling; Recupero, Diego Reforgiato (Ed.)Clinician notes are a rich source of patient information, but often contain inconsistencies due to varied writing styles, abbreviations, medical jargon, grammatical errors, and non-standard formatting. These inconsistencies hinder their direct use in patient care and degrade the performance of downstream computational applications that rely on these notes as input, such as quality improvement, population health analytics, precision medicine, clinical decision support, and research. We present a large-language-model (LLM) approach to the preprocessing of 1618 neurology notes. The LLM corrected spelling and grammatical errors, expanded acronyms, and standardized terminology and formatting, without altering clinical content. Expert review of randomly sampled notes confirmed that no significant information was lost. To evaluate downstream impact, we applied an ontology-based NLP pipeline (Doc2Hpo) to extract biomedical concepts from the notes before and after editing. F1 scores for Human Phenotype Ontology extraction improved from 0.40 to 0.61, confirming our hypothesis that better inputs yielded better outputs. We conclude that LLM-based preprocessing is an effective error correction strategy that improves data quality at the level of free text in clinical notes. This approach may enhance the performance of a broad class of downstream applications that derive their input from unstructured clinical documentation.more » « less
-
Objective Visual cohort analysis utilizing electronic health record data has become an important tool in clinical assessment of patient outcomes. In this article, we introduce Composer, a visual analysis tool for orthopedic surgeons to compare changes in physical functions of a patient cohort following various spinal procedures. The goal of our project is to help researchers analyze outcomes of procedures and facilitate informed decision-making about treatment options between patient and clinician. Methods In collaboration with orthopedic surgeons and researchers, we defined domain-specific user requirements to inform the design. We developed the tool in an iterative process with our collaborators to develop and refine functionality. With Composer, analysts can dynamically define a patient cohort using demographic information, clinical parameters, and events in patient medical histories and then analyze patient-reported outcome scores for the cohort over time, as well as compare it to other cohorts. Using Composer's current iteration, we provide a usage scenario for use of the tool in a clinical setting. Conclusion We have developed a prototype cohort analysis tool to help clinicians assess patient treatment options by analyzing prior cases with similar characteristics. Although Composer was designed using patient data specific to orthopedic research, we believe the tool is generalizable to other healthcare domains. A long-term goal for Composer is to develop the application into a shared decision-making tool that allows translation of comparison and analysis from a clinician-facing interface into visual representations to communicate treatment options to patients.more » « less
-
Abstract The purpose of this study is to identify additional clinical features for sepsis detection through the use of a novel mechanism for interpreting black-box machine learning models trained and to provide a suitable evaluation for the mechanism. We use the publicly available dataset from the 2019 PhysioNet Challenge. It has around 40,000 Intensive Care Unit (ICU) patients with 40 physiological variables. Using Long Short-Term Memory (LSTM) as the representative black-box machine learning model, we adapted the Multi-set Classifier to globally interpret the black-box model for concepts it learned about sepsis. To identify relevant features, the result is compared against: (i) features used by a computational sepsis expert, (ii) clinical features from clinical collaborators, (iii) academic features from literature, and (iv) significant features from statistical hypothesis testing. Random Forest was found to be the computational sepsis expert because it had high accuracies for solving both the detection and early detection, and a high degree of overlap with clinical and literature features. Using the proposed interpretation mechanism and the dataset, we identified 17 features that the LSTM used for sepsis classification, 11 of which overlaps with the top 20 features from the Random Forest model, 10 with academic features and 5 with clinical features. Clinical opinion suggests, 3 LSTM features have strong correlation with some clinical features that were not identified by the mechanism. We also found that age, chloride ion concentration, pH and oxygen saturation should be investigated further for connection with developing sepsis. Interpretation mechanisms can bolster the incorporation of state-of-the-art machine learning models into clinical decision support systems, and might help clinicians to address the issue of early sepsis detection. The promising results from this study warrants further investigation into creation of new and improvement of existing interpretation mechanisms for black-box models, and into clinical features that are currently not used in clinical assessment of sepsis.more » « less
-
Frasch, Martin G. (Ed.)With the wider availability of healthcare data such as Electronic Health Records (EHR), more and more data-driven based approaches have been proposed to improve the quality-of-care delivery. Predictive modeling, which aims at building computational models for predicting clinical risk, is a popular research topic in healthcare analytics. However, concerns about privacy of healthcare data may hinder the development of effective predictive models that are generalizable because this often requires rich diverse data from multiple clinical institutions. Recently, federated learning (FL) has demonstrated promise in addressing this concern. However, data heterogeneity from different local participating sites may affect prediction performance of federated models. Due to acute kidney injury (AKI) and sepsis’ high prevalence among patients admitted to intensive care units (ICU), the early prediction of these conditions based on AI is an important topic in critical care medicine. In this study, we take AKI and sepsis onset risk prediction in ICU as two examples to explore the impact of data heterogeneity in the FL framework as well as compare performances across frameworks. We built predictive models based on local, pooled, and FL frameworks using EHR data across multiple hospitals. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites’ data. A model was updated locally, and its parameters were shared to a central aggregator, which was used to update the federated model’s parameters and then subsequently, shared with each site. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within the EHR data. The different distributions of demographic profiles, medication use, and site information contributed to data heterogeneity.more » « less
