Journal of the American Medical Informatics Association最新文献

Objective: Extracting social determinants of health (SDoHs) from medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. Here, we introduce SDoH-GPT, a novel framework leveraging few-shot learning large language models (LLMs) to automate the extraction of SDoH from unstructured text, aiming to improve both efficiency and generalizability.

Materials and methods: SDoH-GPT is a framework including the few-shot learning LLM methods to extract the SDoH from medical notes and the XGBoost classifiers which continue to classify SDoH using the annotations generated by the few-shot learning LLM methods as training datasets. The unique combination of the few-shot learning LLM methods with XGBoost utilizes the strength of LLMs as great few shot learners and the efficiency of XGBoost when the training dataset is sufficient. Therefore, SDoH-GPT can extract SDoH without relying on extensive medical annotations or costly human intervention.

Results: Our approach achieved tenfold and twentyfold reductions in time and cost, respectively, and superior consistency with human annotators measured by Cohen's kappa of up to 0.92. The innovative combination of LLM and XGBoost can ensure high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores.

Discussion: This study has verified SDoH-GPT on three datasets and highlights the potential of leveraging LLM and XGBoost to revolutionize medical note classification, demonstrating its capability to achieve highly accurate classifications with significantly reduced time and cost.

Conclusion: The key contribution of this study is the integration of LLM with XGBoost, which enables cost-effective and high quality annotations of SDoH. This research sets the stage for SDoH can be more accessible, scalable, and impactful in driving future healthcare solutions.

Objective: Frequent premature ventricular complexes (PVCs) can lead to adverse health conditions such as cardiomyopathy. The linear correlation between PVC frequency and heart rate (as positive, negative, or neutral) on a 24-hour Holter recording has been proposed as a way to classify patients and guide treatment with beta-blockers. Our objective was to evaluate the robustness of this classification to measurement methodology, different 24-hour periods, and nonlinear dependencies of PVCs on heart rate.

Materials and methods: We analyzed 82 multi-day Holter recordings (1-7 days) collected from 48 patients with frequent PVCs (burden 1%-44%). For each record, linear correlation between PVC frequency and heart rate was computed for different 24-hour periods and using different length intervals to determine PVC frequency.

Results: Using a 1-hour interval, the correlation between PVC frequency and heart rate was consistently positive, negative, or neutral on different days in only 36.6% of patients. Using shorter time intervals, the correlation was consistent in 56.1% of patients. Shorter time intervals revealed nonlinear and piecewise linear relationships between PVC frequency and heart rate in many patients.

Discussion: The variability of the correlation between PVC frequency and heart rate across different 24-hour periods and interval durations suggests that the relationship is neither strictly linear nor stationary. A better understanding of the mechanism driving the PVCs, combined with computational and biological models that represent these mechanisms, may provide insight into the observed nonlinear behavior and guide more robust classification strategies.

Conclusion: Linear correlation as a tool to classify patients with frequent PVCs should be used with caution. It is sensitive to the specific 24-hour period analyzed and the methodology used to segment the data. More sophisticated classification approaches that can capture nonlinear and time-varying dependencies should be developed and considered in clinical practice.

Objectives: To improve prediction of chronic kidney disease (CKD) progression to end-stage renal disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to integrated clinical and claims data with varying observation windows, supported by explainable artificial intelligence (AI) to enhance interpretability and reduce bias.

Materials and methods: We utilized data from 10 326 CKD patients, combining clinical and claims information from 2009 to 2018. After preprocessing, cohort identification, and feature engineering, we evaluated multiple statistical, ML and DL models using 5 distinct observation windows. Feature importance and SHapley Additive exPlanations (SHAP) analysis were employed to understand key predictors. Models were tested for robustness, clinical relevance, misclassification patterns, and bias.

Results: Integrated data models outperformed single data source models, with long short-term memory achieving the highest area under the receiver operating characteristic curve (AUROC) (0.93) and F1 score (0.65). A 24-month observation window optimally balanced early detection and prediction accuracy. The 2021 estimated glomerular filtration rate (eGFR) equation improved prediction accuracy and reduced racial bias, particularly for African American patients.

Discussion: Improved prediction accuracy, interpretability, and bias mitigation strategies have the potential to enhance CKD management, support targeted interventions, and reduce health-care disparities.

Conclusion: This study presents a robust framework for predicting ESRD outcomes, improving clinical decision-making through integrated multisourced data and advanced analytics. Future research will expand data integration and extend this framework to other chronic diseases.

Objective: Emerging efforts to identify patients at risk of suicide have focused on the development of predictive algorithms for use in healthcare settings. We address a major challenge in effective risk modeling in healthcare settings with insufficient data with which to create and apply risk models. This study aimed to improve risk prediction using transfer learning or data fusion by incorporating risk information from external data sources to augment the data available in particular clinical settings.

Materials and methods: In this retrospective study, we developed predictive models in individual Connecticut hospitals using medical claims data. We compared conventional models containing demographics and historical medical diagnosis codes with fusion models containing conventional features and fused risk information that described similarities in historical diagnosis codes between patients from the hospital and patients receiving care for suicide attempts at other hospitals.

Results: Our sample contained 27 hospitals and 636 758 18- to 64-year-old patients. Fusion improved prediction for 93% of hospitals, while slightly worsening prediction for 7%. Median areas under the ROC and precision-recall curves of conventional models were 77.6% and 3.4%, respectively. Fusion improved these metrics by a median of 3.3 and 0.3 points, respectively (Ps < .001). Median sensitivities and positive predictive values at 90% and 95% specificity were also improved (Ps < .001).

Discussion: This study provided strong evidence that data fusion improved model performance across hospitals. Improvement was of greatest magnitude in facilities treating relatively few suicidal patients.

Conclusion: Data fusion holds promise as a methodology to improve suicide risk prediction in healthcare settings with limited or incomplete data.

Objectives: This study introduces Smart Imitator (SI), a 2-phase reinforcement learning (RL) solution enhancing personalized treatment policies in healthcare, addressing challenges from imperfect clinician data and complex environments.

Materials and methods: Smart Imitator's first phase uses adversarial cooperative imitation learning with a novel sample selection schema to categorize clinician policies from optimal to nonoptimal. The second phase creates a parameterized reward function to guide the learning of superior treatment policies through RL. Smart Imitator's effectiveness was validated on 2 datasets: a sepsis dataset with 19 711 patient trajectories and a diabetes dataset with 7234 trajectories.

Results: Extensive quantitative and qualitative experiments showed that SI significantly outperformed state-of-the-art baselines in both datasets. For sepsis, SI reduced estimated mortality rates by 19.6% compared to the best baseline. For diabetes, SI reduced HbA1c-High rates by 12.2%. The learned policies aligned closely with successful clinical decisions and deviated strategically when necessary. These deviations aligned with recent clinical findings, suggesting improved outcomes.

Discussion: Smart Imitator advances RL applications by addressing challenges such as imperfect data and environmental complexities, demonstrating effectiveness within the tested conditions of sepsis and diabetes. Further validation across diverse conditions and exploration of additional RL algorithms are needed to enhance precision and generalizability.

Conclusion: This study shows potential in advancing personalized healthcare learning from clinician behaviors to improve treatment outcomes. Its methodology offers a robust approach for adaptive, personalized strategies in various complex and uncertain environments.

Objectives: To pioneer the first artificial intelligence system integrating radiological and objective clinical data, simulating the clinical reasoning process, for the early prediction of high-risk influenza patients.

Materials and methods: Our system was developed using a cohort from National Taiwan University Hospital in Taiwan, with external validation data from ASST Grande Ospedale Metropolitano Niguarda in Italy. Convolutional neural networks pretrained on ImageNet were regressively trained using a 5-point scale to develop the influenza chest X-ray (CXR) severity scoring model, FluDeep-XR. Early, late, and joint fusion structures, incorporating varying weights of CXR severity with clinical data, were designed to predict 30-day mortality and compared with models using only CXR or clinical data. The best-performing model was designated as FluDeep. The explainability of FluDeep-XR and FluDeep was illustrated through activation maps and SHapley Additive exPlanations (SHAP).

Results: The Xception-based model, FluDeep-XR, achieved a mean square error of 0.738 in the external validation dataset. The Random Forest-based late fusion model, FluDeep, outperformed all the other models, achieving an area under the receiver operating curve of 0.818 and a sensitivity of 0.706 in the external dataset. Activation maps highlighted clear lung fields. Shapley additive explanations identified age, C-reactive protein, hematocrit, heart rate, and respiratory rate as the top 5 important clinical features.

Discussion: The integration of medical imaging with objective clinical data outperformed single-modality models to predict 30-day mortality in influenza patients. We ensured the explainability of our models aligned with clinical knowledge and validated its applicability across foreign institutions.

Conclusion: FluDeep highlights the potential of combining radiological and clinical information in late fusion design, enhancing diagnostic accuracy and offering an explainable, and generalizable decision support system.

Objective: This study addresses the significant challenges posed by emerging SARS-CoV-2 variants, particularly in developing diagnostics and therapeutics. Drug repurposing is investigated by identifying critical regulatory proteins impacted by the virus, providing rapid and effective therapeutic solutions for better disease management.

Materials and methods: We employed a comprehensive approach combining mathematical modeling and efficient parameter estimation to study the transient responses of regulatory proteins in both normal and virus-infected cells. Proportional-integral-derivative (PID) controllers were used to pinpoint specific protein targets for therapeutic intervention. Additionally, advanced deep learning models and molecular docking techniques were applied to analyse drug-target and drug-drug interactions, ensuring both efficacy and safety of the proposed treatments. This approach was applied to a case study focused on the cytokine storm in COVID-19, centering on Angiotensin-converting enzyme 2 (ACE2), which plays a key role in SARS-CoV-2 infection.

Results: Our findings suggest that activating ACE2 presents a promising therapeutic strategy, whereas inhibiting AT1R seems less effective. Deep learning models, combined with molecular docking, identified Lomefloxacin and Fostamatinib as stable drugs with no significant thermodynamic interactions, suggesting their safe concurrent use in managing COVID-19-induced cytokine storms.

Discussion: The results highlight the potential of ACE2 activation in mitigating lung injury and severe inflammation caused by SARS-CoV-2. This integrated approach accelerates the identification of safe and effective treatment options for emerging viral variants.

Conclusion: This framework provides an efficient method for identifying critical regulatory proteins and advancing drug repurposing, contributing to the rapid development of therapeutic strategies for COVID-19 and future global pandemics.

Objective: Heightened muscular effort and breathlessness (dyspnea) are disabling sensory experiences. We sought to improve the current approach of assessing these symptoms only at the maximal effort to new paradigms based on their continuous quantification throughout cardiopulmonary exercise testing (CPET).

Materials and methods: After establishing sex- and age-adjusted reference centiles (0-10 Borg scale), we developed a novel algorithm (AI-Techniques Loss-Based Algorithm for Severity Classification [ATLAS]) based on reciprocal exponential loss for CPET data from patients with chronic obstructive lung disease of varied severity.

Results: Categories of dyspnea intensity by ATLAS-but not dyspnea at peak exercise-correctly discriminated patients in progressively higher resting and exercise impairment (P < .05).

Discussion: This new AI-techniques approach will be translated to the care of disabled patients to uncover the seeds and consequences of their activity-related symptoms.

Conclusions: We used innovative informatics research to change paradigms in displaying, quantifying, and analyzing effort-related symptoms in patient populations.

Objectives: We discuss challenges using computational modeling approaches for personalized prediction in clinical practice to predict treatment response for rare diseases treated by novel therapies using clinical oncology as an example context. Several challenges are discussed, including data scarcity, data sparsity, and difficulties in establishing interdisciplinary teams. Machine learning (ML), mechanistic modeling (MM), and hybrid modeling (HM) are discussed in the context of these challenges.

Materials and methods: We present an HM approach, combining ML and MM techniques for improved personalized model estimation in the context of chimeric antigen receptor T-cell therapy for aggressive lymphoma.

Results: The HM approach improved the root mean squared error by 61.27±23.21% compared to using MM alone (MM: 2.36*105∓1.68*105and HM: 9.57*104∓8.37*104, where the units are in cells), computed from 13 patients included in this study.

Discussion: By exploiting the complementary strengths of ML and MM approaches, the developed HM method addresses common limitations such as data scarcity and sparsity in medical settings, especially common for rare diseases.

Conclusion: The HM techniques are likely required to overcome data scarcity and sparsity issues in broad medical settings. Developing these techniques requires dedicated interdisciplinary teams.

Objectives: We aimed to develop a highly interpretable and effective, machine learning (ML)-based risk prediction algorithm to predict in-hospital mortality, intubation, and adverse cardiovascular events in patients hospitalized with coronavirus disease 2019 (COVID-19) in Australia (AUS-COVID Score).

Materials and methods: This prospective study across 21 hospitals included 1714 consecutive patients aged ≥ 18 in their index hospitalization with COVID-19. The dataset was separated into training (80%) and test sets (20%). Eight supervised ML methods were used: least absolute shrinkage and selection operator (LASSO), ridge, elastic net (EN), decision tree, support vector machine, random forest, AdaBoost, and gradient boosting. A feature selection method was used to establish informative variables, which were considered in groups of 5/10/15/20/all. The final model was selected by balancing the optimal area under the curve (AUC) score with interpretability, through the number of included variables. The coefficients of the final models were used to build the AUS-COVID Score.

Results and discussion: Among the patients, 181 (10.6%) died in-hospital, 148 (8.6%) required intubation, and 90 (5.3%) had adverse cardiovascular events. The LASSO model performed best for predicting in-hospital mortality (AUC 0.85) using 5 variables: age, respiratory rate, COVID-19 features on chest X-ray, troponin elevation, and COVID-19 vaccination (≥1 dose). The EN model performed best for predicting intubation (AUC 0.75) and adverse cardiovascular events (AUC 0.64), each with 5 variables. A user-friendly web-based application was built for clinician use at the bedside.

Conclusion: The AUS-COVID Score is an accurate and practical, ML-based risk score to predict in-hospital mortality, intubation, and adverse cardiovascular events in hospitalized COVID-19 patients.