Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare

Healing with hierarchy: Hierarchical attention empowered graph neural networks for predictive analysis in medical data

In healthcare, predictive analysis using unstructured medical data is crucial for gaining insights into patient conditions and outcomes. However, unstructured data, which contains valuable patient information such as symptoms and medical histories, often presents challenges, including lengthy text sequences and incomplete data. To address these issues, we introduce a new framework named Hierarchical Attention-based Integrated Learning (HAIL), designed to predict in-hospital mortality and the duration of stay in the intensive care unit. HAIL combines hierarchical attention mechanisms with graph neural networks to effectively manage missing data and enhance outcome predictions. Our model iteratively refines embeddings, resulting in a more thorough analysis of electronic health record data. Experimental findings demonstrate a notable performance improvement of 2%-3% across various metrics when compared to existing benchmarks on standard datasets, highlighting HAIL's effectiveness in time-sensitive clinical decision-making. Additionally, our analysis underscores the significance of patient networks in maintaining the robustness and consistent performance of the HAIL framework.

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.

Nomogram for Predicting Sepsis After Percutaneous Transhepatic Cholangioscopic Lithotripsy

Purpose

Sepsis is a possible complication of percutaneous transhepatic cholangioscopic lithotripsy (PTCSL) for hepatolithiasis, but risk assessment tools are lacking. This study aimed to identify predictors of sepsis after PTCSL and develop a predictive nomogram.

Patients and Methods

In this nested case‒control study, the data from 298 patients who underwent 528 PTCSL sessions between 1 January 2016 and 1 July 2024 were retrospectively reviewed. All sessions demonstrating sepsis complications were included in the sepsis group. For each session in the sepsis group, two treatment date-matched sessions not demonstrating sepsis were randomly selected via a nested case‒control design. All the matched sessions were divided into training and validation sets. Least absolute shrinkage and selection operator (LASSO) analysis was conducted to preliminarily select predictors of sepsis complications. Multivariable logistic regression was performed to identify factors for constructing the nomogram.

Results

Sepsis was diagnosed in 46 patients (53 sessions), for an incidence of 10.69% (53 among 496 sessions). Three characteristic variables were included in the model: operation technique (odds ratio [OR]=0.170, 95% confidence interval [CI]: 0.048-0.599, P=0.006), cirrhosis (OR=3.769, 95% CI: 1.474-9.638, P=0.006), and postoperative prophylactic dexamethasone (OR=0.267, 95% CI: 0.101-0.703, P=0.008). The area under the curve (AUC) for the nomogram was 0.756 (95% CI, 0.658-0.853) in the training set and 0.762 (95% CI, 0.618-0.906) in the validation set, demonstrating relatively high discriminability. The calibration curves demonstrated the consistency between the predicted and actual values. Decision curve analysis indicated that the nomogram offers net clinical benefits.

Conclusion

The operation technique, cirrhosis, and postoperative prophylactic dexamethasone may predict the occurrence of sepsis after PTCSL. We developed a nomogram to predict sepsis complications following PTCSL and demonstrated its relatively strong performance.

Improving clinical decision support through interpretable machine learning and error handling in electronic health records

OBJECTIVE

To develop an electronic medical record (EMR) data processing tool that confers clinical context to machine learning (ML) algorithms for error handling, bias mitigation, and interpretability.

MATERIALS AND METHODS

We present Trust-MAPS, an algorithm that translates clinical domain knowledge into high-dimensional, mixed-integer programming models that capture physiological and biological constraints on clinical measurements. EMR data are projected onto this constrained space, effectively bringing outliers to fall within a physiologically feasible range. We then compute the distance of each data point from the constrained space modeling healthy physiology to quantify deviation from the norm. These distances, termed "trust-scores," are integrated into the feature space for downstream ML applications. We demonstrate the utility of Trust-MAPS by training a binary classifier for early sepsis prediction on data from the 2019 PhysioNet Computing in Cardiology Challenge, using the XGBoost algorithm and applying SMOTE for overcoming class-imbalance.

RESULTS

The Trust-MAPS framework shows desirable behavior in handling potential errors and boosting predictive performance. We achieve an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.89-0.92) for predicting sepsis 6 hours before onset-a marked 15% improvement over a baseline model trained without Trust-MAPS.

DISCUSSIONS

Downstream classification performance improves after Trust-MAPS preprocessing, highlighting the bias reducing capabilities of the error-handling projections. Trust-scores emerge as clinically meaningful features that not only boost predictive performance for clinical decision support tasks but also lend interpretability to ML models.

CONCLUSION

This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR and confers interpretability and superior predictive power to models trained for clinical decision support.

Automated machine learning for early prediction of systemic inflammatory response syndrome in acute pancreatitis

BACKGROUND

Systemic inflammatory response syndrome (SIRS) is a frequent and serious complication of acute pancreatitis (AP), often associated with increased mortality. This study aims to leverage automated machine learning (AutoML) algorithms to create a model for the early and precise prediction of SIRS in AP.

METHODS

This study retrospectively analyzed patients diagnosed with AP across multiple centers from January 2017 to December 2021. Data from the First Affiliated Hospital of Soochow University and Changshu Hospital were used for training and internal validation, while testing was conducted with data from the Second Affiliated Hospital. Predictive models were constructed and validated using the least absolute shrinkage and selection operator (LASSO) and AutoML. A nomogram was developed based on multivariable logistic regression (LR) analysis, and the performance of the models was assessed through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the AutoML model's effectiveness and interpretability were assessed through DCA, feature importance, SHapley Additive exPlanation (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).

RESULTS

A total of 1,224 patients were included, with 812 in the training cohort, 200 in validation, and 212 in testing. SIRS occurred in 33.7% of the training cohort, 34.0% in validation, and 22.2% in testing. AutoML models outperformed traditional LR, with the deep learning (DL) model achieving an area under the ROC curve of 0.843 in the training set, and 0.848 and 0.867 in validation and testing, respectively.

CONCLUSION

The AutoML model using the DL algorithm is clinically significant for the early prediction of SIRS in AP.

Transforming pulmonary health care: the role of artificial intelligence in diagnosis and treatment

INTRODUCTION

Respiratory diseases like pneumonia, asthma, and COPD are major global health concerns, significantly impacting morbidity and mortality rates worldwide.

AREAS COVERED

A selective search on PubMed, Google Scholar, and ScienceDirect (up to 2024) focused on AI in diagnosing and treating respiratory conditions like asthma, pneumonia, and COPD. Studies were chosen for their relevance to prediction models, AI-driven diagnostics, and personalized treatments. This narrative review highlights technological advancements, clinical applications, and challenges in integrating AI into standard practice, with emphasis on predictive tools, deep learning for imaging, and patient outcomes.

EXPERT OPINION

Despite these advancements, significant challenges remain in fully integrating AI into pulmonary health care. The need for large, diverse datasets to train AI models is critical, and concerns around data privacy, algorithmic transparency, and potential biases must be carefully managed. Regulatory frameworks also need to evolve to address the unique challenges posed by AI in health care. However, with continued research and collaboration between technology developers, clinicians, and policymakers, AI has the potential to revolutionize pulmonary health care, ultimately leading to more effective, efficient, and personalized care for patients.

A methodological systematic review of validation and performance of sepsis real-time prediction models

Sepsis real-time prediction models (SRPMs) provide timely alerts and may improve patient outcomes but face limited clinical adoption due to inconsistent validation methods and potential biases. Comprehensive evaluation, including external full-window validation with model- and outcome-level metrics, is crucial for real-world effectiveness, yet performance evidence remains scarce. This study systematically reviewed SRPM performance across validation methods, analyzing 91 studies from multiple databases. Only 54.9% applied full-window validation with both metric types. Performance decreased under external and full-window validation, with median AUROCs of 0.886 and 0.861 at 6- and 12-hours pre-onset, dropping to 0.783 in full-window external validation. Median Utility Scores declined from 0.381 in internal to -0.164 in external validation. Combining AUROC and Utility Score identified top-performing SRPMs in 18.7% of studies. Hand-crafted features significantly improved performance. Future research should focus on multi-center datasets, hand-crafted features, multi-metric full-window validation, and prospective trials to support clinical implementation.

Embracing a Penta helix hub framework for co-creating sustaining and potentially disruptive sterilization innovation that enables artificial intelligence and sustainability: A scoping review

The supply of safe pipeline medical devices is of paramount importance. Opportunities exist to transform reusable medical devices for improved processing that meets diverse patient needs. There is increased interest in multi-actor hub frameworks to meet innovation challenges globally. The purpose of this scoping paper was to identify critical decontamination and sterilization needs for the medtech and pharmaceutical sectors with a focus on understanding how to effectively use the Penta helix hub framework that combines academia, industry, healthcare, policy-makers/regulators and patients/society. A PRISMA scoping review of PubMed publications was conducted over the period 2010 to January 2025. Thirty of the 124 'helix hub' papers addressed innovation where only 3 of 16 healthcare-focused helices used or mentioned the need for key performance indicators (KPIs). Early-phase helix innovation ecosystems are mainly supported by qualitative or non-empirical data. This review explores multi-actor needs along with describing quantifiable KPIs at micro (end-user), meso (innovation hub) and macro (regional, national and international) levels. This integrated Penta hub approach will help to effectively plan, co-create, manage, analyse and utilize voluminous data, for example there are ca. 60,000 and 56,000 publications per year on artificial intelligence (AI) and medical devices respectively along, with some 35,000 adverse reports on devices submitted to the US FDA. This review addresses sustaining and potentially disruptive opportunities for decontamination and sterilization that includes the use of AI-enabled devices, bespoke training and sustainability.

Perceived Trust and Professional Identity Threat in AI-Based Clinical Decision Support Systems: Scenario-Based Experimental Study on AI Process Design Features

BACKGROUND

Artificial intelligence (AI)-based systems in medicine like clinical decision support systems (CDSSs) have shown promising results in health care, sometimes outperforming human specialists. However, the integration of AI may challenge medical professionals' identities and lead to limited trust in technology, resulting in health care professionals rejecting AI-based systems.

OBJECTIVE

This study aims to explore the impact of AI process design features on physicians' trust in the AI solution and on perceived threats to their professional identity. These design features involve the explainability of AI-based CDSS decision outcomes, the integration depth of the AI-generated advice into the clinical workflow, and the physician's accountability for the AI system-induced medical decisions.

METHODS

We conducted a 3-factorial web-based between-subject scenario-based experiment with 292 medical students in their medical training and experienced physicians across different specialties. The participants were presented with an AI-based CDSS for sepsis prediction and prevention for use in a hospital. Each participant was given a scenario in which the 3 design features of the AI-based CDSS were manipulated in a 2×2×2 factorial design. SPSS PROCESS (IBM Corp) macro was used for hypothesis testing.

RESULTS

The results suggest that the explainability of the AI-based CDSS was positively associated with both trust in the AI system (β=.508; P<.001) and professional identity threat perceptions (β=.351; P=.02). Trust in the AI system was found to be negatively related to professional identity threat perceptions (β=-.138; P=.047), indicating a partially mediated effect on professional identity threat through trust. Deep integration of AI-generated advice into the clinical workflow was positively associated with trust in the system (β=.262; P=.009). The accountability of the AI-based decisions, that is, the system required a signature, was found to be positively associated with professional identity threat perceptions among the respondents (β=.339; P=.004).

CONCLUSIONS

Our research highlights the role of process design features of AI systems used in medicine in shaping professional identity perceptions, mediated through increased trust in AI. An explainable AI-based CDSS and an AI-generated system advice, which is deeply integrated into the clinical workflow, reinforce trust, thereby mitigating perceived professional identity threats. However, explainable AI and individual accountability of the system directly exacerbate threat perceptions. Our findings illustrate the complex nature of the behavioral patterns of AI in health care and have broader implications for supporting the implementation of AI-based CDSSs in a context where AI systems may impact professional identity.

How AI can help us beat AMR

Antimicrobial resistance (AMR) is an urgent public health threat. Advancements in artificial intelligence (AI) and increases in computational power have resulted in the adoption of AI for biological tasks. This review explores the application of AI in bacterial infection diagnostics, AMR surveillance, and antibiotic discovery. We summarize contemporary AI models applied to each of these domains, important considerations when applying AI across diverse tasks, and current limitations in the field.

Advancing sepsis diagnosis and immunotherapy machine learning-driven identification of stable molecular biomarkers and therapeutic targets

Sepsis represents a significant global health challenge, necessitating early detection and effective treatment for improved outcomes. While traditional inflammatory markers facilitate the diagnosis of sepsis, the aspect of immune suppression remains poorly addressed. This study aimed to identify critical immune-related genes (IIRGs) associated with sepsis through genomic analysis and machine learning techniques, thereby enhancing diagnostic and treatment response predictions. Analyses of two extensive datasets were conducted, identifying significant immune genes using the ESTIMATE algorithm, Weighted Gene Correlation Network Analysis (WGCNA), and five machine learning methods. Prediction models were constructed and validated using six machine learning algorithms, achieving high accuracy (AUC > 0.75). Eleven key IIRGs were identified as active in immune pathways, such as the JAK-STAT signaling pathway, and were significantly correlated with immune cell infiltration in sepsis. Additionally, drug sensitivity analysis indicated that IIRGs correlated with responses to anticancer drugs. These results underscore the potential of these genes in enhancing sepsis diagnosis and treatment, highlighting the imperative for further validation across diverse populations.

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 2,500 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.

Low expression of CD39 on monocytes predicts poor survival in sepsis patients

BACKGROUND

Sepsis is a critical condition associated with high morbidity and mortality, emphasizing the need for reliable biomarkers for its diagnosis and prognosis. This study uses advanced immunological techniques to evaluate monocytic CD39 (mCD39) expression as a potential marker in sepsis.

METHODS

This prospective observational cohort study included 206 participants from the First Affiliated Hospital, Zhejiang University School of Medicine between April 2022 and September 2023. Participants were categorized into four groups: healthy donors, patients with mild infections, post-cardiac surgery patients (non-infectious inflammation), and sepsis patients. Peripheral Blood Mononuclear Cells were analyzed using mass cytometry time-of-flight (CyTOF) with a 42-marker immune panel and flow cytometry targeting monocytes. Statistical analyses included ROC curves for diagnostic and prognostic performance and Kaplan-Meier survival analysis for prognostic evaluation.

RESULTS

Sepsis patients exhibited significantly lower monocytic CD39 expression than mild infection and post-surgery groups (p < 0.05). The diagnostic performance analysis revealed that mCD39 effectively distinguished sepsis from mild infection (AUC = 0.877) and non-infectious inflammation (AUC = 0.935). Prognostic analysis identified low mCD39 expression as a strong predictor of short-term survival, with a 7-day survival AUC of 0.85 (p = 0.037). Kaplan-Meier analysis showed that sepsis patients with low mCD39 expression had significantly lower 28-day survival rates (56.7% vs. 80.6%, p = 0.016).

CONCLUSIONS

Low CD39 expression on monocytes might serve as a potential diagnostic biomarker and a strong predictor of poor prognosis in sepsis patients.

A bibliometric analysis of artificial intelligence research in critical illness: a quantitative approach and visualization study

Background

Critical illness medicine faces challenges such as high data complexity, large individual differences, and rapid changes in conditions. Artificial Intelligence (AI) technology, especially machine learning and deep learning, offers new possibilities for addressing these issues. By analyzing large amounts of patient data, AI can help identify diseases earlier, predict disease progression, and support clinical decision-making.

Methods

In this study, scientific literature databases such as Web of Science were searched, and bibliometric methods along with visualization tools R-bibliometrix, VOSviewer 1.6.19, and CiteSpace 6.2.R4 were used to perform a visual analysis of the retrieved data.

Results

This study analyzed 900 articles from 6,653 authors in 82 countries between 2005 and 2024. The United States is a major contributor in this field, with Harvard University having the highest betweenness centrality. Noseworthy PA is a core author in this field, and Frontiers in Cardiovascular Medicine and Diagnostics lead other journals in terms of the number of publications. Artificial Intelligence has tremendous potential in the identification and management of heart failure and sepsis.

Conclusion

The application of AI in critical illness holds great potential, particularly in enhancing diagnostic accuracy, personalized treatment, and clinical decision support. However, to achieve widespread application of AI technology in clinical practice, challenges such as data privacy, model interpretability, and ethical issues need to be addressed. Future research should focus on the transparency, interpretability, and clinical validation of AI models to ensure their effectiveness and safety in critical illness.

Sepsis in silico: definition, development and application of an electronic phenotype for sepsis

Repurposing electronic health record (EHR) or electronic medical record (EMR) data holds significant promise for evidence-based epidemic intelligence and research. Key challenges include sepsis recognition by physicians and issues with EHR and EMR data. Recent advances in data-driven techniques, alongside initiatives like the Surviving Sepsis Campaign and the Severe Sepsis and Septic Shock Management Bundle (SEP-1), have improved sepsis definition, early detection, subtype characterization, prognostication and personalized treatment. This includes identifying potential biomarkers or digital signatures to enhance diagnosis, guide therapy and optimize clinical management. Machine learning applications play a crucial role in identifying biomarkers and digital signatures associated with sepsis and its sub-phenotypes. Additionally, electronic phenotyping, leveraging EHR and EMR data, has emerged as a valuable tool for evidence-based sepsis identification and management. This review examines methods for identifying sepsis cohorts, focusing on two main approaches: utilizing health administrative data with standardized diagnostic coding via the International Classification of Diseases and integrating clinical data. This overview provides a comprehensive analysis of current cohort identification and electronic phenotyping strategies for sepsis, highlighting their potential applications and challenges. The accuracy of an electronic phenotype or signature is pivotal for precision medicine, enabling a shift from subjective clinical descriptions to data-driven insights.

Derivation of an artificial intelligence-based electrocardiographic model for the detection of acute coronary occlusive myocardial infarction

Objectives

We aimed to assess the performance of an artificial intelligence-electrocardiogram (AI-ECG)-based model capable of detecting acute coronary occlusion myocardial infarction (ACOMI) in the setting of patients with acute coronary syndrome (ACS).

Methods

This was a prospective, observational, longitudinal, and single-center study including patients with the initial diagnosis of ACS (both ST-elevation acute myocardial infarction [STEMI] & non-ST-segment elevation myocardial infarction [NSTEMI]). To train the deep learning model in recognizing ACOMI, manual digitization of a patient's ECG was conducted using smartphone cameras of varying quality. We relied on the use of convolutional neural networks as the AI models for the classification of ECG examples. ECGs were also independently evaluated by two expert cardiologists blinded to clinical outcomes; each was asked to determine (a) whether the patient had a STEMI, based on universal criteria or (b) if STEMI criteria were not met, to identify any other ECG finding suggestive of ACOMI. ACOMI was defined by coronary angiography findings meeting any of the following three criteria: (a) total thrombotic occlusion, (b) TIMI thrombus grade 2 or higher + TIMI grade flow 1 or less, or (c) the presence of a subocclusive lesion (> 95% angiographic stenosis) with TIMI grade flow < 3. Patients were classified into four groups: STEMI + ACOMI, NSTEMI + ACOMI, STEMI + non-ACOMI, and NSTEMI + non-ACOMI.

Results

For the primary objective of the study, AI outperformed human experts in both NSTEMI and STEMI, with an area under the curve (AUC) of 0.86 (95% confidence interval [CI] 0.75-0.98) for identifying ACOMI, compared with ECG experts using their experience (AUC: 0.33, 95% CI 0.17-0.49) or under universal STEMI criteria (AUC: 0.50, 95% CI 0.35-0.54), (p value for AUC receiver operating characteristic comparison < 0.001). The AI model demonstrated a PPV of 0.84 and an NPV of 1.0.

Conclusion

Our AI-ECG model demonstrated a higher diagnostic precision for the detection of ACOMI compared with experts and the use of STEMI criteria. Further research and external validation are needed to understand the role of AI-based models in the setting of ACS.

Thrombocytopenia in Sepsis

Platelets, traditionally known for their role in hemostasis, have emerged as key players in immune response and inflammation. Sepsis, a life-threatening condition characterized by systemic inflammation, often presents with thrombocytopenia, which at times, can be significant. Platelets contribute to the inflammatory response by interacting with leukocytes, endothelial cells, and the innate immune system. However, excessive platelet activation and consumption can lead to thrombocytopenia and exacerbate the severity of sepsis. Understanding the multifaceted roles of platelets in sepsis is crucial for developing effective therapeutic strategies. Targeting platelet-mediated inflammatory responses and promoting platelet production may offer potential avenues for improving outcomes in septic patients with thrombocytopenia. Future research should focus on elucidating the mechanisms underlying platelet dysfunction in sepsis and exploring novel therapeutic approaches to optimize platelet function and mitigate inflammation. This review explores the intricate relationship between platelets, inflammation, and thrombosis in the context of sepsis.

An Easy and Quick Risk-Stratified Early Forewarning Model for Septic Shock in the Intensive Care Unit: Development, Validation, and Interpretation Study

BACKGROUND

Septic shock (SS) is a syndrome with high mortality. Early forewarning and diagnosis of SS, which are critical in reducing mortality, are still challenging in clinical management.

OBJECTIVE

We propose a simple and fast risk-stratified forewarning model for SS to help physicians recognize patients in time. Moreover, further insights can be gained from the application of the model to improve our understanding of SS.

METHODS

A total of 5125 patients with sepsis from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database were divided into training, validation, and test sets. In addition, 2180 patients with sepsis from the eICU Collaborative Research Database (eICU) were used as an external validation set. We developed a simplified risk-stratified early forewarning model for SS based on the weight of evidence and logistic regression, which was compared with multi-feature complex models, and clinical characteristics among risk groups were evaluated.

RESULTS

Using only vital signs and rapid arterial blood gas test features according to feature importance, we constructed the Septic Shock Risk Predictor (SORP), with an area under the curve (AUC) of 0.9458 in the test set, which is only slightly lower than that of the optimal multi-feature complex model (0.9651). A median forewarning time of 13 hours was calculated for SS patients. 4 distinct risk groups (high, medium, low, and ultralow) were identified by the SORP 6 hours before onset, and the incidence rates of SS in the 4 risk groups in the postonset interval were 88.6% (433/489), 34.5% (262/760), 2.5% (67/2707), and 0.3% (4/1301), respectively. The severity increased significantly with increasing risk in both clinical features and survival. Clustering analysis demonstrated a high similarity of pathophysiological characteristics between the high-risk patients without SS diagnosis (NS_HR) and the SS patients, while a significantly worse overall survival was shown in NS_HR patients. On further exploring the characteristics of the treatment and comorbidities of the NS_HR group, these patients demonstrated a significantly higher incidence of mean blood pressure <65 mmHg, significantly lower vasopressor use and infused volume, and more severe renal dysfunction. The above findings were further validated by multicenter eICU data.

CONCLUSIONS

The SORP demonstrated accurate forewarning and a reliable risk stratification capability. Among patients forewarned as high risk, similar pathophysiological phenotypes and high mortality were observed in both those subsequently diagnosed as having SS and those without such a diagnosis. NS_HR patients, overlooked by the Sepsis-3 definition, may provide further insights into the pathophysiological processes of SS onset and help to complement its diagnosis and precise management. The importance of precise fluid resuscitation management in SS patients with renal dysfunction is further highlighted. For convenience, an online service for the SORP has been provided.

Clinical validation and optimization of machine learning models for early prediction of sepsis

Introduction

Sepsis is a global health threat that has a high incidence and mortality rate. Early prediction of sepsis onset can drive effective interventions and improve patients' outcome.

Methods

Data were collected retrospectively from a cohort of 2,329 adult patients with positive bacteria cultures from a tertiary hospital in China between October 1, 2019 and September 30, 2020. Thirty six clinical features were selected as inputs for the models. We trained models in predicting sepsis by machine learning (ML) methods, including logistic regression, decision tree, random forest (RF), multi-layer perceptron, and light gradient boosting. We evaluated the performance of the five ML models and the evaluation metrics were: area under the ROC curve (AUC), accuracy, F1-score, sensitivity and specificity. The data of another cohort of 2,286 patients between October 1, 2020 and April 1, 2022 were used to validate the performance of the model performing best in the in the internal validation set. Shapley additive explanations (SHAP) method was applied to evaluate feature importance and explain the predictions of this model.

Results

Of the five machine learning models developed, the RF model demonstrated the best performance in terms of AUC (0.818), F1 value (0.38), and sensitivity (0.746). The RF model also has a comparable AUC (0.771) in the external validation set. The SHAP method identified procalcitonin, albumin, prothrombin time, and sex as the important variables contributing to the prediction of sepsis.

Discussion

The RF model we developed showed the greatest potential for early prediction of sepsis in admitted patients, which could aid clinicians in their decision-making process. Our findings also suggested that male patients with bacterial infections and high procalcitonin levels, lower albumin levels, or prolonged prothrombin times were more likely to develop sepsis.

Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload prediction

BACKGROUND

Fluid overload (FO) in the intensive care unit (ICU) is common, serious, and may be preventable. Intravenous medications (including administered volume) are a primary cause for FO but are challenging to evaluate as a FO predictor given the high frequency and time-dependency of their use and other factors affecting FO. We sought to employ unsupervised machine learning methods to uncover medication administration patterns correlating with FO.

METHODS

This retrospective cohort study included 927 adults admitted to an ICU for ≥72 h. FO was defined as a positive fluid balance ≥7% of admission body weight. After reviewing medication administration record data in 3-h periods, medication exposure was categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann Machine (RBM). Medication regimens of patients with and without FO were compared within clusters to assess their temporal association with FO.

RESULTS

FO occurred in 127 (13.7%) of 927 included patients. Patients received a median (interquartile range) of 31(13-65) discrete intravenous medication administrations over the 72-h period. Across all 47,803 intravenous medication administrations, 10 unique medication clusters, containing 121 to 130 medications per cluster, were identified. The mean number of Cluster 7 medications administered was significantly greater in the FO cohort compared with patients without FO (25.6 vs.10.9, p < 0.0001). A total of 51 (40.2%) of 127 unique Cluster 7 medications were administered in more than five different 3-h periods during the 72-h study window. The most common Cluster 7 medications included continuous infusions, antibiotics, and sedatives/analgesics. Addition of Cluster 7 medications to an FO prediction model including the Acute Physiologic and Chronic Health Evaluation (APACHE) II score and receipt of diuretics improved model predictiveness from an Area Under the Receiver Operation Characteristic (AUROC) curve of 0.719 to 0.741 (p = 0.027).

CONCLUSIONS

Using machine learning approaches, a unique medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict FO compared to traditional prediction models. Integration of this approach into real-time clinical applications may improve early detection of FO to facilitate timely intervention.

Integration of Artificial Intelligence for Diagnostic Methods in Musculoskeletal Conditions: A Systematic Review

Artificial intelligence (AI) is a multi-disciplinary area of research focused on understanding, simulating, and replicating intelligence and cognitive functions by applying computational, mathematical, logical, mechanical, and biological principles and technologies. The concept of AI involves investigating and exploring human intelligence and creating artificial computers that use intelligent algorithms to replicate human intelligence. With the appearance of machine learning (ML), deep learning (DL), and convolutional neural networks (CNNs), the key AI techniques that are particularly effective in capturing feature items and learning, AI has evolved into a powerful approach in image analysis. AI may enable more precise evaluations of musculoskeletal impairments, reducing the likelihood of misdiagnosis and improving treatment outcomes for patients. With improved diagnostic capabilities, physiotherapists can create tailored rehabilitation programs that cater to the specific needs and conditions of individual patients. This study aimed to explore and evaluate the integration of AI technologies in diagnostic methods to enhance assessment accuracy. A systematic review was conducted from available literature on AI applications in musculoskeletal diagnostics. Available articles from 2015 to 2025 were included in the study. Analysis of current research's trends, advantages, constraints, and gaps was recognized. This study highlights the promising role of AI technologies in enhancing the accuracy and efficiency of musculoskeletal diagnostics. The integration of AI has the potential to revolutionize diagnostic methods, offering more precise assessments and reducing the likelihood of misdiagnosis. The issue of deploying AI tools for diagnostic purposes needs more attention.

Enhancing Real-Time Patient Monitoring in Intensive Care Units with Deep Learning and the Internet of Things

The demand for intensive care units (ICUs) is steadily increasing, yet there is a relative shortage of medical staff to meet this need. Intensive care work is inherently heavy and stressful, highlighting the importance of optimizing these units' working conditions and processes. Such optimization is crucial for enhancing work efficiency and elevating the level of diagnosis and treatment provided in ICUs. The intelligent ICU concept represents a novel ward management model that has emerged through advancements in modern science and technology. This includes communication technology, the Internet of Things (IoT), artificial intelligence (AI), robotics, and big data analytics. By leveraging these technologies, the intelligent ICU aims to significantly reduce potential risks associated with human error and improve patient monitoring and treatment outcomes. Deep learning (DL) and IoT technologies have huge potential to revolutionize the surveillance of patients in the ICUs due to the critical and complex nature of their conditions. This article provides an overview of the most recent research and applications of linical data for critically ill patients, with a focus on the execution of AI. In the ICU, seamless and continuous monitoring is critical, as even little delays in patient care decision-making can result in irreparable repercussions or death. This article looks at how modern technologies like DL and the IoT can improve patient monitoring, clinical results, and ICU processes. Furthermore, it investigates the function of wearable and advanced health sensors coupled with IoT networking systems, which enable the secure connection and analysis of various forms of patient data for predictive and remote analysis by medical professionals. By assessing existing patient monitoring systems, outlining the roles of DL and IoT, and analyzing the benefits and limitations of their integration, this study hopes to shed light on the future of ICU patient care and identify opportunities for further research.

Artificial intelligence for body composition assessment focusing on sarcopenia

This study aimed to address the limitations of conventional methods for measuring skeletal muscle mass for sarcopenia diagnosis by introducing an artificial intelligence (AI) system for direct computed tomography (CT) analysis. The primary focus was on enhancing simplicity, reproducibility, and convenience, and assessing the accuracy and speed of AI compared with conventional methods. A cohort of 3096 cases undergoing CT imaging up to the third lumbar (L3) level between 2011 and 2021 were included. Random division into preprocessing and sarcopenia cohorts was performed, with further random splits into training and validation cohorts for BMI_AI and Body_AI creation. Sarcopenia_AI utilizes the Skeletal Muscle Index (SMI), which is calculated as (total skeletal muscle area at L3)/(height)2. The SMI was conventionally measured twice, with the first as the AI label reference and the second for comparison. Agreement and diagnostic change rates were calculated. Three groups were randomly assigned and 10 images before and after L3 were collected for each case. AI models for body region detection (Deeplabv3) and sarcopenia diagnosis (EfficientNetV2-XL) were trained on a supercomputer, and their abilities and speed per image were evaluated. The conventional method showed a low agreement rate (κ coefficient) of 0.478 for the test cohort and 0.236 for the validation cohort, with diagnostic changes in 43% of cases. Conversely, the AI consistently produced identical results after two measurements. The AI demonstrated robust body region detection ability (intersection over Union (IoU) = 0.93), accurately detecting only the body region in all images. The AI for sarcopenia diagnosis exhibited high accuracy, with a sensitivity of 82.3%, specificity of 98.1%, and a positive predictive value of 89.5%. In conclusion, the reproducibility of the conventional method for sarcopenia diagnosis was low. The developed sarcopenia diagnostic AI, with its high positive predictive value and convenient diagnostic capabilities, is a promising alternative for addressing the shortcomings of conventional approaches.

Harnessing artificial intelligence in sepsis care: advances in early detection, personalized treatment, and real-time monitoring

Sepsis remains a leading cause of morbidity and mortality worldwide due to its rapid progression and heterogeneous nature. This review explores the potential of Artificial Intelligence (AI) to transform sepsis management, from early detection to personalized treatment and real-time monitoring. AI, particularly through machine learning (ML) techniques such as random forest models and deep learning algorithms, has shown promise in analyzing electronic health record (EHR) data to identify patterns that enable early sepsis detection. For instance, random forest models have demonstrated high accuracy in predicting sepsis onset in intensive care unit (ICU) patients, while deep learning approaches have been applied to recognize complications such as sepsis-associated acute respiratory distress syndrome (ARDS). Personalized treatment plans developed through AI algorithms predict patient-specific responses to therapies, optimizing therapeutic efficacy and minimizing adverse effects. AI-driven continuous monitoring systems, including wearable devices, provide real-time predictions of sepsis-related complications, enabling timely interventions. Beyond these advancements, AI enhances diagnostic accuracy, predicts long-term outcomes, and supports dynamic risk assessment in clinical settings. However, ethical challenges, including data privacy concerns and algorithmic biases, must be addressed to ensure fair and effective implementation. The significance of this review lies in addressing the current limitations in sepsis management and highlighting how AI can overcome these hurdles. By leveraging AI, healthcare providers can significantly enhance diagnostic accuracy, optimize treatment protocols, and improve overall patient outcomes. Future research should focus on refining AI algorithms with diverse datasets, integrating emerging technologies, and fostering interdisciplinary collaboration to address these challenges and realize AI's transformative potential in sepsis care.

Leveraging artificial intelligence for predicting spontaneous closure of perimembranous ventricular septal defect in children: a multicentre, retrospective study in China

BACKGROUND

Perimembranous ventricular septal defect (PMVSD) is a prevalent congenital heart disease, presenting challenges in predicting spontaneous closure, which is crucial for therapeutic decisions. Existing models mainly rely on structured echocardiographic parameters or restricted data. This study introduces an artificial intelligence (AI)-based model, which uses natural language processing (NLP) and machine learning with the aim of improving spontaneous closure predictability in PMVSD.

METHODS

We did a multicentre, retrospective analysis using data from 29 142 PMVSD patients across six tertiary centres in China from May, 2004, to September, 2022, for training (70%) and validation (30%; dataset 1, 27 269 patients), and from September, 2001, to December, 2009 for testing (dataset 2, 1873 patients). NLP extracted structured data from echocardiography reports and medical records, which were used to develop machine learning models. Models were evaluated for spontaneous closure occurrence and timing by use of area under the receiver operating characteristic curve (AUC), decision curve analysis, and calibration index.

FINDINGS

Spontaneous closure occurred in 3520 patients (12·1%) at a median of 31 months (IQR 16-56). Eleven NLP-derived predictors, identified via least absolute shrinkage and selection operator, highlighted the importance of defect morphology and patient age. The random survival forest algorithm, selected for its superior concordance indexes, showed excellent predictive performance with validation set AUCs (95% CI) of 0·95 (0·94-0·96) for 1-year and 3-year predictions, and 0·95 (0·95-0·96) for 5-year predictions; testing set AUCs were 0·95 (0·94-0·97) for 1-year predictions, 0·97 (0·96-0·98) for 3-year predictions, and 0·98 (0·97-0·99) for 5-year predictions. The model showed high clinical utility through decision curve analysis, calibration, and risk stratification, maintaining consistent accuracy across centres and subgroups.

INTERPRETATION

This AI-based model for predicting spontaneous closure in PMVSD patients represents a substantial advancement, potentially improving patient management, reducing risks of delayed or inappropriate treatment, and enhancing clinical outcomes.

FUNDING

National Natural Science Foundation of China, Shanghai Municipal Hospital Clinical Technology Project, Shanghai Municipal Health Commission, and Clinical Research Unit of XinHua Hospital.

Artificial intelligence in clinical practice: Quality and evidence

A revolution is taking place within the field of artificial intelligence (AI) with the emergence of generative AI. Although we are in an early phase at the clinical level, there is an exponential increase in the number of scientific articles that use AI (discriminative and generative) in their methodology. According to the current situation, we may be in an "AI bubble" stage; requiring filters and tools to evaluate its application, based on the quality and evidence provided. In this sense, initiatives have been developed to determine standards and guidelines for the use of discriminative AI (CONSORT AI, STARD AI and others), and more recently for generative AI (the CHART collaborative). As a new technology, AI requires scientific regulation to guarantee the efficacy and safety of its applications, while maintaining the quality of care; an evidence-based AI (IABE).

Machine learning-based infection diagnostic and prognostic models in post-acute care settings: a systematic review

OBJECTIVES

This study aims to (1) review machine learning (ML)-based models for early infection diagnostic and prognosis prediction in post-acute care (PAC) settings, (2) identify key risk predictors influencing infection-related outcomes, and (3) examine the quality and limitations of these models.

MATERIALS AND METHODS

PubMed, Web of Science, Scopus, IEEE Xplore, CINAHL, and ACM digital library were searched in February 2024. Eligible studies leveraged PAC data to develop and evaluate ML models for infection-related risks. Data extraction followed the CHARMS checklist. Quality appraisal followed the PROBAST tool. Data synthesis was guided by the socio-ecological conceptual framework.

RESULTS

Thirteen studies were included, mainly focusing on respiratory infections and nursing homes. Most used regression models with structured electronic health record data. Since 2020, there has been a shift toward advanced ML algorithms and multimodal data, biosensors, and clinical notes being significant sources of unstructured data. Despite these advances, there is insufficient evidence to support performance improvements over traditional models. Individual-level risk predictors, like impaired cognition, declined function, and tachycardia, were commonly used, while contextual-level predictors were barely utilized, consequently limiting model fairness. Major sources of bias included lack of external validation, inadequate model calibration, and insufficient consideration of data complexity.

DISCUSSION AND CONCLUSION

Despite the growth of advanced modeling approaches in infection-related models in PAC settings, evidence supporting their superiority remains limited. Future research should leverage a socio-ecological lens for predictor selection and model construction, exploring optimal data modalities and ML model usage in PAC, while ensuring rigorous methodologies and fairness considerations.

A novel classical machine learning framework for early sepsis prediction using electronic health record data from ICU patients

Sepsis, a life-threatening condition triggered by the body's response to infection, remains a significant global health challenge, annually affecting millions in the United States alone with substantial mortality and healthcare costs. Early prediction of sepsis is critical for timely intervention and improved patient outcomes. This study introduces an innovative predictive model leveraging machine learning techniques and a specific data-splitting approach on highly imbalanced electronic health records (EHRs). Using PhysioNet/CinC Challenge 2019 data from 40,336 patients, including vital signs, lab values, and demographics. Preliminary assessments using classical and stacked ML models with Synthetic Minority Oversampling Technique (SMOTE) augmentation were conducted, showing improved performance. It is found that stacking ML models enhances overall accuracy but faces limitations in precision, recall, and F1 score for positive class prediction. A novel data-splitting approach with 5-fold cross-validation and SMOTE and COPULA augmentation techniques demonstrated promise, with F1 scores ranging from 93 % to 94 % using the COPULA technique. COPULA excelled at predictions for different hours' onsets compared to the SMOTE technique. The proposed model outperformed existing studies, suggesting clinical viability for early sepsis prediction.

Prediction of postoperative stroke in patients experienced coronary artery bypass grafting surgery: a machine learning approach

Background

Coronary artery bypass grafting (CABG) surgery has been a widely accepted method for treating coronary artery disease. However, its postoperative complications can have a significant effect on long-term patient outcomes. A retrospective study was conducted to identify before and after surgery that contribute to postoperative stroke in patients undergoing CABG, and to develop predictive models and recommendations for single-factor thresholds.

Materials and methods

We utilized data from 1,200 patients who undergone CABG surgery at the Wuhan Union Hospital from 2016 to 2022, which was divided into a training group (n = 841) and a test group (n = 359). 33 preoperative clinical features and 4 postoperative complications were collected in each group. LASSO is a regression analysis method that performs both variable selection and regularization to enhance model prediction accuracy and interpretability. The LASSO method was used to verify the collected features, and the SHAP value was used to explain the machine model prediction. Six machine learning models were employed, and the performance of the models was evaluated by area under the curve (AUC) and decision curve analysis (DCA). AUC, or area under the receiver operating characteristic curve, quantifies the ability of a model to distinguish between positive and negative outcomes. Finally, this study provided a convenient online tool for predicting CABG patient post-operative stroke.

Results

The study included a combined total of 1,200 patients in both the development and validation cohorts. The average age of the participants in the study was 60.26 years. 910 (75.8%) of the patients were men, and 153 (12.8%) patients were in NYHA class III and IV. Subsequently, LASSO model was used to identify 11 important features, which were mechanical ventilation time, preoperative creatinine value, preoperative renal insufficiency, diabetes, the use of an intra-aortic balloon pump (IABP), age, Cardiopulmonary bypass time, Aortic cross-clamp time, Chronic Obstructive Pulmonary Disease (COPD) history, preoperative arrhythmia and Renal artery stenosis in descending order of importance according to the SHAP value. According to the analysis of receiver operating characteristic (ROC) curve, AUC, DCA and sensitivity, all seven machine learning models perform well and random forest (RF) machine model was found to perform best (AUC-ROC = 0.9008, Accuracy: 0.9008, Precision: 0.6905; Recall: 0.7532, F1: 0.7205). Finally, an online tool was established to predict the occurrence of stroke after CABG based on the 11 selected features.

Conclusion

Mechanical ventilation time, preoperative creatinine value, preoperative renal insufficiency, diabetes, the use of an intra-aortic balloon pump (IABP), age, Cardiopulmonary bypass time, Aortic cross-clamp time, Chronic Obstructive Pulmonary Disease (COPD) history, preoperative arrhythmia and Renal artery stenosis in the preoperative and intraoperative period was associated with significant postoperative stroke risk, and these factors can be identified and modeled to assist in implementing proactive measures to protect the brain in high-risk patients after surgery.

Flexible wearable piezoresistive physical sensors with photothermal conversion and self-cleaning functions for human motion monitoring

Flexible wearable sensors can mimic the sensing ability of the skin and transform deformation stimuli into monitorable electrical signals, making them favorable in the fields of personalized healthcare, human motion monitoring, and remote monitoring systems. Here, an innovative piezoresistive physical sensor based on fluorine-free superhydrophobic dodecyltrimethoxysilane/polypyrrole/carbon nanotube (DTMS/PPy/CNT) cotton fabrics (DPC-CFs) was assembled via an environmentally safe and simple dip-coating method. The flexible wearable sensor exhibits self-cleaning capability (high water contact angle of 158.3°), good electrical conductivity (45.43 S m-1), photo-thermal conversion (surface temperature up to 94.8 °C), rapid response/recovery time (60 ms/50 ms), and excellent stability (>2400 cycles), and was successfully applied to dynamic monitoring of a series of human activities such as wrist pulse, voice recognition, and finger bending. Furthermore, the development of the superhydrophobic piezoresistive physical sensor derived from biodegradable cotton fabrics means an important step forward in the evolution of wearable sensors, which not only provide better coverage of three-dimensional irregular surfaces to capture mechanical stimulation signals but also demonstrate better comfort, flexibility and versatility. It is foreseen that such sensors, which are fabricated by utilizing abundant renewable and biodegradable green raw materials, have a broad application prospect in the next generation of biomedical systems, fitness, and human-computer interactive devices.

Digital Information Ecosystems in Modern Care Coordination and Patient Care Pathways and the Challenges and Opportunities for AI Solutions

The integration of digital technologies into health care has significantly enhanced the efficiency and effectiveness of care coordination. Our perspective paper explores the digital information ecosystems in modern care coordination, focusing on the processes of information generation, updating, transmission, and exchange along a patient's care pathway. We identify several challenges within this ecosystem, including interoperability issues, information silos, hard-to-map patient care journeys, increased workload on health care professionals, coordination and communication gaps, and compliance with privacy regulations. These challenges are often associated with inefficiencies and diminished care quality. We also examine how emerging artificial intelligence (AI) tools have the potential to enhance the management of patient information flow. Specifically, AI can boost interoperability across diverse health systems; optimize and monitor patient care pathways; improve information retrieval and care transitions; humanize health care by integrating patients' desired outcomes and patient-reported outcome measures; and optimize clinical workflows, resource allocation, and digital tool usability and user experiences. By strategically leveraging AI, health care systems can establish a more robust and responsive digital information ecosystem, improving care coordination and patient outcomes. This perspective underscores the importance of continued research and investment in AI technologies in patient care pathways. We advocate for a thoughtful integration of AI into health care practices to fully realize its potential in revolutionizing care coordination.

An optimal antibiotic selection framework for Sepsis patients using Artificial Intelligence

In this work we present OptAB, the first completely data-driven online-updateable antibiotic selection model based on Artificial Intelligence for Sepsis patients accounting for side-effects. OptAB performs an iterative optimal antibiotic selection for real-world Sepsis patients focussing on minimizing the Sepsis-related organ failure score (SOFA-Score) as treatment success while accounting for nephrotoxicity and hepatotoxicity as serious antibiotic side-effects. OptAB provides disease progression forecasts for (combinations of) the antibiotics Vancomycin, Ceftriaxone and Piperacillin/Tazobactam and learns realistic treatment influences on the SOFA-Score and the laboratory values creatinine, bilirubin total and alanine-transaminase indicating possible side-effects. OptAB is based on a hybrid neural network differential equation algorithm and can handle the special characteristics of patient data including irregular measurements, a large amount of missing values and time-dependent confounding. OptAB's selected optimal antibiotics exhibit faster efficacy than the administered antibiotics.

CISepsis: a causal inference framework for early sepsis detection

Introduction

The early prediction of sepsis based on machine learning or deep learning has achieved good results.Most of the methods use structured data stored in electronic medical records, but the pathological characteristics of sepsis involve complex interactions between multiple physiological systems and signaling pathways, resulting in mixed structured data. Some researchers will introduce unstructured data when also introduce confounders. These confounders mask the direct causality of sepsis, leading the model to learn misleading correlations. Finally, it affects the generalization ability, robustness, and interpretability of the model.

Methods

To address this challenge, we propose an early sepsis prediction approach based on causal inference which can remove confounding effects and capture causal relationships. First, we analyze the relationship between each type of observation, confounder, and label to create a causal structure diagram. To eliminate the effects of different confounders separately, the methods of back-door adjustment and instrumental variable are used. Specifically, we learn the confounder and an instrumental variable based on mutual information from various observed data and eliminate the influence of the confounder by optimizing mutual information. We use back-door adjustment to eliminate the influence of confounders in clinical notes and static indicators on the true causal effect.

Results

Our method, named CISepsis, was validated on the MIMIC-IV dataset. Compared to existing state-of-the-art early sepsis prediction models such as XGBoost, LSTM, and MGP-AttTCN, our method demonstrated a significant improvement in AUC. Specifically, our model achieved AUC values of 0.921, 0.920, 0.919, 0.923, 0.924, 0.926, and 0.926 at the 6, 5, 4, 3, 2, 1, and 0 time points, respectively. Furthermore, the effectiveness of our method was confirmed through ablation experiments.

Discussion

Our method, based on causal inference, effectively removes the influence of confounding factors, significantly improving the predictive accuracy of the model. Compared to traditional methods, this adjustment allows for a more accurate capture of the true causal effects of sepsis, thereby enhancing the model's generalizability, robustness, and interpretability. Future research will explore the impact of specific indicators or treatment interventions on sepsis using counterfactual adjustments in causal inference, as well as investigate the potential clinical application of our method.

MAPRS: An intelligent approach for post-prescription review based on multi-label learning

Antimicrobial resistance (AMR) is a major threat to public health worldwide. It is a promising way to improve appropriate prescription by the review and stewardship of antimicrobials, and Post-Prescription Review (PPR) is currently the main tool used in hospitals. Existing methods of PPR typically focus on the dichotomy of antimicrobial prescription based on binary classification which, however, is usually a multi-label classification problem. Moreover, previous research did not explain the causes beneath the inappropriate antimicrobial used in the clinical setting, which could be practically important for problem location and decision improvement. In this paper, we collected antimicrobial prescriptions and related data from clean surgery in a hospital in northeastern China, and proposed a Multi-label Antimicrobial Post-Prescription Review System (MAPRS). MAPRS first uses NLP techniques to process unstructured data in prescriptions and explores the value of clinical record text for solving medical problems. Then, Classifier Chains are used to deal with multi-label problems and fused with machine learning algorithms to construct a classifier. At last, a SHAP explanation module is introduced to explain the inappropriate prescriptions. The experimental results show that MAPRS could achieve great performance in a challenging six-category multi-label task, with a subset accuracy of 90.7 % and an average AUROC of 94.3 %. Our results can help hospitals to perform intelligent prescription review and improve the antimicrobial stewardship.

Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis

Background

With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the 'golden hour' is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming to optimize their use in clinical practice.

Methods

We searched Medline, PubMed, Google Scholar, and CENTRAL for studies published from inception to October 2023. We focused on studies predicting sepsis in real-time settings in adult patients in any hospital settings without language limits. The primary outcome was area under the curve (AUC) of the receiver operating characteristic. This meta-analysis was conducted according to PRISMA-NMA guidelines and Cochrane Handbook recommendations. A Network Meta-Analysis using the CINeMA approach compared ML models against traditional scoring systems, with meta-regression identifying factors affecting model quality.

Results

From 3,953 studies, 73 articles encompassing 457,932 septic patients and 256 models were analyzed. The pooled AUC for ML models was 0.825 and it significantly outperformed traditional scoring systems. Neural Network and Decision Tree models demonstrated the highest AUC metrics. Significant factors influencing AUC included ML model type, dataset type, and prediction window.

Conclusion

This study establishes the superiority of ML models, especially Neural Network and Decision Tree types, in sepsis prediction. It highlights the importance of model type and dataset characteristics for prediction accuracy, emphasizing the necessity for standardized reporting and validation in ML healthcare applications. These findings call for broader clinical implementation to evaluate the effectiveness of these models in diverse patient groups.

Systematic review registration

https://inplasy.com/inplasy-2023-12-0062/, identifier, INPLASY2023120062.

Recommendations for Performance Evaluation of Machine Learning in Pathology: A Concept Paper From the College of American Pathologists

CONTEXT.—

Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology.

OBJECTIVE.—

To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation.

DATA SOURCES.—

An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks.

CONCLUSIONS.—

Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice.

Role of artificial intelligence in critical care nutrition support and research

Nutrition plays a key role in the comprehensive care of critically ill patients. Determining optimal nutrition strategy, however, remains a subject of intense debate. Artificial intelligence (AI) applications are becoming increasingly common in medicine, and specifically in critical care, driven by the data-rich environment of intensive care units. In this review, we will examine the evidence regarding the application of AI in critical care nutrition. As of now, the use of AI in critical care nutrition is relatively limited, with its primary emphasis on malnutrition screening and tolerance of enteral nutrition. Despite the current scarcity of evidence, the potential for AI for more personalized nutrition management for critically ill patients is substantial. This stems from the ability of AI to integrate multiple data streams reflecting patients' changing needs while addressing inherent heterogeneity. The application of AI in critical care nutrition holds promise for optimizing patient outcomes through tailored and adaptive nutrition interventions. A successful implementation of AI, however, necessitates a multidisciplinary approach, coupled with careful consideration of challenges related to data management, financial aspects, and patient privacy.

Integrated analysis reveals NLRC4 as a potential biomarker in sepsis pathogenesis

Sepsis remains a significant global health burden and contributor to mortality, yet the precise molecular mechanisms underlying the immune response are not fully elucidated. To gain insight into this issue, we performed a comprehensive analysis using a variety of techniques including bulk RNA sequencing, single-cell RNA sequencing, and enzyme-linked immunosorbent assay (ELISA). We performed enrichment analysis of differentially expressed genes in sepsis and healthy individuals by utilizing Gene Ontology (GO) analysis and indicated significant enrichment of immune-related response. Following Weighted Gene Co-Expression Network Analysis (WGCNA) and protein-protein interaction analysis (PPI) were used to identify key immune-related hub genes and validated by ELISA to show that NLRC4 is highly expressed in sepsis. Additionally, an analysis of scRNA-seq data from newly diagnosed sepsis, sepsis diagnosis at 6 hours, and healthy samples demonstrates a significant increase in both the expression levels and proportions of NLRC4 in sepsis monocytes and neutrophils. In addition, using pySCENIC we identified upstream transcription factors that regulate NLRC4. Our study provides valuable insights into the identification of NLRC4 in peripheral blood as a potential candidate gene for the diagnosis and treatment of sepsis.

The Sepsis Score Dilemma: Balancing Precision and Utility

How to cite this article: Pande R, Pandey M. The Sepsis Score Dilemma: Balancing Precision and Utility. Indian J Crit Care Med 2024;28(10):906-907.

Investigating computational models for diagnosis and prognosis of sepsis based on clinical parameters: Opportunities, challenges, and future research directions

This study investigates the use of computational frameworks for sepsis. We consider two dimensions for investigation - early diagnosis of sepsis (EDS) and mortality prediction rate for sepsis patients (MPS). We concentrate on the clinical parameters on which sepsis diagnosis and prognosis are currently done, including customized treatment plans based on historical data of the patient. We identify the most notable literature that uses computational models to address EDS and MPS based on those clinical parameters. In addition to the review of the computational models built upon the clinical parameters, we also provide details regarding the popular publicly available data sources. We provide brief reviews for each model in terms of prior art and present an analysis of their results, as claimed by the respective authors. With respect to the use of machine learning models, we have provided avenues for model analysis in terms of model selection, model validation, model interpretation, and model comparison. We further present the challenges and limitations of the use of computational models, providing future research directions. This study intends to serve as a benchmark for first-hand impressions on the use of computational models for EDS and MPS of sepsis, along with the details regarding which model has been the most promising to date. We have provided details regarding all the ML models that have been used to date for EDS and MPS of sepsis.

Prediction of sepsis mortality in ICU patients using machine learning methods

PROBLEM

Sepsis, a life-threatening condition, accounts for the deaths of millions of people worldwide. Accurate prediction of sepsis outcomes is crucial for effective treatment and management. Previous studies have utilized machine learning for prognosis, but have limitations in feature sets and model interpretability.

AIM

This study aims to develop a machine learning model that enhances prediction accuracy for sepsis outcomes using a reduced set of features, thereby addressing the limitations of previous studies and enhancing model interpretability.

METHODS

This study analyzes intensive care patient outcomes using the MIMIC-IV database, focusing on adult sepsis cases. Employing the latest data extraction tools, such as Google BigQuery, and following stringent selection criteria, we selected 38 features in this study. This selection is also informed by a comprehensive literature review and clinical expertise. Data preprocessing included handling missing values, regrouping categorical variables, and using the Synthetic Minority Over-sampling Technique (SMOTE) to balance the data. We evaluated several machine learning models: Decision Trees, Gradient Boosting, XGBoost, LightGBM, Multilayer Perceptrons (MLP), Support Vector Machines (SVM), and Random Forest. The Sequential Halving and Classification (SHAC) algorithm was used for hyperparameter tuning, and both train-test split and cross-validation methodologies were employed for performance and computational efficiency.

RESULTS

The Random Forest model was the most effective, achieving an area under the receiver operating characteristic curve (AUROC) of 0.94 with a confidence interval of ±0.01. This significantly outperformed other models and set a new benchmark in the literature. The model also provided detailed insights into the importance of various clinical features, with the Sequential Organ Failure Assessment (SOFA) score and average urine output being highly predictive. SHAP (Shapley Additive Explanations) analysis further enhanced the model's interpretability, offering a clearer understanding of feature impacts.

CONCLUSION

This study demonstrates significant improvements in predicting sepsis outcomes using a Random Forest model, supported by advanced machine learning techniques and thorough data preprocessing. Our approach provided detailed insights into the key clinical features impacting sepsis mortality, making the model both highly accurate and interpretable. By enhancing the model's practical utility in clinical settings, we offer a valuable tool for healthcare professionals to make data-driven decisions, ultimately aiming to minimize sepsis-induced fatalities.

Artificial intelligence in clinical nutrition and dietetics: A brief overview of current evidence

The rapid surge in artificial intelligence (AI) has dominated technological innovation in today's society. As experts begin to understand the potential, a spectrum of opportunities could yield a remarkable revolution. The upsurge in healthcare could transform clinical interventions and outcomes, but it risks dehumanization and increased unethical practices. The field of clinical nutrition and dietetics is no exception. This article finds a multitude of developments underway, which include the use of AI for malnutrition screening; predicting clinical outcomes, such as disease onset, and clinical risks, such as drug interactions; aiding interventions, such as estimating nutrient intake; applying precision nutrition, such as measuring postprandial glycemic response; and supporting workflow through chatbots trained on natural language models. Although the opportunity and scalability of AI is incalculably attractive, especially in the face of poor healthcare resources, the threat cannot be ignored. The risk of malpractice and lack of accountability are some of the main concerns. As such, the healthcare professional's responsibility remains paramount. The data used to train AI models could be biased, which could risk the quality of care to vulnerable or minority patient groups. Standardized AI-development protocols, benchmarked to care recommendations, with rigorous large-scale validation are required to maximize application among different settings. AI could overturn the healthcare landscape, and this article skims the surface of its potential in clinical nutrition and dietetics.

Application Value of the Automated Machine Learning Model Based on Modified Computed Tomography Severity Index Combined With Serological Indicators in the Early Prediction of Severe Acute Pancreatitis

BACKGROUND AND AIMS

Machine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. To assess the value of the Modified Computed Tomography Severity Index (MCTSI) combined with serological indicators for early prediction of severe acute pancreatitis (SAP) by automated ML (AutoML).

PATIENTS AND METHODS

The clinical data, of the patients with acute pancreatitis (AP) hospitalized in Hospital 1 and hospital 2 from January 2017 to December 2021, were retrospectively analyzed. Serological indicators within 24 hours of admission were collected. MCTSI score was completed by noncontrast computed tomography within 24 hours of admission. Data from the hospital 1 were adopted for training, and data from the hospital 2 were adopted for external validation. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of AP. Models were built using traditional logistic regression and AutoML analysis with 4 types of algorithms. The performance of models was evaluated by the receiver operating characteristic curve, the calibration curve, and the decision curve analysis based on logistic regression and decision curve analysis, feature importance, SHapley Additive exPlanation Plot, and Local Interpretable Model Agnostic Explanation based on AutoML.

RESULTS

A total of 499 patients were used to develop the models in the training data set. An independent data set of 201 patients was used to test the models. The model developed by the Deep Neural Net (DL) outperformed other models with an area under the receiver operating characteristic curve (areas under the curve) of 0.907 in the test set. Furthermore, among these AutoML models, the DL and gradient boosting machine models achieved the highest sensitivity values, both exceeding 0.800.

CONCLUSION

The AutoML model based on the MCTSI score combined with serological indicators has good predictive value for SAP in the early stage.

Improving sepsis prediction in intensive care with SepsisAI: A clinical decision support system with a focus on minimizing false alarms

Prediction of sepsis using machine-learning approaches has recently gained traction. However, the lack of translation of these algorithms into clinical routine remains a major issue. Existing early sepsis detection methods are either based on the older definition of sepsis or do not accurately detect sepsis leading to the high frequency of false-positive alarms. This results in a well-known issue of clinicians' "alarm fatigue", leading to decreased responsiveness and identification, ultimately resulting in delayed clinical intervention. Hence, there is a fundamental, unmet need for a clinical decision system capable of accurate and timely sepsis diagnosis, running at the point of need. In this work, SepsisAI-a deep-learning algorithm based on long short-term memory (LSTM) networks was developed to predict the early onset of hospital-acquired sepsis in real-time for patients admitted to the ICU. The models are trained and validated with data from the PhysioNet Challenge, consisting of 40,336 patient data files from two healthcare systems: Beth Israel Deaconess Medical Center and Emory University Hospital. In the short term, the algorithm tracks frequently measured vital signs, sparsely available lab parameters, demographic features, and certain derived features for making predictions. A real-time alert system, which monitors the trajectory of the predictions, is developed on top of the deep-learning framework to minimize false alarms. On a balanced test dataset, the model achieves an AUROC, AUPRC, sensitivity, and specificity of 0.95, 0.96, 88.19%, and 96.75%, respectively at the patient level. In terms of lookahead time, the model issues a warning at a median of 6 hours (IQR 6 to 20 hours) and raises an alert at a median of 4 hours (IQR 2 to 5 hours) ahead of sepsis onset. Most importantly, the model achieves a false-alarm ratio of 3.18% for alerts, which is significantly less than other sepsis alarm systems. Additionally, on a disease prevalence-based test set, the algorithm reported similar outcomes with AUROC and AUPRC of 0.94 and 0.87, respectively, with sensitivity, and specificity of 97.05%, and 96.75%, respectively. The proposed algorithm might serve as a clinical decision support system to assist clinicians in the accurate and timely diagnosis of sepsis. With exceptionally high specificity and low false-alarm rate, this algorithm also helps mitigate the well-known issue of clinician alert fatigue arising from currently proposed sepsis alarm systems. Consequently, the algorithm partially addresses the challenges of successfully integrating machine-learning algorithms into routine clinical care.

Definition and Epidemiology of Sepsis

Here we review the epidemiology of sepsis, focusing on its definition, incidence, and mortality, as well as the demographic insights and risk factors that influence its occurrence and outcomes. We address how age, sex, and racial/ethnic disparities impact upon incidence and mortality rates. Sepsis is more frequent and severe among the elderly, males, and certain racial and ethnic groups. Poor socioeconomic status, geographic location, and pre-existing comorbidities also elevate the risk of developing and dying from sepsis. Seasonal variations, with an increased incidence during winter months, is also apparent. We delve into the predictive value of disease severity scores such as the Sequential Organ Failure Assessment score. We also highlight issues relating to coding and administrative data that can generate erroneous and misleading information, and the need for greater consistency. The Sepsis-3 definitions, offering more precise clinical criteria, are a step in the right direction. This overview will, we hope, facilitate understanding of the multi-faceted epidemiological characteristics of sepsis and current challenges.

Development and Validation of Multimodal Models to Predict the 30-Day Mortality of ICU Patients Based on Clinical Parameters and Chest X-Rays

We aimed to develop and validate multimodal ICU patient prognosis models that combine clinical parameters data and chest X-ray (CXR) images. A total of 3798 subjects with clinical parameters and CXR images were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and an external hospital (the test set). The primary outcome was 30-day mortality after ICU admission. Automated machine learning (AutoML) and convolutional neural networks (CNNs) were used to construct single-modal models based on clinical parameters and CXR separately. An early fusion approach was used to integrate both modalities (clinical parameters and CXR) into a multimodal model named PrismICU. Compared to the single-modal models, i.e., the clinical parameter model (AUC = 0.80, F1-score = 0.43) and the CXR model (AUC = 0.76, F1-score = 0.45) and the scoring system APACHE II (AUC = 0.83, F1-score = 0.77), PrismICU (AUC = 0.95, F1 score = 0.95) showed improved performance in predicting the 30-day mortality in the validation set. In the test set, PrismICU (AUC = 0.82, F1-score = 0.61) was also better than the clinical parameters model (AUC = 0.72, F1-score = 0.50), CXR model (AUC = 0.71, F1-score = 0.36), and APACHE II (AUC = 0.62, F1-score = 0.50). PrismICU, which integrated clinical parameters data and CXR images, performed better than single-modal models and the existing scoring system. It supports the potential of multimodal models based on structured data and imaging in clinical management.

Real-time machine learning-assisted sepsis alert enhances the timeliness of antibiotic administration and diagnostic accuracy in emergency department patients with sepsis: a cluster-randomized trial

Machine learning (ML) has been applied in sepsis recognition across different healthcare settings with outstanding diagnostic accuracy. However, the advantage of ML-assisted sepsis alert in expediting clinical decisions leading to enhanced quality for emergency department (ED) patients remains unclear. A cluster-randomized trial was conducted in a tertiary-care hospital. Adult patient data were subjected to an ML model for sepsis alert. Patient visits were assigned into one of two groups. In the intervention cluster, staff received alerts on a display screen if patients met the ML threshold for sepsis diagnosis, while patients in the control cluster followed the regular alert process. The study compared triage-to-antibiotic (TTA) time, length of stay, and mortality rate between the two groups. Additionally, the diagnostic performance of the ML model was assessed. A total of 256 (intervention) and 318 (control) sepsis patients were analyzed. The proportions of patients who received antibiotics within 1 and 3 h were higher in the intervention group than in the control group (in 1 h; 68.4 vs. 60.1%, respectively; P = 0.04, in 3 h; 94.5 vs. 89.0%, respectively; P = 0.02). The median TTA times were marginally shorter in the intervention group (46 vs. 50 min). The area under the receiver operating characteristic curve (AUROC) of ML in early sepsis identification was significantly higher than qSOFA, SIRS, and MEWS. The ML-assisted sepsis alert system may help sepsis ED patients receive antibiotics more rapidly than with the conventional, human-dedicated alert process. The diagnostic performance of ML in prompt sepsis detection was superior to that of the rule-based system.Trial registration Thai Clinical Trials Registry TCTR20230120001. Registered 16 January 2023-Retrospectively registered, https://www.thaiclinicaltrials.org/show/TCTR20230120001 .