A novel artificial intelligence based intensive care unit monitoring system: using physiological waveforms to identify sepsis

Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study

Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.

Parsimonious Waveform-derived Features consisting of Pulse Arrival Time and Heart Rate Variability Predicts the Onset of Septic Shock

Sepsis is a major public health emergency and one of the leading causes of morbidity and mortality in critically ill patients. For each hour treatment is delayed, shock-related mortality increases, so early diagnosis and intervention is of utmost importance. However, earlier recognition of shock requires active monitoring, which may be delayed due to subclinical manifestations of the disease at the early phase of onset. Machine learning systems can increase timely detection of shock onset by exploiting complex interactions among continuous physiological waveforms. We use a dataset consisting of high-resolution physiological waveforms from intensive care unit (ICU) of a tertiary hospital system. We investigate the use of mean arterial blood pressure (MAP), pulse arrival time (PAT), heart rate variability (HRV), and heart rate (HR) for the early prediction of shock onset. Using only five minutes of the aforementioned vital signals from 239 ICU patients, our developed models can accurately predict septic shock onset 6 to 36 hours prior to clinical recognition with area under the receiver operating characteristic (AUROC) of 0.84 and 0.8 respectively. This work lays foundations for a robust, efficient, accurate and early prediction of septic shock onset which may help clinicians in their decision-making processes. This study introduces machine learning models that provide fast and accurate predictions of septic shock onset times up to 36 hours in advance. BP, PAT and HR dynamics can independently predict septic shock onset with a look-back period of only 5 mins.

A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability

BACKGROUND

Sepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (ML) for predicting sepsis, focusing on aspects such as prognosis, diagnosis, and clinical application, there remains a notable deficiency in the discourse regarding feature engineering. Specifically, the role of feature selection and extraction in enhancing model accuracy has been underexplored.

OBJECTIVES

This scoping review aims to fulfill two primary objectives: To identify pivotal features for predicting sepsis across a variety of ML models, providing valuable insights for future model development, and To assess model efficacy through performance metrics including AUROC, sensitivity, and specificity.

RESULTS

The analysis included 29 studies across diverse clinical settings such as Intensive Care Units (ICU), Emergency Departments, and others, encompassing 1,147,202 patients. The review highlighted the diversity in prediction strategies and timeframes. It was found that feature extraction techniques notably outperformed others in terms of sensitivity and AUROC values, thus indicating their critical role in improving sepsis prediction models.

CONCLUSION

Key dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results. Furthermore, Deep Learning models (DL) reveal unique insights, spotlighting the pivotal role of feature engineering in sepsis prediction, which could greatly benefit clinical practice.

[Artificial intelligence in intensive care medicine]

The integration of artificial intelligence (AI) into intensive care medicine has made considerable progress in recent studies, particularly in the areas of predictive analytics, early detection of complications, and the development of decision support systems. The main challenges remain availability and quality of data, reduction of bias and the need for explainable results from algorithms and models. Methods to explain these systems are essential to increase trust, understanding, and ethical considerations among healthcare professionals and patients. Proper training of healthcare professionals in AI principles, terminology, ethical considerations, and practical application is crucial for the successful use of AI. Careful assessment of the impact of AI on patient autonomy and data protection is essential for its responsible use in intensive care medicine. A balance between ethical and practical considerations must be maintained to ensure patient-centered care while complying with data protection regulations. Synergistic collaboration between clinicians, AI engineers, and regulators is critical to realizing the full potential of AI in intensive care medicine and maximizing its positive impact on patient care. Future research and development efforts should focus on improving AI models for real-time predictions, increasing the accuracy and utility of AI-based closed-loop systems, and overcoming ethical, technical, and regulatory challenges, especially in generative AI systems.

Assessment of Sepsis Risk at Admission to the Emergency Department: Clinical Interpretable Prediction Model

This study aims to develop an interpretable prediction model based on explainable artificial intelligence to predict bacterial sepsis and discover important biomarkers. A total of 1572 adult patients, 560 of whom were sepsis positive and 1012 of whom were negative, who were admitted to the emergency department with suspicion of sepsis, were examined. We investigated the performance characteristics of sepsis biomarkers alone and in combination for confirmed sepsis diagnosis using Sepsis-3 criteria. Three different tree-based algorithms-Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost)-were used for sepsis prediction, and after examining comprehensive performance metrics, descriptions of the optimal model were obtained with the SHAP method. The XGBoost model achieved accuracy of 0.898 (0.868-0.929) and area under the ROC curve (AUC) of 0.940 (0.898-0.980) with a 95% confidence interval. The five biomarkers for predicting sepsis were age, respiratory rate, oxygen saturation, procalcitonin, and positive blood culture. SHAP results revealed that older age, higher respiratory rate, procalcitonin, neutrophil-lymphocyte count ratio, C-reactive protein, plaque, leukocyte particle concentration, as well as lower oxygen saturation, systolic blood pressure, and hemoglobin levels increased the risk of sepsis. As a result, the Explainable Artificial Intelligence (XAI)-based prediction model can guide clinicians in the early diagnosis and treatment of sepsis, providing more effective sepsis management and potentially reducing mortality rates and medical costs.

Optimizing artificial intelligence in sepsis management: Opportunities in the present and looking closely to the future

Sepsis remains a major challenge internationally for healthcare systems. Its incidence is rising due to poor public awareness and delays in its recognition and subsequent management. In sepsis, mortality increases with every hour left untreated. Artificial intelligence (AI) is transforming worldwide healthcare delivery at present. This review has outlined how AI can augment strategies to address this global disease burden. AI and machine learning (ML) algorithms can analyze vast quantities of increasingly complex clinical datasets from electronic medical records to assist clinicians in diagnosing and treating sepsis earlier than traditional methods. Our review highlights how these models can predict the risk of sepsis and organ failure even before it occurs. This gives providers additional time to plan and execute treatment plans, thereby avoiding increasing complications associated with delayed diagnosis of sepsis. The potential for cost savings with AI implementation is also discussed, including improving workflow efficiencies, reducing administrative costs, and improving healthcare outcomes. Despite these advantages, clinicians have been slow to adopt AI into clinical practice. Some of the limitations posed by AI solutions include the lack of diverse data sets for model building so that they are widely applicable for routine clinical use. Furthermore, the subsequent algorithms are often based on complex mathematics leading to clinician hesitancy to embrace such technologies. Finally, we highlight the need for robust political and regulatory frameworks in this area to achieve the trust and approval of clinicians and patients to implement this transformational technology.

The application of artificial intelligence in the management of sepsis

Sepsis is a complex and heterogeneous syndrome that remains a serious challenge to healthcare worldwide. Patients afflicted by severe sepsis or septic shock are customarily placed under intensive care unit (ICU) supervision, where a multitude of apparatus is poised to produce high-granularity data. This reservoir of high-quality data forms the cornerstone for the integration of AI into clinical practice. However, existing reviews currently lack the inclusion of the latest advancements. This review examines the evolving integration of artificial intelligence (AI) in sepsis management. Applications of artificial intelligence include early detection, subtyping analysis, precise treatment and prognosis assessment. AI-driven early warning systems provide enhanced recognition and intervention capabilities, while profiling analyzes elucidate distinct sepsis manifestations for targeted therapy. Precision medicine harnesses the potential of artificial intelligence for pathogen identification, antibiotic selection, and fluid optimization. In conclusion, the seamless amalgamation of artificial intelligence into the domain of sepsis management heralds a transformative shift, ushering in novel prospects to elevate diagnostic precision, therapeutic efficacy, and prognostic acumen. As AI technologies develop, their impact on shaping the future of sepsis care warrants ongoing research and thoughtful implementation.

Prediction of episode of hemodynamic instability using an electrocardiogram based analytic: a retrospective cohort study

BACKGROUND

Predicting the onset of hemodynamic instability before it occurs remains a sought-after goal in acute and critical care medicine. Technologies that allow for this may assist clinicians in preventing episodes of hemodynamic instability (EHI). We tested a novel noninvasive technology, the Analytic for Hemodynamic Instability-Predictive Indicator (AHI-PI), which analyzes a single lead of electrocardiogram (ECG) and extracts heart rate variability and morphologic waveform features to predict an EHI prior to its occurrence.

METHODS

Retrospective cohort study at a quaternary care academic health system using data from hospitalized adult patients between August 2019 and April 2020 undergoing continuous ECG monitoring with intermittent noninvasive blood pressure (NIBP) or with continuous intraarterial pressure (IAP) monitoring.

RESULTS

AHI-PI's low and high-risk indications were compared with the presence of EHI in the future as indicated by vital signs (heart rate > 100 beats/min with a systolic blood pressure < 90 mmHg or a mean arterial blood pressure of < 70 mmHg). 4,633 patients were analyzed (3,961 undergoing NIBP monitoring, 672 with continuous IAP monitoring). 692 patients had an EHI (380 undergoing NIBP, 312 undergoing IAP). For IAP patients, the sensitivity and specificity of AHI-PI to predict EHI was 89.7% and 78.3% with a positive and negative predictive value of 33.7% and 98.4% respectively. For NIBP patients, AHI-PI had a sensitivity and specificity of 86.3% and 80.5% with a positive and negative predictive value of 11.7% and 99.5% respectively. Both groups performed with an AUC of 0.87. AHI-PI predicted EHI in both groups with a median lead time of 1.1 h (average lead time of 3.7 h for IAP group, 2.9 h for NIBP group).

CONCLUSIONS

AHI-PI predicted EHIs with high sensitivity and specificity and within clinically significant time windows that may allow for intervention. Performance was similar in patients undergoing NIBP and IAP monitoring.

Predicting patient decompensation from continuous physiologic monitoring in the emergency department

Anticipation of clinical decompensation is essential for effective emergency and critical care. In this study, we develop a multimodal machine learning approach to predict the onset of new vital sign abnormalities (tachycardia, hypotension, hypoxia) in ED patients with normal initial vital signs. Our method combines standard triage data (vital signs, demographics, chief complaint) with features derived from a brief period of continuous physiologic monitoring, extracted via both conventional signal processing and transformer-based deep learning on ECG and PPG waveforms. We study 19,847 adult ED visits, divided into training (75%), validation (12.5%), and a chronologically sequential held-out test set (12.5%). The best-performing models use a combination of engineered and transformer-derived features, predicting in a 90-minute window new tachycardia with AUROC of 0.836 (95% CI, 0.800-0.870), new hypotension with AUROC 0.802 (95% CI, 0.747-0.856), and new hypoxia with AUROC 0.713 (95% CI, 0.680-0.745), in all cases significantly outperforming models using only standard triage data. Salient features include vital sign trends, PPG perfusion index, and ECG waveforms. This approach could improve the triage of apparently stable patients and be applied continuously for the prediction of near-term clinical deterioration.

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression

We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient's data. To solve this problem, we propose a supervised contrastive learning framework that learns an embedding representation for each time step of a patient time series. Our framework learns the embedding space to have the following properties: (1) nearby points in the embedding space have similar predicted class probabilities, (2) adjacent time steps of the same time series map to nearby points in the embedding space, and (3) time steps with very different raw feature vectors map to far apart regions of the embedding space. To achieve property (3), we employ a nearest neighbor pairing mechanism in the raw feature space. This mechanism also serves as an alternative to "data augmentation", a key ingredient of contrastive learning, which lacks a standard procedure that is adequately realistic for clinical tabular data, to our knowledge. We demonstrate that our approach outperforms state-of-the-art baselines in predicting mortality of septic patients (MIMIC-III dataset) and tracking progression of cognitive impairment (ADNI dataset). Our method also consistently recovers the correct synthetic dataset embedding structure across experiments, a feat not achieved by baselines. Our ablation experiments show the pivotal role of our nearest neighbor pairing.

Development and Comparative Performance of Physiologic Monitoring Strategies in the Emergency Department

IMPORTANCE

Accurate and timely documentation of vital signs affects all aspects of triage, diagnosis, and management. The adequacy of current patient monitoring practices and the potential to improve on them are poorly understood.

OBJECTIVE

To develop measures of fit between documented and actual patient vital signs throughout the visit, as determined from continuous physiologic monitoring, and to compare the performance of actual practice with alternative patient monitoring strategies.

DESIGN, SETTING, AND PARTICIPANTS

This cross-sectional study evaluated 25 751 adult visits to continuously monitored emergency department (ED) beds between August 1, 2020, and December 31, 2021. A series of monitoring strategies for the documentation of vital signs (heart rate [HR], respiratory rate [RR], oxygen saturation by pulse oximetry [Spo2], mean arterial pressure [MAP]) was developed and the strategies' ability to capture physiologic trends and vital sign abnormalities simulated. Strategies included equal spacing of charting events, charting at variable intervals depending on the last observed values, and discrete optimization of charting events.

MAIN OUTCOMES AND MEASURES

Coverage was defined as the proportion of monitor-derived vital sign measurements (at 1-minute resolution) that fall within the bounds of nursing-charted values over the course of an ED visit (HR ± 5 beats/min, RR ± 3 breaths/min, Spo2 ± 2%, and MAP ± 6 mm Hg). Capture was defined as the documentation of a vital sign abnormality detected by bedside monitor (tachycardia [HR >100 beats/min], bradycardia [HR <60 beats/min], hypotension [MAP <65 mm Hg], and hypoxia [Spo2 <95%]).

RESULTS

Median patient age was 60 years (IQR, 43-75 years), and 13 329 visits (51.8%) were by women. Monitored visits had a median of 4 (IQR, 2-5) vital sign charting events per visit. Compared with actual practice, a simple rule, which observes vital signs more frequently if the last observation fell outside the bounds of the previous values, and using the same number of observations as actual practice, produced relative coverage improvements of 31.5% (95% CI, 30.5%-32.5%) for HR, 31.0% (95% CI, 30.0%-32.0%) for MAP, 16.8% (95% CI, 16.0%-17.6%) for RR, and 7.8% (95% CI, 7.3%-8.3%) for Spo2. The same strategy improved capture of abnormalities by 38.9% (95% CI, 26.8%-52.2%) for tachycardia, 38.1% (95% CI, 29.0%-47.9%) for bradycardia, 39.0% (95% CI, 24.2%-55.7%) for hypotension, and 123.1% (95% CI, 110.7%-136.3%) for hypoxia. Analysis of optimal coverage suggested an additional scope for improvement through more sophisticated strategies.

CONCLUSIONS AND RELEVANCE

In this cross-sectional study, actual documentation of ED vital signs was variable and incomplete, missing important trends and abnormalities. Alternative monitoring strategies may improve on current practice without increasing the overall frequency of patient monitoring.

Characterization of Physiologic Patients' Response to Fluid Interventions in the Intensive Care Unit

Fluid administration is one of the most common therapies performed on intensive care patients. However, no clinical evidence is available to establish optimal strategies for fluid management as well as characterizing the effects on the cardiovascular system after therapy initiation. Moreover, fluid overload showed a correlation with worse clinical outcomes. This study aims at characterizing the response to the fluid intervention of intensive care unit patients. We extracted a population of 57 subjects with available electrocardiogram and arterial blood pressure recordings from the MIMIC-III database and evaluated the induced changes in cardiovascular and autonomic indices. We compare autonomic indices obtained from a statistical model of heartbeat dynamics before and after the intervention. Results show significant differences in RR interval, blood pressure, autonomic and Baroreflex activities up to 60 minutes after fluid administration. Specifically, we observed a median increase in RR interval, Baroreflex activity, and overall activity both in pressure and RR time series, as well as a reduction in systolic blood pressure. Specifically, a subgroup of survived patients shows an imbalance toward sympathetic activity, whereas non-survivors have a persistent vagal state after fluid administration. Clinical relevance - The observed differences in autonomic response after fluid administration, together with the assessment of their correlation with patients' mortality, paves the way for the inclusion of heart rate variability indices as markers for assessing fluid responsiveness as associated with ICU patients' state.

Advanced computation in cardiovascular physiology: new challenges and opportunities

Recent developments in computational physiology have successfully exploited advanced signal processing and artificial intelligence tools for predicting or uncovering characteristic features of physiological and pathological states in humans. While these advanced tools have demonstrated excellent diagnostic capabilities, the high complexity of these computational 'black boxes' may severely limit scientific inference, especially in terms of biological insight about both physiology and pathological aberrations. This theme issue highlights current challenges and opportunities of advanced computational tools for processing dynamical data reflecting autonomic nervous system dynamics, with a specific focus on cardiovascular control physiology and pathology. This includes the development and adaptation of complex signal processing methods, multivariate cardiovascular models, multiscale and nonlinear models for central-peripheral dynamics, as well as deep and transfer learning algorithms applied to large datasets. The width of this perspective highlights the issues of specificity in heartbeat-related features and supports the need for an imminent transition from the black-box paradigm to explainable and personalized clinical models in cardiovascular research. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.