A computational approach to early sepsis detection

Sepsis mortality prediction with Machine Learning Tecniques

OBJECTIVE

To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU).

DESIGN

Cross-sectional descriptive study.

SETTING

The Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database.

PATIENTS

180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database.

MAIN VARIABLES OF INTEREST

Age, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels.

RESULTS

A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%.

CONCLUSIONS

According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.

Automating detection of diagnostic error of infectious diseases using machine learning

Diagnostic error, a cause of substantial morbidity and mortality, is largely discovered and evaluated through self-report and manual review, which is costly and not suitable to real-time intervention. Opportunities exist to leverage electronic health record data for automated detection of potential misdiagnosis, executed at scale and generalized across diseases. We propose a novel automated approach to identifying diagnostic divergence considering both diagnosis and risk of mortality. Our objective was to identify cases of emergency department infectious disease misdiagnoses by measuring the deviation between predicted diagnosis and documented diagnosis, weighted by mortality. Two machine learning models were trained for prediction of infectious disease and mortality using the first 24h of data. Charts were manually reviewed by clinicians to determine whether there could have been a more correct or timely diagnosis. The proposed approach was validated against manual reviews and compared using the Spearman rank correlation. We analyzed 6.5 million ED visits and over 700 million associated clinical features from over one hundred emergency departments. The testing set performances of the infectious disease (Macro F1 = 86.7, AUROC 90.6 to 94.7) and mortality model (Macro F1 = 97.6, AUROC 89.1 to 89.1) were in expected ranges. Human reviews and the proposed automated metric demonstrated positive correlations ranging from 0.231 to 0.358. The proposed approach for diagnostic deviation shows promise as a potential tool for clinicians to find diagnostic errors. Given the vast number of clinical features used in this analysis, further improvements likely need to either take greater account of data structure (what occurs before when) or involve natural language processing. Further work is needed to explain the potential reasons for divergence and to refine and validate the approach for implementation in real-world settings.

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.

Diagnostic test accuracy in longitudinal study settings: theoretical approaches with use cases from clinical practice

OBJECTIVES

In this study, we evaluate how to estimate diagnostic test accuracy (DTA) correctly in the presence of longitudinal patient data (ie, repeated test applications per patient).

STUDY DESIGN AND SETTING

We used a nonparametric approach to estimate the sensitivity and specificity of three tests for different target conditions with varying characteristics (ie, episode length and disease-free intervals between episodes): 1) systemic inflammatory response syndrome (n = 36), 2) depression (n = 33), and 3) epilepsy (n = 30). DTA was estimated on the levels 'time', 'block', and 'patient-time' for each diagnosis, representing different research questions. The estimation was conducted for the time units per minute, per hour, and per day.

RESULTS

A comparison of DTA per and across use cases showed variations in the estimates, which resulted from the used level, the time unit, the resulting number of observations per patient, and the diagnosis-specific characteristics. Intra- and inter-use-case comparisons showed that the time-level had the highest DTA, particularly the larger the time unit, and that the patient-time-level approximated 50% sensitivity and specificity.

CONCLUSION

Researchers need to predefine their choices (ie, estimation levels and time units) based on their individual research aims, estimands, and diagnosis-specific characteristics of the target outcomes to make sure that unbiased and clinically relevant measures are communicated. In cases of uncertainty, researchers could report the DTA of the test using more than one estimation level and/or time unit.

Brave New World of Artificial Intelligence: Its Use in Antimicrobial Stewardship-A Systematic Review

Antimicrobial resistance (AMR) is a growing public health problem in the One Health dimension. Artificial intelligence (AI) is emerging in healthcare, since it is helpful to deal with large amounts of data and as a prediction tool. This systematic review explores the use of AI in antimicrobial stewardship programs (ASPs) and summarizes the predictive performance of machine learning (ML) algorithms, compared with clinical decisions, in inpatients and outpatients who need antimicrobial prescriptions. This review includes eighteen observational studies from PubMed, Scopus, and Web of Science. The exclusion criteria comprised studies conducted only in vitro, not addressing infectious diseases, or not referencing the use of AI models as predictors. Data such as study type, year of publication, number of patients, study objective, ML algorithms used, features, and predictors were extracted from the included publications. All studies concluded that ML algorithms were useful to assist antimicrobial stewardship teams in multiple tasks such as identifying inappropriate prescribing practices, choosing the appropriate antibiotic therapy, or predicting AMR. The most extracted performance metric was AUC, which ranged from 0.64 to 0.992. Despite the risks and ethical concerns that AI raises, it can play a positive and promising role in ASP.

A time series driven model for early sepsis prediction based on transformer module

Sepsis remains a critical concern in intensive care units due to its high mortality rate. Early identification and intervention are paramount to improving patient outcomes. In this study, we have proposed predictive models for early sepsis prediction based on time-series data, utilizing both CNN-Transformer and LSTM-Transformer architectures. By collecting time-series data from patients at 4, 8, and 12 h prior to sepsis diagnosis and subjecting it to various network models for analysis and comparison. In contrast to traditional recurrent neural networks, our model exhibited a substantial improvement of approximately 20%. On average, our model demonstrated an accuracy of 0.964 (± 0.018), a precision of 0.956 (± 0.012), a recall of 0.967 (± 0.012), and an F1 score of 0.959 (± 0.014). Furthermore, by adjusting the time window, it was observed that the Transformer-based model demonstrated exceptional predictive capabilities, particularly within the earlier time window (i.e., 12 h before onset), thus holding significant promise for early clinical diagnosis and intervention. Besides, we employed the SHAP algorithm to visualize the weight distribution of different features, enhancing the interpretability of our model and facilitating early clinical diagnosis and intervention.

Global research trends in artificial intelligence for critical care with a focus on chord network charts: Bibliometric analysis

BACKGROUND

The field of critical care-related artificial intelligence (AI) research is rapidly gaining interest. However, there is still a lack of comprehensive bibliometric studies that measure and analyze scientific publications on a global scale. Network charts have traditionally been used to highlight author collaborations and coword phenomena (ACCP). It is necessary to determine whether chord network charts (CNCs) can provide a better understanding of ACCP, thus requiring clarification. This study aimed to achieve 2 objectives: evaluate global research trends in AI in intensive care medicine on publication outputs, coauthorships between nations, citations, and co-occurrences of keywords; and demonstrate the use of CNCs for ACCP in bibliometric analysis.

METHODS

The web of science database was searched for a total of 1992 documents published between 2013 and 2022. The document type was limited to articles and article reviews, and titles and abstracts were screened for eligibility. The characteristics of the publications, including preferred journals, leading research countries, international collaborations, top institutions, and major keywords, were analyzed using the category-journal rank-authorship-L-index score and trend analysis. The 100 most highly cited articles are also listed in detail.

RESULTS

Between 2018 and 2022, there was a sharp increase in publications, which accounted for 92.8% (1849/1992) of all papers included in the study. The United States and China were responsible for nearly 50% (936/1992) of the total publications. The leading countries, institutes, departments, authors, and journals in terms of publications were the US, Massachusetts Gen Hosp (US), Medical School, Zhongheng Zhang (China), and Science Reports. The top 3 primary keywords denoting research hotspots for AI in critically ill patients were mortality, model, and intensive care unit, with mortality having the highest burst strength (4.49). The keywords risk and system showed the highest growth trend (0.98) in counts over the past 4 years.

CONCLUSIONS

This study provides valuable insights into the potential for ACCP and future research opportunities. For AI-based clinical research to become widely accepted in critical care practice, collaborative research efforts are necessary to strengthen the maturity and robustness of AI-driven models using CNCs for display.

Frequent temporal patterns of physiological and biological biomarkers and their evolution in sepsis

Sepsis is one of the most challenging health conditions worldwide, with relatively high incidence and mortality rates. It is shown that preventing sepsis is the key to avoid potentially irreversible organ dysfunction. However, data-driven early identification of sepsis is challenging as sepsis shares signs and symptoms with other health conditions. This paper adopts a temporal pattern mining approach to identify frequent temporal and evolving patterns of physiological and biological biomarkers in sepsis patients. We show that using these frequent patterns as features for classifying sepsis and non-sepsis patients can improve the prediction accuracy and performance up to 7%. Most of the temporal modeling approaches adopted in the sepsis literature are based on deep learning methods. Although these approaches produce high accuracy, they generally have limited model explainability and interpretability. Using the adopted methods in this study, we could identify the most important features contributing to the patients' sepsis incidence, such as fluctuations in platelet, lactate, and creatinine, or evolution of patterns including renal and metabolic organ systems, and consequently, enhance the findings' clinical interpretability.

Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis

BACKGROUND AND AIM

Preterm infants are prone to neonatal infections such as late-onset sepsis (LOS). The consequences of LOS can be severe and potentially life-threatening. Unfortunately, LOS often presents with unspecific symptoms, and early screening laboratory tests have limited diagnostic value and are often late. This study aimed to build a predictive algorithm to aid doctors in the early detection of LOS in very preterm infants.

METHODS

In a retrospective cohort study, all consecutively admitted preterm infants (GA ≤ 32 weeks) from 2008 until 2019 were included. They were classified as LOS or control according to blood culture results, currently the gold standard. To generate features, routine and continuously measured oxygen saturation and heart rate data with a minute-by-minute sampling rate were extracted from electronic medical records. Care was taken not to include variables indicative of existing LOS suspicion. The timing of a positive blood culture served as a proxy for LOS-onset. An equivalent timestamp was generated in gestational-age-matched control patients without a positive blood culture. Three machine learning (ML) techniques (generalized additive models, logistic regression, and XGBoost) were used to build a classification algorithm. To simulate the performance of the algorithm in clinical practice, a simulation using multiple alarm thresholds was performed on hourly predictions for the total hospitalization period.

RESULTS

292 infants with LOS were matched to 1497 controls. The median gestational age before matching was 28.1 and 30.3 weeks, respectively. Evaluation of the overall discriminative power of the LR algorithm yielded an AUC of 0.73 (p < 0.05) at the moment of clinical suspicion (t = 0). In the longitudinal simulation, our algorithm detects LOS in at least 47% of the patients before clinical suspicion without exceeding the alarm fatigue threshold of 3 alarms per day. Furthermore, medical experts evaluated the algorithm as clinically relevant regarding the feature contributions in the model explanations.

CONCLUSIONS

An ML algorithm was trained for the early detection of LOS. Performance was evaluated on both prediction horizons and in a clinical impact simulation. To the best of our knowledge, our assessment of clinical impact with a retrospective simulation on longitudinal data is the most extensive in the literature on LOS prediction to date. The clinically relevant algorithm, based on routinely collected data, can potentially accelerate clinical decisions in the early detection of LOS, even with limited inputs.

Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review

BACKGROUND

Sepsis, a life-threatening infection-induced inflammatory condition, has significant global health impacts. Timely detection is crucial for improving patient outcomes as sepsis can rapidly progress to severe forms. The application of machine learning (ML) and deep learning (DL) to predict sepsis using electronic health records (EHRs) has gained considerable attention for timely intervention.

METHODS

PubMed, IEEE Xplore, Google Scholar, and Scopus were searched for relevant studies. All studies that used ML/DL to detect or early-predict the onset of sepsis in the adult population using EHRs were considered. Data were extracted and analyzed from all studies that met the criteria and were also evaluated for their quality.

RESULTS

This systematic review examined 1942 articles, selecting 42 studies while adhering to strict criteria. The chosen studies were predominantly retrospective (n = 38) and spanned diverse geographic settings, with a focus on the United States. Different datasets, sepsis definitions, and prevalence rates were employed, necessitating data augmentation. Heterogeneous parameter utilization, diverse model distribution, and varying quality assessments were observed. Longitudinal data enabled early sepsis prediction, and quality criteria fulfillment varied, with inconsistent funding-article quality correlation.

CONCLUSIONS

This systematic review underscores the significance of ML/DL methods for sepsis detection and early prediction through EHR data.

Machine Learning for Early Prediction of Sepsis in Intensive Care Unit (ICU) Patients

Background and Objectives: Early detection of sepsis is crucial and can save lives. However, identifying sepsis early and accurately remains a difficult task in the medical field. This study aims to investigate a new machine-learning approach. By analyzing the clinical laboratory results and vital signs of adult patients in the ICU, this approach can predict and detect the initial signs of sepsis. Materials and Methods: To examine survival rates and predict outcomes, the study utilized several models, including the proportional hazards model and data mining algorithms. We analyzed data from the BESTCare database at KAMC, with a focus on patients aged 14 and older who were admitted to the ICU between April and October 2018. We conducted a thorough analysis of the medical records of a total of 1182 patients who were diagnosed with sepsis. Results: We studied two approaches to predict sepsis in ICU patients. The regression model utilizing survival analysis showed moderate predictive ability, emphasizing the importance of only three factors-time (from sepsis to an outcome; discharge or death), lactic acid, and temperature-had a significant p-value (p = 0.000568, p = 0.01, p = 0.02, respectively). Other data mining algorithms may have limitations due to their assumptions of variable independence and linear classification nature. Conclusions: To achieve progress and accuracy in the field of sepsis prediction, it is important to continuously strive for improvement. By meticulously cleaning and selecting data attributes, we can create a strong foundation for future advancements in this area.

Temporal convolution attention model for sepsis clinical assistant diagnosis prediction

Sepsis is an organ failure disease caused by an infection acquired in an intensive care unit (ICU), which leads to a high mortality rate. Developing intelligent monitoring and early warning systems for sepsis is a key research area in the field of smart healthcare. Early and accurate identification of patients at high risk of sepsis can help doctors make the best clinical decisions and reduce the mortality rate of patients with sepsis. However, the scientific understanding of sepsis remains inadequate, leading to slow progress in sepsis research. With the accumulation of electronic medical records (EMRs) in hospitals, data mining technologies that can identify patient risk patterns from the vast amount of sepsis-related EMRs and the development of smart surveillance and early warning models show promise in reducing mortality. Based on the Medical Information Mart for Intensive Care Ⅲ, a massive dataset of ICU EMRs published by MIT and Beth Israel Deaconess Medical Center, we propose a Temporal Convolution Attention Model for Sepsis Clinical Assistant Diagnosis Prediction (TCASP) to predict the incidence of sepsis infection in ICU patients. First, sepsis patient data is extracted from the EMRs. Then, the incidence of sepsis is predicted based on various physiological features of sepsis patients in the ICU. Finally, the TCASP model is utilized to predict the time of the first sepsis infection in ICU patients. The experiments show that the proposed model achieves an area under the receiver operating characteristic curve (AUROC) score of 86.9% (an improvement of 6.4% ) and an area under the precision-recall curve (AUPRC) score of 63.9% (an improvement of 3.9% ) compared to five state-of-the-art models.

Deployment of machine learning algorithms to predict sepsis: systematic review and application of the SALIENT clinical AI implementation framework

OBJECTIVE

To retrieve and appraise studies of deployed artificial intelligence (AI)-based sepsis prediction algorithms using systematic methods, identify implementation barriers, enablers, and key decisions and then map these to a novel end-to-end clinical AI implementation framework.

MATERIALS AND METHODS

Systematically review studies of clinically applied AI-based sepsis prediction algorithms in regard to methodological quality, deployment and evaluation methods, and outcomes. Identify contextual factors that influence implementation and map these factors to the SALIENT implementation framework.

RESULTS

The review identified 30 articles of algorithms applied in adult hospital settings, with 5 studies reporting significantly decreased mortality post-implementation. Eight groups of algorithms were identified, each sharing a common algorithm. We identified 14 barriers, 26 enablers, and 22 decision points which were able to be mapped to the 5 stages of the SALIENT implementation framework.

DISCUSSION

Empirical studies of deployed sepsis prediction algorithms demonstrate their potential for improving care and reducing mortality but reveal persisting gaps in existing implementation guidance. In the examined publications, key decision points reflecting real-word implementation experience could be mapped to the SALIENT framework and, as these decision points appear to be AI-task agnostic, this framework may also be applicable to non-sepsis algorithms. The mapping clarified where and when barriers, enablers, and key decisions arise within the end-to-end AI implementation process.

CONCLUSIONS

A systematic review of real-world implementation studies of sepsis prediction algorithms was used to validate an end-to-end staged implementation framework that has the ability to account for key factors that warrant attention in ensuring successful deployment, and which extends on previous AI implementation frameworks.

Early prediction of sepsis using double fusion of deep features and handcrafted features

Sepsis is a life-threatening medical condition that is characterized by the dysregulated immune system response to infections, having both high morbidity and mortality rates. Early prediction of sepsis is critical to the decrease of mortality. This paper presents a novel early warning model called Double Fusion Sepsis Predictor (DFSP) for sepsis onset. DFSP is a double fusion framework that combines the benefits of early and late fusion strategies. First, a hybrid deep learning model that combines both the convolutional and recurrent neural networks to extract deep features is proposed. Second, deep features and handcrafted features, such as clinical scores, are concatenated to build the joint feature representation (early fusion). Third, several tree-based models based on joint feature representation are developed to generate the risk scores of sepsis onset that are combined with an End-to-End neural network for final sepsis detection (late fusion). To evaluate DFSP, a retrospective study was conducted, which included patients admitted to the ICUs of a hospital in Shanghai China. The results demonstrate that the DFSP outperforms state-of-the-art approaches in early sepsis prediction.

Predicting respiratory decompensation in mechanically ventilated adult ICU patients

Introduction: Mechanical ventilation is a life-saving treatment in the Intensive Care Unit (ICU), but often causes patients to be at risk of further respiratory complication. We created a statistical model utilizing electronic health record and physiologic vitals data to predict the Center for Disease Control and Prevention (CDC) defined Ventilator Associated Complications (VACs). Further, we evaluated the effect of data temporal resolution and feature generation method choice on the accuracy of such a constructed model. Methods: We constructed a random forest model to predict occurrence of VACs using health records and chart events from adult patients in the Medical Information Mart for Intensive Care III (MIMIC-III) database. We trained the machine learning models on two patient populations of 1921 and 464 based on low and high frequency data availability. Model features were generated using both basic statistical summaries and tsfresh, a python library that generates a large number of derived time-series features. Classification to determine whether a patient will experience VAC one hour after 35 h of ventilation was performed using a random forest classifier. Two different sample spaces conditioned on five varying feature extraction techniques were evaluated to identify the most optimal selection of features resulting in the best VAC discrimination. Each dataset was assessed using K-folds cross-validation (k = 10), giving average area under the receiver operating characteristic curves (AUROCs) and accuracies. Results: After feature selection, hyperparameter tuning, and feature extraction, the best performing model used automatically generated features on high frequency data and achieved an average AUROC of 0.83 ± 0.11 and an average accuracy of 0.69 ± 0.10. Discussion: Results show the potential viability of predicting VACs using machine learning, and indicate that higher-resolution data and the larger feature set generated by tsfresh yield better AUROCs compared to lower-resolution data and manual statistical features.

Ethical considerations in implementing AI for mortality prediction in the emergency department: Linking theory and practice

Background

Artificial intelligence (AI) is predicted to be a solution for improving healthcare, increasing efficiency, and saving time and recourses. A lack of ethical principles for the use of AI in practice has been highlighted by several stakeholders due to the recent attention given to it. Research has shown an urgent need for more knowledge regarding the ethical implications of AI applications in healthcare. However, fundamental ethical principles may not be sufficient to describe ethical concerns associated with implementing AI applications.

Objective

The aim of this study is twofold, (1) to use the implementation of AI applications to predict patient mortality in emergency departments as a setting to explore healthcare professionals' perspectives on ethical issues in relation to ethical principles and (2) to develop a model to guide ethical considerations in AI implementation in healthcare based on ethical theory.

Methods

Semi-structured interviews were conducted with 18 participants. The abductive approach used to analyze the empirical data consisted of four steps alternating between inductive and deductive analyses.

Results

Our findings provide an ethical model demonstrating the need to address six ethical principles (autonomy, beneficence, non-maleficence, justice, explicability, and professional governance) in relation to ethical theories defined as virtue, deontology, and consequentialism when AI applications are to be implemented in clinical practice.

Conclusions

Ethical aspects of AI applications are broader than the prima facie principles of medical ethics and the principle of explicability. Ethical aspects thus need to be viewed from a broader perspective to cover different situations that healthcare professionals, in general, and physicians, in particular, may face when using AI applications in clinical practice.

SEPRES: Intensive Care Unit Clinical Data Integration System to Predict Sepsis

BACKGROUND

The lack of information interoperability between different devices and systems in the intensive care unit (ICU) hinders further utilization of data, especially for early warning of specific diseases in the ICU.

OBJECTIVES

We aimed to establish a data integration system. Based on this system, the sepsis prediction module was added to compose the Sepsis PREdiction System (SEPRES), where real-time early warning of sepsis can be implemented at the bedside in the ICU.

METHODS

Data are collected from bedside devices through the integration hub and uploaded to the integration system through the local area network. The data integration system was designed to integrate vital signs data, laboratory data, ventilator data, demographic data, pharmacy data, nursing data, etc. from multiple medical devices and systems. It integrates, standardizes, and stores information, making the real-time inference of the early warning module possible. The built-in sepsis early warning module can detect the onset of sepsis within 5 hours preceding at most.

RESULTS

Our data integration system has already been deployed in Ruijin Hospital, confirming the feasibility of our system.

CONCLUSION

We highlight that SEPRES has the potential to improve ICU management by helping medical practitioners identify at-sepsis-risk patients and prepare for timely diagnosis and intervention.

Prediction of sepsis onset in hospital admissions using survival analysis

To determine the efficacy of modern survival analysis methods for predicting sepsis onset in ICU, emergency, medical/surgical, and TCU departments. We performed a retrospective analysis on ICU, med/surg, ED, and TCU cases from multiple Mercy Health hospitals from August 2018 to March 2020. Patients in these departments were monitored by the Mercy Virtual vSepsis team and sepsis cases were determined and documented in the Mercy EHR via a rule-based engine utilizing clinical data. We used survival-based modeling methods to predict sepsis onset in these cases. The three survival methods that were used to predict the onset of severe sepsis and septic shock produced AUC values > 0.85 and each provided a median lead time of > 20 h prior to disease onset. This methodology improves upon previous work by demonstrating excellent model performance when generalizing survival-based prediction methods to both severe sepsis and septic shock as well as non-ICU departments.IRB InformationTrial Registration ID: 1,532,327-1.Trial Effective Date: 12/02/2019.

Classifying sepsis from photoplethysmography

Sepsis is a life-threatening organ dysfunction. It is caused by a dysregulated immune response to an infection and is one of the leading causes of death in the intensive care unit (ICU). Early detection and treatment of sepsis can increase the survival rate of patients. The use of devices such as the photoplethysmograph could allow the early evaluation in addition to continuous monitoring of septic patients. The aim of this study was to verify the possibility of detecting sepsis in patients from whom the photoplethysmographic signal was acquired via a pulse oximeter. In this work, we developed a deep learning-based model for sepsis identification. The model takes a single input, the photoplethysmographic signal acquired by pulse oximeter, and performs a binary classification between septic and nonseptic samples. To develop the method, we used MIMIC-III database, which contains data from ICU patients. Specifically, the selected dataset includes 85 septic subjects and 101 control subjects. The PPG signals acquired from these patients were segmented, processed and used as input for the developed model with the aim of identifying sepsis. The proposed method achieved an accuracy of 76.37% with a sensitivity of 70.95% and a specificity of 81.04% on the test set. As regards the ROC curve, the Area Under Curve reached a value of 0.842. The results of this study indicate how the plethysmographic signal can be used as a warning sign for the early detection of sepsis with the aim of reducing the time for diagnosis and therapeutic intervention. Furthermore, the proposed method is suitable for integration in continuous patient monitoring.

Explainable Artificial Intelligence Helps in Understanding the Effect of Fibronectin on Survival of Sepsis

Fibronectin (FN) plays an essential role in the host’s response to infection. In previous studies, a significant decrease in the FN level was observed in sepsis; however, it has not been clearly elucidated how this parameter affects the patient’s survival. To better understand the relationship between FN and survival, we utilized innovative approaches from the field of explainable machine learning, including local explanations (Break Down, Shapley Additive Values, Ceteris Paribus), to understand the contribution of FN to predicting individual patient survival. The methodology provides new opportunities to personalize informative predictions for patients. The results showed that the most important indicators for predicting survival in sepsis were INR, FN, age, and the APACHE II score. ROC curve analysis showed that the model’s successful classification rate was 0.92, its sensitivity was 0.92, its positive predictive value was 0.76, and its accuracy was 0.79. To illustrate these possibilities, we have developed and shared a web-based risk calculator for exploring individual patient risk. The web application can be continuously updated with new data in order to further improve the model.

Machine Learning Models for Early Prediction of Sepsis on Large Healthcare Datasets

Sepsis is a highly lethal syndrome with heterogeneous clinical manifestation that can be hard to identify and treat. Early diagnosis and appropriate treatment are critical to reduce mortality and promote survival in suspected cases and improve the outcomes. Several screening prediction systems have been proposed for evaluating the early detection of patient deterioration, but the efficacy is still limited at individual level. The increasing amount and the versatility of healthcare data suggest implementing machine learning techniques to develop models for predicting sepsis. This work presents an experimental study of some machine-learning-based models for sepsis prediction considering vital signs, laboratory test results, and demographics using Medical Information Mart for Intensive Care III (MIMIC-III) (v1.4), a publicly available dataset. The experimental results demonstrate an overall higher performance of machine learning models over the commonly used Sequential Organ Failure Assessment (SOFA) and Quick SOFA (qSOFA) scoring systems at the time of sepsis onset.

Dynamic sepsis prediction for intensive care unit patients using XGBoost-based model with novel time-dependent features

Sepsis is a systemic inflammatory response caused by pathogens such as bacteria. Because its pathogenesis is not clear, the clinical manifestations of patients vary greatly, and the alarming incidence and mortality pose a great threat to patients and medical systems, especially in Intensive Care Unit (ICU). The traditional judgment criteria have the problem of low specificity. Artificial intelligence models could greatly improve the accuracy of sepsis prediction and judgment. Based on the XGBoost machine learning framework taken demographic, vital signs, laboratory tests and medical intervention data as input, this paper proposes a novel model for dynamically predicting sepsis and assessing risk. To realize the model, two methods for feature construction are introduced. For the observed time series data of vital signs and laboratory tests, time-dependent method performs to construct the time- dependent characteristics after statistical screening. For the clinical intervention data, statistical counting method is applied to construct count-dependent characteristics. Moreover, a new objective function is proposed for the XGBoost framework, and the first-order and second-order gradient of the objective function are also given for model training. Compared with the state-of-the-art methods at present, the proposed model has the best performance, with AUROC improved by 5.4% on the MIMIC-III dataset and 2.1% on PhysioNet Challenge 2019 dataset. The data processing and training methods of this model can be conveniently applied in different electronic health record systems, and has a wide application prospect.

Fusion of fully integrated analog machine learning classifier with electronic medical records for real-time prediction of sepsis onset

The objective of this work is to develop a fusion artificial intelligence (AI) model that combines patient electronic medical record (EMR) and physiological sensor data to accurately predict early risk of sepsis. The fusion AI model has two components—an on-chip AI model that continuously analyzes patient electrocardiogram (ECG) data and a cloud AI model that combines EMR and prediction scores from on-chip AI model to predict fusion sepsis onset score. The on-chip AI model is designed using analog circuits for sepsis prediction with high energy efficiency for integration with resource constrained wearable device. Combination of EMR and sensor physiological data improves prediction performance compared to EMR or physiological data alone, and the late fusion model has an accuracy of 93% in predicting sepsis 4 h before onset. The key differentiation of this work over existing sepsis prediction literature is the use of single modality patient vital (ECG) and simple demographic information, instead of comprehensive laboratory test results and multiple vital signs. Such simple configuration and high accuracy makes our solution favorable for real-time, at-home use for self-monitoring.

Early Prediction of Sepsis Onset Using Neural Architecture Search Based on Genetic Algorithms

Sepsis is a life-threatening condition with a high mortality rate. Early prediction and treatment are the most effective strategies for increasing survival rates. This paper proposes a neural architecture search (NAS) model to predict the onset of sepsis with a low computational cost and high search performance by applying a genetic algorithm (GA). The proposed model shares the weights of all possible connection nodes internally within the neural network. Externally, the search cost is reduced through the weight-sharing effect between the genotypes of the GA. A predictive analysis was performed using the Medical Information Mart for Intensive Care III (MIMIC-III), a medical time-series dataset, with the primary objective of predicting sepsis onset 3 h before occurrence. In addition, experiments were conducted under various prediction times (0-12 h) for comparison. The proposed model exhibited an area under the receiver operating characteristic curve (AUROC) score of 0.94 (95% CI: 0.92-0.96) for 3 h, which is 0.31-0.26 higher than the scores obtained using the Sequential Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Simplified Acute Physiology Score (SAPS) II scoring systems. Furthermore, the proposed model exhibited a 12% improvement in the AUROC value over a simple model based on the long short-term memory neural network. Additionally, it is not only optimally searchable for sepsis onset prediction, but also outperforms conventional models that use similar predictive purposes and datasets. Notably, it is sufficiently robust to shape changes in the input data and has less structural dependence.

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.

The Interplay between Host Defense, Infection, and Clinical Status in Septic Patients: A Narrative Review

Sepsis is a life-threatening condition that arises when the body's response to an infection injures its own tissues and organs. Despite significant morbidity and mortality throughout the world, its pathogenesis and mechanisms are not clearly understood. In this narrative review, we aimed to summarize the recent developments in our understanding of the hallmarks of sepsis pathogenesis (immune and adaptive immune response, the complement system, the endothelial disfunction, and autophagy) and highlight novel laboratory diagnostic approaches. Clinical management is also discussed with pivotal consideration for antimicrobic therapy management in particular settings, such as intensive care unit, altered renal function, obesity, and burn patients.

Implementation and evaluation of sepsis surveillance and decision support in medical ICU and emergency department

OBJECTIVE

To improve the timely diagnosis and treatment of sepsis many institutions implemented automated sepsis alerts. Poor specificity, time delays, and a lack of actionable information lead to limited adoption by bedside clinicians and no change in practice or clinical outcomes. We aimed to compare sepsis care compliance before and after a multi-year implementation of a sepsis surveillance coupled with decision support in a tertiary care center.

DESIGN

Single center before and after study.

SETTING

Large academic Medical Intensive Care Unit (MICU) and Emergency Department (ED).

POPULATION

Patients 18 years of age or older admitted to *** Hospital MICU and ED from 09/4/2011 to 05/01/2018 with severe sepsis or septic shock.

INTERVENTIONS

Electronic medical record-based sepsis surveillance system augmented by clinical decision support and completion feedback.

MEASUREMENTS AND MAIN RESULTS

There were 1950 patients admitted to the MICU with the diagnosis of severe sepsis or septic shock during the study period. The baseline characteristics were similar before (N = 854) and after (N = 1096) implementation of sepsis surveillance. The performance of the alert was modest with a sensitivity of 79.9%, specificity of 76.9%, positive predictive value (PPV) 27.9%, and negative predictive value (NPV) 97.2%. There were 3424 unique alerts and 1131 confirmed sepsis patients after the sniffer implementation. During the study period average care bundle compliance was higher; however after taking into account improvements in compliance leading up to the intervention, there was no association between intervention and improved care bundle compliance (Odds ratio: 1.16; 95% CI: 0.71 to 1.89; p-value 0.554). Similarly, the intervention was not associated with improvement in hospital mortality (Odds ratio: 1.55; 95% CI: 0.95 to 2.52; p-value: 0.078).

CONCLUSIONS

A sepsis surveillance system incorporating decision support or completion feedback was not associated with improved sepsis care and patient outcomes.

A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients

Background: Although numerous studies are conducted every year on how to reduce the fatality rate associated with sepsis, it is still a major challenge faced by patients, clinicians, and medical systems worldwide. Early identification and prediction of patients at risk of sepsis and adverse outcomes associated with sepsis are critical. We aimed to develop an artificial intelligence algorithm that can predict sepsis early.

Methods: This was a secondary analysis of an observational cohort study from the Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University. A total of 4,449 infected patients were randomly assigned to the development and validation data set at a ratio of 4:1. After extracting electronic medical record data, a set of 55 features (variables) was calculated and passed to the random forest algorithm to predict the onset of sepsis.

Results: The pre-procedure clinical variables were used to build a prediction model from the training data set using the random forest machine learning method; a 5-fold cross-validation was used to evaluate the prediction accuracy of the model. Finally, we tested the model using the validation data set. The area obtained by the model under the receiver operating characteristic (ROC) curve (AUC) was 0.91, the sensitivity was 87%, and the specificity was 89%.

Conclusions: This newly established machine learning-based model has shown good predictive ability in Chinese sepsis patients. External validation studies are necessary to confirm the universality of our method in the population and treatment practice.

The impact of recency and adequacy of historical information on sepsis predictions using machine learning

Sepsis is a major public and global health concern. Every hour of delay in detecting sepsis significantly increases the risk of death, highlighting the importance of accurately predicting sepsis in a timely manner. A growing body of literature has examined developing new or improving the existing machine learning (ML) approaches for timely and accurate predictions of sepsis. This study contributes to this literature by providing clear insights regarding the role of the recency and adequacy of historical information in predicting sepsis using ML. To this end, we implemented a deep learning model using a bidirectional long short-term memory (BiLSTM) algorithm and compared it with six other ML algorithms based on numerous combinations of the prediction horizons (to capture information recency) and observation windows (to capture information adequacy) using different measures of predictive performance. Our results indicated that the BiLSTM algorithm outperforms all other ML algorithms and provides a great separability of the predicted risk of sepsis among septic versus non-septic patients. Moreover, decreasing the prediction horizon (in favor of information recency) always boosts the predictive performance; however, the impact of expanding the observation window (in favor of information adequacy) depends on the prediction horizon and the purpose of prediction. More specifically, when the prediction is responsive to the positive label (i.e., Sepsis), increasing historical data improves the predictive performance when the prediction horizon is short-moderate.

Machine Learning Model to Identify Sepsis Patients in the Emergency Department: Algorithm Development and Validation

Accurate stratification of sepsis can effectively guide the triage of patient care and shared decision making in the emergency department (ED). However, previous research on sepsis identification models focused mainly on ICU patients, and discrepancies in model performance between the development and external validation datasets are rarely evaluated. The aim of our study was to develop and externally validate a machine learning model to stratify sepsis patients in the ED. We retrospectively collected clinical data from two geographically separate institutes that provided a different level of care at different time periods. The Sepsis-3 criteria were used as the reference standard in both datasets for identifying true sepsis cases. An eXtreme Gradient Boosting (XGBoost) algorithm was developed to stratify sepsis patients and the performance of the model was compared with traditional clinical sepsis tools; quick Sequential Organ Failure Assessment (qSOFA) and Systemic Inflammatory Response Syndrome (SIRS). There were 8296 patients (1752 (21%) being septic) in the development and 1744 patients (506 (29%) being septic) in the external validation datasets. The mortality of septic patients in the development and validation datasets was 13.5% and 17%, respectively. In the internal validation, XGBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.86, exceeding SIRS (0.68) and qSOFA (0.56). The performance of XGBoost deteriorated in the external validation (the AUROC of XGBoost, SIRS and qSOFA was 0.75, 0.57 and 0.66, respectively). Heterogeneity in patient characteristics, such as sepsis prevalence, severity, age, comorbidity and infection focus, could reduce model performance. Our model showed good discriminative capabilities for the identification of sepsis patients and outperformed the existing sepsis identification tools. Implementation of the ML model in the ED can facilitate timely sepsis identification and treatment. However, dataset discrepancies should be carefully evaluated before implementing the ML approach in clinical practice. This finding reinforces the necessity for future studies to perform external validation to ensure the generalisability of any developed ML approaches.

Timing of antibiotic therapy in the ICU

Severe or life threatening infections are common among patients in the intensive care unit (ICU). Most infections in the ICU are bacterial or fungal in origin and require antimicrobial therapy for clinical resolution. Antibiotics are the cornerstone of therapy for infected critically ill patients. However, antibiotics are often not optimally administered resulting in less favorable patient outcomes including greater mortality. The timing of antibiotics in patients with life threatening infections including sepsis and septic shock is now recognized as one of the most important determinants of survival for this population. Individuals who have a delay in the administration of antibiotic therapy for serious infections can have a doubling or more in their mortality. Additionally, the timing of an appropriate antibiotic regimen, one that is active against the offending pathogens based on in vitro susceptibility, also influences survival. Thus not only is early empiric antibiotic administration important but the selection of those agents is crucial as well. The duration of antibiotic infusions, especially for β-lactams, can also influence antibiotic efficacy by increasing antimicrobial drug exposure for the offending pathogen. However, due to mounting antibiotic resistance, aggressive antimicrobial de-escalation based on microbiology results is necessary to counterbalance the pressures of early broad-spectrum antibiotic therapy. In this review, we examine time related variables impacting antibiotic optimization as it relates to the treatment of life threatening infections in the ICU. In addition to highlighting the importance of antibiotic timing in the ICU we hope to provide an approach to antimicrobials that also minimizes the unnecessary use of these agents. Such approaches will increasingly be linked to advances in molecular microbiology testing and artificial intelligence/machine learning. Such advances should help identify patients needing empiric antibiotic therapy at an earlier time point as well as the specific antibiotics required in order to avoid unnecessary administration of broad-spectrum antibiotics.

Machine learning identification of specific changes in myeloid cell phenotype during bloodstream infections

The early identification of bacteremia is critical for ensuring appropriate treatment of nosocomial infections in intensive care unit (ICU) patients. The aim of this study was to use flow cytometric data of myeloid cells as a biomarker of bloodstream infection (BSI). An eight-color antibody panel was used to identify seven monocyte and two dendritic cell subsets. In the learning cohort, immunophenotyping was applied to (1) control subjects, (2) postoperative heart surgery patients, as a model of noninfectious inflammatory responses, and (3) blood culture-positive patients. Of the complex changes in the myeloid cell phenotype, a decrease in myeloid and plasmacytoid dendritic cell numbers, increase in CD14⁺CD16⁺ inflammatory monocyte numbers, and upregulation of neutrophils CD64 and CD123 expression were prominent in BSI patients. An extreme gradient boosting (XGBoost) algorithm called the “infection detection and ranging score” (iDAR), ranging from 0 to 100, was developed to identify infection-specific changes in 101 phenotypic variables related to neutrophils, monocytes and dendritic cells. The tenfold cross-validation achieved an area under the receiver operating characteristic (AUROC) of 0.988 (95% CI 0.985–1) for the detection of bacteremic patients. In an out-of-sample, in-house validation, iDAR achieved an AUROC of 0.85 (95% CI 0.71–0.98) in differentiating localized from bloodstream infection and 0.95 (95% CI 0.89–1) in discriminating infected from noninfected ICU patients. In conclusion, a machine learning approach was used to translate the changes in myeloid cell phenotype in response to infection into a score that could identify bacteremia with high specificity in ICU patients.

A framework for validating AI in precision medicine: considerations from the European ITFoC consortium

BACKGROUND

Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks.

METHODS

The European "ITFoC (Information Technology for the Future Of Cancer)" consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology.

RESULTS

This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the "ITFoC Challenge". This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets.

CONCLUSIONS

The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care.

Proximity of Cellular and Physiological Response Failures in Sepsis

Sepsis is a devastating multi-stage health condition with a high mortality rate. Its complexity, prevalence, and dependency of its outcomes on early detection have attracted substantial attention from data science and machine learning communities. Previous studies rely on individual cellular and physiological responses representing organ system failures to predict health outcomes or the onset of different sepsis stages. However, it is known that organ systems' failures and dynamics are not independent events. In this study, we identify the dependency patterns of significant proximate sepsis-related failures of cellular and physiological responses using data from 12,223 adult patients hospitalized between July 2013 and December 2015. The results show that proximate failures of cellular and physiological responses create better feature sets for outcome prediction than individual responses. Our findings reveal the few significant proximate failures that play the major roles in predicting patients' outcomes. This study's results can be simply translated into clinical practices and inform the prediction and improvement of patients' conditions and outcomes.

Ambulatory Risk Models for the Long-Term Prevention of Sepsis: Retrospective Study

Background

Sepsis is a life-threatening condition that can rapidly lead to organ damage and death. Existing risk scores predict outcomes for patients who have already become acutely ill.

Objective

We aimed to develop a model for identifying patients at risk of getting sepsis within 2 years in order to support the reduction of sepsis morbidity and mortality.

Methods

Machine learning was applied to 2,683,049 electronic health records (EHRs) with over 64 million encounters across five states to develop models for predicting a patient’s risk of getting sepsis within 2 years. Features were selected to be easily obtainable from a patient’s chart in real time during ambulatory encounters.

Results

The models showed consistent prediction scores, with the highest area under the receiver operating characteristic curve of 0.82 and a positive likelihood ratio of 2.9 achieved with gradient boosting on all features combined. Predictive features included age, sex, ethnicity, average ambulatory heart rate, standard deviation of BMI, and the number of prior medical conditions and procedures. The findings identified both known and potential new risk factors for long-term sepsis. Model variations also illustrated trade-offs between incrementally higher accuracy, implementability, and interpretability.

Conclusions

Accurate implementable models were developed to predict the 2-year risk of sepsis, using EHR data that is easy to obtain from ambulatory encounters. These results help advance the understanding of sepsis and provide a foundation for future trials of risk-informed preventive care.

The automation of doctors and machines: A classification for AI in medicine (ADAM framework)

The advances in artificial intelligence (AI) provide an opportunity to expand the frontier of medicine to improve diagnosis, efficiency and management. By extension of being able to perform any task that a human could, a machine that meets the requirements of artificial general intelligence ('strong' AI; AGI) possesses the basic necessities to perform as, or at least qualify to become, a doctor. In this emerging field, this article explores the distinctions between doctors and AGI, and the prerequisites for AGI performing as clinicians. In doing so, it necessitates the requirement for a classification of medical AI and prepares for the development of AGI. With its imminent arrival, it is beneficial to create a framework from which leading institutions can define specific criteria for AGI.

Temporal Differential Expression of Physiomarkers Predicts Sepsis in Critically Ill Adults

BACKGROUND

Sepsis is a life-threatening condition with high mortality rates. Early detection and treatment are critical to improving outcomes. Our primary objective was to develop artificial intelligence capable of predicting sepsis earlier using a minimal set of streaming physiological data in real time.

METHODS AND FINDINGS

A total of 29,552 adult patients were admitted to the intensive care unit across five regional hospitals in Memphis, Tenn, over 18 months from January 2017 to July 2018. From these, 5,958 patients were selected after filtering for continuous (minute-by-minute) physiological data availability. A total of 617 (10.4%) patients were identified as sepsis cases, using the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria. Physiomarkers, a set of signal processing features, were derived from five physiological data streams including heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from the bedside monitors. A support vector machine classifier was used for classification. The model accurately predicted sepsis up to a mean and 95% confidence interval of 17.4 ± 0.22 h before sepsis onset, with an average test accuracy of 83.0% (average sensitivity, specificity, and area under the receiver operating characteristics curve of 0.757, 0.902, and 0.781, respectively).

CONCLUSIONS

This study demonstrates that salient physiomarkers derived from continuous bedside monitoring are temporally and differentially expressed in septic patients. Using this information, minimalistic artificial intelligence models can be developed to predict sepsis earlier in critically ill patients.

Multi-Branching Temporal Convolutional Network for Sepsis Prediction

Sepsis is among the leading causes of morbidity and mortality in modern intensive care units. Accurate sepsis prediction is of critical importance to save lives and reduce medical costs. The rapid advancements in sensing and information technology facilitate the effective monitoring of patients health conditions, generating a wealth of medical data, and provide an unprecedented opportunity for data-driven diagnosis of sepsis. However, real-world medical data are often complexly structured with a high level of uncertainty (e.g., missing values, imbalanced data). Realizing the full data potential depends on developing effective analytical models. In this paper, we propose a novel predictive framework with Multi-Branching Temporal Convolutional Network (MB-TCN) to model the complexly structured medical data for robust prediction of sepsis. The MB-TCN framework not only efficiently handles the missing value and imbalanced data issues but also effectively captures the temporal pattern and heterogeneous variable interactions. We evaluate the performance of the proposed MB-TCN in predicting sepsis using real-world medical data from PhysioNet/Computing in Cardiology Challenge 2019. Experimental results show that MB-TCN outperforms existing methods that are commonly used in current practice.

Prediction of Impending Septic Shock in Children With Sepsis

Objectives

Sepsis and septic shock are leading causes of in-hospital mortality. Timely treatment is crucial in improving patient outcome, yet treatment delays remain common. Early prediction of those patients with sepsis who will progress to its most severe form, septic shock, can increase the actionable window for interventions. We aim to extend a time-evolving risk score, previously developed in adult patients, to predict pediatric sepsis patients who are likely to develop septic shock before its onset, and to determine whether or not these risk scores stratify into groups with distinct temporal evolution once this prediction is made.

Design

Retrospective cohort study.

Setting

Academic medical center from July 1, 2016, to December 11, 2020.

Patients

Six-thousand one-hundred sixty-one patients under 18 admitted to the Johns Hopkins Hospital PICU.

Interventions

None.

Measurements and Main Results

We trained risk models to predict impending transition into septic shock and compute time-evolving risk scores representative of a patient's probability of developing septic shock. We obtain early prediction performance of 0.90 area under the receiver operating curve, 43% overall positive predictive value, patient-specific positive predictive value as high as 62%, and an 8.9-hour median early warning time using Sepsis-3 labels based on age-adjusted Sequential Organ Failure Assessment score. Using spectral clustering, we stratified pediatric sepsis patients into two clusters differing in septic shock prevalence, mortality, and proportion of patients adequately fluid resuscitated.

CONCLUSIONS

We demonstrate the applicability of our methodology for early prediction and stratification for risk of septic shock in pediatric sepsis patients. Through analyses of risk score evolution over time, we corroborate our past finding of an abrupt transition preceding onset of septic shock in children and are able to stratify pediatric sepsis patients using their risk score trajectories into low and high-risk categories.

Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review

Background: Sepsis is among the leading causes of death in intensive care units (ICUs) worldwide and its recognition, particularly in the early stages of the disease, remains a medical challenge. The advent of an affluence of available digital health data has created a setting in which machine learning can be used for digital biomarker discovery, with the ultimate goal to advance the early recognition of sepsis. Objective: To systematically review and evaluate studies employing machine learning for the prediction of sepsis in the ICU. Data Sources: Using Embase, Google Scholar, PubMed/Medline, Scopus, and Web of Science, we systematically searched the existing literature for machine learning-driven sepsis onset prediction for patients in the ICU. Study Eligibility Criteria: All peer-reviewed articles using machine learning for the prediction of sepsis onset in adult ICU patients were included. Studies focusing on patient populations outside the ICU were excluded. Study Appraisal and Synthesis Methods: A systematic review was performed according to the PRISMA guidelines. Moreover, a quality assessment of all eligible studies was performed. Results: Out of 974 identified articles, 22 and 21 met the criteria to be included in the systematic review and quality assessment, respectively. A multitude of machine learning algorithms were applied to refine the early prediction of sepsis. The quality of the studies ranged from "poor" (satisfying ≤ 40% of the quality criteria) to "very good" (satisfying ≥ 90% of the quality criteria). The majority of the studies (n = 19, 86.4%) employed an offline training scenario combined with a horizon evaluation, while two studies implemented an online scenario (n = 2, 9.1%). The massive inter-study heterogeneity in terms of model development, sepsis definition, prediction time windows, and outcomes precluded a meta-analysis. Last, only two studies provided publicly accessible source code and data sources fostering reproducibility. Limitations: Articles were only eligible for inclusion when employing machine learning algorithms for the prediction of sepsis onset in the ICU. This restriction led to the exclusion of studies focusing on the prediction of septic shock, sepsis-related mortality, and patient populations outside the ICU. Conclusions and Key Findings: A growing number of studies employs machine learning to optimize the early prediction of sepsis through digital biomarker discovery. This review, however, highlights several shortcomings of the current approaches, including low comparability and reproducibility. Finally, we gather recommendations how these challenges can be addressed before deploying these models in prospective analyses. Systematic Review Registration Number: CRD42020200133.

Utilization of the Signature Method to Identify the Early Onset of Sepsis From Multivariate Physiological Time Series in Critical Care Monitoring

OBJECTIVES

Patients in an ICU are particularly vulnerable to sepsis. It is therefore important to detect its onset as early as possible. This study focuses on the development and validation of a new signature-based regression model, augmented with a particular choice of the handcrafted features, to identify a patient's risk of sepsis based on physiologic data streams. The model makes a positive or negative prediction of sepsis for every time interval since admission to the ICU.

DESIGN

The data were sourced from the PhysioNet/Computing in Cardiology Challenge 2019 on the "Early Prediction of Sepsis from Clinical Data." It consisted of ICU patient data from three separate hospital systems. Algorithms were scored against a specially designed utility function that rewards early predictions in the most clinically relevant region around sepsis onset and penalizes late predictions and false positives.

SETTING

The work was completed as part of the PhysioNet 2019 Challenge alongside 104 other teams.

PATIENTS

PhysioNet sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. The Sepsis-3 criteria was used to define the onset of sepsis.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

The algorithm yielded a utility function score which was the first placed entry in the official phase of the challenge.

An Explainable Artificial Intelligence Predictor for Early Detection of Sepsis

OBJECTIVES

Early detection of sepsis is critical in clinical practice since each hour of delayed treatment has been associated with an increase in mortality due to irreversible organ damage. This study aimed to develop an explainable artificial intelligence model for early predicting sepsis by analyzing the electronic health record data from ICU provided by the PhysioNet/Computing in Cardiology Challenge 2019.

DESIGN

Retrospective observational study.

SETTING

We developed our model on the shared ICUs publicly data and verified on the full hidden populations for challenge scoring.

PATIENTS

Public database included 40,336 patients' electronic health records sourced from Beth Israel Deaconess Medical Center (hospital system A) and Emory University Hospital (hospital system B). A total of 24,819 patients from hospital systems A, B, and C (an unidentified hospital system) were sequestered as full hidden test sets.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

A total of 168 features were extracted on hourly basis. Explainable artificial intelligence sepsis predictor model was trained to predict sepsis in real time. Impact of each feature on hourly sepsis prediction was explored in-depth to show the interpretability. The algorithm demonstrated the final clinical utility score of 0.364 in this challenge when tested on the full hidden test sets, and the scores on three separate test sets were 0.430, 0.422, and -0.048, respectively.

CONCLUSIONS

Explainable artificial intelligence sepsis predictor model achieves superior performance for predicting sepsis risk in a real-time way and provides interpretable information for understanding sepsis risk in ICU.

Rethinking PICO in the Machine Learning Era: ML-PICO

BACKGROUND

Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers.

OBJECTIVE

We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care.

CONCLUSION

The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.

Predicting in-hospital mortality in ICU patients with sepsis using gradient boosting decision tree

Sepsis is a leading cause of mortality in the intensive care unit. Early prediction of sepsis can reduce the overall mortality rate and cost of sepsis treatment. Some studies have predicted mortality and development of sepsis using machine learning models. However, there is a gap between the creation of different machine learning algorithms and their implementation in clinical practice.This study utilized data from the Medical Information Mart for Intensive Care III. We established and compared the gradient boosting decision tree (GBDT), logistic regression (LR), k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM).A total of 3937 sepsis patients were included, with 34.3% mortality in the Medical Information Mart for Intensive Care III group. In our comparison of 5 machine learning models (GBDT, LR, KNN, RF, and SVM), the GBDT model showed the best performance with the highest area under the receiver operating characteristic curve (0.992), recall (94.8%), accuracy (95.4%), and F1 score (0.933). The RF, SVM, and KNN models showed better performance (area under the receiver operating characteristic curve: 0.980, 0.898, and 0.877, respectively) than the LR (0.876).The GBDT model showed better performance than other machine learning models (LR, KNN, RF, and SVM) in predicting the mortality of patients with sepsis in the intensive care unit. This could be used to develop a clinical decision support system in the future.

MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis

With a mortality rate of 5.4 million lives worldwide every year and a healthcare cost of more than 16 billion dollars in the USA alone, sepsis is one of the leading causes of hospital mortality and an increasing concern in the ageing western world. Recently, medical and technological advances have helped re-define the illness criteria of this disease, which is otherwise poorly understood by the medical society. Together with the rise of widely accessible Electronic Health Records, the advances in data mining and complex nonlinear algorithms are a promising avenue for the early detection of sepsis. This work contributes to the research effort in the field of automated sepsis detection with an open-access labelling of the medical MIMIC-III data set. Moreover, we propose MGP-AttTCN: a joint multitask Gaussian Process and attention-based deep learning model to early predict the occurrence of sepsis in an interpretable manner. We show that our model outperforms the current state-of-the-art and present evidence that different labelling heuristics lead to discrepancies in task difficulty. For instance, when predicting sepsis five hours prior to onset on our new realistic labels, our proposed model achieves an area under the ROC curve of 0.660 and an area under the PR curve of 0.483, whereas the (less interpretable) previous state-of-the-art model (MGP-TCN) achieves 0.635 AUROC and 0.460 AUPR and the popular commercial InSight model achieves 0.490 AUROC and 0.359 AUPR.

Tensor learning of pointwise mutual information from EHR data for early prediction of sepsis

Early detection of sepsis can facilitate early clinical intervention with effective treatment and may reduce sepsis mortality rates. In view of this, machine learning-based automated diagnosis of sepsis using easily recordable physiological data can be more promising as compared to the gold standard rule-based clinical criteria in current practice. This study aims to develop such a machine learning framework that demonstrates the quantification of heterogeneity within the tabular electronic health records (EHR) data of clinical covariates to capture both linear relationships and nonlinear correlation for the early prediction of sepsis. Here, the statistics of pairwise association for each hour-covariate pair within the EHR data for every 6-hours window-duration with selected 24 covariates is described using pointwise mutual information (PMI) matrix. This matrix gives the heterogeneity of data as a two-dimensional map. Such matrices are fused horizontally along the z-axis as vertical slices in the xy plane to form a 3-way tensor for each record with the corresponding Length of Stay (L). Tensor factorization of such fused tensor for every record is performed using Tucker decomposition, and only the core tensors are retained later, excluding the 3 unitary matrices to provide the latent feature set for the prediction of sepsis onset. A five-fold cross-validation scheme is employed wherein the obtained 120 latent features from the reshaped core tensor, are fed to Light Gradient Boosting Machine Learning models (LightGBM) for binary classification, further alleviating the involved class imbalance. The machine-learning framework is designed via Bayesian optimization, yielding an average normalized utility score of 0.4519 as defined by challenge organizers and area under the receiver operating characteristic curve (AUROC) of 0.8621 on publicly available PhysioNet/Computing in Cardiology Challenge 2019 training data. The proposed tensor decomposition of 3-way fused tensor formulated using PMI matrices leverages higher-order temporal interactions between the pairwise associations among the clinical values for early prediction of sepsis. This is validated with improved risk prediction power for every hour of admission to the ICU in terms of utility score, AUROC, and F1 score. The results obtained show a significant improvement particularly in terms of utility score of ~1.5-2% under a 5-fold cross-validation scheme on entire training data as compared to a top entrant research study that participated in the challenge.

Aiding clinical assessment of neonatal sepsis using hematological analyzer data with machine learning techniques

INTRODUCTION

Early diagnosis and antibiotic administration are essential for reducing sepsis morbidity and mortality; however, diagnosis remains difficult due to complex pathogenesis and presentation. We created a machine learning model for bacterial sepsis identification in the neonatal intensive care unit (NICU) using hematological analyzer data.

METHODS

Hematological analyzer data were gathered from NICU patients up to 48 hours prior to clinical evaluation for bacterial sepsis. Five models, Support Vector Machine, K-nearest-neighbors, Logistic Regression, Random Forest (RF), and Extreme Gradient boosting (XGBoost), were trained on 60 hematological and nine clinical variables for 2357 cases (1692 control, 665 septic). Clinical feature only models (nine variables) were additionally trained and compared with models including hematological variables. Feature importance was used to assess relative contributions of parameters to performance.

RESULTS

The three best performing models were RF, Logistic Regression, and XGBoost. RF achieved an average accuracy of 0.74, AUC-ROC of 0.73, Sensitivity of 0.38, and Specificity of 0.88. Logistic Regression achieved an average accuracy of 0.70, AUC-ROC of 0.74, Sensitivity of 0.62, and Specificity of 0.73. XGBoost achieved an average accuracy of 0.72, AUC-ROC of 0.71, Sensitivity of 0.40, and Specificity of 0.85. All models with hematological variables had significantly stronger performance than models trained on only clinical features. Neutrophil parameters had the highest average feature importance.

CONCLUSIONS

Machine learning models using hematological analyzer data can classify NICU patients as sepsis positive or negative with stronger performance compared to clinical feature only models. Hematological analyzer variables could augment current sepsis classification machine learning algorithms.