Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis

Optimising the use of electronic medical records for large scale research in psychiatry

The explosion and abundance of digital data could facilitate large-scale research for psychiatry and mental health. Research using so-called "real world data"-such as electronic medical/health records-can be resource-efficient, facilitate rapid hypothesis generation and testing, complement existing evidence (e.g. from trials and evidence-synthesis) and may enable a route to translate evidence into clinically effective, outcomes-driven care for patient populations that may be under-represented. However, the interpretation and processing of real-world data sources is complex because the clinically important 'signal' is often contained in both structured and unstructured (narrative or "free-text") data. Techniques for extracting meaningful information (signal) from unstructured text exist and have advanced the re-use of routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey the opportunities, risks and progress made in the use of electronic medical record (real-world) data for psychiatric research.

Early prediction of sepsis-induced respiratory tract infection using a biomarker-based machine-learning algorithm

Early and differential diagnosis of sepsis is essential to avoid unnecessary antibiotic use and further reduce patient morbidity and mortality. Here, we aimed to identify predictors of sepsis and advance a machine-learning strategy to predict sepsis-induced respiratory tract infection (RTI). Patients with sepsis and RTI were selected via retrospective analysis, and essential population characteristics and laboratory parameters were recorded. To improve the performance of the primary model and avoid over-fitting, a recursive feature elimination with cross-validation (RFECV) strategy was used to screen the optimal subset of biomarkers and construct nine machine-learning models based on this subset; the average accuracy, precision, recall, and F1-score were used for evaluation of the models. We identified 430 patients with sepsis and 686 patients with RTI. A total of 39 features were collected, with 23 features identified for initial model construction. Using the RFECV algorithm, we found that the XGBoost classifier, which only needed to include seven biomarkers, demonstrated the best performance among all prediction models, with an average accuracy of 89.24 ± 2.28, while the Ridge classifier, which included 11 biomarkers, had an average accuracy of only 83.87 ± 4.69. The remaining models had prediction accuracies greater than 88%. We developed nine models for predicting sepsis using a strategy that combined RFECV with machine learning. Among these models, the XGBoost classifier, which included seven biomarkers, showed the best performance and highest accuracy for predicting sepsis and may be a promising tool for the timely identification of sepsis.

Machine learning algorithms in sepsis

Sepsis remains a significant global health challenge due to its high mortality and morbidity, compounded by the difficulty of early detection given its variable clinical manifestations. The integration of machine learning (ML) into laboratory medicine for timely sepsis identification and outcome forecasting is an emerging field of interest. This comprehensive review assesses the current body of research on ML applications for sepsis within the realm of laboratory diagnostics, detailing both their strengths and shortcomings. An extensive literature search was performed by two independent investigators across PubMed and Scopus databases, employing the keywords "Sepsis," "Machine Learning," and "Laboratory" without publication date limitations, culminating in January 2023. Each selected study was meticulously evaluated for various aspects, including its design, intent (diagnostic or prognostic), clinical environment, demographics, sepsis criteria, data gathering period, and the scope and nature of features, in addition to the ML methodologies and their validation procedures. Out of 135 articles reviewed, 39 fulfilled the criteria for inclusion. Among these, the majority (30 studies) were focused on devising ML algorithms for diagnosis, fewer (8 studies) on prognosis, and one study addressed both aspects. The dissemination of these studies across an array of journals reflects the interdisciplinary engagement in the development of ML algorithms for sepsis. This analysis highlights the promising role of ML in the early diagnosis of sepsis while drawing attention to the need for uniformity in validating models and defining features, crucial steps for ensuring the reliability and practicality of ML in clinical setting.

Identifying Effective Biomarkers for Accurate Pancreatic Cancer Prognosis Using Statistical Machine Learning

Pancreatic cancer (PC) has one of the lowest survival rates among all major types of cancer. Consequently, it is one of the leading causes of mortality worldwide. Serum biomarkers historically correlate well with the early prognosis of post-surgical complications of PC. However, attempts to identify an effective biomarker panel for the successful prognosis of PC were almost non-existent in the current literature. The current study investigated the roles of various serum biomarkers including carbohydrate antigen 19-9 (CA19-9), chemokine (C-X-C motif) ligand 8 (CXCL-8), procalcitonin (PCT), and other relevant clinical data for identifying PC progression, classified into sepsis, recurrence, and other post-surgical complications, among PC patients. The most relevant biochemical and clinical markers for PC prognosis were identified using a random-forest-powered feature elimination method. Using this informative biomarker panel, the selected machine-learning (ML) classification models demonstrated highly accurate results for classifying PC patients into three complication groups on independent test data. The superiority of the combined biomarker panel (Max AUC-ROC = 100%) was further established over using CA19-9 features exclusively (Max AUC-ROC = 75%) for the task of classifying PC progression. This novel study demonstrates the effectiveness of the combined biomarker panel in successfully diagnosing PC progression and other relevant complications among Egyptian PC survivors.

Predicting sepsis using a combination of clinical information and molecular immune markers sampled in the ambulance

Sepsis is a time dependent condition. Screening tools based on clinical parameters have been shown to increase the identification of sepsis. The aim of current study was to evaluate the additional predictive value of immunological molecular markers to our previously developed prehospital screening tools. This is a prospective cohort study of 551 adult patients with suspected infection in the ambulance setting of Stockholm, Sweden between 2017 and 2018. Initially, 74 molecules and 15 genes related to inflammation were evaluated in a screening cohort of 46 patients with outcome sepsis and 50 patients with outcome infection no sepsis. Next, 12 selected molecules, as potentially synergistic predictors, were evaluated in combination with our previously developed screening tools based on clinical parameters in a prediction cohort (n = 455). Seven different algorithms with nested cross-validation were used in the machine learning of the prediction models. Model performances were compared using posterior distributions of average area under the receiver operating characteristic (ROC) curve (AUC) and difference in AUCs. Model variable importance was assessed by permutation of variable values, scoring loss of classification as metric and with model-specific weights when applicable. When comparing the screening tools with and without added molecular variables, and their interactions, the molecules per se did not increase the predictive values. Prediction models based on the molecular variables alone showed a performance in terms of AUCs between 0.65 and 0.70. Among the molecular variables, IL-1Ra, IL-17A, CCL19, CX3CL1 and TNF were significantly higher in septic patients compared to the infection non-sepsis group. Combing immunological molecular markers with clinical parameters did not increase the predictive values of the screening tools, most likely due to the high multicollinearity of temperature and some of the markers. A group of sepsis patients was consistently miss-classified in our prediction models, due to milder symptoms as well as lower expression levels of the investigated immune mediators. This indicates a need of stratifying septic patients with a priori knowledge of certain clinical and molecular parameters in order to improve prediction for early sepsis diagnosis.Trial registration: NCT03249597. Registered 15 August 2017.

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.

Significance of sTREM-1 and sST2 combined diagnosis for sepsis detection and prognosis prediction

The diagnosis of sepsis still lacks a practical and reliable gold standard. The purpose of this study was to confirm the effect of soluble triggering receptor expressed on myeloid cells-1 (sTREM-1) combined with soluble suppression of tumorigenicity 2 (sST2) in the diagnosis of sepsis through the correlation between sTREM-1, sST2, and sequential organ failure assessment (SOFA) scores. Baseline data of 91 patients with sepsis in the intensive care unit were collected, sTREM-1 and sST2 were detected, and the correlation between markers and SOFA score was analyzed. Besides, the prognostic value of baseline and postadmission indicators for sepsis was analyzed with death as the outcome. The results showed that the expressions of sST2 and sTREM-1 in death group and survival group were higher than those in the survival group (p < 0.05). Correlation analysis showed that sST2, sTREM-1, and the joint diagnosis model had a high correlation with SOFA score (p < 0.05), but poor correlation with Acute Physiology and Chronic Health Evaluation Ⅱ score (p > 0.05). Among them, joint diagnosis model has the highest correlation. Receiver operating characteristic curve analysis showed that combined diagnosis had higher area under curve values. sTREM-1/sST2 can be better used in the diagnosis of sepsis than the single biomarker detection, and the combination of the above two biomarkers has potential application value in the detection and prognosis prediction of sepsis.

Cerebrospinal Fluid Biomarkers for Diagnosis and the Prognostication of Acute Ischemic Stroke: A Systematic Review

Despite the high incidence and burden of stroke, biological biomarkers are not used routinely in clinical practice to diagnose, determine progression, or prognosticate outcomes of acute ischemic stroke (AIS). Because of its direct interface with neural tissue, cerebrospinal fluid (CSF) is a potentially valuable source for biomarker development. This systematic review was conducted using three databases. All trials investigating clinical and preclinical models for CSF biomarkers for AIS diagnosis, prognostication, and severity grading were included, yielding 22 human trials and five animal studies for analysis. In total, 21 biomarkers and other multiomic proteomic markers were identified. S100B, inflammatory markers (including tumor necrosis factor-alpha and interleukin 6), and free fatty acids were the most frequently studied biomarkers. The review showed that CSF is an effective medium for biomarker acquisition for AIS. Although CSF is not routinely clinically obtained, a potential benefit of CSF studies is identifying valuable biomarkers from the pathophysiologic microenvironment that ultimately inform optimization of targeted low-abundance assays from peripheral biofluid samples (e.g., plasma). Several important catabolic and anabolic markers can serve as effective measures of diagnosis, etiology identification, prognostication, and severity grading. Trials with large cohorts studying the efficacy of biomarkers in altering clinical management are still needed.

Machine learning model for predicting ciprofloxacin resistance and presence of ESBL in patients with UTI in the ED

Increasing antimicrobial resistance in uropathogens is a clinical challenge to emergency physicians as antibiotics should be selected before an infecting pathogen or its antibiotic resistance profile is confirmed. We created a predictive model for antibiotic resistance of uropathogens, using machine learning (ML) algorithms. This single-center retrospective study evaluated patients diagnosed with urinary tract infection (UTI) in the emergency department (ED) between January 2020 and June 2021. Thirty-nine variables were used to train the model to predict resistance to ciprofloxacin and the presence of urinary pathogens' extended-spectrum beta-lactamases. The model was built with Gradient-Boosted Decision Tree (GBDT) with performance evaluation. Also, we visualized feature importance using SHapely Additive exPlanations. After two-step customization of threshold adjustment and feature selection, the final model was compared with that of the original prescribers in the emergency department (ED) according to the ineffectiveness of the antibiotic selected. The probability of using ineffective antibiotics in the ED was significantly lowered by 20% in our GBDT model through customization of the decision threshold. Moreover, we could narrow the number of predictors down to twenty and five variables with high importance while maintaining similar model performance. An ML model is potentially useful for predicting antibiotic resistance improving the effectiveness of empirical antimicrobial treatment in patients with UTI in the ED. The model could be a point-of-care decision support tool to guide clinicians toward individualized antibiotic prescriptions.

Research frontiers and trends in the application of artificial intelligence to sepsis: A bibliometric analysis

Background

With the increasing interest of academics in the application of artificial intelligence to sepsis, thousands of papers on this field had been published in the past few decades. It is difficult for researchers to understand the themes and latest research frontiers in this field from a multi-dimensional perspective. Consequently, the purpose of this study is to analyze the relevant literature in the application of artificial intelligence to sepsis through bibliometrics software, so as to better understand the development status, study the core hotspots and future development trends of this field.

Methods

We collected relevant publications in the application of artificial intelligence to sepsis from the Web of Science Core Collection in 2000 to 2021. The type of publication was limited to articles and reviews, and language was limited to English. Research cooperation network, journals, cited references, keywords in this field were visually analyzed by using CiteSpace, VOSviewer, and COOC software.

Results

A total of 8,481 publications in the application of artificial intelligence to sepsis between 2000 and 2021 were included, involving 8,132 articles and 349 reviews. Over the past 22 years, the annual number of publications had gradually increased exponentially. The USA was the most productive country, followed by China. Harvard University, Schuetz, Philipp, and Intensive Care Medicine were the most productive institution, author, and journal, respectively. Vincent, Jl and Critical Care Medicine were the most cited author and cited journal, respectively. Several conclusions can be drawn from the analysis of the cited references, including the following: screening and identification of sepsis biomarkers, treatment and related complications of sepsis, and precise treatment of sepsis. Moreover, there were a spike in searches relating to machine learning, antibiotic resistance and accuracy based on burst detection analysis.

Conclusion

This study conducted a comprehensive and objective analysis of the publications on the application of artificial intelligence in sepsis. It can be predicted that precise treatment of sepsis through machine learning technology is still research hotspot in this field.

A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System

The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of the patient's conditions. Successively, we will be presenting a detailed survey for the medical XAI with the model enhancements, evaluation methods, significant overview of case studies with open box architecture, medical open datasets, and future improvements. Potential differences in AI and XAI methods are provided with the recent XAI methods stated as (i) local and global methods for preprocessing, (ii) knowledge base and distillation algorithms, and (iii) interpretable machine learning. XAI characteristics details with future healthcare explainability is included prominently, whereas the pre-requisite provides insights for the brainstorming sessions before beginning a medical XAI project. Practical case study determines the recent XAI progress leading to the advance developments within the medical field. Ultimately, this survey proposes critical ideas surrounding a user-in-the-loop approach, with an emphasis on human-machine collaboration, to better produce explainable solutions. The surrounding details of the XAI feedback system for human rating-based evaluation provides intelligible insights into a constructive method to produce human enforced explanation feedback. For a long time, XAI limitations of the ratings, scores and grading are present. Therefore, a novel XAI recommendation system and XAI scoring system are designed and approached from this work. Additionally, this paper encourages the importance of implementing explainable solutions into the high impact medical field.

Novel biomarker panel for the diagnosis and prognosis assessment of sepsis based on machine learning

Background: The authors investigated a panel of novel biomarkers for diagnosis and prognosis assessment of sepsis using machine learning (ML) methods. Methods: Hematological parameters, liver function indices and inflammatory marker levels of 332 subjects were retrospectively analyzed. Results: The authors constructed sepsis diagnosis models and identified the random forest (RF) model to be the most optimal. Compared with PCT (procalcitonin) and CRP (C-reactive protein), the RF model identified sepsis patients at an earlier stage. The sepsis group had a mortality rate of 36.3%, and the RF model had greater predictive ability for the 30-day mortality risk of sepsis patients. Conclusion: The RF model facilitated the identification of sepsis patients and showed greater accuracy in predicting the 30-day mortality risk of sepsis patients.

Machine Learning in Infectious Disease for Risk Factor Identification and Hypothesis Generation: Proof of Concept Using Invasive Candidiasis

Background

Machine learning (ML) models can handle large datasets without assuming underlying relationships and can be useful for evaluating disease characteristics; yet, they are more commonly used for predicting individual disease risk rather than identifying factors at the population level. We offer a proof of concept applying random forest (RF) algorithms to Candida-positive hospital encounters in an electronic health record database of patients in the U.S.

Methods

Candida-positive encounters were extracted from the Cerner HealthFacts database; invasive infections were laboratory positive sterile site Candida infections. Features included demographics, admission source, care setting, physician specialty, diagnostic and procedure codes, and medications received prior to the first positive Candida culture. We used RF to assess risk factors for three outcomes: any invasive candidiasis (IC) vs non-IC, within-species IC vs non-IC (e.g. invasive C. glabrata vs non-invasive C. glabrata), and between-species IC (e.g. invasive C. glabrata vs all other IC).

Results

14 of 169 (8%) variables were consistently identified as important features in the ML models. When evaluating within-species IC, for example invasive C. glabrata vs non-invasive C. glabrata, we identified known features like central venous catheters, ICU stay, and gastrointestinal operations. In contrast, important variables for invasive C. glabrata vs all other IC included renal disease and medications like diabetes therapeutics, cholesterol medications, and antiarrhythmics.

Conclusions

Known and novel risk factors for IC were identified using ML, demonstrating the hypotheses generating utility of this approach for infectious disease conditions about which less is known, specifically at the species-level or for rarer diseases.

Functional Characterization of Neutrophils Allows Source Control Evaluation in a Murine Sepsis Model

INTRODUCTION

Current surgical guidelines for the treatment of intra-abdominal sepsis recommend interventional source control as the key element of therapy, alongside resuscitation and antibiotic administration. Past trials attempted to predict the success of interventional source control to assess whether further interventional therapy is needed. However, no predictive score could be developed.

MATERIALS AND METHODS

We utilized an established murine abdominal sepsis model, the cecal ligation and puncture (CLP), and performed a successful surgical source control intervention after full development of sepsis, the CLP-excision (CLP/E). We then sought to evaluate the success of the source control by characterizing circulating neutrophil phenotype and functionality 24 h postintervention.

RESULTS

We showed a significant relative increase of neutrophils and a significant absolute and relative increase of activated neutrophils in septic mice. Source control with CLP/E restored these numbers back to baseline. Moreover, main neutrophil functions, the acidification of cell compartments, such as lysosomes, and the production of Tumor Necrosis Factor-alpha (TNF-α), were impaired in septic mice but restored after CLP/E intervention.

CONCLUSIONS

Neutrophil characterization by phenotyping and evaluating their functionality indicates successful source control in septic mice and can serve as a prognostic tool. These findings provide a rationale for the phenotypic and functional characterization of neutrophils in human patients with infection. Further studies will be needed to determine whether a predictive score for the assessment of successful surgical source control can be established.

Discriminant analysis and binary logistic regression enable more accurate prediction of autism spectrum disorder than principal component analysis

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by impaired social interaction and restricted, repetitive behavior. Multiple studies have suggested mitochondrial dysfunction, glutamate excitotoxicity, and impaired detoxification mechanism as accepted etiological mechanisms of ASD that can be targeted for therapeutic intervention. In the current study, blood samples were collected from 40 people with autism and 40 control participants after informed consent and full approval from the Institutional Review Board of King Saud University. Sodium (Na⁺), Potassium (K⁺), lactate dehydrogenase (LDH), glutathione-s-transferase (GST), and mitochondrial respiratory chain complex I (MRC1) were measured in plasma of both groups. Predictive models were established to discriminate individuals with ASD from controls. The predictive power of these five variables, individually and in combination, was compared using the area under a ROC curve (AUC). We compared the performance of principal component analysis (PCA), discriminant analysis (DA), and binary logistic regression (BLR) as ways to combine single variables and create the predictive models. K⁺ had the highest AUC (0.801) of any single variable, followed by GST, LDH, Na⁺, and MRC1, respectively. Combining the five variables resulted in higher AUCs than those obtained using single variables across all models. Both DA and BLR were superior to PCA and comparable to each other. In our study, the combination of Na⁺, K⁺, LDH, GST, and MRC1 showed the highest promise in discriminating individuals with autism from controls. These results provide a platform that can potentially be used to verify the efficacy of our models with a larger sample size or evaluate other biomarkers.

Screening of Long Non-coding RNAs Biomarkers for the Diagnosis of Tuberculosis and Preliminary Construction of a Clinical Diagnosis Model

Background

Pathogenic testing for tuberculosis (TB) is not yet sufficient for early and differential clinical diagnosis; thus, we investigated the potential of screening long non-coding RNAs (lncRNAs) from human hosts and using machine learning (ML) algorithms combined with electronic health record (EHR) metrics to construct a diagnostic model.

Methods

A total of 2,759 subjects were included in this study, including 12 in the primary screening cohort [7 TB patients and 5 healthy controls (HCs)] and 2,747 in the selection cohort (798 TB patients, 299 patients with non-TB lung disease, and 1,650 HCs). An Affymetrix HTA2.0 array and qRT-PCR were applied to screen new specific lncRNA markers for TB in individual nucleated cells from host peripheral blood. A ML algorithm was established to combine the patients’ EHR information and lncRNA data via logistic regression models and nomogram visualization to differentiate PTB from suspected patients of the selection cohort.

Results

Two differentially expressed lncRNAs (TCONS_00001838 and n406498) were identified (p < 0.001) in the selection cohort. The optimal model was the “LncRNA + EHR” model, which included the above two lncRNAs and eight EHR parameters (age, hemoglobin, lymphocyte count, gamma interferon release test, weight loss, night sweats, polymorphic changes, and calcified foci on imaging). The best model was visualized by a nomogram and validated, and the accuracy of the “LncRNA + EHR” model was 0.79 (0.75–0.82), with a sensitivity of 0.81 (0.78–0.86), a specificity of 0.73 (0.64–0.79), and an area under the ROC curve (AUC) of 0.86. Furthermore, the nomogram showed good compliance in predicting the risk of TB and a higher net benefit than the “EHR” model for threshold probabilities of 0.2–1.

Conclusion

LncRNAs TCONS_00001838 and n406498 have the potential to become new molecular markers for PTB, and the nomogram of “LncRNA + EHR” model is expected to be effective for the early clinical diagnosis of TB.

Micro- and nanosensors for detecting blood pathogens and biomarkers at different points of sepsis care

Severe infections can cause a dysregulated response leading to organ dysfunction known as sepsis. Sepsis can be lethal if not identified and treated right away. This requires measuring biomarkers and pathogens rapidly at the different points where sepsis care is provided. Current commercial approaches for sepsis diagnosis are not fast, sensitive, and/or specific enough for meeting this medical challenge. In this article, we review recent advances in the development of diagnostic tools for sepsis management based on micro- and nanostructured materials. We start with a brief introduction to the most popular biomarkers for sepsis diagnosis (lactate, procalcitonin, cytokines, C-reactive protein, and other emerging protein and non-protein biomarkers including miRNAs and cell-based assays) and methods for detecting bacteremia. We then highlight the role of nano- and microstructured materials in developing biosensors for detecting them taking into consideration the particular needs of every point of sepsis care (e.g., ultrafast detection of multiple protein biomarkers for diagnosing in triage, emergency room, ward, and intensive care unit; quantitative detection to de-escalate treatment; ultrasensitive and culture-independent detection of blood pathogens for personalized antimicrobial therapies; robust, portable, and web-connected biomarker tests outside the hospital). We conclude with an overview of the most utilized nano- and microstructured materials used thus far for solving issues related to sepsis diagnosis and point to new challenges for future development.

Evaluating machine learning models for sepsis prediction: A systematic review of methodologies

Studies for sepsis prediction using machine learning are developing rapidly in medical science recently. In this review, we propose a set of new evaluation criteria and reporting standards to assess 21 qualified machine learning models for quality analysis based on PRISMA. Our assessment shows that (1.) the definition of sepsis is not consistent among the studies; (2.) data sources and data preprocessing methods, machine learning models, feature engineering, and inclusion types vary widely among the studies; (3.) the closer to the onset of sepsis, the higher the value of AUROC is; (4.) the improvement in AUROC is primarily due to using machine learning as a feature engineering tool; (5.) deep neural networks coupled with Sepsis-3 diagnostic criteria tend to yield better results on the time series data collected from patients with sepsis. The new evaluation criteria and reporting standards will facilitate the development of improved machine learning models for clinical applications.

•

New evaluation/reporting standard for sepsis prediction machine learning models

•

Major limitations in the current models for sepsis prediction have been identified

•

We strongly suggest using machine learning as a feature engineering tool

•

Recommending multilayer neural networks and Sepsis 3.0 for yield better result

Diagnostic Challenges in Sepsis

Purpose of Review

Sepsis is a leading cause of death worldwide. Groundbreaking international collaborative efforts have culminated in the widely accepted surviving sepsis guidelines, with iterative improvements in management strategies and definitions providing important advances in care for patients. Key to the diagnosis of sepsis is identification of infection, and whilst the diagnostic criteria for sepsis is now clear, the diagnosis of infection remains a challenge and there is often discordance between clinician assessments for infection.

Recent Findings

We review the utility of common biochemical, microbiological and radiological tools employed by clinicians to diagnose infection and explore the difficulty of making a diagnosis of infection in severe inflammatory states through illustrative case reports. Finally, we discuss some of the novel and emerging approaches in diagnosis of infection and sepsis.

Summary

While prompt diagnosis and treatment of sepsis is essential to improve outcomes in sepsis, there remains no single tool to reliably identify or exclude infection. This contributes to unnecessary antimicrobial use that is harmful to individuals and populations. There is therefore a pressing need for novel solutions. Machine learning approaches using multiple diagnostic and clinical inputs may offer a potential solution but as yet these approaches remain experimental.

Early Prediction of Sepsis Based on Machine Learning Algorithm

Sepsis is an organ failure disease caused by an infection resulting in extremely high mortality. Machine learning algorithms XGBoost and LightGBM are applied to construct two processing methods: mean processing method and feature generation method, aiming to predict early sepsis 6 hours in advance. The feature generation methods are constructed by combining different features, including statistical strength features, window features, and medical features. Miceforest multiple interpolation method is applied to tackle large missing data problems. Results show that the feature generation method outperforms the mean processing method. XGBoost and LightGBM algorithms are both excellent in prediction performance (AUC: 0.910∼0.979), among which LightGBM boasts a faster running speed and is stronger in generalization ability especially on multidimensional data, with AUC reaching 0.979 in the feature generation method. PTT, WBC, and platelets are the key risk factors to predict early sepsis.

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.

Point-of-critical-care diagnostics for sepsis enabled by multiplexed micro and nanosensing technologies

Sepsis is responsible for the highest economic and mortality burden in critical care settings around the world, prompting the World Health Organization in 2018 to designate it as a global health priority. Despite its high universal prevalence and mortality rate, a disproportionately low amount of sponsored research funding is directed toward diagnosis and treatment of sepsis, when early treatment has been shown to significantly improve survival. Additionally, current technologies and methods are inadequate to provide an accurate and timely diagnosis of septic patients in multiple clinical environments. For improved patient outcomes, a comprehensive immunological evaluation is critical which is comprised of both traditional testing and quantifying recently proposed biomarkers for sepsis. There is an urgent need to develop novel point-of-care, low-cost systems which can accurately stratify patients. These point-of-critical-care sensors should adopt a multiplexed approach utilizing multimodal sensing for heterogenous biomarker detection. For effective multiplexing, the sensors must satisfy criteria including rapid sample to result delivery, low sample volumes for clinical sample sparring, and reduced costs per test. A compendium of currently developed multiplexed micro and nano (M/N)-based diagnostic technologies for potential applications toward sepsis are presented. We have also explored the various biomarkers targeted for sepsis including immune cell morphology changes, circulating proteins, small molecules, and presence of infectious pathogens. An overview of different M/N detection mechanisms are also provided, along with recent advances in related nanotechnologies which have shown improved patient outcomes and perspectives on what future successful technologies may encompass. This article is categorized under: Diagnostic Tools > Biosensing.

Diagnostic and prognostic capabilities of a biomarker and EMR-based machine learning algorithm for sepsis

Sepsis is a major cause of mortality among hospitalized patients worldwide. Shorter time to administration of broad‐spectrum antibiotics is associated with improved outcomes, but early recognition of sepsis remains a major challenge. In a two‐center cohort study with prospective sample collection from 1400 adult patients in emergency departments suspected of sepsis, we sought to determine the diagnostic and prognostic capabilities of a machine‐learning algorithm based on clinical data and a set of uncommonly measured biomarkers. Specifically, we demonstrate that a machine‐learning model developed using this dataset outputs a score with not only diagnostic capability but also prognostic power with respect to hospital length of stay (LOS), 30‐day mortality, and 3‐day inpatient re‐admission both in our entire testing cohort and various subpopulations. The area under the receiver operating curve (AUROC) for diagnosis of sepsis was 0.83. Predicted risk scores for patients with septic shock were higher compared with patients with sepsis but without shock (p < 0.0001). Scores for patients with infection and organ dysfunction were higher compared with those without either condition (p < 0.0001). Stratification based on predicted scores of the patients into low, medium, and high‐risk groups showed significant differences in LOS (p < 0.0001), 30‐day mortality (p < 0.0001), and 30‐day inpatient readmission (p < 0.0001). In conclusion, a machine‐learning algorithm based on electronic medical record (EMR) data and three nonroutinely measured biomarkers demonstrated good diagnostic and prognostic capability at the time of initial blood culture.

Microfluidics for sepsis early diagnosis and prognosis: a review of recent methods

Sepsis is a complex disorder of immune system response to infections that can be caused by a wide range of clinical contexts. Traditional methods for sepsis detection include molecular diagnosis, biomarkers either based on protein concentration or cell surface expression, and microbiological cultures. Development of point-of-care (POC) instruments, which can provide high accuracy and consume less time, is in unprecedented demand. Within the past few years, applications of microfluidic systems for sepsis detection have achieved excellent performance. In this review, we discuss the most recent microfluidic applications specifically in sepsis detection, and propose their advantages and disadvantages. We also present a comprehensive review of other traditional and current sepsis diagnosis methods to obtain a general understanding of the present conditions, which can hopefully direct the development of a new sepsis roadmap.

The potential of artificial intelligence to improve patient safety: a scoping review

Artificial intelligence (AI) represents a valuable tool that could be used to improve the safety of care. Major adverse events in healthcare include: healthcare-associated infections, adverse drug events, venous thromboembolism, surgical complications, pressure ulcers, falls, decompensation, and diagnostic errors. The objective of this scoping review was to summarize the relevant literature and evaluate the potential of AI to improve patient safety in these eight harm domains. A structured search was used to query MEDLINE for relevant articles. The scoping review identified studies that described the application of AI for prediction, prevention, or early detection of adverse events in each of the harm domains. The AI literature was narratively synthesized for each domain, and findings were considered in the context of incidence, cost, and preventability to make projections about the likelihood of AI improving safety. Three-hundred and ninety-two studies were included in the scoping review. The literature provided numerous examples of how AI has been applied within each of the eight harm domains using various techniques. The most common novel data were collected using different types of sensing technologies: vital sign monitoring, wearables, pressure sensors, and computer vision. There are significant opportunities to leverage AI and novel data sources to reduce the frequency of harm across all domains. We expect AI to have the greatest impact in areas where current strategies are not effective, and integration and complex analysis of novel, unstructured data are necessary to make accurate predictions; this applies specifically to adverse drug events, decompensation, and diagnostic errors.

Potential Targets to Mitigate Trauma- or Sepsis-Induced Immune Suppression

In sepsis and trauma, pathogens and injured tissue provoke a systemic inflammatory reaction which can lead to overwhelming inflammation. Concurrent with the innate hyperinflammatory response is adaptive immune suppression that can become chronic. A current key issue today is that patients who undergo intensive medical care after sepsis or trauma have a high mortality rate after being discharged. This high mortality is thought to be associated with persistent immunosuppression. Knowledge about the pathophysiology leading to this state remains fragmented. Immunosuppressive cytokines play an essential role in mediating and upholding immunosuppression in these patients. Specifically, the cytokines Interleukin-10 (IL-10), Transforming Growth Factor-β (TGF-β) and Thymic stromal lymphopoietin (TSLP) are reported to have potent immunosuppressive capacities. Here, we review their ability to suppress inflammation, their dynamics in sepsis and trauma and what drives the pathologic release of these cytokines. They do exert paradoxical effects under certain conditions, which makes it necessary to evaluate their functions in the context of dynamic changes post-sepsis and trauma. Several drugs modulating their functions are currently in clinical trials in the treatment of other pathologies. We provide an overview of the current literature on the effects of IL-10, TGF-β and TSLP in sepsis and trauma and suggest therapeutic approaches for their modulation.

Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective

Sepsis is a major cause of death worldwide. Over the past years, prediction of clinically relevant events through machine learning models has gained particular attention. In the present perspective, we provide a brief, clinician-oriented vision on the following relevant aspects concerning the use of machine learning predictive models for the early detection of sepsis in the daily practice: (i) the controversy of sepsis definition and its influence on the development of prediction models; (ii) the choice and availability of input features; (iii) the measure of the model performance, the output, and their usefulness in the clinical practice. The increasing involvement of artificial intelligence and machine learning in health care cannot be disregarded, despite important pitfalls that should be always carefully taken into consideration. In the long run, a rigorous multidisciplinary approach to enrich our understanding in the application of machine learning techniques for the early recognition of sepsis may show potential to augment medical decision-making when facing this heterogeneous and complex syndrome.

Host Diagnostic Biomarkers of Infection in the ICU: Where Are We and Where Are We Going?

Purpose of Review

Early identification of infection in the critically ill patient and initiation of appropriate treatment is key to reducing morbidity and mortality. On the other hand, the indiscriminate use of antimicrobials leads to harms, many of which may be exaggerated in the critically ill population. The current method of diagnosing infection in the intensive care unit relies heavily on clinical gestalt; however, this approach is plagued by biases. Therefore, a reliable, independent biomarker holds promise in the accurate determination of infection. We discuss currently used host biomarkers used in the intensive care unit and review new and emerging approaches to biomarker discovery.

Recent Findings

White cell count (including total white cell count, left shift, and the neutrophil-leucocyte ratio), C-reactive protein, and procalcitonin are the most common host diagnostic biomarkers for sepsis used in current clinical practice. However, their utility in the initial diagnosis of infection, and their role in the subsequent decision to commence treatment, remains limited. Novel approaches to biomarker discovery that are currently being investigated include combination biomarkers, host 'sepsis signatures' based on differential gene expression, site-specific biomarkers, biomechanical assays, and incorporation of new and pre-existing host biomarkers into machine learning algorithms.

Summary

To date, no single reliable independent biomarker of infection exists. Whilst new approaches to biomarker discovery hold promise, their clinical utility may be limited if previous mistakes that have afflicted sepsis biomarker research continue to be repeated.

Lymphocyte Immunosuppression and Dysfunction Contributing to Persistent Inflammation, Immunosuppression, and Catabolism Syndrome (PICS)

ABSTRACT

Persistent Inflammation, Immune Suppression, and Catabolism Syndrome (PICS) is a disease state affecting patients who have a prolonged recovery after the acute phase of a large inflammatory insult. Trauma and sepsis are two pathologies after which such an insult evolves. In this review, we will focus on the key clinical determinants of PICS: Immunosuppression and cellular dysfunction. Currently, relevant immunosuppressive functions have been attributed to both innate and adaptive immune cells. However, there are significant gaps in our knowledge, as for trauma and sepsis the immunosuppressive functions of these cells have mostly been described in acute phase of inflammation so far, and their clinical relevance for the development of prolonged immunosuppression is mostly unknown. It is suggested that the initial immune imbalance determines the development of PCIS. Additionally, it remains unclear what distinguishes the onset of immune dysfunction in trauma and sepsis and how this drives immunosuppression in these cells. In this review, we will discuss how regulatory T cells (Tregs), innate lymphoid cells, natural killer T cells (NKT cells), TCR-a CD4- CD8- double-negative T cells (DN T cells), and B cells can contribute to the development of post-traumatic and septic immunosuppression. Altogether, we seek to fill a gap in the understanding of the contribution of lymphocyte immunosuppression and dysfunction to the development of chronic immune disbalance. Further, we will provide an overview of promising diagnostic and therapeutic interventions, whose potential to overcome the detrimental immunosuppression after trauma and sepsis is currently being tested.

Combining host-derived biomarkers with patient characteristics improves signature performance in predicting tuberculosis treatment outcomes

Tuberculosis (TB) is a global health concern. Treatment is prolonged, and patients on anti-TB therapy (ATT) often experience treatment failure for various reasons. There is an urgent need to identify signatures for early detection of failure and initiation of a treatment switch.

We investigated how gene biomarkers and/or basic patient characteristics could be used to define signatures for treatment outcomes in Indian adult pulmonary-TB patients treated with standard ATT. Using blood samples at baseline, a 12-gene signature combined with information on gender, previously-diagnosed TB, severe thinness, smoking and alcohol consumption was highly predictive of treatment failure at 6 months. Likewise a 4-protein biomarker signature combined with the same patient characteristics was almost as highly predictive of treatment failure. Combining biomarkers and basic patient characteristics may be useful for predicting and hence identification of treatment failure at an early stage of TB therapy.

Sivakumaran et al. show that a 12-gene signature combined with gender, previously diagnosed tuberculosis (TB), severe thinness, smoking, and alcohol consumption predict the treatment outcome at 6 months. This study suggests that the combination of biomarkers and basic patient characteristics may better predict the treatment failure at an early stage of TB therapy.

Long Noncoding RNA and Predictive Model To Improve Diagnosis of Clinically Diagnosed Pulmonary Tuberculosis

Clinically diagnosed pulmonary tuberculosis (PTB) patients lack microbiological evidence of Mycobacterium tuberculosis, and misdiagnosis or delayed diagnosis often occurs as a consequence. We investigated the potential of long noncoding RNAs (lncRNAs) and corresponding predictive models to diagnose these patients. We enrolled 1,764 subjects, including clinically diagnosed PTB patients, microbiologically confirmed PTB cases, non-TB disease controls, and healthy controls, in three cohorts (screening, selection, and validation).

Clinically diagnosed pulmonary tuberculosis (PTB) patients lack microbiological evidence of Mycobacterium tuberculosis, and misdiagnosis or delayed diagnosis often occurs as a consequence. We investigated the potential of long noncoding RNAs (lncRNAs) and corresponding predictive models to diagnose these patients. We enrolled 1,764 subjects, including clinically diagnosed PTB patients, microbiologically confirmed PTB cases, non-TB disease controls, and healthy controls, in three cohorts (screening, selection, and validation). Candidate lncRNAs differentially expressed in blood samples of the PTB and healthy control groups were identified by microarray and reverse transcription-quantitative PCR (qRT-PCR) in the screening cohort. Logistic regression models were developed using lncRNAs and/or electronic health records (EHRs) from clinically diagnosed PTB patients and non-TB disease controls in the selection cohort. These models were evaluated by area under the concentration-time curve (AUC) and decision curve analyses, and the optimal model was presented as a Web-based nomogram, which was evaluated in the validation cohort. Three differentially expressed lncRNAs (ENST00000497872, n333737, and n335265) were identified. The optimal model (i.e., nomogram) incorporated these three lncRNAs and six EHRs (age, hemoglobin, weight loss, low-grade fever, calcification detected by computed tomography [CT calcification], and interferon gamma release assay for tuberculosis [TB-IGRA]). The nomogram showed an AUC of 0.89, a sensitivity of 0.86, and a specificity of 0.82 in differentiating clinically diagnosed PTB cases from non-TB disease controls of the validation cohort, which demonstrated better discrimination and clinical net benefit than the EHR model. The nomogram also had a discriminative power (AUC, 0.90; sensitivity, 0.85; specificity, 0.81) in identifying microbiologically confirmed PTB patients. lncRNAs and the user-friendly nomogram could facilitate the early identification of PTB cases among suspected patients with negative M. tuberculosis microbiological evidence.

Simultaneous electrical detection of IL-6 and PCT using a microfluidic biochip platform

Sepsis, a life-threatening organ dysfunction caused by a dysregulated host response, leads the U.S in both mortality rate and cost of treatment. Sepsis treatment protocols currently rely on broad and non-specific parameters like heart and respiration rate, and temperature; however, studies show that biomarkers Interlukin-6 (IL-6) and Procalcitonin (PCT) correlate to sepsis progression and response to treatment. Prior work also suggests that using multi-parameter predictive analytics with biomarkers and clinical information can inform treatment to improve outcome. A point-of-care (POC) platform that provides information for multiple biomarkers can aid in the diagnosis and prognosis of potentially septic patients. Using impedance cytometry, microbead immunoassays, and biotin-streptavidin binding, we report a microfluidic POC system that correlates microbead capture to IL-6 and PCT concentrations. A multiplexed microbead immunoassay is developed and validated for simultaneous detection of both IL-6 and PCT from human plasma samples. Using the POC platform, we quantified plasma samples containing healthy, medium (~10³pg/ml) and high (~10⁵pg/ml) IL-6 and PCT concentrations with various levels of significance (P < 0.05-P < 0.00001) and validated the concept of this device as a POC platform for sepsis biomarkers.

Machine learning for the detection of early immunological markers as predictors of multi-organ dysfunction

The immune response to major trauma has been analysed mainly within post-hospital admission settings where the inflammatory response is already underway and the early drivers of clinical outcome cannot be readily determined. Thus, there is a need to better understand the immediate immune response to injury and how this might influence important patient outcomes such as multi-organ dysfunction syndrome (MODS). In this study, we have assessed the immune response to trauma in 61 patients at three different post-injury time points (ultra-early (<=1 h), 4-12 h, 48-72 h) and analysed relationships with the development of MODS. We developed a pipeline using Absolute Shrinkage and Selection Operator and Elastic Net feature selection methods that were able to identify 3 physiological features (decrease in neutrophil CD62L and CD63 expression and monocyte CD63 expression and frequency) as possible biomarkers for MODS development. After univariate and multivariate analysis for each feature alongside a stability analysis, the addition of these 3 markers to standard clinical trauma injury severity scores yields a Generalized Liner Model (GLM) with an average Area Under the Curve value of 0.92 ± 0.06. This performance provides an 8% improvement over the Probability of Survival (PS14) outcome measure and a 13% improvement over the New Injury Severity Score (NISS) for identifying patients at risk of MODS.

Molecular and biomarker-based diagnostics in early sepsis: current challenges and future perspectives

Introduction: Sepsis, defined as a life-threatening organ dysfunction resulting from dysregulated host response to infection, is still a major challenge for healthcare systems. Early diagnosis is highly needed, yet challenging, due to the non-specificity of clinical symptoms. Rapid and targeted application of therapy strategies is crucial for patient's outcome.Areas covered: Faster and better diagnostics with high accuracy is promised by novel host response biomarkers and a wide variety of direct pathogen identification technologies, which have emerged over the last years. This review will cover both - host response-guided diagnostics and methods for direct pathogen detection. Some of the markers and technologies are already market-ready, others are more likely aspirants. We will discuss them in terms of their performance and benefit for use in clinical diagnostics.Expert opinion: Latest technological advances enable the development of promising diagnostic tests, detecting the host response as well as identifying pathogens without the need of cultivation. However, the syndrome's heterogeneity makes it difficult to develop a universal test suitable for routine use. Moreover, the robustness of the biomarkers and technologies still has to be verified. Combining these technologies and clinical routine parameters with bioinformatic methods (e.g., machine-learning algorithms) may revolutionize sepsis diagnostics.

Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Clinical applications of artificial intelligence in sepsis: A narrative review

Many studies have been published on a variety of clinical applications of artificial intelligence (AI) for sepsis, while there is no overview of the literature. The aim of this review is to give an overview of the literature and thereby identify knowledge gaps and prioritize areas with high priority for further research. A literature search was conducted in PubMed from inception to February 2019. Search terms related to AI were combined with terms regarding sepsis. Articles were included when they reported an area under the receiver operator characteristics curve (AUROC) as outcome measure. Fifteen articles on diagnosis of sepsis with AI models were included. The best performing model reached an AUROC of 0.97. There were also seven articles on prognosis, predicting mortality over time with an AUROC of up to 0.895. Finally, there were three articles on assistance of treatment of sepsis, where the use of AI was associated with the lowest mortality rates. Of the articles, twenty-two were judged to be at high risk of bias or had major concerns regarding applicability. This was mostly because predictor variables in these models, such as blood pressure, were also part of the definition of sepsis, which led to overestimation of the performance. We conclude that AI models have great potential for improving early identification of patients who may benefit from administration of antibiotics. Current AI prediction models to diagnose sepsis are at major risks of bias when the diagnosis criteria are part of the predictor variables in the model. Furthermore, generalizability of these models is poor due to overfitting and a lack of standardized protocols for the construction and validation of the models. Until these problems have been resolved, a large gap remains between the creation of an AI algorithm and its implementation in clinical practice.

Future Directions of Pharmacovigilance Studies Using Electronic Medical Recording and Human Genetic Databases

Adverse drug reactions (ADRs) constitute key factors in determining successful medication therapy in clinical situations. Integrative analysis of electronic medical record (EMR) data and use of proper analytical tools are requisite to conduct retrospective surveillance of clinical decisions on medications. Thus, we suggest that electronic medical recording and human genetic databases are considered together in future directions of pharmacovigilance. We analyzed EMR-based ADR studies indexed on PubMed during the period from 2005 to 2017 and retrospectively acquired 1161 (29.6%) articles describing drug-induced adverse reactions (e.g., liver, kidney, nervous system, immune system, and inflammatory responses). Of them, only 102 (8.79%) articles contained useful information to detect or predict ADRs in the context of clinical medication alerts. Since insufficiency of EMR datasets and their improper analyses may provide false warnings on clinical decision, efforts should be made to overcome possible problems on data-mining, analysis, statistics, and standardization. Thus, we address the characteristics and limitations on retrospective EMR database studies in hospital settings. Since gene expression and genetic variations among individuals impact ADRs, pharmacokinetics, and pharmacodynamics, appropriate paths for pharmacovigilance may be optimized using suitable databases available in public domain (e.g., genome-wide association studies (GWAS), non-coding RNAs, microRNAs, proteomics, and genetic variations), novel targets, and biomarkers. These efforts with new validated biomarker analyses would be of help to repurpose clinical and translational research infrastructure and ultimately future personalized therapy considering ADRs.

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

BACKGROUND

Machine learning (ML) is a growing field in medicine. This narrative review describes the current body of literature on ML for clinical decision support in infectious diseases (ID).

OBJECTIVES

We aim to inform clinicians about the use of ML for diagnosis, classification, outcome prediction and antimicrobial management in ID.

SOURCES

References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, ACM Digital Library, arXiV and IEEE Xplore Digital Library up to July 2019.

CONTENT

We found 60 unique ML-clinical decision support systems (ML-CDSS) aiming to assist ID clinicians. Overall, 37 (62%) focused on bacterial infections, 10 (17%) on viral infections, nine (15%) on tuberculosis and four (7%) on any kind of infection. Among them, 20 (33%) addressed the diagnosis of infection, 18 (30%) the prediction, early detection or stratification of sepsis, 13 (22%) the prediction of treatment response, four (7%) the prediction of antibiotic resistance, three (5%) the choice of antibiotic regimen and two (3%) the choice of a combination antiretroviral therapy. The ML-CDSS were developed for intensive care units (n = 24, 40%), ID consultation (n = 15, 25%), medical or surgical wards (n = 13, 20%), emergency department (n = 4, 7%), primary care (n = 3, 5%) and antimicrobial stewardship (n = 1, 2%). Fifty-three ML-CDSS (88%) were developed using data from high-income countries and seven (12%) with data from low- and middle-income countries (LMIC). The evaluation of ML-CDSS was limited to measures of performance (e.g. sensitivity, specificity) for 57 ML-CDSS (95%) and included data in clinical practice for three (5%).

IMPLICATIONS

Considering comprehensive patient data from socioeconomically diverse healthcare settings, including primary care and LMICs, may improve the ability of ML-CDSS to suggest decisions adapted to various clinical contexts. Currents gaps identified in the evaluation of ML-CDSS must also be addressed in order to know the potential impact of such tools for clinicians and patients.

Using Data Analytics to Predict Hospital Mortality in Sepsis Patients

Predictive analytics can be used to anticipate the risks associated with some patients, and prediction models can be employed to alert physicians and allow timely proactive interventions. Recently, health care providers have been using different types of tools with prediction capabilities. Sepsis is one of the leading causes of in-hospital death in the United States and worldwide. In this study, the authors used a large medical dataset to develop and present a model that predicts in-hospital mortality among Sepsis patients. The predictive model was developed using a dataset of more than one million records of hospitalized patients. The independent predictors of in-hospital mortality were identified using the chi-square automatic interaction detector. The authors found that adding hospital attributes to the predictive model increased the accuracy from 82.08% to 85.3% and the area under the curve from 0.69 to 0.84, which is favorable compared to using only patients' attributes. The authors discuss the practical and research contributions of using a predictive model that incorporates both patient and hospital attributes in identifying high-risk patients.

Procalcitonin, C-Reactive Protein, Albumin, and Blood Cultures as Early Markers of Sepsis Diagnosis or Predictors of Outcome: A Prospective Analysis

Purpose:

Sepsis is a condition with high mortality rates and its diagnosis remains a challenge. We assessed epidemiological, clinical data, multiple biomarker profiles, and blood culture with respect to sepsis diagnosis and predictors of outcome.

Methods:

In total, 183 patients who were suspected of having sepsis and underwent blood culture collection were followed up for 7 days. Sepsis-related Organ Failure Assessment (SOFA) and Acute Physiology and Chronic Health Evaluation (APACHE) II scores were calculated daily; biomarkers and blood culture test results were evaluated.

Results:

In total, 78 (43%) had sepsis, 50 (27%) had septic shock, and 55 (30%) had no sepsis. Blood culture was positive in 28% and 42% of the sepsis and septic shock groups, respectively (P < .001). Regarding clinical profiles and biomarker values, there were no differences between the sepsis and non-sepsis groups, but significant differences were observed in the septic shock group. Multivariate logistic regression models revealed that age, serum albumin level, APACHE II, and SOFA 1^st day scores were the independent variables for death.

Conclusions:

The challenge in the diagnosis of sepsis continues as clinical and laboratory differences found between the groups were due to septic shock. Older aged patients with lower albumin levels and higher APACHE II and SOFA 1^st day scores have a greater probability of mortality.

Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients

Sepsis, a dysregulated host response to infection, is a major health burden in terms of both mortality and cost. The difficulties clinicians face in diagnosing sepsis, alongside the insufficiencies of diagnostic biomarkers, motivate the present study. This work develops a machine-learning-based sepsis diagnostic for a high-risk patient group, using a geographically and institutionally diverse collection of nearly 500,000 patient health records. Using only a minimal set of clinical variables, our diagnostics outperform common severity scoring systems and sepsis biomarkers and benefit from being available immediately upon ordering.

Following anticancer drug activity in cell lysates with DNA devices

There is a great need to track the selectivity of anticancer drug activity and to understand the mechanisms of associated biological activity. Here we focus our studies on the specific NQO1 bioactivatable drug, ß-lapachone, which is in several Phase I clinical trials to treat human non-small cell lung, pancreatic and breast cancers. Multi-electrode chips with electrochemically-active DNA monolayers are used to track anticancer drug activity in cellular lysates and correlate cell death activity with DNA damage. Cells were prepared from the triple-negative breast cancer (TNBC) cell line, MDA-MB-231 (231) to be proficient or deficient in expression of the NAD(P)H:quinone oxidoreductase 1 (NQO1) enzyme, which is overexpressed in most solid cancers and lacking in control healthy cells. Cells were lysed and added to chips, and the impact of β-lapachone (β-lap), an NQO1-dependent DNA-damaging drug, was tracked with DNA electrochemical signal changes arising from drug-induced DNA damage. Electrochemical DNA devices showed a 3.7-fold difference in the electrochemical responses in NQO1+ over NQO1- cell lysates, as well as 10-20-fold selectivity to catalase and dicoumarol controls that deactivate DNA damaging pathways. Concentration-dependence studies revealed that 1.4 µM β-lap correlated with the onset of cell death from viability assays and the midpoint of DNA damage on the chip, and 2.5 µM β-lap correlated with the midpoint of cell death and the saturation of DNA damage on the chip. Results indicate that these devices could inform therapeutic decisions for cancer treatment.

Multivariate computational analysis of biosensor's data for improved CD64 quantification for sepsis diagnosis

Sepsis, as a leading cause of death worldwide, relies on systemic inflammatory response syndrome (SIRS) criteria for its diagnosis. SIRS is highly non-specific as it relies on monitoring of patients' vitals for sepsis diagnosis, which are known to change with many confounding factors. Changes in leukocyte counts and CD64 expression levels are known specific biomarkers of pro-inflammatory host response at the onset of sepsis. Recently, we have developed a biosensor chip that can enumerate the leukocyte counts and quantify the neutrophil CD64 expression levels from a drop of blood. We were able to show improved sepsis diagnosis and prognosis in clinical studies by measuring these parameters during different times of the patients' stay in hospital. In this paper, we investigated the rate of cell capture with CD64 expression levels and used this in a multivariate computational model using artificial neural networks (ANNs) and showed improved accuracy of quantifying CD64 expression levels from the biosensor (n = 106 whole blood experiments). We found a high coefficient of determination and low error between biosensor- and flow cytometry-based neutrophil CD64 expression levels using multiple ANN training methods in comparison to those of univariate regression commonly employed. This approach can find many applications in biosensor data analytics by utilizing multiple features of the biosensor's data for output determination.

Emerging Technologies for Molecular Diagnosis of Sepsis

Rapid and accurate profiling of infection-causing pathogens remains a significant challenge in modern health care. Despite advances in molecular diagnostic techniques, blood culture analysis remains the gold standard for diagnosing sepsis. However, this method is too slow and cumbersome to significantly influence the initial management of patients. The swift initiation of precise and targeted antibiotic therapies depends on the ability of a sepsis diagnostic test to capture clinically relevant organisms along with antimicrobial resistance within 1 to 3 h. The administration of appropriate, narrow-spectrum antibiotics demands that such a test be extremely sensitive with a high negative predictive value. In addition, it should utilize small sample volumes and detect polymicrobial infections and contaminants. All of this must be accomplished with a platform that is easily integrated into the clinical workflow. In this review, we outline the limitations of routine blood culture testing and discuss how emerging sepsis technologies are converging on the characteristics of the ideal sepsis diagnostic test. We include seven molecular technologies that have been validated on clinical blood specimens or mock samples using human blood. In addition, we discuss advances in machine learning technologies that use electronic medical record data to provide contextual evaluation support for clinical decision-making.