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

Artificial intelligence and prescription of antibiotic therapy: present and future

INTRODUCTION

In the past few years, the use of artificial intelligence in healthcare has grown exponentially. Prescription of antibiotics is not exempt from its rapid diffusion, and various machine learning (ML) techniques, from logistic regression to deep neural networks and large language models, have been explored in the literature to support decisions regarding antibiotic prescription.

AREAS COVERED

In this narrative review, we discuss promises and challenges of the application of ML-based clinical decision support systems (ML-CDSSs) for antibiotic prescription. A search was conducted in PubMed up to April 2024.

EXPERT OPINION

Prescribing antibiotics is a complex process involving various dynamic phases. In each of these phases, the support of ML-CDSSs has shown the potential, and also the actual ability in some studies, to favorably impacting relevant clinical outcomes. Nonetheless, before widely exploiting this massive potential, there are still crucial challenges ahead that are being intensively investigated, pertaining to the transparency of training data, the definition of the sufficient degree of prediction explanations when predictions are obtained through black box models, and the legal and ethical framework for decision responsibility whenever an antibiotic prescription is supported by ML-CDSSs.

Strengthening the use of artificial intelligence within healthcare delivery organizations: balancing regulatory compliance and patient safety

OBJECTIVES

Surface the urgent dilemma that healthcare delivery organizations (HDOs) face navigating the US Food and Drug Administration (FDA) final guidance on the use of clinical decision support (CDS) software.

MATERIALS AND METHODS

We use sepsis as a case study to highlight the patient safety and regulatory compliance tradeoffs that 6129 hospitals in the United States must navigate.

RESULTS

Sepsis CDS remains in broad, routine use. There is no commercially available sepsis CDS system that is FDA cleared as a medical device. There is no public disclosure of an HDO turning off sepsis CDS due to regulatory compliance concerns. And there is no public disclosure of FDA enforcement action against an HDO for using sepsis CDS that is not cleared as a medical device.

DISCUSSION AND CONCLUSION

We present multiple policy interventions that would relieve the current tension to enable HDOs to utilize artificial intelligence to improve patient care while also addressing FDA concerns about product safety, efficacy, and equity.

Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause of sepsis is crucial, and identifying those at risk of complications and death is imperative for triaging treatment and resource allocation. Here, we explored the potential of explainable machine learning models to predict mortality and causative pathogen in sepsis patients. By using a modelling pipeline employing multiple feature selection algorithms, we demonstrate the feasibility of identifying integrative patterns from clinical parameters, plasma biomarkers, and extensive phenotyping of blood immune cells. While no single variable had sufficient predictive power, models that combined five and more features showed a macro area under the curve (AUC) of 0.85 to predict 90-day mortality after sepsis diagnosis, and a macro AUC of 0.86 to discriminate between Gram-positive and Gram-negative bacterial infections. Parameters associated with the cellular immune response contributed the most to models predictive of 90-day mortality, most notably, the proportion of T cells among PBMCs, together with expression of CXCR3 by CD4+ T cells and CD25 by mucosal-associated invariant T (MAIT) cells. Frequencies of Vδ2+ γδ T cells had the most profound impact on the prediction of Gram-negative infections, alongside other T-cell-related variables and total neutrophil count. Overall, our findings highlight the added value of measuring the proportion and activation patterns of conventional and unconventional T cells in the blood of sepsis patients in combination with other immunological, biochemical, and clinical parameters.

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.

Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis

BACKGROUND AND OBJECTIVES

Sepsis is accompanied by a considerably high risk of mortality in the short term, despite the availability of recommended mortality risk assessment tools. However, these risk assessment tools seem to have limited predictive value. With the gradual integration of machine learning into clinical practice, some researchers have attempted to employ machine learning for early mortality risk prediction in sepsis patients. Nevertheless, there is a lack of comprehensive understanding regarding the construction of predictive variables using machine learning and the value of various machine learning methods. Thus, we carried out this systematic review and meta-analysis to explore the predictive value of machine learning for sepsis-related death at different time points.

METHODS

PubMed, Embase, Cochrane, and Web of Science databases were searched until August 9th, 2022. The risk of bias in predictive models was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST). We also performed subgroup analysis according to time of death and type of model and summarized current predictive variables used to construct models for sepsis death prediction.

RESULTS

Fifty original studies were included, covering 104 models. The combined Concordance index (C-index), sensitivity, and specificity of machine learning models were 0.799, 0.81, and 0.80 in the training set, and 0.774, 0.71, and 0.68 in the validation set, respectively. Machine learning outperformed conventional clinical scoring tools and showed excellent C-index, sensitivity, and specificity in different subgroups. Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) are the preferred machine learning models because they showed more favorable accuracy with similar modeling variables. This study found that lactate was the most frequent predictor but was seriously ignored by current clinical scoring tools.

CONCLUSION

Machine learning methods demonstrate relatively favorable accuracy in predicting the mortality risk in sepsis patients. Given the limitations in accuracy and applicability of existing prediction scoring systems, there is an opportunity to explore updates based on existing machine learning approaches. Specifically, it is essential to develop or update more suitable mortality risk assessment tools based on the specific contexts of use, such as emergency departments, general wards, and intensive care units.

Decoding Sepsis-Induced Disseminated Intravascular Coagulation: A Comprehensive Review of Existing and Emerging Therapies

Disseminated intravascular coagulation (DIC) is a recurrent complication of sepsis. Since DIC not only promotes organ dysfunction but also represents a strong prognostic factor, it is important to diagnose DIC as early as possible. When coagulation is activated, fibrinolysis is inhibited, blood thinners are consumed, and a condition is created that promotes blood clotting, making it more difficult for the body to remove fibrin or prevent it from being deposited in the blood vessels. This leads to microvascular thrombosis, which plays a role in organ dysfunction. Despite efforts to understand the underlying mechanisms of sepsis-induced DIC, healthcare providers worldwide still face challenges in effectively treating this condition. In this review, we provide an in-depth analysis of the available strategies for sepsis-induced DIC, considering their effectiveness, limitations, and potential for future advances. Corticosteroids (CS), recombinant thrombomodulin (rTM), vitamin C, fibrinolytic therapy, and platelet transfusion are among the treatments discussed in the review. In addition, we are specifically addressing immunomodulatory therapy (IMT) by investigating treatments such as granulocyte colony-stimulating factor (G-CSF), granulocyte-macrophage colony-stimulating factor (GM-CSF), interferon gamma (IFN-γ), and mesenchymal stem cell therapy (MSC). Finally, we also examined how these therapies might affect COVID-19 cases, which often present with sepsis-induced DIC. The review suggests that targeted experiments with randomization are needed to verify the effectiveness of these treatments and to discover novel approaches to treat sepsis-induced DIC. By increasing our knowledge of sepsis-induced DIC, we can develop targeted treatments that have the potential to save lives and improve outcomes.

Using machine learning for process improvement in sepsis management

INTRODUCTION

In the U.S., sepsis afflicts 1.7 million adults, causing 270,000 deaths each year. Early detection of sepsis could decrease the number of deaths by 92,000 annually and decrease hospital expenditures by 1.5 billion USD. Few prior studies and reviews have presented a holistic understanding of the relationship between machine learning and existing process improvement measures. This study, in addition to discussing machine learning and existing process improvements measures, elaborates on the disadvantages and the barriers to integrating machine learning into the clinic. This article synthesizes previous studies to educate healthcare professionals on effectively managing sepsis by leveraging the benefits of machine learning.

METHODS

This study used the PubMed database. Search terms include sepsis antibiotics, sepsis process improvement, sepsis machine learning. Our search criteria included previous studies published between January 1, 2017, and February 1, 2022.

RESULTS/DISCUSSION

Although machine learning algorithms have better predictive capabilities, their effectiveness in the clinical setting is limited as studies show mixed results because the medical staff often fails to intervene. To overcome poor interventional response, clinicians need to work with the facility's IT department to ensure integration into clinical workflow and minimize alert-fatigue. Algorithms should enhance the productivity of clinical teams, not attempt to replace them entirely.

CONCLUSION

Hospitals can employ process improvement measures that effectively utilize machine learning algorithms to ensure integration into clinical workflows. Healthcare professionals can utilize workflow tools in addition to the predictive capabilities of machine learning to enhance clinical decisions in 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 Models for the Identification of Prognostic and Predictive Cancer Biomarkers: A Systematic Review

The identification of biomarkers plays a crucial role in personalized medicine, both in the clinical and research settings. However, the contrast between predictive and prognostic biomarkers can be challenging due to the overlap between the two. A prognostic biomarker predicts the future outcome of cancer, regardless of treatment, and a predictive biomarker predicts the effectiveness of a therapeutic intervention. Misclassifying a prognostic biomarker as predictive (or vice versa) can have serious financial and personal consequences for patients. To address this issue, various statistical and machine learning approaches have been developed. The aim of this study is to present an in-depth analysis of recent advancements, trends, challenges, and future prospects in biomarker identification. A systematic search was conducted using PubMed to identify relevant studies published between 2017 and 2023. The selected studies were analyzed to better understand the concept of biomarker identification, evaluate machine learning methods, assess the level of research activity, and highlight the application of these methods in cancer research and treatment. Furthermore, existing obstacles and concerns are discussed to identify prospective research areas. We believe that this review will serve as a valuable resource for researchers, providing insights into the methods and approaches used in biomarker discovery and identifying future research opportunities.

Biofabrication of Multiplexed Electrochemical Immunosensors for Simultaneous Detection of Clinical Biomarkers in Complex Fluids

Simultaneous detection of multiple disease biomarkers in unprocessed whole blood is considered the gold standard for accurate clinical diagnosis. Here, this study reports the development of a 4-plex electrochemical (EC) immunosensor with on-chip negative control capable of detecting a range of biomarkers in small volumes (15 µL) of complex biological fluids, including serum, plasma, and whole blood. A framework for fabricating and optimizing multiplexed sandwich immunoassays is presented that is enabled by use of EC sensor chips coated with an ultra-selective, antifouling, and nanocomposite coating. Cyclic voltammetry evaluation of sensor performance is carried out by monitoring the local precipitation of an electroactive product generated by horseradish peroxidase linked to a secondary antibody. EC immunosensors demonstrate high sensitivity and specificity without background signal with a limit of detection in single-digit picogram per milliliter in multiple complex biological fluids. These multiplexed immunosensors enable the simultaneous detection of four different biomarkers in plasma and whole blood with excellent sensitivity and selectivity. This rapid and cost-effective biosensor platform can be further adapted for use with different high affinity probes for any biomarker, and thereby create for a new class of highly sensitive and specific multiplexed diagnostics.

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.

Ultrarapid Method for Coating Electrochemical Sensors with Antifouling Conductive Nanomaterials Enables Highly Sensitive Multiplexed Detection in Whole Blood

The commercialization of electrochemical (EC)-sensors for medical diagnostics is currently limited by their rapid fouling in biological fluids, and use of potential antifouling coatings is hindered by the complexity and cost of application methods. Here, a simple ultrafast (< 1 min) method is described for coating EC-sensors with cross-linked bovine serum albumin infused with conductive, pentaamine-functionalized, graphene particles that can be stored at room temperature for at least 20-weeks, which provides unprecedented sensitivity and selectivity for diagnostic applications. The antifouling coating is applied directly on-chip using rapid heating via simple dip-coating, which provides unprecedented high levels of electrode conductivity for up to 9-weeks in unprocessed biological samples. This method is leveraged to develop a multiplexed platform for detecting clinically relevant biomarkers including myocardial infarction and traumatic brain injury using only 15 µL of blood. Single-digit pg mL^-1 sensitivity is obtained within minutes in unprocessed human plasma and whole blood, which is faster and at least 50 times more sensitive than traditional enzyme-linked immunosorbent assays, and the signal generated is stable enough to be measured after 1 week of storage. The multiplexed EC-sensor platform is validated by analyzing 22 patient samples and demonstrating excellent correlation with reported clinical values.

Identification of Risk Factors for Suicidal Ideation and Attempt Based on Machine Learning Algorithms: A Longitudinal Survey in Korea (2007-2019)

Investigating suicide risk factors is critical for socioeconomic and public health, and many researchers have tried to identify factors associated with suicide. In this study, the risk factors for suicidal ideation were compared, and the contributions of different factors to suicidal ideation and attempt were investigated. To reflect the diverse characteristics of the population, the large-scale and longitudinal dataset used in this study included both socioeconomic and clinical variables collected from the Korean public. Three machine learning algorithms (XGBoost classifier, support vector classifier, and logistic regression) were used to detect the risk factors for both suicidal ideation and attempt. The importance of the variables was determined using the model with the best classification performance. In addition, a novel risk-factor score, calculated from the rank and importance scores of each variable, was proposed. Socioeconomic and sociodemographic factors showed a high correlation with risks for both ideation and attempt. Mental health variables ranked higher than other factors in suicidal attempts, posing a relatively higher suicide risk than ideation. These trends were further validated using the conditions from the integrated and yearly dataset. This study provides novel insights into suicidal risk factors for suicidal ideations and attempts.

Enabling Multiplexed Electrochemical Detection of Biomarkers with High Sensitivity in Complex Biological Samples

The ability to perform multiplexed detection of various biomarkers within complex biological fluids in a robust, rapid, sensitive, and cost-effective manner could transform clinical diagnostics and enable personalized healthcare. Electrochemical (EC) sensor technology has been explored as a way to address this challenge because it does not require optical instrumentation and it is readily compatible with both integrated circuit and microfluidic technologies; yet this approach has had little impact as a viable commercial bioanalytical tool to date. The most critical limitation hindering their clinical application is the fact that EC sensors undergo rapid biofouling when exposed to complex biological samples (e.g., blood, plasma, saliva, urine), leading to the loss of sensitivity and selectivity. Thus, to break through this barrier, we must solve this biofouling problem.In response to this challenge, our group has developed a rapid, robust, and low-cost nanocomposite-based antifouling coating for multiplexed EC sensors that enables unprecedented performance in terms of biomarker signal detection compared to reported literature. The bioinspired antifouling coating that we developed is a nanoporous composite that contains various conductive nanomaterials, including gold nanowires (AuNWs), carbon nanotubes (CNTs), or reduced graphene oxide nanoflakes (rGOx). Each study has progressively evolved this technology to provide increasing performance while simplifying process flow, reducing time, and decreasing cost. For example, after successfully developing a semipermeable nanocomposite coating containing AuNWs cross-linked to bovine serum albumin (BSA) using glutaraldehyde, we replaced the nanomaterials with reduced graphene oxide, reducing the cost by 100-fold while maintaining similar signal transduction and antifouling properties. We, subsequently, developed a localized heat-induced coating method that significantly improved the efficiency of the drop-casting coating process and occurs within the unprecedented time of <1 min (at least 3 orders of magnitude faster than state-of-the-art). Moreover, the resulting coated electrodes can be stored at room temperature for at least 5 months and still maintain full sensitivity and specificity. Importantly, this improved coating showed excellent antifouling activity against various biological fluids, including plasma, serum, whole blood, urine, and saliva.To enable affinity-based sensing of multiple biomarkers simultaneously, we have developed multiplexed EC sensors coated with the improved nanocomposite coating and then employed a sandwich enzyme-linked immunosorbent assay (ELISA) format for signal detection in which the substrate for the enzyme bound to the secondary antibody precipitates locally at the molecular binding site above the electrode surface. Using this improved EC sensor platform, we demonstrated ultrasensitive detection of a wide range of biomarkers from biological fluids, including clinical biomarkers, in both single and multiplex formats (N = 4) with assay times of 37 and 15 min when integrated with a microfluidic system. These biosensors developed demonstrate the vast potential of solving the biofouling problem, and how it can enable potential clinically important diagnostic applications. This Account reviews our antifouling surface chemistry and the multiplexed EC sensor-based biodetection method we developed and places it in context of the various innovative contributions that have been made by other researchers in this field. We are optimistic that future iterations of these systems will change the way diagnostic testing is done, and where it can be carried out, in the future.