Applying Artificial Intelligence to Identify Physiomarkers Predicting Severe Sepsis in the PICU

How does training given to pediatric nurses about artificial intelligence and robot nurses affect their opinions and attitude levels? A quasi-experimental study

PURPOSE

This study was conducted to investigate the effect of training provided to pediatric nurses on their knowledge and attitude levels about artificial intelligence and robot nurses.

DESIGN AND METHODS

In this study, a single-group pre- and post-test quasi-experimental design was used. Data were collected from pediatric nurses working in Training and Research Hospital located in western Turkey. Forty-three pediatric nurses participated in the study. The study data were collected using the "Pediatric Nurses' Descriptive Characteristics Form", "Artificial Intelligence Knowledge Form", and "Artificial Intelligence General Attitude Scale".

RESULTS

The mean scores of the participating pediatric nurses obtained from the Artificial Intelligence Knowledge Form before, right after and one month after the training were 41.16 ± 14.95, 68.25 ± 13.57 and 69.06 ± 13.19, respectively. The mean scores they obtained from the Positive Attitudes towards Artificial Intelligence subscale of the Artificial Intelligence General Attitude Scale before and after the training were 3.43 ± 0.54 and 3.59 ± 0.60, respectively whereas the mean scores they obtained from its Negative Attitudes towards Artificial Intelligence subscale were 2.68 ± 0.67 and 2.77 ± 0.75, respectively.

CONCLUSIONS

It was determined that the training given to the pediatric nurses about artificial intelligence and robot nurses increased the nurses' knowledge levels and their artificial intelligence attitude scores, but this increase in the artificial intelligence attitude scores was not significant.

PRACTICE IMPLICATIONS

The use of artificial intelligence and robotics or advanced technology in pediatric nursing care can be fostered.

Predicting adverse long-term neurocognitive outcomes after pediatric intensive care unit admission

BACKGROUND AND OBJECTIVE

Critically ill children may suffer from impaired neurocognitive functions years after ICU (intensive care unit) discharge. To assess neurocognitive functions, these children are subjected to a fixed sequence of tests. Undergoing all tests is, however, arduous for former pediatric ICU patients, resulting in interrupted evaluations where several neurocognitive deficiencies remain undetected. As a solution, we propose using machine learning to predict the optimal order of tests for each child, reducing the number of tests required to identify the most severe neurocognitive deficiencies.

METHODS

We have compared the current clinical approach against several machine learning methods, mainly multi-target regression and label ranking methods. We have also proposed a new method that builds several multi-target predictive models and combines the outputs into a ranking that prioritizes the worse neurocognitive outcomes. We used data available at discharge, from children who participated in the PEPaNIC-RCT trial (ClinicalTrials.gov-NCT01536275), as well as data from a 2-year follow-up study. The institutional review boards at each participating site have also approved this follow-up study (ML8052; NL49708.078; Pro00038098).

RESULTS

Our proposed method managed to outperform other machine learning methods and also the current clinical practice. Precisely, our method reaches approximately 80% precision when considering top-4 outcomes, in comparison to 65% and 78% obtained by the current clinical practice and the state-of-the-art method in label ranking, respectively.

CONCLUSIONS

Our experiments demonstrated that machine learning can be competitive or even superior to the current testing order employed in clinical practice, suggesting that our model can be used to severely reduce the number of tests necessary for each child. Moreover, the results indicate that possible long-term adverse outcomes are already predictable as early as at ICU discharge. Thus, our work can be seen as the first step to allow more personalized follow-up after ICU discharge leading to preventive care rather than curative.

Artificial Intelligence in Pediatric Emergency Medicine: Applications, Challenges, and Future Perspectives

The dawn of Artificial intelligence (AI) in healthcare stands as a milestone in medical innovation. Different medical fields are heavily involved, and pediatric emergency medicine is no exception. We conducted a narrative review structured in two parts. The first part explores the theoretical principles of AI, providing all the necessary background to feel confident with these new state-of-the-art tools. The second part presents an informative analysis of AI models in pediatric emergencies. We examined PubMed and Cochrane Library from inception up to April 2024. Key applications include triage optimization, predictive models for traumatic brain injury assessment, and computerized sepsis prediction systems. In each of these domains, AI models outperformed standard methods. The main barriers to a widespread adoption include technological challenges, but also ethical issues, age-related differences in data interpretation, and the paucity of comprehensive datasets in the pediatric context. Future feasible research directions should address the validation of models through prospective datasets with more numerous sample sizes of patients. Furthermore, our analysis shows that it is essential to tailor AI algorithms to specific medical needs. This requires a close partnership between clinicians and developers. Building a shared knowledge platform is therefore a key step.

Promises, Pitfalls, and Clinical Applications of Artificial Intelligence in Pediatrics

Artificial intelligence (AI) broadly describes a branch of computer science focused on developing machines capable of performing tasks typically associated with human intelligence. Those who connect AI with the world of science fiction may meet its growing rise with hesitancy or outright skepticism. However, AI is becoming increasingly pervasive in our society, from algorithms helping to sift through airline fares to substituting words in emails and SMS text messages based on user choices. Data collection is ongoing and is being leveraged by software platforms to analyze patterns and make predictions across multiple industries. Health care is gradually becoming part of this technological transformation, as advancements in computational power and storage converge with the rapid expansion of digitized medical information. Given the growing and inevitable integration of AI into health care systems, it is our viewpoint that pediatricians urgently require training and orientation to the uses, promises, and pitfalls of AI in medicine. AI is unlikely to solve the full array of complex challenges confronting pediatricians today; however, if used responsibly, it holds great potential to improve many aspects of care for providers, children, and families. Our aim in this viewpoint is to provide clinicians with a targeted introduction to the field of AI in pediatrics, including key promises, pitfalls, and clinical applications, so they can play a more active role in shaping the future impact of AI in medicine.

Predicting long-term neurocognitive outcome after pediatric intensive care unit admission for bronchiolitis-preliminary exploration of the potential of machine learning

PURPOSE

For successful prevention and intervention, it is important to unravel the complex constellation of factors that affect neurocognitive functioning after pediatric intensive care unit (PICU) admission. This study aims (1) to elucidate the potential relevance of patient and PICU-related characteristics for long-term adverse neurocognitive outcome after PICU admission for bronchiolitis, and (2) to perform a preliminary exploration of the potential of machine learning as compared to linear regression to improve neurocognitive outcome prediction in a relatively small sample of children after PICU admission.

METHODS

This cross-sectional observational study investigated 65 children aged 6-12 years with previous PICU admission for bronchiolitis (age ≤ 1 year). They were compared to demographically comparable healthy peers (n = 76) on neurocognitive functioning. Patient and PICU-related characteristics used for the prediction models were as follows: demographic characteristics, perinatal and disease parameters, laboratory results, and intervention characteristics, including hourly validated mechanical ventilation parameters. Neurocognitive outcome was measured by intelligence and computerized neurocognitive testing. Prediction models were developed for each of the neurocognitive outcomes using Regression Trees, k-Nearest Neighbors, and conventional linear regression analysis.

RESULTS

The patient group had lower intelligence than the control group (p < .001, d = -0.59) and poorer performance in neurocognitive functions, i.e., speed and attention (p = .03, d = -0.41) and verbal memory (p < .001, d = -0.60). Lower intelligence was predicted by lower birth weight and lower socioeconomic status (R2 = 25.9%). Poorer performance on the speed and attention domain was predicted by younger age at follow-up (R2 = 53.5%). Poorer verbal memory was predicted by lower birth weight, younger age at follow-up, and greater exposure to acidotic events (R2 = 50.6%). The machine learning models did not reveal added value in terms of model performance as compared to linear regression.

CONCLUSION

The findings of this study suggest that in children with previous PICU admission for bronchiolitis, (1) lower birth weight, younger age at follow-up, and lower socioeconomic status are associated with poorer neurocognitive outcome; and (2) greater exposure to acidotic events during PICU admission is associated with poorer verbal memory outcome. The findings of this study provide no evidence for the added value of machine learning models as compared to linear regression analysis in the prediction of long-term neurocognitive outcome in a relatively small sample of children.

WHAT IS KNOWN

• Adverse neurocognitive outcomes are described in PICU survivors, which are known to interfere with development in other major domains of functioning, such as mental health, academic achievement, and socioeconomic success, highlighting neurocognition as an important outcome after PICU admission. • Machine learning is a rapidly growing field of artificial intelligence that is increasingly applied in health care settings, with great potential to capture the complexity of outcome prediction.

WHAT IS NEW

• This study shows that lower birth weight, lower socioeconomic status, and greater exposure to acidotic events during PICU admission for bronchiolitis are associated with poorer long-term neurocognitive outcome after PICU admission. Results provide no evidence for the added value of machine learning models in a relatively small sample of children. • As bronchiolitis seldom manifests neurologically, the relation between acidotic events and neurocognitive outcome may reflect either potentially harmful effects of acidosis itself or related processes such as hypercapnia or hypoxic and/or ischemic events during PICU admission. This study further highlights the importance of structured follow-up to monitor long-term outcome of children after PICU admission.

Pediatric Sepsis Diagnosis, Management, and Sub-phenotypes

Sepsis and septic shock are major causes of morbidity, mortality, and health care costs for children worldwide, including >3 million deaths annually and, among survivors, risk for new or worsening functional impairments, including reduced quality of life, new respiratory, nutritional, or technological assistance, and recurrent severe infections. Advances in understanding sepsis pathophysiology highlight a need to update the definition and diagnostic criteria for pediatric sepsis and septic shock, whereas new data support an increasing role for automated screening algorithms and biomarker combinations to assist earlier recognition. Once sepsis or septic shock is suspected, attention to prompt initiation of broad-spectrum empiric antimicrobial therapy, fluid resuscitation, and vasoactive medications remain key components to initial management with several new and ongoing studies offering new insights into how to optimize this approach. Ultimately, a key goal is for screening to encompass as many children as possible at risk for sepsis and trigger early treatment without increasing unnecessary broad-spectrum antibiotics and preventable hospitalizations. Although the role for adjunctive treatment with corticosteroids and other metabolic therapies remains incompletely defined, ongoing studies will soon offer updated guidance for optimal use. Finally, we are increasingly moving toward an era in which precision therapeutics will bring novel strategies to improve outcomes, especially for the subset of children with sepsis-induced multiple organ dysfunction syndrome and sepsis subphenotypes for whom antibiotics, fluid, vasoactive medications, and supportive care remain insufficient.

A Near Real-Time Risk Analytics Algorithm Predicts Elevated Lactate Levels in Pediatric Cardiac Critical Care Patients

BACKGROUND

Postoperative pediatric congenital heart patients are predisposed to develop low-cardiac output syndrome. Serum lactate (lactic acid [LA]) is a well-defined marker of inadequate systemic oxygen delivery.

OBJECTIVES

We hypothesized that a near real-time risk index calculated by a noninvasive predictive analytics algorithm predicts elevated LA in pediatric patients admitted to a cardiac ICU (CICU).

DERIVATION COHORT

Ten tertiary CICUs in the United States and Pakistan.

VALIDATION COHORT

Retrospective observational study performed to validate a hyperlactatemia (HLA) index using T3 platform data (Etiometry, Boston, MA) from pediatric patients less than or equal to 12 years of age admitted to CICU (n = 3,496) from January 1, 2018, to December 31, 2020. Patients lacking required data for module or LA measurements were excluded.

PREDICTION MODEL

Physiologic algorithm used to calculate an HLA index that incorporates physiologic data from patients in a CICU. The algorithm uses Bayes' theorem to interpret newly acquired data in a near real-time manner given its own previous assessment of the physiologic state of the patient.

RESULTS

A total of 58,168 LA measurements were obtained from 3,496 patients included in a validation dataset. HLA was defined as LA level greater than 4 mmol/L. Using receiver operating characteristic analysis and a complete dataset, the HLA index predicted HLA with high sensitivity and specificity (area under the curve 0.95). As the index value increased, the likelihood of having higher LA increased (p < 0.01). In the validation dataset, the relative risk of having LA greater than 4 mmol/L when the HLA index is less than 1 is 0.07 (95% CI: 0.06-0.08), and the relative risk of having LA less than 4 mmol/L when the HLA index greater than 99 is 0.13 (95% CI, 0.12-0.14).

CONCLUSIONS

These results validate the capacity of the HLA index. This novel index can provide a noninvasive prediction of elevated LA. The HLA index showed strong positive association with elevated LA levels, potentially providing bedside clinicians with an early, noninvasive warning of impaired cardiac output and oxygen delivery. Prospective studies are required to analyze the effect of this index on clinical decision-making and outcomes in pediatric population.

Leveraging Data Science and Novel Technologies to Develop and Implement Precision Medicine Strategies in Critical Care

Precision medicine aims to identify treatments that are most likely to result in favorable outcomes for subgroups of patients with similar clinical and biological characteristics. The gaps for the development and implementation of precision medicine strategies in the critical care setting are many, but the advent of data science and multi-omics approaches, combined with the rich data ecosystem in the intensive care unit, offer unprecedented opportunities to realize the promise of precision critical care. In this article, the authors review the data-driven and technology-based approaches being leveraged to discover and implement precision medicine strategies in the critical care setting.

Artificial intelligence in sickle disease

Artificial intelligence (AI) is rapidly becoming an established arm in medical sciences and clinical practice in numerous medical fields. Its implications have been rising and are being widely used in research, diagnostics, and treatment options for many pathologies, including sickle cell disease (SCD). AI has started new ways to improve risk stratification and diagnosing SCD complications early, allowing rapid intervention and reallocation of resources to high-risk patients. We reviewed the literature for established and new AI applications that may enhance management of SCD through advancements in diagnosing SCD and its complications, risk stratification, and the effect of AI in establishing an individualized approach in managing SCD patients in the future. Aim: to review the benefits and drawbacks of resources utilizing AI in clinical practice for improving the management for SCD cases.

Pediatric Critical Care in the Twenty-first Century and Beyond

Pediatric critical care addresses prevention, diagnosis, and treatment of organ dysfunction in the setting of increasingly complex patients, therapies, and environments. Soon burgeoning data science will enable all aspects of intensive care: driving facilitated diagnostics, empowering a learning health-care environment, promoting continuous advancement of care, and informing the continuum of critical care outside the intensive care unit preceding and following critical illness/injury. Although novel technology will progressively objectify personalized critical care, humanism, practiced at the bedside, defines the essence of pediatric critical care now and in the future.

Novel approaches to capturing and using continuous cardiorespiratory physiological data in hospitalized children

Continuous cardiorespiratory physiological monitoring is a cornerstone of care in hospitalized children. The data generated by monitoring devices coupled with machine learning could transform the way we provide care. This scoping review summarizes existing evidence on novel approaches to continuous cardiorespiratory monitoring in hospitalized children. We aimed to identify opportunities for the development of monitoring technology and the use of machine learning to analyze continuous physiological data to improve the outcomes of hospitalized children. We included original research articles published on or after January 1, 2001, involving novel approaches to collect and use continuous cardiorespiratory physiological data in hospitalized children. OVID Medline, PubMed, and Embase databases were searched. We screened 2909 articles and performed full-text extraction of 105 articles. We identified 58 articles describing novel devices or approaches, which were generally small and single-center. In addition, we identified 47 articles that described the use of continuous physiological data in prediction models, but only 7 integrated multidimensional data (e.g., demographics, laboratory results). We identified three areas for development: (1) further validation of promising novel devices; (2) more studies of models integrating multidimensional data with continuous cardiorespiratory data; and (3) further dissemination, implementation, and validation of prediction models using continuous cardiorespiratory data. IMPACT: We performed a comprehensive scoping review of novel approaches to capture and use continuous cardiorespiratory physiological data for monitoring, diagnosis, providing care, and predicting events in hospitalized infants and children, from novel devices to machine learning-based prediction models. We identified three key areas for future development: (1) further validation of promising novel devices; (2) more studies of models integrating multidimensional data with continuous cardiorespiratory data; and (3) further dissemination, implementation, and validation of prediction models using cardiorespiratory data.

The use of machine learning and artificial intelligence within pediatric critical care

The field of pediatric critical care has been hampered in the era of precision medicine by our inability to accurately define and subclassify disease phenotypes. This has been caused by heterogeneity across age groups that further challenges the ability to perform randomized controlled trials in pediatrics. One approach to overcome these inherent challenges include the use of machine learning algorithms that can assist in generating more meaningful interpretations from clinical data. This review summarizes machine learning and artificial intelligence techniques that are currently in use for clinical data modeling with relevance to pediatric critical care. Focus has been placed on the differences between techniques and the role of each in the clinical arena. The various forms of clinical decision support that utilize machine learning are also described. We review the applications and limitations of machine learning techniques to empower clinicians to make informed decisions at the bedside. IMPACT: Critical care units generate large amounts of under-utilized data that can be processed through artificial intelligence. This review summarizes the machine learning and artificial intelligence techniques currently being used to process clinical data. The review highlights the applications and limitations of these techniques within a clinical context to aid providers in making more informed decisions at the bedside.

OnAI-Comp: An Online AI Experts Competing Framework for Early Sepsis Detection

Sepsis is a major public concern due to its high mortality, morbidity, and financial cost. There are many existing works of early sepsis prediction using different machine learning models to mitigate the outcomes brought by sepsis. In the practical scenario, the dataset grows dynamically as new patients visit the hospital. Most existing models, being "offline" models and having used retrospective observational data, cannot be updated and improved dynamically using the new observational data. Incorporating the new data to improve the offline models requires retraining the model, which is very computationally expensive. To solve the challenge mentioned above, we propose an Online Artificial Intelligence Experts Competing Framework (OnAI-Comp) for early sepsis detection using an online learning algorithm called Multi-armed Bandit. We selected several machine learning models as the artificial intelligence experts and used average regret to evaluate the performance of our model. The experimental analysis demonstrated that our model would converge to the optimal strategy in the long run. Meanwhile, our model can provide clinically interpretable predictions using existing local interpretable model-agnostic explanation technologies, which can aid clinicians in making decisions and might improve the probability of survival.

Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics

Purpose

To build machine learning models for predicting the risk of in-hospital death in patients with sepsis within 48 h, using only dynamic changes in the patient's vital signs.

Methods

This retrospective observational cohort study enrolled septic patients from five emergency departments (ED) in Taiwan. We adopted seven variables, i.e., age, sex, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature.

Results

Among all 353,253 visits, after excluding 159,607 visits (45%), the study group consisted of 193,646 ED visits. With a leading time of 6 h, the convolutional neural networks (CNNs), long short-term memory (LSTM), and random forest (RF) had accuracy rates of 0.905, 0.817, and 0.835, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.840, 0.761, and 0.770, respectively. With a leading time of 48 h, the CNN, LSTM, and RF achieved accuracy rates of 0.828, 0759, and 0.805, respectively, and an AUC of 0.811, 0.734, and 0.776, respectively.

Conclusion

By analyzing dynamic vital sign data, machine learning models can predict mortality in septic patients within 6 to 48 h of admission. The performance of the testing models is more accurate if the lead time is closer to the event.

The Risk of Coding Racism into Pediatric Sepsis Care: The Necessity of Antiracism in Machine Learning

Machine learning holds the possibility of improving racial health inequalities by compensating for human bias and structural racism. However, unanticipated racial biases may enter during model design, training, or implementation and perpetuate or worsen racial inequalities if ignored. Pre-existing racial health inequalities could be codified into medical care by machine learning without clinicians being aware. To illustrate the importance of a commitment to antiracism at all stages of machine learning, we examine machine learning in predicting severe sepsis in Black children, focusing on the impacts of structural racism that may be perpetuated by machine learning and difficult to discover. To move toward antiracist machine learning, we recommend partnering with ethicists and experts in model development, enrolling representative samples for training, including socioeconomic inputs with proximate causal associations to racial inequalities, reporting outcomes by race, and committing to equitable models that narrow inequality gaps or at least have equal benefit.

Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission

INTRODUCTION

Septic patients requiring intensive care unit (ICU) readmission are at high risk of mortality, but research focusing on the association of ICU readmission due to sepsis and mortality is limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting in-hospital mortality in septic patients readmitted to the ICU using routinely available clinical data.

METHODS

The data used in this study were obtained from the Medical Information Mart for Intensive Care (MIMIC-IV, v1.0) database, between 2008 and 2019. The study cohort included patients with sepsis requiring ICU readmission. The data were randomly split into a training (75%) data set and a validation (25%) data set. Nine popular ML models were developed to predict mortality in septic patients readmitted to the ICU. The model with the best accuracy and area under the curve (A.C.) in the validation cohort was defined as the optimal model and was selected for further prediction studies. The SHAPELY Additive explanations (SHAP) values and Local Interpretable Model-Agnostic Explanation (LIME) methods were used to improve the interpretability of the optimal model.

RESULTS

A total of 1117 septic patients who had required ICU readmission during the study period were enrolled in the study. Of these participants, 434 (38.9%) were female, and the median (interquartile range [IQR]) age was 68.6 (58.4-79.2) years. The median (IQR) ICU interval duration was 2.60 (0.64-5.78) days. After feature selection, 31 of 47 clinical factors were ultimately chosen for use in model construction. Of the nine ML models tested, the best performance was achieved with the random forest (RF) model, with an A.C. of 0.81, an accuracy of 85% and a precision of 62% in the validation cohort. The SHAP summary analysis revealed that Glasgow Coma Scale score, urine output, blood urea nitrogen, lactate, platelet count and systolic blood pressure were the top six most important factors contributing to the RF model. Additionally, the LIME method demonstrated how the RF model works in terms of explaining risk of death prediction in septic patients requiring ICU readmission.

CONCLUSION

The ML models reported here showed a good prognostic prediction ability in septic patients requiring ICU readmission. Of the features selected, the parameters related to organ perfusion made the largest contribution to outcome prediction during ICU readmission in septic patients.

Clinical Informatics and Quality Improvement in the Pediatric Intensive Care Unit

Clinical informatics can support quality improvement and patient safety in the pediatric intensive care unit (PICU) in several ways including data extraction, analysis, and decision support enabled by electronic health records (EHRs), and databases and registries. Clinical decision support (CDS), embedded in EHRs, now an integral part of the workflow in the PICU, includes several tools and is increasingly leveraging artificial intelligence (AI). Understanding the opportunities and challenges can improve the engagement of clinicians with the design, validation, and implementation of CDS, improve satisfaction with CDS, and improve patient safety, care quality, and value.

Analyzing Relationships Between Economic and Neighborhood-Related Social Determinants of Health and Intensive Care Unit Length of Stay for Critically Ill Children With Medical Complexity Presenting With Severe Sepsis

Objectives

Of the Social Determinants of Health (SDoH), we evaluated socioeconomic and neighborhood-related factors which may affect children with medical complexity (CMC) admitted to a Pediatric Intensive Care Unit (PICU) in Shelby County, Tennessee with severe sepsis and their association with PICU length of stay (LOS). We hypothesized that census tract-level socioeconomic and neighborhood factors were associated with prolonged PICU LOS in CMC admitted with severe sepsis in the underserved community.

Methods

This single-center retrospective observational study included CMC living in Shelby County, Tennessee admitted to the ICU with severe sepsis over an 18-month period. Severe sepsis CMC patients were identified using an existing algorithm incorporated into the electronic medical record at a freestanding children's hospital. SDoH information was collected and analyzed using patient records and publicly available census-tract level data, with ICU length of stay as the primary outcome.

Results

83 encounters representing 73 patients were included in the analysis. The median PICU LOS was 9.04 days (IQR 3.99–20.35). The population was 53% male with a median age of 4.1 years (IQR 1.96–12.02). There were 57 Black/African American patients (68.7%) and 85.5% had public insurance. Based on census tract-level data, about half (49.4%) of the CMC severe sepsis population lived in census tracts classified as suffering from high social vulnerability. There were no statistically significant relationships between any socioeconomic and neighborhood level factors and PICU LOS.

Conclusion

Pediatric CMC severe sepsis patients admitted to the PICU do not have prolonged lengths of ICU stay related to socioeconomic and neighborhood-level SDoH at our center. A larger sample with the use of individual-level screening would need to be evaluated for associations between social determinants of health and PICU outcomes of these patients.

Considerations for the implementation of machine learning into acute care settings

INTRODUCTION

Management of patients in the acute care setting requires accurate diagnosis and rapid initiation of validated treatments; therefore, this setting is likely to be an environment in which cognitive augmentation of the clinician's provision of care with technology rooted in artificial intelligence, such as machine learning (ML), is likely to eventuate.

SOURCES OF DATA

PubMed and Google Scholar with search terms that included ML, intensive/critical care unit, electronic health records (EHR), anesthesia information management systems and clinical decision support were the primary sources for this report.

AREAS OF AGREEMENT

Different categories of learning of large clinical datasets, often contained in EHRs, are used for training in ML. Supervised learning uses algorithm-based models, including support vector machines, to pair patients' attributes with an expected outcome. Unsupervised learning uses clustering algorithms to define to which disease grouping a patient's attributes most closely approximates. Reinforcement learning algorithms use ongoing environmental feedback to deterministically pursue likely patient outcome.

AREAS OF CONTROVERSY

Application of ML can result in undesirable outcomes over concerns related to fairness, transparency, privacy and accountability. Whether these ML technologies irrevocably change the healthcare workforce remains unresolved.

GROWING POINTS

Well-resourced Learning Health Systems are likely to exploit ML technology to gain the fullest benefits for their patients. How these clinical advantages can be extended to patients in health systems that are neither well-endowed, nor have the necessary data gathering technologies, needs to be urgently addressed to avoid further disparities in healthcare.

Altered Heart Rate Variability Early in ICU Admission Differentiates Critically Ill Coronavirus Disease 2019 and All-Cause Sepsis Patients

IMPORTANCE

Altered heart rate variability has been associated with autonomic dysfunction in a number of disease profiles, in this work we elucidate differences in the biomarker among patients with all-cause sepsis and coronavirus disease 2019.

OBJECTIVES

To measure heart rate variability metrics in critically ill coronavirus disease 2019 patients with comparison to all-cause critically ill sepsis patients.

DESIGN SETTING AND PARTICIPANTS

Retrospective analysis of coronavirus disease 2019 patients admitted to an ICU for at least 24 hours at any of Emory Healthcare ICUs between March 2020 and April 2020 up to 5 days of ICU stay. The comparison group was a cohort of all-cause sepsis patients prior to coronavirus disease 2019 pandemic.

MAIN OUTCOMES AND MEASURES

Continuous waveforms were captured from the patient monitor. The electrocardiogram was then analyzed for each patient over a 300 seconds observational window that was shifted by 30 seconds in each iteration from admission till discharge. A total of 23 heart rate variability metrics were extracted in each iteration. We use the Kruskal-Wallis and Steel-Dwass tests (p < 0.05) for statistical analysis and interpretations of heart rate variability multiple measures.

RESULTS

A total of 141 critically ill coronavirus disease 2019 patients met inclusion criteria, who were compared with 208 patients with all-cause sepsis. Three nonlinear markers, including the ratio of standard deviation derived from the Poincaré plot, sample entropy, and approximate entropy and four linear features, including mode of beat-to-beat interval, acceleration capacity, deceleration capacity, and the proportion of consecutive RR intervals that differ by more than 50 ms, were all statistically significant (p < 0.05) between the coronavirus disease 2019 and all-cause sepsis cohorts. The three nonlinear features and acceleration capacity, deceleration capacity, and beat-to-beat interval (mode) were statistically significant (p < 0.05) when comparing pairwise analysis among the combinations of survivors and nonsurvivors between the coronavirus disease 2019 and sepsis cohorts. Temporal analysis of the main markers showed low variability across the 5 days of analysis compared with sepsis patients.

CONCLUSIONS AND RELEVANCE

In this descriptive statistical study, heart rate variability measures were found to be statistically different across critically ill patients infected with severe acute respiratory syndrome coronavirus 2 and distinct from bacterial sepsis.

Dynamic tracking of microvascular hemoglobin content for continuous perfusion monitoring in the intensive care unit: pilot feasibility study

PURPOSE

There is a need for bedside methods to monitor oxygen delivery in the microcirculation. Near-infrared spectroscopy commonly measures tissue oxygen saturation, but does not reflect the time-dependent variability of microvascular hemoglobin content (MHC) that attempts to match oxygen supply with demand. The objective of this study is to determine the feasibility of MHC monitoring in critically ill patients using high-resolution near-infrared spectroscopy to assess perfusion in the peripheral microcirculation.

METHODS

Prospective observational cohort of 36 patients admitted within 48 h at a tertiary intensive care unit. Perfusion was measured on the quadriceps, biceps, and/or deltoid, using the temporal change in optical density at the isosbestic wavelength of hemoglobin (798 nm). Continuous wavelet transform was applied to the hemoglobin signal to delineate frequency ranges corresponding to physiological oscillations in the cardiovascular system.

RESULTS

31/36 patients had adequate signal quality for analysis, most commonly affected by motion artifacts. MHC signal demonstrates inter-subject heterogeneity in the cohort, indicated by different patterns of variability and frequency composition. Signal characteristics were concordant between muscle groups in the same patient, and correlated with systemic hemoglobin levels and oxygen saturation. Signal power was lower for patients receiving vasopressors, but not correlated with mean arterial pressure. Mechanical ventilation directly impacts MHC in peripheral tissue.

CONCLUSION

MHC can be measured continuously in the ICU with high-resolution near-infrared spectroscopy, and reflects the dynamic variability of hemoglobin distribution in the microcirculation. Results suggest this novel hemodynamic metric should be further evaluated for diagnosing microvascular dysfunction and monitoring peripheral perfusion.

Accurate diagnosis of sepsis using a neural network: Pilot study using routine clinical variables

BACKGROUND AND OBJECTIVES

Sepsis is a severe infection that increases mortality risk and is one if the main causes of death in intensive care units. Accurate detection is key to successful interventions, but diagnosis of sepsis is complicated because the initial signs and symptoms are not specific. Biomarkers that have been proposed have low specificity and sensitivity, are expensive, and not available in every hospital. In this study, we propose the use of artificial intelligence in the form of a neural network to diagnose sepsis using only common laboratory tests and vital signs that are routine and widely available.

METHODS

A retrospective, cross sectional cohort of 113 patients from an intensive care unit, each with 48 routinely evaluated vital signs and biochemical parameters was used to train, validate and test a neural network with 48 inputs, 10 neurons in a single hidden layer and one output. The sensitivity and specificity of the neural network as a point sampled diagnostic test was calculated.

RESULTS

All but one case were correctly diagnosed by the neural network, with 91% sensitivity and 100% specificity in the validation data set, and 100% sensitivity and specificity in the test data set.

CONCLUSIONS

The designed neural network system can identify patients with sepsis, with minimal resources using standard laboratory tests widely available in most health care facilities. This should reduce the burden on the medical staff of a difficult diagnosis and should improve outcomes for patients with sepsis.

eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19

We present an interpretable machine learning algorithm called ‘eARDS’ for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner^® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88–0.90), sensitivity of 0.77 (95% CI = 0.75–0.78), specificity 0.85 (95% CI = 085–0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81–0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO₂), standard deviation of the systolic blood pressure (SBP), O₂ flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18–40) (AUROC = 0.93 [0.92–0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81–0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.

Artificial Intelligence May Predict Early Sepsis After Liver Transplantation

Background: Sepsis, post-liver transplantation, is a frequent challenge that impacts patient outcomes. We aimed to develop an artificial intelligence method to predict the onset of post-operative sepsis earlier. Methods: This pilot study aimed to identify "physiomarkers" in continuous minute-by-minute physiologic data streams, such as heart rate, respiratory rate, oxygen saturation (SpO2), and blood pressure, to predict the onset of sepsis. The model was derived from a cohort of 5,748 transplant and non-transplant patients across intensive care units (ICUs) over 36 months, with 92 post-liver transplant patients who developed sepsis. Results: Using an alert timestamp generated with the Third International Consensus Definition of Sepsis (Sepsis-3) definition as a reference point, we studied up to 24 h of continuous physiologic data prior to the event, totaling to 8.35 million data points. One hundred fifty-five features were generated using signal processing and statistical methods. Feature selection identified 52 highly ranked features, many of which included blood pressures. An eXtreme Gradient Boost (XGB) classifier was then trained on the ranked features by 5-fold cross validation on all patients (n = 5,748). We identified that the average sensitivity, specificity, positive predictive value (PPV), and area under the receiver-operator curve (AUC) of the model after 100 iterations was 0.94 ± 0.02, 0.9 ± 0.02, 0.89 ± 0.01, respectively, and 0.97 ± 0.01 for predicting sepsis 12 h before meeting criteria. Conclusion: The data suggest that machine learning/deep learning can be applied to continuous streaming data in the transplant ICU to monitor patients and possibly predict sepsis.

Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables

Supplemental Digital Content is available in the text.

OBJECTIVE:

Specific factors affecting generalizability of clinical prediction models are poorly understood. Our main objective was to investigate how measurement indicator variables affect external validity in clinical prediction models for predicting onset of vasopressor therapy.

DESIGN:

We fit logistic regressions on retrospective cohorts to predict vasopressor onset using two classes of variables: seemingly objective clinical variables (vital signs and laboratory measurements) and more subjective variables denoting recency of measurements.

SETTING:

Three cohorts from two tertiary-care academic hospitals in geographically distinct regions, spanning general inpatient and critical care settings.

PATIENTS:

Each cohort consisted of adult patients (age greater than or equal to 18 yr at time of hospitalization), with lengths of stay between 6 and 600 hours, and who did not receive vasopressors in the first 6 hours of hospitalization or ICU admission. Models were developed on each of the three derivation cohorts and validated internally on the derivation cohort and externally on the other two cohorts.

INTERVENTIONS:

None.

MEASUREMENTS AND MAIN RESULTS:

The prevalence of vasopressors was 0.9% in the general inpatient cohort and 12.4% and 11.5% in the two critical care cohorts. Models utilizing both classes of variables performed the best in-sample, with C-statistics for predicting vasopressor onset in 4 hours of 0.862 (95% CI, 0.844–0.879), 0.822 (95% CI, 0.793–0.852), and 0.889 (95% CI, 0.880–0.898). Models solely using the subjective variables denoting measurement recency had poor external validity. However, these practice-driven variables helped adjust for differences between the two hospitals and led to more generalizable models using clinical variables.

CONCLUSIONS:

We developed and externally validated models for predicting the onset of vasopressors. We found that practice-specific features denoting measurement recency improved local performance and also led to more generalizable models if they are adjusted for during model development but discarded at validation. The role of practice-specific features such as measurement indicators in clinical prediction modeling should be carefully considered if the goal is to develop generalizable models.

Kinematics approach with neural networks for early detection of sepsis (KANNEDS)

BACKGROUND

Sepsis is a severe illness that affects millions of people worldwide, and its early detection is critical for effective treatment outcomes. In recent years, researchers have used models to classify positive patients or identify the probability for sepsis using vital signs and other time-series variables as input.

METHODS

In our study, we analyzed patients' conditions by their kinematics position, velocity, and acceleration, in a six-dimensional space defined by six vital signs. The patient is affected by the disease after a period if the position gets "near" to a calculated sepsis position in space. We imputed these kinematics features as explanatory variables of long short-term memory (LSTM), convolutional neural network (CNN) and linear neural network (LNN) and compared the prediction accuracies with only the vital signs as input. The dataset used contained information of approximately 4800 patients, each with 48 hourly registers.

RESULTS

We demonstrated that the kinematics features models had an improved performance compared with vital signs models. The kinematics features model of LSTM achieved the best accuracy, 0.803, which was nine points higher than the vital signs model. Although with lesser accuracies, the kinematics features models of the CNN and LNN showed better performances than vital signs models.

CONCLUSION

Applying our novel approach for early detection of sepsis using neural networks will prove to be an invaluable, more accurate method than considering only simple vital signs as input variables. We expect that other researchers with similar objectives can use the model presented in this innovative approach to improve their results.

Predicting presumed serious infection among hospitalized children on central venous lines with machine learning

BACKGROUND

Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care.

METHODS

Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train machine learning models (XGBoost and ElasticNet) to predict the occurrence of PSI 8 h prior to clinical suspicion. Prediction for PSI was benchmarked against PRISM-III.

RESULTS

Our model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI = [0.82, 0.85]), sensitivity of 0.73 [0.69, 0.74], and positive predictive value (PPV) of 0.36 [0.34, 0.36]. The PRISM-III conversely achieved a lower sensitivity of 0.19 [0.16, 0.22] and PPV of 0.30 [0.26, 0.34] at a cut-off of ≥ 10. The features with the most impact on the PSI prediction were maximum diastolic blood pressure prior to PSI prediction (mean SHAP = 3.4), height (mean SHAP = 3.2), and maximum temperature prior to PSI prediction (mean SHAP = 2.6).

CONCLUSION

A machine learning model using common features in the electronic medical records can predict the onset of serious infections in children with central venous lines at least 8 h prior to when a clinical team drew a blood culture.

Development and validation of an early warning tool for sepsis and decompensation in children during emergency department triage

This study was designed to develop and validate an early warning system for sepsis based on a predictive model of critical decompensation. Data from the electronic medical records for 537,837 visits to a pediatric Emergency Department (ED) from March 2013 to December 2019 were collected. A multiclass stochastic gradient boosting model was built to identify early warning signs associated with death, severe sepsis, non-severe sepsis, and bacteremia. Model features included triage vital signs, previous diagnoses, medications, and healthcare utilizations within 6 months of the index ED visit. There were 483 patients who had severe sepsis and/or died, 1102 had non-severe sepsis, 1103 had positive bacteremia tests, and the remaining had none of the events. The most important predictors were age, heart rate, length of stay of previous hospitalizations, temperature, systolic blood pressure, and prior sepsis. The one-versus-all area under the receiver operator characteristic curve (AUROC) were 0.979 (0.967, 0.991), 0.990 (0.985, 0.995), 0.976 (0.972, 0.981), and 0.968 (0.962, 0.974) for death, severe sepsis, non-severe sepsis, and bacteremia without sepsis respectively. The multi-class macro average AUROC and area under the precision recall curve were 0.977 and 0.316 respectively. The study findings were used to develop an automated early warning decision tool for sepsis. Implementation of this model in pediatric EDs will allow sepsis-related critical decompensation to be predicted accurately after a few seconds of triage.

Machine Learning Identifies Complicated Sepsis Course and Subsequent Mortality Based on 20 Genes in Peripheral Blood Immune Cells at 24 H Post-ICU Admission

A complicated clinical course for critically ill patients admitted to the intensive care unit (ICU) usually includes multiorgan dysfunction and subsequent death. Owing to the heterogeneity, complexity, and unpredictability of the disease progression, ICU patient care is challenging. Identifying the predictors of complicated courses and subsequent mortality at the early stages of the disease and recognizing the trajectory of the disease from the vast array of longitudinal quantitative clinical data is difficult. Therefore, we attempted to perform a meta-analysis of previously published gene expression datasets to identify novel early biomarkers and train the artificial intelligence systems to recognize the disease trajectories and subsequent clinical outcomes. Using the gene expression profile of peripheral blood cells obtained within 24 h of pediatric ICU (PICU) admission and numerous clinical data from 228 septic patients from pediatric ICU, we identified 20 differentially expressed genes predictive of complicated course outcomes and developed a new machine learning model. After 5-fold cross-validation with 10 iterations, the overall mean area under the curve reached 0.82. Using a subset of the same set of genes, we further achieved an overall area under the curve of 0.72, 0.96, 0.83, and 0.82, respectively, on four independent external validation sets. This model was highly effective in identifying the clinical trajectories of the patients and mortality. Artificial intelligence systems identified eight out of twenty novel genetic markers (SDC4, CLEC5A, TCN1, MS4A3, HCAR3, OLAH, PLCB1, and NLRP1) that help predict sepsis severity or mortality. While these genes have been previously associated with sepsis mortality, in this work, we show that these genes are also implicated in complex disease courses, even among survivors. The discovery of eight novel genetic biomarkers related to the overactive innate immune system, including neutrophil function, and a new predictive machine learning method provides options to effectively recognize sepsis trajectories, modify real-time treatment options, improve prognosis, and patient survival.

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.

An interpretable deep-learning model for early prediction of sepsis in the emergency department

Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. Early prediction of sepsis improves survival in septic patients. In this paper, we report our top-performing method in the 2019 DII National Data Science Challenge to predict onset of sepsis 4 h before its diagnosis on electronic health records of over 100,000 unique patients in emergency departments. A long short-term memory (LSTM)-based model with event embedding and time encoding is leveraged to model clinical time series and boost prediction performance. Attention mechanism and global max pooling techniques are utilized to enable interpretation for the deep-learning model. Our model achieved an average area under the curve of 0.892 and was selected as one of the winners of the challenge for both prediction accuracy and clinical interpretability. This study paves the way for future intelligent clinical decision support, helping to deliver early, life-saving care to the bedside of septic patients.

Barriers and Proposed Solutions to a Successful Implementation of Pediatric Sepsis Protocols

The implementation of managed protocols contributes to a systematized approach to the patient and continuous evaluation of results, focusing on improving clinical practice, early diagnosis, treatment, and outcomes. Advantages to the adoption of a pediatric sepsis recognition and treatment protocol include: a reduction in time to start fluid and antibiotic administration, decreased kidney dysfunction and organ dysfunction, reduction in length of stay, and even a decrease on mortality. Barriers are: absence of a written protocol, parental knowledge, early diagnosis by healthcare professionals, venous access, availability of antimicrobials and vasoactive drugs, conditions of work, engagement of healthcare professionals. There are challenges in low-middle-income countries (LMIC). The causes of sepsis and resources differ from high-income countries. Viral agent such as dengue, malaria are common in LMIC and initial approach differ from bacterial infections. Some authors found increased or no impact in mortality or increased length of stay associated with the implementation of the SCC sepsis bundle which reinforces the importance of adapting it to most frequent diseases, disposable resources, and characteristics of healthcare professionals. Conclusions: (1) be simple; (2) be precise; (3) education; (5) improve communication; (5) work as a team; (6) share and celebrate results.

The Vagal Autonomic Pathway of COVID-19 at the Crossroad of Alzheimer's Disease and Aging: A Review of Knowledge

Coronavirus Disease 2019 (COVID-19) pandemic-triggered mortality is significantly higher in older than in younger populations worldwide. Alzheimer's disease (AD) is related to aging and was recently reported to be among the major risk factors for COVID-19 mortality in older people. The symptomatology of COVID-19 indicates that lethal outcomes of infection rely on neurogenic mechanisms. The present review compiles the available knowledge pointing to the convergence of COVID-19 complications with the mechanisms of autonomic dysfunctions in AD and aging. The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is prone to neuroinvasion from the lung along the vagus nerve up to the brainstem autonomic nervous centers involved in the coupling of cardiovascular and respiratory rhythms. The brainstem autonomic network allows SARS-CoV-2 to trigger a neurogenic switch to hypertension and hypoventilation, which may act in synergy with aging- and AD-induced dysautonomias, along with an inflammatory "storm". The lethal outcomes of COVID-19, like in AD and unhealthy aging, likely rely on a critical hypoactivity of the efferent vagus nerve cholinergic pathway, which is involved in lowering cardiovascular pressure and systemic inflammation tone. We further discuss the emerging evidence supporting the use of 1) the non-invasive stimulation of vagus nerve as an additional therapeutic approach for severe COVID-19, and 2) the demonstrated vagal tone index, i.e., heart rate variability, via smartphone-based applications as a non-serological low-cost diagnostic of COVID-19. These two well-known medical approaches are already available and now deserve large-scale testing on human cohorts in the context of both AD and COVID-19.

Multiplexed Plasma Immune Mediator Signatures Can Differentiate Sepsis From NonInfective SIRS: American Surgical Association 2020 Annual Meeting Paper

OBJECTIVES

Sepsis and sterile both release "danger signals' that induce the systemic inflammatory response syndrome (SIRS). So differentiating infection from SIRS can be challenging. Precision diagnostic assays could limit unnecessary antibiotic use, improving outcomes.

METHODS

After surveying human leukocyte cytokine production responses to sterile damage-associated molecular patterns (DAMPs), bacterial pathogen-associated molecular patterns, and bacteria we created a multiplex assay for 31 cytokines. We then studied plasma from patients with bacteremia, septic shock, "severe sepsis," or trauma (ISS ≥15 with circulating DAMPs) as well as controls. Infections were adjudicated based on post-hospitalization review. Plasma was studied in infection and injury using univariate and multivariate means to determine how such multiplex assays could best distinguish infective from noninfective SIRS.

RESULTS

Infected patients had high plasma interleukin (IL)-6, IL-1α, and triggering receptor expressed on myeloid cells-1 (TREM-1) compared to controls [false discovery rates (FDR) <0.01, <0.01, <0.0001]. Conversely, injury suppressed many mediators including MDC (FDR <0.0001), TREM-1 (FDR <0.001), IP-10 (FDR <0.01), MCP-3 (FDR <0.05), FLT3L (FDR <0.05), Tweak, (FDR <0.05), GRO-α (FDR <0.05), and ENA-78 (FDR <0.05). In univariate studies, analyte overlap between clinical groups prevented clinical relevance. Multivariate models discriminated injury and infection much better, with the 2-group random-forest model classifying 11/11 injury and 28/29 infection patients correctly in out-of-bag validation.

CONCLUSIONS

Circulating cytokines in traumatic SIRS differ markedly from those in health or sepsis. Variability limits the accuracy of single-mediator assays but machine learning based on multiplexed plasma assays revealed distinct patterns in sepsis- and injury-related SIRS. Defining biomarker release patterns that distinguish specific SIRS populations might allow decreased antibiotic use in those clinical situations. Large prospective studies are needed to validate and operationalize this approach.

SSP: Early prediction of sepsis using fully connected LSTM-CNN model

BACKGROUND

Sepsis is a life-threatening condition that occurs due to the body's reaction to infections, and it is a leading cause of morbidity and mortality in hospitals. Early prediction of sepsis onset facilitates early interventions that promote the survival of suspected patients. However, reliable and intelligent systems for predicting sepsis are scarce.

METHODS

This paper presents a novel technique called Smart Sepsis Predictor (SSP) to predict sepsis onset in patients admitted to an intensive care unit (ICU). SSP is a deep neural network architecture that encompasses long short-term memory (LSTM), convolutional, and fully connected layers to achieve early prediction of sepsis. SSP can work in two modes; Mode 1 uses demographic data and vital signs, and Mode 2 uses laboratory test results in addition to demographic data and vital signs. To evaluate SSP, we have used the 2019 PhysioNet/CinC Challenge dataset, which includes the records of 40,366 patients admitted to the ICU.

RESULTS

To compare SSP with existing state-of-the-art methods, we have measured the accuracy of the SSP in 4-, 8-, and 12-h prediction windows using publicly available data. Our results show that the SSP performance in Mode 1 and Mode 2 is much higher than existing methods, achieving an area under the receiver operating characteristic curve (AUROC) of 0.89 and 0.92, 0.88 and 0.87, and 0.86 and 0.84 for 4 h, 8 h, and 12 h before sepsis onset, respectively.

CONCLUSIONS

Using ICU data, sepsis onset can be predicted up to 12 h in advance. Our findings offer an early solution for mitigating the risk of sepsis onset.

Machine learning predicts mortality in septic patients using only routinely available ABG variables: a multi-centre evaluation

PURPOSE

To evaluate the application of machine learning methods, specifically Deep Neural Networks (DNN) models for intensive care (ICU) mortality prediction. The aim was to predict mortality within 96 hours after admission to mirror the clinical situation of patient evaluation after an ICU trial, which consists of 24-48 hours of ICU treatment and then "re-triage". The input variables were deliberately restricted to ABG values to maximise real-world practicability.

METHODS

We retrospectively evaluated septic patients in the multi-centre eICU dataset as well as single centre MIMIC-III dataset. Included were all patients alive after 48 hours with available data on ABG (n = 3979 and n = 9655 ICU stays for the multi-centre and single centre respectively). The primary endpoint was 96 -h-mortality.

RESULTS

The model was developed using long short-term memory (LSTM), a type of DNN designed to learn temporal dependencies between variables. Input variables were all ABG values within the first 48 hours. The SOFA score (AUC of 0.72) was moderately predictive. Logistic regression showed good performance (AUC of 0.82). The best performance was achieved by the LSTM-based model with AUC of 0.88 in the multi-centre study and AUC of 0.85 in the single centre study.

CONCLUSIONS

An LSTM-based model could help physicians with the "re-triage" and the decision to restrict treatment in patients with a poor prognosis.

Survival prediction of patients with sepsis from age, sex, and septic episode number alone

Sepsis is a life-threatening condition caused by an exaggerated reaction of the body to an infection, that leads to organ failure or even death. Since sepsis can kill a patient even in just one hour, survival prediction is an urgent priority among the medical community: even if laboratory tests and hospital analyses can provide insightful information about the patient, in fact, they might not come in time to allow medical doctors to recognize an immediate death risk and treat it properly. In this context, machine learning can be useful to predict survival of patients within minutes, especially when applied to few medical features easily retrievable. In this study, we show that it is possible to achieve this goal by applying computational intelligence algorithms to three features of patients with sepsis, recorded at hospital admission: sex, age, and septic episode number. We applied several data mining methods to a cohort of 110,204 admissions of patients, and obtained high prediction scores both on this complete dataset (top precision-recall area under the curve PR AUC = 0.966) and on its subset related to the recent Sepsis-3 definition (top PR AUC = 0.860). Additionally, we tested our models on an external validation cohort of 137 patients, and achieved good results in this case too (top PR AUC = 0.863), confirming the generalizability of our approach. Our results can have a huge impact on clinical settings, allowing physicians to forecast the survival of patients by sex, age, and septic episode number alone.

Automated prediction of sepsis using temporal convolutional network

Multiple organ failure is the trademark of sepsis. Sepsis occurs when the body's reaction to infection causes injury to its tissues and organs. As a consequence, fluid builds up in the tissues causing organ failure and leading to septic shock eventually. Some symptoms of sepsis include fever, arrhythmias, blood vessel leaks, impaired clotting, and generalised inflammation. In order to address the limitations in current diagnosis, we have proposed a cost-effective automated diagnostic tool in this study. A deep temporal convolution network has been developed for the prediction of sepsis. Septic data was fed to the model and a high accuracy and area under ROC curve (AUROC) of 98.8% and 98.0% were achieved respectively, for per time-step metrics. A relatively high accuracy and AUROC of 95.5% and 91.0% were also achieved respectively, for per-patient metrics. This is a novel study in that it has investigated per time-step metrics, compared to other studies which investigated per-patient metrics. Our model has also been evaluated by three validation methods. Thus, the recommended model is robust with high accuracy and precision and has the potential to be used as a tool for the prediction of sepsis in hospitals.

Electrocardiographic changes predate Parkinson's disease onset

Autonomic nervous system involvement precedes the motor features of Parkinson's disease (PD). Our goal was to develop a proof-of-concept model for identifying subjects at high risk of developing PD by analysis of cardiac electrical activity. We used standard 10-s electrocardiogram (ECG) recordings of 60 subjects from the Honolulu Asia Aging Study including 10 with prevalent PD, 25 with prodromal PD, and 25 controls who never developed PD. Various methods were implemented to extract features from ECGs including simple heart rate variability (HRV) metrics, commonly used signal processing methods, and a Probabilistic Symbolic Pattern Recognition (PSPR) method. Extracted features were analyzed via stepwise logistic regression to distinguish between prodromal cases and controls. Stepwise logistic regression selected four features from PSPR as predictors of PD. The final regression model built on the entire dataset provided an area under receiver operating characteristics curve (AUC) with 95% confidence interval of 0.90 [0.80, 0.99]. The five-fold cross-validation process produced an average AUC of 0.835 [0.831, 0.839]. We conclude that cardiac electrical activity provides important information about the likelihood of future PD not captured by classical HRV metrics. Machine learning applied to ECGs may help identify subjects at high risk of having prodromal PD.

Machine learning for early detection of sepsis: an internal and temporal validation study

OBJECTIVE

Determine if deep learning detects sepsis earlier and more accurately than other models. To evaluate model performance using implementation-oriented metrics that simulate clinical practice.

MATERIALS AND METHODS

We trained internally and temporally validated a deep learning model (multi-output Gaussian process and recurrent neural network [MGP-RNN]) to detect sepsis using encounters from adult hospitalized patients at a large tertiary academic center. Sepsis was defined as the presence of 2 or more systemic inflammatory response syndrome (SIRS) criteria, a blood culture order, and at least one element of end-organ failure. The training dataset included demographics, comorbidities, vital signs, medication administrations, and labs from October 1, 2014 to December 1, 2015, while the temporal validation dataset was from March 1, 2018 to August 31, 2018. Comparisons were made to 3 machine learning methods, random forest (RF), Cox regression (CR), and penalized logistic regression (PLR), and 3 clinical scores used to detect sepsis, SIRS, quick Sequential Organ Failure Assessment (qSOFA), and National Early Warning Score (NEWS). Traditional discrimination statistics such as the C-statistic as well as metrics aligned with operational implementation were assessed.

RESULTS

The training set and internal validation included 42 979 encounters, while the temporal validation set included 39 786 encounters. The C-statistic for predicting sepsis within 4 h of onset was 0.88 for the MGP-RNN compared to 0.836 for RF, 0.849 for CR, 0.822 for PLR, 0.756 for SIRS, 0.619 for NEWS, and 0.481 for qSOFA. MGP-RNN detected sepsis a median of 5 h in advance. Temporal validation assessment continued to show the MGP-RNN outperform all 7 clinical risk score and machine learning comparisons.

CONCLUSIONS

We developed and validated a novel deep learning model to detect sepsis. Using our data elements and feature set, our modeling approach outperformed other machine learning methods and clinical scores.