Trajectories of the heart rate characteristics index, a physiomarker of sepsis in premature infants, predict Neonatal ICU mortality

Vital sign-based detection of sepsis in neonates using machine learning

AIM

Sepsis is a leading cause of morbidity and mortality in neonates. Early diagnosis is key but difficult due to non-specific signs. We investigate the predictive value of machine learning-assisted analysis of non-invasive, high frequency monitoring data and demographic factors to detect neonatal sepsis.

METHODS

Single centre study, including a representative cohort of 325 infants (2866 hospitalisation days). Personalised event timelines including interventions and clinical findings were generated. Time-domain features from heart rate, respiratory rate and oxygen saturation values were calculated and demographic factors included. Sepsis prediction was performed using Naïve Bayes algorithm in a maximum a posteriori framework up to 24 h before clinical sepsis suspicion.

RESULTS

Twenty sepsis cases were identified. Combining multiple vital signs improved algorithm performance compared to heart rate characteristics alone. This enabled a prediction of sepsis with an area under the receiver operating characteristics curve of 0.82, up to 24 h before clinical sepsis suspicion. Moreover, 10 h prior to clinical suspicion, the risk of sepsis increased 150-fold.

CONCLUSION

The present algorithm using non-invasive patient data provides useful predictive value for neonatal sepsis detection. Machine learning-assisted algorithms are promising novel methods that could help individualise patient care and reduce morbidity and mortality.

Superhuman performance on sepsis MIMIC-III data by distributional reinforcement learning

We present a novel setup for treating sepsis using distributional reinforcement learning (RL). Sepsis is a life-threatening medical emergency. Its treatment is considered to be a challenging high-stakes decision-making problem, which has to procedurally account for risk. Treating sepsis by machine learning algorithms is difficult due to a couple of reasons: There is limited and error-afflicted initial data in a highly complex biological system combined with the need to make robust, transparent and safe decisions. We demonstrate a suitable method that combines data imputation by a kNN model using a custom distance with state representation by discretization using clustering, and that enables superhuman decision-making using speedy Q-learning in the framework of distributional RL. Compared to clinicians, the recovery rate is increased by more than 3% on the test data set. Our results illustrate how risk-aware RL agents can play a decisive role in critical situations such as the treatment of sepsis patients, a situation acerbated due to the COVID-19 pandemic (Martineau 2020). In addition, we emphasize the tractability of the methodology and the learning behavior while addressing some criticisms of the previous work (Komorowski et al. 2018) on this topic.

Monitoring of heart rate characteristics to detect neonatal sepsis

BACKGROUND

Monitoring of heart rate characteristics (HRC) index may improve outcomes of late-onset neonatal sepsis (LOS) through early detection. We aimed at describing the association between LOS and elevated HRC index.

METHODS

This single-center retrospective case-control study included neonates who presented with blood culture-proven hospital-acquired LOS. Controls were matched to cases (ratio 1:2) based on gestational age, postnatal age, and birthweight. We compared the highest HRC indexes in the 48 h preceding blood culture sampling in LOS cases to the highest HRC indexes at the same postnatal days in controls.

RESULTS

In 59 LOS cases and 123 controls, an HRC index > 2 was associated with LOS (OR 7.1, 95% CI 2.6-19.0). Sensitivity and specificity of an HRC index > 2 to predict LOS were 53% (32/59) and 79% (98/123). Sensitivity increased from 25% in infants born > 32 weeks to 76% in infants born < 28 weeks. Specificity decreased from 97% in infants > 32 weeks to 63% in those born < 28 weeks.

CONCLUSIONS

An increase of HRC index > 2 has a significant association with the diagnosis of LOS, supporting the use of HRC monitoring to assist early detection of LOS. Clinicians using HRC monitoring should be aware of its diagnostic accuracy and limitations in different gestational age groups.

IMPACT

There is a paucity of data regarding the predictive value of heart rate characteristics (HRC) monitoring for early diagnosis of late-onset neonatal sepsis (LOS) in daily clinical practice. Monitoring of heart rate characteristics provides valuable information to assist the early diagnosis of LOS across all gestational age groups. However, the strong influence of gestational age on positive and negative predictive values adds complexity to the interpretation of HRC indexes.

Beyond prediction: Off-target uses of artificial intelligence-based predictive analytics in a learning health system

Introduction

Artificial-intelligence (AI)-based predictive analytics provide new opportunities to leverage rich sources of continuous data to improve patient care through early warning of the risk of clinical deterioration and improved situational awareness.Part of the success of predictive analytic implementation relies on integration of the analytic within complex clinical workflows. Pharmaceutical interventions have off-target uses where a drug indication has not been formally studied for a different indication but has potential for clinical benefit. An analog has not been described in the context of AI-based predictive analytics, that is, when a predictive analytic has been trained on one outcome of interest but is used for additional applications in clinical practice.

Methods

In this manuscript we present three clinical vignettes describing off-target use of AI-based predictive analytics that evolved organically through real-world practice.

Results

Off-target uses included:real-time feedback about treatment effectiveness, indication of readiness to discharge, and indication of the acuity of a hospital unit.

Conclusion

Such practice fits well with the learning health system goals to continuously integrate data and experience to provide.

The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU

In 2011, a multicenter group spearheaded at the University of Virginia demonstrated reduced mortality from real-time continuous cardiorespiratory monitoring in the neonatal ICU using what we now call Artificial Intelligence, Big Data, and Machine Learning. The large, randomized heart rate characteristics trial made real, for the first time that we know of, the promise that early detection of illness would allow earlier and more effective intervention and improved patient outcomes. Currently, though, we hear as much of failures as we do of successes in the rapidly growing field of predictive analytics monitoring that has followed. This Perspective aims to describe the principles of how we developed heart rate characteristics monitoring for neonatal sepsis and then applied them throughout adult ICU and hospital medicine. It primarily reflects the work since the 1990s of the University of Virginia group: the theme is that sudden and catastrophic deteriorations can be preceded by subclinical but measurable physiological changes apparent in the continuous cardiorespiratory monitoring and electronic health record.

Individual illness dynamics: An analysis of children with sepsis admitted to the pediatric intensive care unit

Illness dynamics and patterns of recovery may be essential features in understanding the critical illness course. We propose a method to characterize individual illness dynamics in patients who experienced sepsis in the pediatric intensive care unit. We defined illness states based on illness severity scores generated from a multi-variable prediction model. For each patient, we calculated transition probabilities to characterize movement among illness states. We calculated the Shannon entropy of the transition probabilities. Using the entropy parameter, we determined phenotypes of illness dynamics based on hierarchical clustering. We also examined the association between individual entropy scores and a composite variable of negative outcomes. Entropy-based clustering identified four illness dynamic phenotypes in a cohort of 164 intensive care unit admissions where at least one sepsis event occurred. Compared to the low-risk phenotype, the high-risk phenotype was defined by the highest entropy values and had the most ill patients as defined by a composite variable of negative outcomes. Entropy was significantly associated with the negative outcome composite variable in a regression analysis. Information-theoretical approaches to characterize illness trajectories offer a novel way of assessing the complexity of a course of illness. Characterizing illness dynamics with entropy offers additional information in conjunction with static assessments of illness severity. Additional attention is needed to test and incorporate novel measures representing the dynamics of illness.

Cardiovascular waveforms - can we extract more from routine signals?

Cardiovascular waveforms such as blood pressure, ECG and photoplethysmography (PPG), are routinely acquired by specialised monitoring devices. Such devices include bedside monitors, wearables and radiotelemetry which sample at very high fidelity, yet most of this numerical data is disregarded and focus tends to reside on single point averages such as the maxima, minima, amplitude, rate and intervals. Whilst, these measures are undoubtedly of value, we may be missing important information by simplifying the complex waveform signal in this way. This Special Collection showcases recent advances in the appraisal of routine signals. Ultimately, such approaches and technologies may assist in improving the accuracy and sensitivity of detecting physiological change. This, in turn, may assist with identifying efficacy or safety signals for investigational new drugs or aidpatient diagnosis and management, supporting scientific and clinical decision making.

Neonatal sepsis prediction through clinical decision support algorithms: A systematic review

AIM

To systematically summarise the current evidence of employing clinical decision support algorithms (CDSAs) using non-invasive parameters for sepsis prediction in neonates.

METHODS

A comprehensive search in PubMed, CENTRAL and EMBASE was conducted. Screening, data extraction and risk of bias were performed by two authors. The certainty of the evidence was assessed using GRADE.

PROSPERO ID

CRD42020205143.

RESULTS

After abstract and full-text screening, 36 studies comprising 18,096 infants were included. Most CDSAs evaluated heart rate (HR)-based parameters. Two publications derived from one randomised-controlled trial assessing HR characteristics reported significant reduction in 30-day septicaemia-related mortality. Thirty-four non-randomised studies found promising yet inconclusive results.

CONCLUSION

Heart rate-based parameters are reliable components of CDSAs for sepsis prediction, particularly in combination with additional vital signs and demographics. However, inconclusive evidence and limited standardisation restricts clinical implementation of CDSAs outside of a controlled research environment. Further experimentation and comparison of parameter combinations and testing of new CDSAs are warranted.

Dynamic Transitions of Pediatric Sepsis: A Markov Chain Analysis

Pediatric sepsis is a heterogeneous disease with varying physiological dynamics associated with recovery, disability, and mortality. Using risk scores generated from a sepsis prediction model to define illness states, we used Markov chain modeling to describe disease dynamics over time by describing how children transition among illness states. We analyzed 18,666 illness state transitions over 157 pediatric intensive care unit admissions in the 3 days following blood cultures for suspected sepsis. We used Shannon entropy to quantify the differences in transition matrices stratified by clinical characteristics. The population-based transition matrix based on the sepsis illness severity scores in the days following a sepsis diagnosis can describe a sepsis illness trajectory. Using the entropy based on Markov chain transition matrices, we found a different structure of dynamic transitions based on ventilator use but not age group. Stochastic modeling of transitions in sepsis illness severity scores can be useful in describing the variation in transitions made by patient and clinical characteristics.