Heart rate characteristic monitoring-HeRO or villain?

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.

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.

Heart rate characteristic index monitoring for bloodstream infection in an NICU: a 3-year experience

BACKGROUND

Bloodstream infection (BSI) among neonatal intensive care unit (NICU) infants is a frequent problem associated with poor outcomes. Monitoring for abnormal heart rate characteristics (HRCs) may decrease infant mortality by alerting clinicians to sepsis before it becomes clinically apparent.

METHODS

HRC scores were acquired using the HRC (HeRO) monitor system from Medical Predictive Science Corporation and entered into the electronic medical record by bedside staff. We retrospectively analysed HRC scores recorded twice daily in the medical record during a 30-month period (1 January 2010 through 30 June 2012) for infants in the NICU at the Monroe Carell Jr. Children's Hospital at Vanderbilt. We identified infants that met Centers for Disease Control criteria for late-onset BSI (>3 days of life) during the study period.

RESULTS

During the study period, we recorded 127 673 HRC scores from 2384 infants. We identified 46 infants with BSI. Although 8% (9701/127 673) of the HRC scores were ≥2 and 1% (1387/127 673) were ≥5, BSI (at any time) was observed in just 5% of patients with HRC scores ≥2, and 9% of patients with HRC scores ≥5. Of infants with BSI, 5/46 (11%) had at least one HRC score ≥5 and 17/46 (37%) had at least one score ≥2 recorded in the 48 h period prior to the evaluation that resulted in the first positive blood culture of the episode.

CONCLUSIONS

In our single-centre retrospective study, elevated HRC scores had limited ability to detect BSI. BSI was infrequent at any time during hospitalisation in infants with significantly elevated HRC scores.