What is the clinical evidence from this study?

Study design: Observational. Population: Disorders of consciousness (n=58). Intervention: Heart rate variability (HRV) parameters. Primary outcome: Prediction of patient outcome (good vs bad) at 3 months using a Support Vector Machine (SVM) model (Accuracy 96%).

What does this research mean for the field?

A support vector machine model utilizing baseline and stimulation-induced heart rate variability features can predict three-month outcomes in patients with disorders of consciousness with high accuracy. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 18, 2024Scientific Reports19 citationsOpen Access

Central autonomic network and early prognosis in patients with disorders of consciousness

FRFrancesco RiganelloIstituto S.Anna Crotone MVMartina VatranoIstituto S.Anna Crotone MCMaria Daniela CorteseIstituto S.Anna Crotone

Key Result

Support vector machine analysis of early heart rate variability parameters and time from injury predicted the 3-month clinical outcome of patients with disorders of consciousness with 96% accuracy.

Study Design

Type

Observational (n=58)

Multicenter

Structured PICO

Does heart rate variability analysis combined with machine learning predict 3-month outcomes in patients with disorders of consciousness?

Population

58 patients with disorders of consciousness following acquired brain injury, assessed within 10 days of hospitalization and followed for 3 months to predict clinical outcome.

Exposure

Heart rate variability (HRV) analysis during baseline and acoustic/visual stimulation combined with Support Vector Machine (SVM) modeling.

Outcome

Good vs bad outcome at 3 months, assessed by the Coma Recovery Scale-Revised (CRS-R).

Heart rate variability parameters combined with machine learning can accurately predict 3-month consciousness recovery outcomes in patients with severe acquired brain injury.

Main Result

Effect estimate: Accuracy 96%

Limitations

Small sample size of patients limits generalizability
Heterogeneous nature of brain injuries and variability of clinical presentations
Focuses only on the early stages of recovery without longitudinal assessment
Did not include other analytical techniques like Poincaré plot or detrended fluctuation analysis
Limited sample size

Abstract

The central autonomic network (CAN) plays a crucial role in modulating the autonomic nervous system. Heart rate variability (HRV) is a valuable marker for assessing CAN function in disorders of consciousness (DOC) patients. We used HRV analysis for early prognosis in 58 DOC patients enrolled within ten days of hospitalization. They underwent a five-minute electrocardiogram during baseline and acoustic/visual stimulation. The coma recovery scale-revised (CRS-R) was used to define the patient's consciousness level and categorize the good/bad outcome at three months. The high-frequency Power Spectrum Density and the standard deviation of normal-to-normal peaks in baseline, the sample entropy during the stimulation, and the time from injury features were used in the support vector machine analysis (SVM) for outcome prediction. The SVM predicted the patients' outcome with an accuracy of 96% in the training test and 100% in the validation test, underscoring its potential to provide crucial clinical information about prognosis.

KI fragen

Bookmark

View Full Paper