Key result
An artificial neural network classifier evaluating multiscale waveform features predicted 28-day mortality in sepsis patients with greater prognostic accuracy than standard clinical severity scores.
Why the study?
Does an artificial neural network classifier evaluating multiscale waveform features improve 28-day mortality prediction accuracy compared to standard clinical severity scores in sepsis patients?
Does an artificial neural network classifier evaluating multiscale waveform features improve 28-day mortality prediction accuracy compared to standard clinical severity scores in sepsis patients?
Answers are grounded in this paper and cite their sources.
A novel neural network framework classifying multiscale features of beat-to-beat dynamics provides robust patient state tracking and improves mortality prediction in sepsis.
OBJECTIVE: state-of-the-art algorithms that quantify nonlinear dynamics in physiologic waveforms are underutilized clinically due to their esoteric nature. We present a generalizable framework for classifying multiscalar waveform features, designed for patient-state tracking directly at the bedside. METHODS: an artificial neural network classifier was designed to evaluate multiscale waveform features against a fingerprint database of multifractal synthetic time series. The results are mapped into a physiologic state space for near real-time patient-state tracking. RESULTS: the framework was validated on cardiac beat-to-beat dynamics processed with the multiscale entropy algorithm, and assessed using PhysioNet databases. We then applied our algorithm to predict 28-day mortality for sepsis patients, and found it had greater prognostic accuracy than standard clinical severity scores. CONCLUSION: we developed a novel framework to classify multiscale features of beat-to-beat dynamics, and performed an initial clinical validation to demonstrate that our approach generates a robust quantification of a patient's state, compatible with real-time bedside implementations. SIGNIFICANCE: the framework generates meaningful and actionable patient-specific information, and could facilitate the dissemination of a new class of "always-on" diagnostic tools.
No takes yet. Share an insight, caveat, or question.
Vandendriessche et al. (2017) studied Sepsis. Artificial neural network classifier for multiscalar waveform features vs. Standard clinical severity scores was evaluated on 28-day mortality. An artificial neural network classifier evaluating multiscale waveform features predicted 28-day mortality in sepsis patients with greater prognostic accuracy than standard clinical severity scores.
Synapse has enriched 10 related papers. Consider them for comparative context: