Classifying sepsis from photoplethysmography

Lombardi, Sara; Partanen, Petri; Francia, Piergiorgio; Calamai, Italo; Deodati, Rossella; Luchini, Marco; Spina, Rosario; Bocchi, Leonardo

doi:10.1007/s13755-022-00199-3

Cited by 8 publications

(3 citation statements)

References 55 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the details of internally developed signal annotator is not shared. In [24], authors utilize raw PPG signals in the ResNet algorithm resulting in an AUC of 0.84 to classify sepsis at onset time. Our results show superior performance when compared with the results in [24].…”

Section: Resultsmentioning

confidence: 99%

“…In [24], authors utilize raw PPG signals in the ResNet algorithm resulting in an AUC of 0.84 to classify sepsis at onset time. Our results show superior performance when compared with the results in [24]. In addition, authors simply employ ICD-9 codes for the subject selection.…”

Section: Resultsmentioning

confidence: 99%

“…In [23], the Medical Information Mart for Intensive Care (MIMIC)-III dataset was used for the proposed method where the Gaussian process adapter framework was combined with temporal convolutional networks (TCNs) to evaluate predictive performance of sepsis. For instance, Lombardi et al [24] trained a well-known CNN-based model called ResNet [25] utilizing raw fingertip photoplethysmography (PPG) time-series from MIMIC-III database. While discussing the importance of physiological signals for continuous monitoring of sepsis patients, this study is also investigating selection strategies for dataset preparation based on the utilization of PPG data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Advancing Early Detection of Sepsis With Temporal Convolutional Networks Using ECG Signals

Apalak,

Kiasaleh

2024

IEEE Access

View full text Add to dashboard Cite

In the hours leading up to the onset time of sepsis, the autonomic nervous system presents sub-clinical indicators of disease that may not be observable to providers. The objective of this research is to create an interpretable sepsis prediction algorithm utilizing continuous electrocardiography (ECG) signals, with the aim of implementing it in patient monitoring systems for individuals in intensive care units (ICU). We develop an early sepsis detection algorithm utilizing two datasets; in particular, the Medical Information Mart for Intensive Care (MIMIC-III) Clinical Dataset and MIMIC-Waveform Database. We carry out a systematic approach to selecting ECG segments of superior quality that are recorded in highly dynamic intensive care unit environments. Later, we use the single-lead ECG waveform to investigate the potential of heart rate variability (HRV) for continuous monitoring. In this study, 715 patients were included, of whom 65 are sepsis patients labeled with recent sepsis definition on an hourly basis. The predictive potential of the critical features is visualized to assist the interpretation of the model in a clinical practice. Moreover, since we are framing the early sepsis prediction as a supervised time series classification task, we evaluate the model performance by implementing Temporal Convolutional Networks (TCN). Performance analysis reported with varying prediction windows preceding sepsis onset time using area under the receiveroperating-characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). The deep learning model delivers promising results by leveraging time series with the use of temporal convolutions. Our findings reveal that the HRV characteristics of adults can be a valuable indicator for continuous sepsis monitoring in an ICU. Finally, this research work adds to the field of early sepsis detection by providing an annotated continuous waveform dataset from the MIMIC-Waveform Database, which is made accessible to the public.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%