A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction

Sudarsan Sadasivuni; Sumukh Prashant Bhanushali; Imon Banerjee; Arindam Sanyal

doi:10.1109/BioCAS54905.2022.9948610

A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction

Sudarsan Sadasivuni, Sumukh Prashant Bhanushali, Imon Banerjee, Arindam Sanyal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This work presents an artificial intelligence (AI) framework for real-time, personalized sepsis prediction four hours before onset through fusion of electrocardiogram (ECG) and patient electronic medical record. An on-chip classifier combines analog reservoir-computer and artificial neural network to perform in-sensor classification at 43.6 TOPS/W (normalized efficiency of 528 TOPS/W) which reduces energy by 155× compared to conventional sensors and 4× compared to state-of-the-art bio-medical AI circuits. The proposed AI framework predicts sepsis onset with state-of-the-art 92.9% accuracy on patient data from MIMIC-III. The proposed framework is noninvasive and does not require lab tests which makes it suitable for at-home monitoring.

Original language	English (US)
Title of host publication	BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference
Subtitle of host publication	Intelligent Biomedical Systems for a Better Future, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	569-572
Number of pages	4
ISBN (Electronic)	9781665469173
DOIs	https://doi.org/10.1109/BioCAS54905.2022.9948610
State	Published - 2022
Event	2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022 - Taipei, Taiwan, Province of China Duration: Oct 13 2022 → Oct 15 2022

Publication series

Name	BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings

Conference

Conference	2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022
Country/Territory	Taiwan, Province of China
City	Taipei
Period	10/13/22 → 10/15/22

Keywords

artificial intelligence
artificial neural network
data fusion
in-memory computing
reservoir-computer
sepsis

ASJC Scopus subject areas

Artificial Intelligence
Signal Processing
Biomedical Engineering
Electrical and Electronic Engineering
Neuroscience (miscellaneous)
Instrumentation

Access to Document

10.1109/BioCAS54905.2022.9948610

Cite this

Sadasivuni, S., Bhanushali, S. P., Banerjee, I., & Sanyal, A. (2022). A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction. In BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings (pp. 569-572). (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BioCAS54905.2022.9948610

A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction. / Sadasivuni, Sudarsan; Bhanushali, Sumukh Prashant; Banerjee, Imon et al.
BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 569-572 (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sadasivuni, S, Bhanushali, SP, Banerjee, I & Sanyal, A 2022, A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction. in BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 569-572, 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022, Taipei, Taiwan, Province of China, 10/13/22. https://doi.org/10.1109/BioCAS54905.2022.9948610

Sadasivuni S, Bhanushali SP, Banerjee I, Sanyal A. A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction. In BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 569-572. (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings). doi: 10.1109/BioCAS54905.2022.9948610

Sadasivuni, Sudarsan ; Bhanushali, Sumukh Prashant ; Banerjee, Imon et al. / A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction. BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 569-572 (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings).

@inproceedings{ba48aa0e15d94728bfc251df95c52f6b,

title = "A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction",

abstract = "This work presents an artificial intelligence (AI) framework for real-time, personalized sepsis prediction four hours before onset through fusion of electrocardiogram (ECG) and patient electronic medical record. An on-chip classifier combines analog reservoir-computer and artificial neural network to perform in-sensor classification at 43.6 TOPS/W (normalized efficiency of 528 TOPS/W) which reduces energy by 155× compared to conventional sensors and 4× compared to state-of-the-art bio-medical AI circuits. The proposed AI framework predicts sepsis onset with state-of-the-art 92.9% accuracy on patient data from MIMIC-III. The proposed framework is noninvasive and does not require lab tests which makes it suitable for at-home monitoring.",

keywords = "artificial intelligence, artificial neural network, data fusion, in-memory computing, reservoir-computer, sepsis",

author = "Sudarsan Sadasivuni and Bhanushali, {Sumukh Prashant} and Imon Banerjee and Arindam Sanyal",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022 ; Conference date: 13-10-2022 Through 15-10-2022",

year = "2022",

doi = "10.1109/BioCAS54905.2022.9948610",

language = "English (US)",

series = "BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "569--572",

booktitle = "BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference",

}

TY - GEN

T1 - A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction

AU - Sadasivuni, Sudarsan

AU - Bhanushali, Sumukh Prashant

AU - Banerjee, Imon

AU - Sanyal, Arindam

PY - 2022

Y1 - 2022

N2 - This work presents an artificial intelligence (AI) framework for real-time, personalized sepsis prediction four hours before onset through fusion of electrocardiogram (ECG) and patient electronic medical record. An on-chip classifier combines analog reservoir-computer and artificial neural network to perform in-sensor classification at 43.6 TOPS/W (normalized efficiency of 528 TOPS/W) which reduces energy by 155× compared to conventional sensors and 4× compared to state-of-the-art bio-medical AI circuits. The proposed AI framework predicts sepsis onset with state-of-the-art 92.9% accuracy on patient data from MIMIC-III. The proposed framework is noninvasive and does not require lab tests which makes it suitable for at-home monitoring.

AB - This work presents an artificial intelligence (AI) framework for real-time, personalized sepsis prediction four hours before onset through fusion of electrocardiogram (ECG) and patient electronic medical record. An on-chip classifier combines analog reservoir-computer and artificial neural network to perform in-sensor classification at 43.6 TOPS/W (normalized efficiency of 528 TOPS/W) which reduces energy by 155× compared to conventional sensors and 4× compared to state-of-the-art bio-medical AI circuits. The proposed AI framework predicts sepsis onset with state-of-the-art 92.9% accuracy on patient data from MIMIC-III. The proposed framework is noninvasive and does not require lab tests which makes it suitable for at-home monitoring.

KW - artificial intelligence

KW - artificial neural network

KW - data fusion

KW - in-memory computing

KW - reservoir-computer

KW - sepsis

UR - http://www.scopus.com/inward/record.url?scp=85142924049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85142924049&partnerID=8YFLogxK

U2 - 10.1109/BioCAS54905.2022.9948610

DO - 10.1109/BioCAS54905.2022.9948610

M3 - Conference contribution

AN - SCOPUS:85142924049

T3 - BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings

SP - 569

EP - 572

BT - BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022

Y2 - 13 October 2022 through 15 October 2022

ER -

A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this