PiMS: A Pre-ML Labelling Tool

Irini Logothetis; Scott Barnett; Leonard Hoon; Srikanth Thudumu; Joseph Mathew; Carl Luckhoff; Gerard O'Reilly; David Collard; Rajesh Vasa; Kon Mouzakis; Mark Fitzgerald

doi:10.1109/eScience55777.2022.00073

PiMS: A Pre-ML Labelling Tool

Irini Logothetis, Scott Barnett, Leonard Hoon, Srikanth Thudumu, Joseph Mathew, Carl Luckhoff, Gerard O'Reilly, David Collard, Rajesh Vasa, Kon Mouzakis, Mark Fitzgerald

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other › peer-review

2 Citations (Scopus)

Abstract

Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians.

Original language	English
Title of host publication	Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	431-432
Number of pages	2
ISBN (Electronic)	9781665461245
DOIs	https://doi.org/10.1109/eScience55777.2022.00073
Publication status	Published - 2022
Externally published	Yes
Event	IEEE International Conference on e-Science 2022 - Thomas S. Monson Center, Salt Lake City, United States of America Duration: 10 Oct 2022 → 14 Oct 2022 Conference number: 18th https://ieeexplore.ieee.org/xpl/conhome/9973400/proceeding

Publication series

Name	Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022

Conference

Conference	IEEE International Conference on e-Science 2022
Abbreviated title	eScience 22
Country/Territory	United States of America
City	Salt Lake City
Period	10/10/22 → 14/10/22
Other	co-located with the 3rd GRP Workshop (3GRP) and the National Science Data Fabric All-Hands meeting.
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9973400/proceeding

Keywords

Clinical Decision Support Systems (CDSS)
Human-in-the-loop Validation
ML Labelling
Triaging Algorithm

Access to Document

10.1109/eScience55777.2022.00073

Cite this

Logothetis, I., Barnett, S., Hoon, L., Thudumu, S., Mathew, J., Luckhoff, C., O'Reilly, G., Collard, D., Vasa, R., Mouzakis, K., & Fitzgerald, M. (2022). PiMS: A Pre-ML Labelling Tool. In Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022 (pp. 431-432). (Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/eScience55777.2022.00073

@inproceedings{f3a6ba917b644d46850a428a93d84260,

title = "PiMS: A Pre-ML Labelling Tool",

abstract = "Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians.",

keywords = "Clinical Decision Support Systems (CDSS), Human-in-the-loop Validation, ML Labelling, Triaging Algorithm",

author = "Irini Logothetis and Scott Barnett and Leonard Hoon and Srikanth Thudumu and Joseph Mathew and Carl Luckhoff and Gerard O'Reilly and David Collard and Rajesh Vasa and Kon Mouzakis and Mark Fitzgerald",

note = "Funding Information: ACKNOWLEDGMENT This work was supported by NIB Health Insurance, Alfred Health and Monash Health. The system was commercialised under the brand VMS. Publisher Copyright: {\textcopyright} 2022 IEEE. Listed under the Poster section of the table of contents; IEEE International Conference on e-Science 2022, eScience 22 ; Conference date: 10-10-2022 Through 14-10-2022",

year = "2022",

doi = "10.1109/eScience55777.2022.00073",

language = "English",

series = "Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "431--432",

booktitle = "Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/9973400/proceeding",

}

Logothetis, I, Barnett, S, Hoon, L, Thudumu, S, Mathew, J, Luckhoff, C, O'Reilly, G, Collard, D, Vasa, R, Mouzakis, K & Fitzgerald, M 2022, PiMS: A Pre-ML Labelling Tool. in Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022. Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 431-432, IEEE International Conference on e-Science 2022, Salt Lake City, Utah, United States of America, 10/10/22. https://doi.org/10.1109/eScience55777.2022.00073

PiMS: A Pre-ML Labelling Tool. / Logothetis, Irini; Barnett, Scott; Hoon, Leonard et al.
Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2022. p. 431-432 (Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other › peer-review

TY - GEN

T1 - PiMS

T2 - IEEE International Conference on e-Science 2022

AU - Logothetis, Irini

AU - Barnett, Scott

AU - Hoon, Leonard

AU - Thudumu, Srikanth

AU - Mathew, Joseph

AU - Luckhoff, Carl

AU - O'Reilly, Gerard

AU - Collard, David

AU - Vasa, Rajesh

AU - Mouzakis, Kon

AU - Fitzgerald, Mark

N1 - Conference code: 18th

PY - 2022

Y1 - 2022

N2 - Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians.

AB - Machine Learning (ML) techniques in clinical decision support systems are scarce due to the limited availability of clinically validated and labelled training data sets. We present a framework to (1) enable quality controls at data submission toward ML appropriate data, (2) provide in-situ algorithm assessments, and (3) prepare dataframes for ML training and robust stochastic analysis. We developed and evaluated PiMS (Pandemic Intervention and Monitoring Systems): a remote monitoring solution for patients that are Covid-positive. The system was trialled at two hospitals in Melbourne, Australia (Alfred Health and Monash Health) involving 109 patients and 15 clinicians.

KW - Clinical Decision Support Systems (CDSS)

KW - Human-in-the-loop Validation

KW - ML Labelling

KW - Triaging Algorithm

UR - http://www.scopus.com/inward/record.url?scp=85145436032&partnerID=8YFLogxK

U2 - 10.1109/eScience55777.2022.00073

DO - 10.1109/eScience55777.2022.00073

M3 - Conference Paper

AN - SCOPUS:85145436032

T3 - Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022

SP - 431

EP - 432

BT - Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

Y2 - 10 October 2022 through 14 October 2022

ER -

Logothetis I, Barnett S, Hoon L, Thudumu S, Mathew J, Luckhoff C et al. PiMS: A Pre-ML Labelling Tool. In Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2022. p. 431-432. (Proceedings - 2022 IEEE 18th International Conference on e-Science, eScience 2022). doi: 10.1109/eScience55777.2022.00073

PiMS: A Pre-ML Labelling Tool

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this