Feasibility of remote speech analysis in evaluation of dynamic fluid overload in heart failure patients undergoing haemodialysis treatment

Offer Amir; Stefan D. Anker; Ittamar Gork; William T. Abraham; Sean P. Pinney; Daniel Burkhoff; Ilan D. Shallom; Ronit Haviv; Elazer R. Edelman; Chaim Lotan

doi:10.1002/ehf2.13367

Feasibility of remote speech analysis in evaluation of dynamic fluid overload in heart failure patients undergoing haemodialysis treatment

Offer Amir, Stefan D. Anker, Ittamar Gork, William T. Abraham, Sean P. Pinney, Daniel Burkhoff, Ilan D. Shallom, Ronit Haviv, Elazer R. Edelman, Chaim Lotan

Bar-Ilan University - Azrieli Faculty of Medicine

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Aims: This study aimed to assess the ability of a voice analysis application to discriminate between wet and dry states in chronic heart failure (CHF) patients undergoing regular scheduled haemodialysis treatment due to volume overload as a result of their chronic renal failure. Methods and results: In this single-centre, observational study, five patients with CHF, peripheral oedema of ≥2, and pulmonary congestion-related dyspnoea, undergoing haemodialysis three times per week, recorded five sentences into a standard smartphone/tablet before and after haemodialysis. Recordings were provided that same noon/early evening and the next morning and evening. Patient weight was measured at the hospital before and after each haemodialysis session. Recordings were analysed by a smartphone application (app) algorithm, to compare speech measures (SMs) of utterances collected over time. On average, patients provided recordings throughout 25.8 ± 3.9 dialysis treatment cycles, resulting in a total of 472 recordings. Weight changes of 1.95 ± 0.64 kg were documented during cycles. Median baseline SM prior to dialysis was 0.87 ± 0.17, and rose to 1.07 ± 0.15 following the end of the dialysis session, at noon (P = 0.0355), and remained at a similar level until the following morning (P = 0.007). By the evening of the day following dialysis, SMs returned to baseline levels (0.88 ± 0.19). Changes in patient weight immediately after dialysis positively correlated with SM changes, with the strongest correlation measured the evening of the dialysis day [slope: −0.40 ± 0.15 (95% confidence interval: −0.71 to −0.10), P = 0.0096]. Conclusions: The fluid-controlled haemodialysis model demonstrated the ability of the app algorithm to identify cyclic changes in SMs, which reflected bodily fluid levels. The voice analysis platform bears considerable potential as a harbinger of impending fluid overload in a range of clinical scenarios, which will enhance monitoring and triage efforts, ultimately optimizing remote CHF management.

Original language	English
Pages (from-to)	2467-2472
Number of pages	6
Journal	ESC heart failure
Volume	8
Issue number	4
DOIs	https://doi.org/10.1002/ehf2.13367
State	Published - Aug 2021

Bibliographical note

Publisher Copyright:
© 2021 The Authors. ESC Heart Failure published by John Wiley & Sons Ltd on behalf of European Society of Cardiology.

Funding

This work was supported by Cordio Medical Ltd. O.A. is a paid consultant to Cordio Medical Ltd. S.D.A. reports receiving grant support from Abbott and Vifor Pharma and fees from Abbott, Bayer, Boehringer Ingelheim, Cardiac Dimension, Impulse Dynamics, Novartis, Servier, and Vifor Pharma and is a consultant to Cordio Medical Ltd. I.G. has no interest to declare. W.T.A. is a consultant to Cordio Medical Ltd. and has received consulting fees from Abbott, Boehringer Ingelheim, CVRx, Edwards Lifesciences, and Respicardia; salary support from V‐Wave Medical; and research support from the US National Institutes of Health/National Heart, Lung, and Blood Institute. S.P.P. is a consultant to Cordio Medical Ltd. and has received consulting fees from Abbott, CareDx, Medtronic, NuPulse, and Procyrion. D.B. is a consultant to Cordio Medical Ltd. I.D.S. is the Chief Technology Officer of Cordio Medical Ltd. R.H. is the Clinical SrVP at Cordio Medical Ltd. E.R.E. is supported in part by a grant from the US National Institutes of Health (NIH R01 49039) and is a paid consultant to Cordio Medical Ltd. C.L. is a board member of Cordio Medical Ltd. and receiving lecture fees from Boehringer Ingelheim.

Funders	Funder number
CVRx
Cordio Medical Ltd
Cordio Medical Ltd
Respicardia
National Institutes of Health	R01 49039
National Heart, Lung, and Blood Institute
Abbott Laboratories
Bayer
Edwards Lifesciences
Boehringer Ingelheim
Vifor Pharma

Keywords

Acute heart failure (AHF)
Dialysis
Remote voice analysis
Speech measure (SM)

Access to Document

10.1002/ehf2.13367

Cite this

@article{8fbdda627d6344168c52bd1d5d5a33ea,

title = "Feasibility of remote speech analysis in evaluation of dynamic fluid overload in heart failure patients undergoing haemodialysis treatment",

abstract = "Aims: This study aimed to assess the ability of a voice analysis application to discriminate between wet and dry states in chronic heart failure (CHF) patients undergoing regular scheduled haemodialysis treatment due to volume overload as a result of their chronic renal failure. Methods and results: In this single-centre, observational study, five patients with CHF, peripheral oedema of ≥2, and pulmonary congestion-related dyspnoea, undergoing haemodialysis three times per week, recorded five sentences into a standard smartphone/tablet before and after haemodialysis. Recordings were provided that same noon/early evening and the next morning and evening. Patient weight was measured at the hospital before and after each haemodialysis session. Recordings were analysed by a smartphone application (app) algorithm, to compare speech measures (SMs) of utterances collected over time. On average, patients provided recordings throughout 25.8 ± 3.9 dialysis treatment cycles, resulting in a total of 472 recordings. Weight changes of 1.95 ± 0.64 kg were documented during cycles. Median baseline SM prior to dialysis was 0.87 ± 0.17, and rose to 1.07 ± 0.15 following the end of the dialysis session, at noon (P = 0.0355), and remained at a similar level until the following morning (P = 0.007). By the evening of the day following dialysis, SMs returned to baseline levels (0.88 ± 0.19). Changes in patient weight immediately after dialysis positively correlated with SM changes, with the strongest correlation measured the evening of the dialysis day [slope: −0.40 ± 0.15 (95% confidence interval: −0.71 to −0.10), P = 0.0096]. Conclusions: The fluid-controlled haemodialysis model demonstrated the ability of the app algorithm to identify cyclic changes in SMs, which reflected bodily fluid levels. The voice analysis platform bears considerable potential as a harbinger of impending fluid overload in a range of clinical scenarios, which will enhance monitoring and triage efforts, ultimately optimizing remote CHF management.",

keywords = "Acute heart failure (AHF), Dialysis, Remote voice analysis, Speech measure (SM)",

author = "Offer Amir and Anker, {Stefan D.} and Ittamar Gork and Abraham, {William T.} and Pinney, {Sean P.} and Daniel Burkhoff and Shallom, {Ilan D.} and Ronit Haviv and Edelman, {Elazer R.} and Chaim Lotan",

note = "Publisher Copyright: {\textcopyright} 2021 The Authors. ESC Heart Failure published by John Wiley & Sons Ltd on behalf of European Society of Cardiology.",

year = "2021",

month = aug,

doi = "10.1002/ehf2.13367",

language = "אנגלית",

volume = "8",

pages = "2467--2472",

journal = "ESC heart failure",

issn = "2055-5822",

publisher = "John Wiley and Sons Inc.",

number = "4",

}

TY - JOUR

T1 - Feasibility of remote speech analysis in evaluation of dynamic fluid overload in heart failure patients undergoing haemodialysis treatment

AU - Amir, Offer

AU - Anker, Stefan D.

AU - Gork, Ittamar

AU - Abraham, William T.

AU - Pinney, Sean P.

AU - Burkhoff, Daniel

AU - Shallom, Ilan D.

AU - Haviv, Ronit

AU - Edelman, Elazer R.

AU - Lotan, Chaim

PY - 2021/8

Y1 - 2021/8

N2 - Aims: This study aimed to assess the ability of a voice analysis application to discriminate between wet and dry states in chronic heart failure (CHF) patients undergoing regular scheduled haemodialysis treatment due to volume overload as a result of their chronic renal failure. Methods and results: In this single-centre, observational study, five patients with CHF, peripheral oedema of ≥2, and pulmonary congestion-related dyspnoea, undergoing haemodialysis three times per week, recorded five sentences into a standard smartphone/tablet before and after haemodialysis. Recordings were provided that same noon/early evening and the next morning and evening. Patient weight was measured at the hospital before and after each haemodialysis session. Recordings were analysed by a smartphone application (app) algorithm, to compare speech measures (SMs) of utterances collected over time. On average, patients provided recordings throughout 25.8 ± 3.9 dialysis treatment cycles, resulting in a total of 472 recordings. Weight changes of 1.95 ± 0.64 kg were documented during cycles. Median baseline SM prior to dialysis was 0.87 ± 0.17, and rose to 1.07 ± 0.15 following the end of the dialysis session, at noon (P = 0.0355), and remained at a similar level until the following morning (P = 0.007). By the evening of the day following dialysis, SMs returned to baseline levels (0.88 ± 0.19). Changes in patient weight immediately after dialysis positively correlated with SM changes, with the strongest correlation measured the evening of the dialysis day [slope: −0.40 ± 0.15 (95% confidence interval: −0.71 to −0.10), P = 0.0096]. Conclusions: The fluid-controlled haemodialysis model demonstrated the ability of the app algorithm to identify cyclic changes in SMs, which reflected bodily fluid levels. The voice analysis platform bears considerable potential as a harbinger of impending fluid overload in a range of clinical scenarios, which will enhance monitoring and triage efforts, ultimately optimizing remote CHF management.

AB - Aims: This study aimed to assess the ability of a voice analysis application to discriminate between wet and dry states in chronic heart failure (CHF) patients undergoing regular scheduled haemodialysis treatment due to volume overload as a result of their chronic renal failure. Methods and results: In this single-centre, observational study, five patients with CHF, peripheral oedema of ≥2, and pulmonary congestion-related dyspnoea, undergoing haemodialysis three times per week, recorded five sentences into a standard smartphone/tablet before and after haemodialysis. Recordings were provided that same noon/early evening and the next morning and evening. Patient weight was measured at the hospital before and after each haemodialysis session. Recordings were analysed by a smartphone application (app) algorithm, to compare speech measures (SMs) of utterances collected over time. On average, patients provided recordings throughout 25.8 ± 3.9 dialysis treatment cycles, resulting in a total of 472 recordings. Weight changes of 1.95 ± 0.64 kg were documented during cycles. Median baseline SM prior to dialysis was 0.87 ± 0.17, and rose to 1.07 ± 0.15 following the end of the dialysis session, at noon (P = 0.0355), and remained at a similar level until the following morning (P = 0.007). By the evening of the day following dialysis, SMs returned to baseline levels (0.88 ± 0.19). Changes in patient weight immediately after dialysis positively correlated with SM changes, with the strongest correlation measured the evening of the dialysis day [slope: −0.40 ± 0.15 (95% confidence interval: −0.71 to −0.10), P = 0.0096]. Conclusions: The fluid-controlled haemodialysis model demonstrated the ability of the app algorithm to identify cyclic changes in SMs, which reflected bodily fluid levels. The voice analysis platform bears considerable potential as a harbinger of impending fluid overload in a range of clinical scenarios, which will enhance monitoring and triage efforts, ultimately optimizing remote CHF management.

KW - Acute heart failure (AHF)

KW - Dialysis

KW - Remote voice analysis

KW - Speech measure (SM)

UR - http://www.scopus.com/inward/record.url?scp=85105205160&partnerID=8YFLogxK

U2 - 10.1002/ehf2.13367

DO - 10.1002/ehf2.13367

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 33955187

AN - SCOPUS:85105205160

SN - 2055-5822

VL - 8

SP - 2467

EP - 2472

JO - ESC heart failure

JF - ESC heart failure

IS - 4

ER -

Feasibility of remote speech analysis in evaluation of dynamic fluid overload in heart failure patients undergoing haemodialysis treatment

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this