Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy

Georgios Ponirakis, Hassan Fadavi, Ioannis N. Petropoulos, Shazli Azmi, Maryam Ferdousi, Mohammad A. Dabbah, Ahmad Kheyami, Uazman Alam, Omar Asghar, Andrew Marshall, Mitra Tavakoli, Ahmed Al-Ahmar, Saad Javed, Maria Jeziorska, Rayaz Malik

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Neuropad is currently a categorical visual screening test that identifies diabetic patients at risk of foot ulceration. The diagnostic performance of Neuropad was compared between the categorical and continuous (image-analysis (Sudometrics)) outputs to diagnose diabetic peripheral neuropathy (DPN). 110 subjects with type 1 and 2 diabetes underwent assessment with Neuropad, Neuropathy Disability Score (NDS), peroneal motor nerve conduction velocity (PMNCV), sural nerve action potential (SNAP), Deep Breathing-Heart Rate Variability (DB-HRV), intraepidermal nerve fibre density (IENFD), and corneal confocal microscopy (CCM). 46/110 patients had DPN according to the Toronto consensus. The continuous output displayed high sensitivity and specificity for DB-HRV (91%, 83%), CNFD (88%, 78%), and SNAP (88%, 83%), whereas the categorical output showed high sensitivity but low specificity. The optimal cut-off points were 90% for the detection of autonomic dysfunction (DB-HRV) and 80% for small fibre neuropathy (CNFD). The diagnostic efficacy of the continuous Neuropad output for abnormal DB-HRV (AUC: 91%, P = 0.0003) and CNFD (AUC: 82%, P = 0.01) was better than for PMNCV (AUC: 60%). The categorical output showed no significant difference in diagnostic efficacy for these same measures. An image analysis algorithm generating a continuous output (Sudometrics) improved the diagnostic ability of Neuropad, particularly in detecting autonomic and small fibre neuropathy.

Original languageEnglish
Article number847854
JournalJournal of Diabetes Research
Volume2015
DOIs
Publication statusPublished - 2015

Fingerprint

Diabetic Neuropathies
Respiration
Heart Rate
Area Under Curve
Sural Nerve
Peroneal Nerve
Neural Conduction
Peripheral Nervous System Diseases
Action Potentials
Sensitivity and Specificity
Type 1 Diabetes Mellitus
Nerve Fibers
Confocal Microscopy
Type 2 Diabetes Mellitus
Foot
Small Fiber Neuropathy

ASJC Scopus subject areas

  • Endocrinology, Diabetes and Metabolism
  • Endocrinology

Cite this

Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy. / Ponirakis, Georgios; Fadavi, Hassan; Petropoulos, Ioannis N.; Azmi, Shazli; Ferdousi, Maryam; Dabbah, Mohammad A.; Kheyami, Ahmad; Alam, Uazman; Asghar, Omar; Marshall, Andrew; Tavakoli, Mitra; Al-Ahmar, Ahmed; Javed, Saad; Jeziorska, Maria; Malik, Rayaz.

In: Journal of Diabetes Research, Vol. 2015, 847854, 2015.

Research output: Contribution to journalArticle

Ponirakis, G, Fadavi, H, Petropoulos, IN, Azmi, S, Ferdousi, M, Dabbah, MA, Kheyami, A, Alam, U, Asghar, O, Marshall, A, Tavakoli, M, Al-Ahmar, A, Javed, S, Jeziorska, M & Malik, R 2015, 'Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy', Journal of Diabetes Research, vol. 2015, 847854. https://doi.org/10.1155/2015/847854
Ponirakis, Georgios ; Fadavi, Hassan ; Petropoulos, Ioannis N. ; Azmi, Shazli ; Ferdousi, Maryam ; Dabbah, Mohammad A. ; Kheyami, Ahmad ; Alam, Uazman ; Asghar, Omar ; Marshall, Andrew ; Tavakoli, Mitra ; Al-Ahmar, Ahmed ; Javed, Saad ; Jeziorska, Maria ; Malik, Rayaz. / Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy. In: Journal of Diabetes Research. 2015 ; Vol. 2015.
@article{b46918114b164339870d497ab31478a5,
title = "Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy",
abstract = "Neuropad is currently a categorical visual screening test that identifies diabetic patients at risk of foot ulceration. The diagnostic performance of Neuropad was compared between the categorical and continuous (image-analysis (Sudometrics)) outputs to diagnose diabetic peripheral neuropathy (DPN). 110 subjects with type 1 and 2 diabetes underwent assessment with Neuropad, Neuropathy Disability Score (NDS), peroneal motor nerve conduction velocity (PMNCV), sural nerve action potential (SNAP), Deep Breathing-Heart Rate Variability (DB-HRV), intraepidermal nerve fibre density (IENFD), and corneal confocal microscopy (CCM). 46/110 patients had DPN according to the Toronto consensus. The continuous output displayed high sensitivity and specificity for DB-HRV (91{\%}, 83{\%}), CNFD (88{\%}, 78{\%}), and SNAP (88{\%}, 83{\%}), whereas the categorical output showed high sensitivity but low specificity. The optimal cut-off points were 90{\%} for the detection of autonomic dysfunction (DB-HRV) and 80{\%} for small fibre neuropathy (CNFD). The diagnostic efficacy of the continuous Neuropad output for abnormal DB-HRV (AUC: 91{\%}, P = 0.0003) and CNFD (AUC: 82{\%}, P = 0.01) was better than for PMNCV (AUC: 60{\%}). The categorical output showed no significant difference in diagnostic efficacy for these same measures. An image analysis algorithm generating a continuous output (Sudometrics) improved the diagnostic ability of Neuropad, particularly in detecting autonomic and small fibre neuropathy.",
author = "Georgios Ponirakis and Hassan Fadavi and Petropoulos, {Ioannis N.} and Shazli Azmi and Maryam Ferdousi and Dabbah, {Mohammad A.} and Ahmad Kheyami and Uazman Alam and Omar Asghar and Andrew Marshall and Mitra Tavakoli and Ahmed Al-Ahmar and Saad Javed and Maria Jeziorska and Rayaz Malik",
year = "2015",
doi = "10.1155/2015/847854",
language = "English",
volume = "2015",
journal = "Journal of Diabetes Research",
issn = "2314-6745",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Automated quantification of neuropad improves its diagnostic ability in patients with diabetic neuropathy

AU - Ponirakis, Georgios

AU - Fadavi, Hassan

AU - Petropoulos, Ioannis N.

AU - Azmi, Shazli

AU - Ferdousi, Maryam

AU - Dabbah, Mohammad A.

AU - Kheyami, Ahmad

AU - Alam, Uazman

AU - Asghar, Omar

AU - Marshall, Andrew

AU - Tavakoli, Mitra

AU - Al-Ahmar, Ahmed

AU - Javed, Saad

AU - Jeziorska, Maria

AU - Malik, Rayaz

PY - 2015

Y1 - 2015

N2 - Neuropad is currently a categorical visual screening test that identifies diabetic patients at risk of foot ulceration. The diagnostic performance of Neuropad was compared between the categorical and continuous (image-analysis (Sudometrics)) outputs to diagnose diabetic peripheral neuropathy (DPN). 110 subjects with type 1 and 2 diabetes underwent assessment with Neuropad, Neuropathy Disability Score (NDS), peroneal motor nerve conduction velocity (PMNCV), sural nerve action potential (SNAP), Deep Breathing-Heart Rate Variability (DB-HRV), intraepidermal nerve fibre density (IENFD), and corneal confocal microscopy (CCM). 46/110 patients had DPN according to the Toronto consensus. The continuous output displayed high sensitivity and specificity for DB-HRV (91%, 83%), CNFD (88%, 78%), and SNAP (88%, 83%), whereas the categorical output showed high sensitivity but low specificity. The optimal cut-off points were 90% for the detection of autonomic dysfunction (DB-HRV) and 80% for small fibre neuropathy (CNFD). The diagnostic efficacy of the continuous Neuropad output for abnormal DB-HRV (AUC: 91%, P = 0.0003) and CNFD (AUC: 82%, P = 0.01) was better than for PMNCV (AUC: 60%). The categorical output showed no significant difference in diagnostic efficacy for these same measures. An image analysis algorithm generating a continuous output (Sudometrics) improved the diagnostic ability of Neuropad, particularly in detecting autonomic and small fibre neuropathy.

AB - Neuropad is currently a categorical visual screening test that identifies diabetic patients at risk of foot ulceration. The diagnostic performance of Neuropad was compared between the categorical and continuous (image-analysis (Sudometrics)) outputs to diagnose diabetic peripheral neuropathy (DPN). 110 subjects with type 1 and 2 diabetes underwent assessment with Neuropad, Neuropathy Disability Score (NDS), peroneal motor nerve conduction velocity (PMNCV), sural nerve action potential (SNAP), Deep Breathing-Heart Rate Variability (DB-HRV), intraepidermal nerve fibre density (IENFD), and corneal confocal microscopy (CCM). 46/110 patients had DPN according to the Toronto consensus. The continuous output displayed high sensitivity and specificity for DB-HRV (91%, 83%), CNFD (88%, 78%), and SNAP (88%, 83%), whereas the categorical output showed high sensitivity but low specificity. The optimal cut-off points were 90% for the detection of autonomic dysfunction (DB-HRV) and 80% for small fibre neuropathy (CNFD). The diagnostic efficacy of the continuous Neuropad output for abnormal DB-HRV (AUC: 91%, P = 0.0003) and CNFD (AUC: 82%, P = 0.01) was better than for PMNCV (AUC: 60%). The categorical output showed no significant difference in diagnostic efficacy for these same measures. An image analysis algorithm generating a continuous output (Sudometrics) improved the diagnostic ability of Neuropad, particularly in detecting autonomic and small fibre neuropathy.

UR - http://www.scopus.com/inward/record.url?scp=84930673140&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930673140&partnerID=8YFLogxK

U2 - 10.1155/2015/847854

DO - 10.1155/2015/847854

M3 - Article

C2 - 26064991

AN - SCOPUS:84930673140

VL - 2015

JO - Journal of Diabetes Research

JF - Journal of Diabetes Research

SN - 2314-6745

M1 - 847854

ER -