Prospective Validation of Machine-assisted Electrophysiologic and Online Clinical Support Tools in Chronic Inflammatory Demyelinating Polyradiculoneuropathy
Michael Skolka1, Grace Swart2, Shahar Shelly3, Thapat Wannarong4, Stefan Stalberg5, Benjamin Stalberg5, Abe Gardner5, Jacob Price5, Ruple Laughlin6, Divyanshu Dubey7, John Mills7, Jayawant Mandrekar6, Christopher Klein7
1Mayo Clinic Florida, 2University of Sydney, 3Rambam Medical Center, 4Department of Neurological Sciences, University of Nebraska Medical Center, 5Cadwell Laboratories, Inc, 6Mayo Clinic Rochester, 7Mayo Clinic
Objective:

To validate a machine-assisted electrodiagnostic (EDX) support tool in chronic inflammatory demyelinating polyradiculoneuropathy (CIDP) in conjunction with an online CIDP clinical calculator.

Background:
CIDP is one of the most common, treatable, autoimmune, demyelinating neuropathies.  While the European Academy of Neurology/Peripheral Nerve Society (EAN/PNS) in 2021 published EDX criteria for CIDP, misdiagnosis is common in part due to the complexity of EDX interpretation of demyelination.  Previously, our group developed an Excel-based EDX assistant for automated application of 2021-EAN/PNS EDX criteria which formed the basis of an online clinical calculator to identify CIDP versus mimic disorders (https://news.mayocliniclabs.com/cidp-calculator/).  Currently, in collaboration with Cadwell Industries, a CIDP-EDX diagnostic machine-assisted program was developed integrating directly with nerve conduction study software to alert providers in real time when 2021-EAN/PNS CIDP criteria are met.
Design/Methods:

We prospectively evaluated 100 consecutive patients with referral or EDX diagnosis of polyradiculoneuropathy beginning January 1, 2024. Fifty patients were included each from Jacksonville and Rochester Mayo Clinics. EMG reports were compared to a machine-assisted support tool applying CIDP 2021-EAN/PNS EDX criteria for demyelination. The EDX-calculator performance was compared to final diagnosis and our previously reported online CIDP clinical prediction tool. 

Results:

Among 100 patients (60% male; median age 64), 30 had a final CIDP diagnosis with 29 having post-IVIG follow-up, 27 (93%) improved and 2 (7%) stabilized. Routine EMGs reported demyelination in 14 of 30 (46%), with 46% sensitivity and 79% specificity. The EDX calculator supported CIDP demyelination in 28 of 30 (93%), with 93% sensitivity and 57% specificity. The clinical calculator detected CIDP in 30 of 30 (100%) with 86% specificity, increasing to 94% after excluding false positives lacking demyelinating features per the EDX calculator.

Conclusions:

A real-time EDX machine-assisted support tool paired with an established clinical web-based calculator assists CIDP assessment facilitating clinical decision-making by improving standardized identification of demyelinating nerve conductions.

10.1212/WNL.0000000000212788
Disclaimer: Abstracts were not reviewed by Neurology® and do not reflect the views of Neurology® editors or staff.