The MNd-5 algorithm was developed with the steering committee for the purpose of screening EMR databases to identify patients at risk of ALS. During validation, the algorithm achieved 93.9% sensitivity at 98.0% specificity.
MNd-5 generates probabilistic estimates of amyotrophic lateral sclerosis ("ALS") for individual patients based on data extracted from their electronic health records. The constellations of clinical and electromyogram (“EMG”) findings are categorized as “Unlikely,” “Equivocal” or “Probable” ALS when compared with a reference population in which ALS has been diagnosed or ruled out by clinical experts.
Clinical characteristics are extracted by trained members of the Ensho Clinical Operations Team using the Apollo aEDC system. Patients diagnosed with ALS or in which ALS has previously been ruled out are excluded from analyses as are individuals with prior traumatic brain injury, multiple sclerosis, Huntington's disease, chorea, essential tremors, and known genetic forms Parkinson's disease.
MNd-5 was trained on the complete de-identified electronic health records of 123 patients of five community neurologists of which 71 (58%) were diagnosed with ALS and 52 (42%) had ALS ruled out. It was retrospectively validated in a cohort of 117 patients of which 66 (56%) were diagnosed with ALS and 51 (44%) had ALS ruled out. MNd-5 achieved a 93.9% sensitivity at a 98.0% specificity in the validation cohort.
It was evaluated prospectively against 500 patients who consecutively visited a single community neurology practice and for whom ALS was not previously considered. Three were identified as having clinical characteristics suggestive of ALS. None of the patients identified had a definitive diagnosis for their symptoms and ALS was considered a possibility in one patient with a provisional diagnosis of primary lateral sclerosis ("PLS").
Participants will have their EMR databases screened using the MNd-5 algorithm for amyotrophic lateral sclerosis by the Toronto data lab of Ensho Health every 90 days beginning on the date of their enrollment and ending nine months thereafter. Each analysis will include the records of patients they encountered in the previous 90 days. The analysis will include all document types within the EMR including PDFs, image files and narrated encounter notes. No structure or coding systems are required.
MNd-5 is intended for use as a decision support tool to aid qualified healthcare professionals in identifying individuals in which follow-up investigations for ALS or referral to a specialty centre may be clinically appropriate. It is not diagnostic and does not replace the independent judgment of the treating physician. Any medical diagnosis and all decisions related to patient care and treatment choices should be based on the independent judgment of the treating physician and should take into account all information related to the patient, including without limitation, the patient and family history, direct physical examination and diagnostic tests.
The MNd-5 algorithm is a process for converting input parameters to a likelihood estimate. It is deployed at the Toronto, Canada data lab of Ensho Health through the MNd-5 CDL Module ("CDL Module"). The CDL Module is comprised of the MNd-5 Likelihood Estimator ("Likelihood Estimator") which encodes it in software and a graphical user interface called the MNd-5 Controller ("Controller"). The CDL Module was developed to the ISO 13485:2016 standard for medical devices in compliance with Ensho’s Quality Management System.
The MNd-5 CDL Module is registered as medical device software in Canada under the Medical Device Establishment License of Ensho Health (license 16208).