Data-driven deep phenotyping of multiple sclerosis patients using patient-reported outcome measures (P3-3.015)

Abstract

<h3>Objective:</h3> To identify distinct clusters of persons with multiple sclerosis (PwMS) with shared impairment patterns across 11 functional domains. <h3>Background:</h3> PwMS experience wide-ranging symptoms across multiple domains, alone or in combination, with varied severity. We sought to characterize naturally occurring clusters of MS using seemingly heterogeneous longitudinal patient-reported outcome measure (PROMs) responses, which are increasingly used in clinical trials and practice. <h3>Design/Methods:</h3> From the electronic health records of 6,619 MS patients with extended care (≥2 encounters 6 months apart) at a tertiary referral center between 2008–2015, we abstracted responses for 11 validated MS-PROMs include 8 MS Performance Scales© (mobility, hand function, vision, fatigue, cognition, bladder/bowel, sensory, spasticity) and 3 MS Functional Scales (pain, depression, tremor/coordination). We applied unsupervised machine learning through mixture modeling (latent profile analysis) to the 11 MS-PROMs at baseline, to identify a set of discrete and non-overlapping clusters of MS patients with similar impairment patterns. <h3>Results:</h3> Nine patient clusters were detected, and were differentiated by low (4 clusters), medium (1 cluster), and high (4 clusters) levels of mobility impairment. The low mobility impairment clusters were differentiated by low impairment across domains (31.7%), to moderate fatigue (18.7%), to moderate fatigue + moderately-high sensory dysfunction (7.9%), and to moderately-high fatigue + pain (10%). The medium mobility cluster had moderately-high impairment across domains (10.2%). The clusters with high mobility impairments varied with mild impairment (8.3%) to high impairment (4.1%) across all domains, and two clusters with moderate impairment across domains but not sensory dysfunction (low [3.9%] vs high [5.1%]). The clusters also varied by sociodemographic and clinical attributes. The most impaired cluster had the highest proportion of Black patients, the lowest quality of life, and lived in ZIP codes with the highest levels of deprivation. <h3>Conclusions:</h3> We leveraged PROMs to innovatively deep phenotype MS patients into distinct subgroups with varying levels of disability and symptomatology. <b>Disclosure:</b> The institution of Prof. Briggs has received research support from NIH. The institution of Prof. Briggs has received research support from Michael J. Fox Foundation. Doug Gunzler has nothing to disclose. Dr. Ontaneda has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Novartis. Dr. Ontaneda has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Genentech/Roche. Dr. Ontaneda has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Biogen Idec. Dr. Ontaneda has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Genentech/Roche. The institution of Dr. Ontaneda has received research support from NIH. The institution of Dr. Ontaneda has received research support from PCORI. The institution of Dr. Ontaneda has received research support from NMSS. The institution of Dr. Ontaneda has received research support from Genetech. Dr. Miller has received intellectual property interests from a discovery or technology relating to health care. Mr. Zamora has nothing to disclose. Alessandro De Nadai has nothing to disclose.