Machine Learning Approach for Rapid, Accurate Point-of-Care Prediction of M-Spike Values in Multiple Myeloma

PURPOSE The gold standard for monitoring response status in patients with multiple myeloma (MM) is serum and urine protein electrophoresis which quantify M-spike proteins; however, the turnaround time for results is 3-7 days which delays treatment decisions. We hypothesized that machine learning (ML) could integrate readily available clinical and laboratory data to rapidly and accurately predict patient M-spike values. METHODS A retrospective chart review was performed using the deidentified, electronic medical records of 171 patients with MM. RESULTS Random forest (RF) analysis identified the weighted value of each independent variable (N 5 43) integrated into the ML algorithm. Pearson and Spearman coefficients indicated that the ML-predicted M-spike values correlated highly with laboratory-measured serum protein electrophoresis values. Feature selected RF modeling revealed that only two variables-the first lagged M-spike and serum total protein-accurately predicted the M-spike. CONCLUSION Taken together, our results demonstrate the feasibility and prognostic potential of ML tools that integrate electronic data to longitudinally monitor disease burden. ML tools support the seamless, secure exchange of patient information to expedite and personalize clinical decision making and overcome geographic, financial, and social barriers that currently limit the access of underserved populations to cancer care specialists so that the benefits of medical progress are not limited to selected groups.