Fig. 6: Nonlinear regression can be used to identify the inflection point in longitudinal data where learning stops occurring.
From: Smartphone-based symbol-digit modalities test reliably captures brain damage in multiple sclerosis
Out of 16 participants (denoted by A–P; 1 HV; 15 MS) with longitudinal data (≥20 test sittings), nonlinear regression was able to identify the inflection point in 14 individuals. The solid orange line indicates the period where the individual is still learning. The dotted black line signifies the point learning inflection point that the algorithm identified. The dashed orange line denotes the algorithm’s assumption of the data’s regression line after the learning period. The solid blue line represents the actual regression line of the data after the learning period. On average, learning stops occurring after eight sittings.
