The objective of this project is to work towards automating Transcranial Doppler (TCD) imaging data in cerebral malaria (CM) patients. Functional principal component analysis (FPCA) was used to identify important features of TCD data and quantify variation in TCD data explained by each feature. Cox regression was used to test the association between the most recent TCD measurements and mortality hazards rate. A functional clustering algorithm was employed to cluster TCD waveform data into distinct phenotypic groups. Fisher’s exact test and one-way analysis of variance (ANOVA) were used to test the association between 14 variables including demographic data, laboratory measurements, clinical features, and the TCD-defined phenotypic groups. We found that the systolic, diastolic, and mean velocities as well as the Windkessel notch together explain more than 98% of total TCD data variation in the middle cerebral arteries (MCAs) and the basilar artery (BA). The clustering algorithm identified 7 clusters for the MCA TCD data. No associations between phenotypic groups and demographics, clinical features, or laboratory measurements were detected. TCD measurements (mean, systolic and diastolic velocities) were associated with the survival hazards rates after adjusting for age and gender (chi-squared test statistic = 31.56, p-value = 0.025). TCD may be useful as a diagnostic and monitoring tool in CM. Developing an algorithm-driven approach to interpreting the waveforms will enhance the scalability of this assessment.