Daily experience of pain can lead to long-term disability, particularly for individuals with Sickle Cell Disease (SCD). Inheritance of this genetic disorder leads to changes in hemoglobin causing the stiffening and distorting of red blood cells into the shape of “sickles”. As a result, patients experience both chronic and acute pain caused by this sickling that restricts blood flow to different parts of their bodies. The experience of sickle cell pain has been found to be extremely variable within and across patients with respect to location, frequency, severity, age and co-morbidities; each patient is truly unique when it comes to the presentation of pain, making it difficult to define a consistent pain management procedure. Current developments in mobile technology provide new tools for understanding and managing SCD pain outside the clinical setting, where characteristics of pain can be captured using self-report measures administered using mobile applications on patients’ smart phones. Mobile sensor technology also allows for the continuous monitoring of physiological measures including heart rate variability, arousal, temperature, and movement. The current project aimed to assess patterns of changes in these physiological measures across different pain intensities, in order to identify if these measures can serve as indicators of pain intensity or the onset of severe pain events in patients with SCD. Four young-adult patients with SCD were recruited from Cincinnati Children’s Hospital Medical Center (CCHMC). The sample included two males, two females, all 20 yrs. old and African Americans. Patients wore the Empatica E4 wristband for four consecutive days which tracked their movement, blood volume pulse (BPV), heart rate (HR), electrodermal activity (EDA), movement, and skin temperature (ST). They also used the Catch My Pain mobile application to track their pain location, pain intensity, pain descriptors, happiness, stress and fatigue. Regression and machine learning analyses were employed to test the hypothesis that the physiological measures captured by the Empatica could predict changes in the patients’ reported levels of pain intensity across different periods of the day. Linear regression analyses revealed different combinations of significant predictors for each individual patient; these included the average and standard deviation of heart rate, the average maxline and recurrence of skin temperature, average maxline of skin conductance, and average value of blood volume pulse. For the machine learning, three different classification algorithms Linear Regression, Multi-layer Perceptron and Random Forrest significantly predicted pain severity in two of the four patients. In conclusion, the current study demonstrates the potential to detect pain severity through the examination of patterns of changes in physiological signals including heart rate and skin conductance. It provides new insights into the nature of pain experience as unique to each individual patient, and reveals significant potential in developing pain management interventions that are mindful and adaptive to the individual needs and experiences of patients with SCD.