Process mining in mHealth data analysis

Abstract

This perspective article explores how process mining can extract clinical insights from mobile health data and complement data-driven techniques like machine learning. Despite technological advances, challenges such as selection bias and the complex dynamics of health data require advanced approaches. Process mining focuses on analyzing temporal process patterns and provides complementary insights into health condition variability. The article highlights the potential of process mining for analyzing mHealth data and beyond.

Fig. 1. Data analysis techniques (i.e., machine learning, process mining) for EMA on the first question of the TrackYourTinnitus (TYT) daily 8-question questionnaire.

This figure illustrates the data analysis techniques used for the Ecological Momentary Assessment (EMA) questions (i.e., first question (Q) of TYT daily 8-question questionnaire) in the TYT project. The first technique, 1) machine learning, is employed, among other things for pattern recognition, while 2) process mining is used for process discovery, complementing existing data-driven techniques. This comparison helps in understanding the dynamics of tinnitus symptom reports, showcasing how process mining can reveal - inter alia - process state transitions and symptom changes over time.

Fig. 2. Definition of Ecological Momentary Assessment (EMA) data for process mining.

This figure demonstrates the structure definition of EMA TYT data for the first question (i.e., tinnitus perception with no (0)/yes (1) of the TYT daily 8-question questionnaire for process mining. In this example (see orange area), the user_id functions as the unique case identifier, responses to the first question are represented as activities, and the record creation timestamp offers the essential chronological sequence. Additional elements in the dataset can be interpreted from different perspectives, such as case attributes or event attributes.

Fig. 3. Ecological Momentary Assessment (EMA) data from TYT regarding tinnitus perception visualized as behavioral process map.

This figure presents EMA data from TYT regarding tinnitus perception (i.e., 0 = no, 1 = yes, N/A = not available) visualized as behavioral process map. It highlights key events and transitions in participants' tinnitus perception over time. The process map includes events (1) & (7), nodes (2), dependencies (3), (4), & (5), and statistics (6).

Fig. 4. Other perspectives depicted in process maps.

a Other perspectives depicted in process maps. This figure shows the average number of times participants reported the presence and absence of tinnitus over the course of the TrackYourTinnitus study. Participants reported tinnitus presence (1) an average of 27 times (see red area) and tinnitus absence (0) an average of 7 times (see green area). This data highlights the variability in tinnitus perception among participants. b Other perspectives depicted in process maps. This figure illustrates the time intervals between participants' responses regarding tinnitus perception. It highlights the changes between perceiving and not perceiving tinnitus over a period of days. For example, it appears that changes between tinnitus presence and absence typically occur after 4 or 5 days (see blue area). These temporal insights are crucial for understanding the cyclic nature of tinnitus and can help in tailoring intervention strategies to manage symptoms more effectively.

Fig. 5. Application interface of process discovery regarding tinnitus perception for female and male TrackYourTinnitus (TYT) users.

This figure depicts the application interface of process mining, while analyzing the tinnitus perception between female (i.e., left) and male (i.e., right) users of TYT. The red area represents visualization settings, in which different perspectives and statistics can be chosen (e.g., show different questions from TYT or other frequencies). The green area shows abstraction setting offering changes in the level of granularity for activities and arcs (e.g., show only 50 % of all activities, sorted by low case frequency), whereas the blue area contains specific log information such as number of cases and case variants. Temporal information (e.g., log time frame) are represented in the yellow area. Finally, the purple area shows the behavioral process maps, based on relative frequency, regarding tinnitus perception representing common user journeys between female and male users of TYT.

Fig. 6. Dynamic real-time change of the level of granularity in process maps.

This figure depicts how varying granularity levels in the process map, based on specific criteria like the most common patient journey, can impact the analysis of another question within the TrackYourTinnitus (TYT) data. It shows different granular perspectives by illustrating 50, 75, and 100 % of all activities, as well as 10, 25, and 50 % of all transitions. This approach highlights both the inherent variability and complexity within the data and enables a more targeted examination of the most significant or frequent paths by adjusting the visibility of complexity.

Fig. 7. Process mining dashboard for detailed insights.

This figure shows different statistics in a visual dashboard regarding tinnitus perception for female users of TrackYourTinnitus (TYT). The figure shows descriptive information concerning number of cases, variants, activity instances, and several temporal aspects. Regarding the latter, aspects (e.g., activity frequency over time) are presented, indicating variability in response behavior over time. User specific journeys are shown allowing for an intra- or inter-individual analysis. The figure highlights the application of filters (see black area) based on, for example, attributes (e.g., show only the occurrence of specific activities), temporal (e.g., filter out all activities, which appeared at night) or performance (e.g., retain all cases with a defined threshold for the frequency of activities) aspects.

Fig. 8. Conformance checking to identify deviations in patient journeys.

This figure demonstrates the use of conformance checking to identify deviations in patient journeys from the overall sample. The conformance checking process compares individual patient data to the expected model, identifying consistent behaviors (green), deviations (red), movements (yellow), missing data (grey), and unutilized data (black). This analysis helps to highlight differences in patient behavior, uncovering potential issues such as incorrect treatments or external factors that may influence treatment outcomes. By identifying these patterns, healthcare providers can adjust treatment plans and offer more personalized interventions.