Applying process mining and semantic reasoning for process model customisation in healthcare

Supporting patients and clinicians during the breast cancer care path with AI: The Arianna solution

The onset of cancer disease is a traumatic experience for both patients and their families that suddenly change the patient's life and is accompanied by important physical, emotional, and psycho-social problems. The complexity of this scenario has been exacerbated by the COVID-19 pandemic which dramatically affected the continuity of the provision of optimal care to chronic patients. Telemedicine can support the management of oncology care paths by furnishing a suite of effective and efficient tools to monitor the therapies of cancer patients. In particular, this is a suitable setting for therapies that are administered at home. In this paper, we present an AI-based system, called Arianna, designed and implemented to support and monitor patients treated by the professionals belonging to the Breast Cancer Unit Network (BCU-Net) along the entire clinical path of breast cancer treatment. We describe in this work the three modules composing the Arianna system (the tools for patients and clinicians, and the symbolic AI-based module). The system has been validated in a qualitative way and we demonstrated how the Arianna solution reached a high level of acceptability by all types of end-users by making it suitable for a concrete integration into the daily practice of the BCU-Net.

Prescriptive process monitoring: Quo vadis?

Prescriptive process monitoring methods seek to optimize a business process by recommending interventions at runtime to prevent negative outcomes or address poorly performing cases. In recent years, various prescriptive process monitoring methods have been proposed. This article studies existing methods in this field via a systematic literature review (SLR). In order to structure the field, this article proposes a framework for characterizing prescriptive process monitoring methods according to their performance objective, performance metrics, intervention types, modeling techniques, data inputs, and intervention policies. The SLR provides insights into challenges and areas for future research that could enhance the usefulness and applicability of prescriptive process monitoring methods. This article highlights the need to validate existing and new methods in real-world settings, extend the types of interventions beyond those related to the temporal and cost perspectives, and design policies that take into account causality and second-order effects.

Semantic Modeling Approach Supporting Process Modeling and Analysis in Aircraft Development

With the increasing complexity of aircraft development programs, the development processes of aircraft and their subsystems are continuously becoming complicated, leading to the growing risks of development cost across the entire life cycle. In this study, we proposed a model-based systems engineering approach to support process modeling of aircraft development using a multi-architecture modeling language KARMA. Simultaneously, property verification and hybrid automata simulation were used to implement the static cost analysis of each work task and dynamic cost analysis of the entire development process. Finally, a development process model of aircraft avionics system was created using a case study, in which cost analysis is implemented by the KARMA language. From the result, we found that the KARMA language enables the integration of the process modeling with static and dynamic analyses of the development process in a multi-architecture modeling tool MetaGraph 2.0.

Dynamic Demand-Centered Process-Oriented Data Model for Inventory Management of Hemovigilance Systems

Objectives

This paper presents a reference data model for blood bank management to control blood inventories considering real-world uncertainties and constraints. It helps information systems identify blood product status for various critical decisions (such as replenishment, assignment, and issuing) instantly. Additionally, some significant optimization concepts of the inventory management literature for blood wastage and shortage reduction, such as clearance sale and substitution based on medical priorities, are applied in the model.

Methods

The proposed model was constructed by object-oriented and ICAM (Integrated Computer Aided Manufacturing) definition φ (IDEF0) techniques for function modeling. Through semi-structured questionnaires and interviews, the research team elicited and classified user requirements. Then, the demand-centered sub-processes and comprehensive functions were mapped to manage the process.

Results

The model captures and integrates the top-level features of the inventory system entities. It also provides insights into a developed data dictionary to understand the system’s elements and attributes, where a data item fits in the structure, and what values it may contain. For designing the system’s process and following-up data, the main relevant inputs are considered.

Conclusions

A flexible and applicable demand-centered framework for managing a typical blood bank’s inventory process was developed by focusing on user requirements. The proposed model can be applied to design and monitor inventory information and decision-support systems. The model provides real-time iterative dynamic process insights. It can also provide the data needed for logistic planning systems and the design of blood operational infrastructure.

Mining post-surgical care processes in breast cancer patients

In this work we describe the application of a careflow mining algorithm to detect the most frequent patterns of care in a cohort of 3000 breast cancer patients. The applied method relies on longitudinal data extracted from electronic health records, recorded from the first surgical procedure after a breast cancer diagnosis. Careflows are mined from events data recorded for administrative purposes, including procedures from ICD9 - CM billing codes and chemotherapy treatments. Events data have been pre-processed with Topic Modelling to create composite events based on concurrent procedures. The results of the careflow mining algorithm allow the discovery of electronic temporal phenotypes across the studied population. These phenotypes are further characterized on the basis of clinical traits and tumour histopathology, as well as in terms of relapses, metastasis occurrence and 5-year survival rates. Results are highly significant from a clinical perspective, since phenotypes describe well characterized pathology classes, and the careflows are well matched with existing clinical guidelines. The analysis thus facilitates deriving real-world evidence that can inform clinicians as well as hospital decision makers.

The Business Process Model and Notation Used for the Representation of Alzheimer’s Disease Patients Care Process

Currently, the number of patients with neurological diseases is increasing, especially those older than 65 suffering from Alzheimer’s disease. This development increases the emphasis on understanding and mapping treatment and care processes, not only for the elderly. Service providers (of both treatment and care) are under general pressure to decrease charges and maintain or improve existing levels of care. This situation is significantly influenced by a comprehensive knowledge of the whole process and its values. This publication therefore aims to describe the fundamental procedural aspects of caring for patients with Alzheimer’s disease, using Business Process Model and Notation (BPMN). It also aims to show the possibilities of using BPMN in the description of treatment and care. Modeling of the business process is more frequently being applied not only by businesses but also by scientists involved in process models. It is used to model medical topics, with approximately 10% of its publications only, and most of these publications deal only with clinical pathways, not with overall treatment and care processes. However, the BPMN model allows the whole process of medical and nonmedical care for patients with Alzheimer’s disease to be described, including the decomposition of partial activities into individual threads and sub-processes or atomic tasks. This paper presents the BPMN modeling and mapping of the specific care path for neurodegenerative patients. The text provides a new perspective on the BPMN modeling of Alzheimer’s disease. The presented model offers the option of expanding treatment cost calculation to simulate the process using graphical tools and languages. The overall view of this system creates a much more complex concept of the system and its surroundings.