Towards a Compliance Support Framework for Adaptive Case Management

Enabling flexibility in unpredictable situations with ad hoc actions decided at runtime by knowledge workers is the main focus of Adaptive Case Management (ACM) systems. However, ad hoc actions added during case execution and ACM templates prepared at design time need to be within the boundaries defined by business constraints, company regulations and legal systems. In this paper we report our experience in addressing this challenge by using model checking and runtime monitoring techniques for behavioral consistency checking that can handle both ACM aspects: support by means of predefined process templates and high flexibility by allowing ad hoc actions at runtime. Our study is conducted using a practical ACM system for repair service management handling different customer requirements under diverse compliance and law regulations.

The paper outlines the recent trends in the evolution of adaptive case management (ACM). One such trend is for ACM systems to increasingly often include, besides decision support and knowledge management, functionalities that are typical of group work support or social networking. A social ACM (SACM) connects knowledge workers within a collaborative environment and brings business cases, along with supporting components, into a social space, thus turning them into elements of a social network. In addition, SACM offers mechanisms to capture and formalize feedback and interactions. The paper seeks to illustrate ways in which modern-day social networking technology and existing social networks can be exploited by businesses. Since ACM is commonly incorporated into decision support systems (DSS), the paper also attempts to explore the evolution of ACM and DSS from an architectural perspective, making a reference to the DSS architecture described in a prior article by these same authors [1].

As the demand for the modeling of knowledge intensive processes grows, so does the necessity to support this task by appropriate models. Adaptive Case Management (ACM) was proposed as appropriate, whereas still confined mostly to theoretical work. This paper compares the execution of BPM process models to ACM models by applying agent based simulations to different processes based on support case handling. The simulation tools applied to the ACM process models were developed in the course of this work. The greater flexibility of ACM models is found to be more effective in processing executions with competent knowledge workers. Another key observation is the possible improvement of average case duration due to parallelization effects.

Adaptive Case Management (ACM) is information technology for the secure and transparent management of structured and unstructured business processes, consisting of data, content, related work tasks and rules executed towards well-defined process goals. Thus, it goes beyond combining benefits of workflow diagrams with ad-hoc task mechanisms. One of the notorious weaknesses of classical workflow technology is the experts’ effort for getting a sufficiently complete specification of the process to create an executable which typically takes several months. In contrast, ACM provides goal-oriented mechanisms to enable performers to define and execute work tasks ad-hoc. In this paper, based on the definition of the ACM concepts, we analyze which setup steps have to be conducted for an ACM system in a typical scenario from the service industry. Our contribution is an identification of major factors that influence the setup initiated by experts and the maintenance performed by business users.

Adaptive case management addresses the shift away from the prescriptive process-centric view of operations towards a declarative framework for operational descriptions that promotes dynamic task selection in knowledge-intensive operations. A key difference between prescriptive services and declarative services is the way by which control flow is defined. Repeatable and straight-thru processes have been successfully used to model and optimise simple activity-based value chains. Increasingly, traditional process modeling techniques are being applied to knowledge intensive activities with often poor outcomes. By taking an adaptive case management approach to knowledge-intensive services, it is possible to model and execute workflows such as medical protocols that have previously been too difficult to describe with typical BPM frameworks. In this chapter, the authors describe an approach to design-level adaptive case management leveraging off existing repositories' semantically annotated business process models.

Knowledge-intensive Processes are difficult to support by traditional workflow oriented Business Process Management approaches. Reasons lie in in ad-hoc decisions and unpredictable workflows that come with them. Adaptive Case Management (ACM) is a paradigm for the management of knowledge-intensive processes that has recently drawn attention in industry and the scientific community. This development led to the standardization of CMMN as a notation for process models for the ACM implementation. This study assess the availability of method support for the use of ACM and the fitness of CMMN for fulfilling the modeling requirements in this context based on a systematic literature review. As a result missing method support, CMMN shortcomings as well as suggestions for the implementation of ACM in combination with CMMN are discussed.

An adaptive case management system to support integrated care services: Lessons learned from the NEXES project

A Concept for an Adaptive Case Management System Supporting the Incident Management Process

Implementation of an Adaptive Case Management System Supporting the Incident Management Process in ABAP-Based SAP Systems

The emergency responses required during large-scale crises or disasters are extremely knowledge-intensive processes and are usually characterized by a high degree of unpredictability and unrepeatability. An emergency response is mission- and time-critical, unstructured, very dynamic, and it is very difficult to predefine or even to anticipate all possible response scenarios. Therefore, designing and implementing a software system to support such a response system is highly complicated and challenging. This research aims to investigate and discuss how Adaptive Case Management (ACM) can be leveraged in the design and implementation of a case-based emergency response system. In particular, this research considers the best practices of the National Incident Management System (NIMS), which is an essential part of the National Response Framework (NRF) developed in the United States. As a proof-of-concept, a prototype demonstration has been carried out on a leading commercial ACM platform. In addition, a walkthrough scenario is discussed to elaborate how ACM can support emergency response activities in real settings using the Incident Command System (ICS) organizational structure. The key benefit of this research is to guide the development and implementation of cased-based emergency response systems with a flexible and agile approach.

Adaptive Case Management (ACM) is a new paradigm to support dynamic business processes that are mainly unpredictable and knowledge-intensive. However, fundamental knowledge about this approach is currently scattered across a series of collective volumes and web blogs that tend to focus on isolated aspects or domain-specific challenges and solution approaches. As the ongoing discussion still lacks comprehensive theoretical literature, principles are driven mostly by individual circumstances and common ideas are not transparent. Therefore, the paper at hand provides a structured, domain-independent overview about the common principles in ACM and derives a set of distinct challenges in order to contribute to the general understanding of this paradigm. This work consolidates existing literature and subsequently focuses on the implied role of collaboration. To complement the theoretical discussion, a reference implementation demonstrates the key concepts.

The aim of the study was to investigate the application and importance of Learning and Adaptive Management by the Ministry of Women Affairs, Community, Small and Medium Enterprises Development (MWACSMED) and beneficiaries when implementing development programs in Zaka district. The study investigated the objectives of the programs implemented by MWACSMED in Zaka district, the extent to which learning, risk management and adaptive management mechanisms are used by MWACSMED Zaka district are effective. The study also examined the challenges faced MWACSMED and beneficiaries with development programs in Zaka district. The study also aimed at developing a model for learning, risk management, adaptive management, monitoring, and evaluation for the efficient and effective implementation of development programs and the Monitoring, Evaluation, Learning, Adaptive and Risk Management model (MELARM) was developed. The researcher chose to conduct his research in this area because Zaka district is one of the districts in the country that is heavily reliant on subsistence farming, with farmers lacking adequate rain and inputs. Furthermore, there is no other industry or activity in the district that contributes to people's well-being. According to Chingarande and Matondi (2020:3), Zaka district is in a province that is reliant on activities such as livestock production, irrigated farming, wildlife conservation and smallholder agricultural production to support its population. Zimbabwe, where Zaka district is in the province of Masvingo used to be one of Southern Africa’s most vibrant, productive, and resilient countries, but the country has been facing economic and political challenges for close to two decades linked to decades of poor governance and corruption. Approximately 63% of Zimbabwean households are living in poverty and 16% in extreme poverty (USAID Country Development Cooperation Strategy 2016-2021:4). Given the above challenges in Zimbabwe, it is important to investigate whether decisionmakers are investing in long-term management approaches such as Adaptive Management. Decision-makers tend to be reluctant to invest in long-term management approaches which cover the concept of Adaptive Management and choose small-scale experiments instead. Moreover, they do not utilize opportunities to adjust and make improvements in their approach to management. Managers have often been making decisions based on funding opportunities that are short-term and political requests, rather than using the actual objectives of a program. The study used the quantitative approach in the form of a questionnaire that was designed using Google forms and shared through a link that was send to research participants through emails and WhatsApp. The sample population for the research questionnaire was 10 officials from MWACSMED and 7 beneficiaries of the programs managed by the Ministry in Zaka district. As shown by the study, the Ministry has not yet fully recognized the use of Learning and Adaptive Management to address the complexity and uncertainty of development programs. The Ministry has been managing programs through traditional monitoring and evaluation systems. The results of the study show that the Ministry was not using Adaptive Management approaches or learning thorough monitoring and evaluation systems, which may be because of socio-economic and political reasons. The introduction of adaptive programming and management calls for using information and learning to inform adjustments during implementation, which requires monitoring and evaluation systems that go beyond reporting on pre-specified indicators The study made recommendations for Learning and Adaptive Management mechanisms that are essential for development projects. The study also drafted a model known as the Monitoring, Evaluation, Learning, Adaptive and Risk Management Framework (MELARM). These recommendations are all based on the findings of the study. In general, government departments should avoid traditional thinking about program cycles, and they should merge program design, implementation, and evaluation through Learning and Adaptive Management. Government departments/agencies should also identify and document how procurement, contracting, work planning, reporting and risk management can foster adaptive programming and management to achieve intended development goals.

Traditional BPM systems perform well with structured processes and controlled interactions between participants. However, most business functions involve both structured processes with ad hoc activities, and can range from topdown delegation to social collaboration. A key trend in business is the increased focus on knowledge worker productivity as the routine work becomes more automated, which has led to fragmentation of the BPM market: in addition to traditional BPM systems, a new breed of adaptive case management (ACM) systems manage unstructured processes, collaboration is taking hold both in process design and runtime environments, and user interfaces are borrowing from social media to put a new face on BPM. But do the differences between structured and unstructured process management, or between authoritarian and collaborative interactions, warrant the use of different types of systems? Or do they just represent different parts of a spectrum of process functionality? How can they best be combined to manage a broad variety of business process types? What types of hybrid process systems will emerge to match these business needs?.

Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.

Purpose of ReviewTheoretical frameworks for adaptive natural resource management are quite common, whereas documented examples showing successful implementation of adaptive management and learning through multiple time intervals have remained uncommon. Measures of quality of adaptive natural resource management processes are needed to examine potential factors driving the successful implementation. To address this gap, we developed a multimetric index composed of 22 metrics to assess quality of case studies using quantitative decision support (QDS) to inform adaptive forest management (AFM). Metrics represented three main tasks, including conceptual setup, modeling, and application. We further distinguished these into subtasks: definition of objectives and management options (setup); specifying uncertainty, prediction, and optimization (modeling); and stakeholder involvement along with practice and learning (application). We used a multimetric index to examine temporal and geographic variation in quality of reviewed case studies using QDS to inform AFM. We then conducted a structured literature review of 179 articles, wherein 34 case studies met a priori criteria.Recent FindingsWhen applying the multimetric index to these case studies, we found that over the past decade the index has been intermediate and annual average scores declined by 33% from 4.5 to 3.0 of 10 (where 10 is the highest possible quality score). Aligning with reviews of adaptive natural resource management, reported on-ground application of QDS to inform AFM was rare (n = 2). We also confirmed the expectation that there has been a substantial lack of stakeholder engagement during QDS development tasks.SummaryOur multimetric index provides a novel tool to examine gaps in the use of QDS for adaptive management in diverse domains including but not limited to forests.