Case-Based Reasoning Paradigm Research Articles

Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning

Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers’ requirements of improving models rather than clinical users’ demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands.

Medical Case Based Reasoning Frameworks

Case-Based Reasoning (CBR) is one of the most suitable AI techniques for building clinical decision support systems. Medical domain complexity introduces many challenges for building these systems. Building the systems' knowledge base from the Electronic Health Record (EHR), the encoding of case-base knowledge with standard medical ontology, and the handling of vague data are examples of these challenges. Although several advantages of using CBR in medicine have been identified, there are no real systems acceptable to physicians. This systematic review examines the current state of CBR and its limitations in the medical domain, especially for diabetes mellitus. The critical evaluation of the status of diabetes CBR systems presents unique opportunities for improving these systems. The literature review covers most of the English language studies extracted from relevant databases by using search terms relating CBR, ontology, Fuzzy, and standard terminology concepts. The authors identify 38 articles published between 1999 and 15 January 2015, which represent original researches in CBR domain. The study includes 15 (39.5%) non-medical studies and 23 (60.5%) medical studies with ~22% for diabetes CBR. A list of 18 integrated evaluation metrics has been proposed and used in the analysis. The results show that the non-medical CBR systems achieved higher advances (50%) than medical systems (42.9%). In addition, the diabetes management CBR systems achieve the lowest advances (21.4%) compared to other systems. These shortages explain the question “why CBR paradigm are not fully utilized in the commercial medical systems?” As a result, there is a distinct need for more comprehensive enhancements in clinical CBR especially diabetes systems.

Metadata support to retrieve and revise solutions in case-based reasoning

Case Based Reasoning (CBR) is a knowledge management approach that consists of the development of decision-support systems where problems are solved by analogy with similar problems solved in the past. In this way, the system supports users in finding solutions without starting from scratch. CBR has become a very important research topic in artificial intelligence, with the definition of methodologies and architectural patterns for supporting developers in the design and implementation of case-based systems. This paper presents one of these frameworks, namely CRePERIE, an on-going research project based on the integration between CBR paradigm and metadata approach to obtain domain-independent case structure and retrieval algorithm definition. The paper focuses on how the developed retrieval strategy can be profitably exploited for the CBR revision step too, according to a substitutional approach.

A Case-Based Approach to Adaptive Hypermedia Navigation

Hypermedia, with its combination of multimedia and non-linear organization of links among informative nodes, provides a highly interactive environment. In structured domains such as Web-based Educational Systems, the complexity of the learning domain often requires a large set of learning nodes and conceptual interrelationships that can cause several issues, e.g.: lack of comprehension, disorientation and inefficacious learning strategies. In this article we propose a new approach to guided navigation in hypermedia-based domains, suitable for helping users in structured and complex learning environments such as cultural heritage domains. Our proposal draws inspiration from the Case-Based Reasoning paradigm associated with a hypermedia structural analysis. In particular, our presentation highlights the use of a hybrid architecture for Adaptive Navigation Support, where the indexing problem of the case-based reasoner is solved by way of a sub-symbolic approach. A case study in the Neo-Realist Italian Cinema domain is discussed along with a formal and controlled evaluation that proves the advantages of the proposed approach.

Intelligent workstation for immediate decision helping in process supervision: A new paradigm ?

We present an application of the case-based reasoning paradigm to a decision-helping for operators in an industrial context. The level of supervision is the highest in the hierarchy and the system helps the operator to remind past situations in order to adapt corresponding supervision strategy to the current situation. Reminding process is based on conceptual distances between the subjects of supervision and refined by a specific situation distance involving events sequence as premisses of the situation. Adaptation uses deep knowledge to instanciate relevant dashboards and views. The knowledge base is issued from the different models describing the system to supervise at the design stage.

Wastewater Treatment Systems from Case–Based Reasoning

Case-Based Reasoning (CBR) is one of the emerging paradigms for designing intelligent systems. Preliminary studies indicate that the area is ripe for theoretical advances and innovative applications. Heuristic search is one of the most widely used techniques for obtaining optimal solutions to many real-world problems. We formulated the design of wastewater treatment systems as a heuristic search problem. In this article we identify some necessary properties of the heuristic search problems to be solved in the CBR paradigm. We designed a CBR system based on these observations and performed several experiments with the wastewater treatment problem. We compare the performance of the CBR system with the A* search algorithm.