Medical datasets are typically affected by issues such as missing values, class imbalance, a heterogeneous feature types, and a high number of features versus a relatively small number of samples, preventing machine learning models from obtaining proper results in classification and regression tasks. This paper introduces AutoML-Med, an Automated Machine Learning tool specifically designed to address these challenges, minimizing user intervention and identifying the optimal combination of preprocessing techniques and predictive models. AutoML-Med's architecture incorporates Latin Hypercube Sampling (LHS) for exploring preprocessing methods, trains models using selected metrics, and utilizes Partial Rank Correlation Coefficient (PRCC) for fine-tuned optimization of the most influential preprocessing steps. Experimental results demonstrate AutoML-Med's effectiveness in two different clinical settings, achieving higher balanced accuracy and sensitivity, which are crucial for identifying at-risk patients, compared to other state-of-the-art tools. AutoML-Med's ability to improve prediction results, especially in medical datasets with sparse data and class imbalance, highlights its potential to streamline Machine Learning applications in healthcare.

In medical process mining, specific domain characteristics have to be dealt with: in particular, in medicine, a significant amount of expert knowledge is typically available; moreover, an interactive approach, letting medical users be involved in the work of process model discovery, is more acceptable than a completely automated strategy. To this end, in our recent work we have defined SIM (Semantic Interactive Miner), an innovative process mining tool able to: (i) support the interaction with medical experts, who can progressively merge parts of the initially mined model, obtaining a more generalized version; (ii) exploit pre-encoded domain knowledge, to move from a model where activities are reported at the ground level to a more user-interpretable high-level version. In this paper we illustrate the features of our tool by showing its application to the case study of neonatal resuscitation simulation: we use SIM to mine the process models produced by two different groups of students of a simulation course, aiming at verifying whether differently skilled young professionals produce different processes, which can finally be compared to the correct guideline.

Logs recording the traces of execution of previous process instances can be exploited for different process management tasks, such as prediction and recommendation in operational support. Efficient retrieval of past traces can be very important to achieve such tasks, while building a model of the process from the log can support problem/anomaly detection and, more generally, process analysis. Trace retrieval is gaining attention in the Case Based Reasoning research community, but so far it has been faced in a completely separate way from the construction of a process model from the log, instead, we propose an approach aiming at integrating these two goals. The core notion of our proposal is the log-tree, which constitutes a "bridge" between the notions of (log) index and process model. We propose a mining algorithm to build it, and an algorithm exploiting it for trace retrieval. Future extensions of our initial contribution are also widely discussed.

Computer Interpretable Guidelines (CIG) are an emerging area of research, to support medical decision making through evidence-based recommendations. However, new challenges in the data management field have to be faced, to integrate CIG management with a proper treatment of patient data, and of other forms of medical knowledge (e.g., causal and behavioral knowledge). In this position paper, we summarize a proposal for a research agenda that, in our opinion, can lead to a significant advancement in the field. The goal of the work is to provide suitable models and reasoning methodologies to cope with the aforementioned aspects, and to properly integrate them for medical decision support. Achieving such a goal requires advances in data management, and, in particular, in the treatment of indeterminate valid-time data in relational databases, of temporal abstraction on time series, of case retrieval on time series, of design-time and run-time model-based verification of guidelines, of case-based reasoning, of non-monotonic logics, of formal ontologies, of probabilistic graphical models (Bayesian Networks and Influence Diagrams).

The cooperative construction of data/knowledge bases has recently had a significant impulse (see, e.g., Wikipedia [1]). In cases in which data/knowledge quality and reliability are crucial, proposals of update/insertion/deletion need to be evaluated by experts. To the best of our knowledge, no theoretical framework has been devised to model the semantics of update proposal/ evaluation in the relational context. Since time is an intrinsic part of most domains (as well as of the proposal/evaluation process itself), semantic approaches to temporal relational databases (specifically, Bitemporal Conceptual Data Model (henceforth, BCDM) [2]) are the starting point of our approach. In this paper, we propose BCDMPV, a semantic temporal relational model that extends BCDM to deal with multiple update/insertion/deletion proposals and with acceptances/rejections of proposals themselves. We propose a theoretical framework, defining the new data structures, manipulation operations and temporal relational algebra and proving some basic properties, namely that BCDMPVis a consistent extension of BCDM and that it is reducible to BCDM. These properties ensure consistency with most relational temporal database frameworks, facilitating implementations.

Supporting decision making in domains in which the observed phenomenon dynamics have to be dealt with, can greatly benefit of retrieval of past cases, provided that proper representation and retrieval techniques are implemented. In particular, when the parameters of interest take the form of time series, dimensionality reduction and flexible retrieval have to be addresses to this end. Classical methodological solutions proposed to cope with these issues, typically based on mathematical transforms, are characterized by strong limitations, such as a difficult interpretation of retrieval results for end users, reduced flexibility and interactivity, or inefficiency. In this paper, we describe a novel framework, in which time-series features are summarized by means of Temporal Abstractions, and then retrieved resorting to abstraction similarity. Our approach grants for interpretability of the output results, and understandability of the (user-guided) retrieval process. In particular, multilevel abstraction mechanisms and proper indexing techniques are provided, for flexible query issuing, and efficient and interactive query answering. Experimental results have shown the efficiency of our approach in a scalability test, and its superiority with respect to the use of a classical mathematical technique in flexibility, user friendliness, and also quality of results.

Studying the interactions between arbuscular mycorrhizal fungi (AMFs) and their symbiotic endo bacteria has potentially strong impacts on the development of new biotechnology applications. The analysis of genomic data and syntenies is a key technique for acquiring information about phylogenetic relationships and metabolic functions of such organisms. In this paper we describe a case-based retrieval tool, which supports customized comparative genomics searches, and which is part of a modular architecture meant to support in-silico genome sequence analysis, being developed within the project BIOBITS. From a methodological viewpoint, the tool takes advantage of an abstraction technique similar to Temporal Abstractions, thus allowing to neglect un-relevant details. Retrieval is made flexible by the use of such multi-level abstractions, and efficient by the use of proper taxonomical index structures. Moreover, end-users are allowed to progressively relax or refine their queries, in an interactive way. A case study taken from the application domain is used to illustrate the approach.

CBR systems designers and developers' research can benefit from the availability of existing platforms, able to provide software design and implementation assistance. The JColibri platform, realized and maintained by the University of Madrid, is one of the most well known among such tools. In this work, we describe a couple of extensions we have provided to the core JColibri open source software. In particular, our extensions are meant to optimize case retrieval performances, in data-rich applications. Specifically, we focused our attention on treating (i) large case bases, in which retrieval time may become unacceptable, and (ii) cases with high-dimensional features - namely time series features - on which proper case representation and retrieval solutions need to be studied. The implemented code has been preliminarly tested, and it is now ready to be integrated with the JColibri code, and made available to the CBR research community. Additional extensions, always dealing with retrieval optimization, are foreseen as our future work.

Despite the recognized advantages that can be obtained in clinical practice when following clinical guidelines (GL), situations of noncompliance with them may emerge. Keeping track of such deviations from the default GL execution, and documenting the physician's motivations, would clearly be an added value. Moreover, repeated alterations of GL actions (or flow) may highlight the need for an adaptation of the GL itself to the local reality, or may even indicate an improper or weak initial GL definition. In this article, we propose an approach for managing noncompliance with GL, based on the case‐based reasoning methodology. In front of a new noncompliance case, our tool allows the physician to retrieve past situations similar to the current one, and to decide whether to reapply the same GL modifications adopted in them. Moreover, the tool is able to learn indications from the ground noncompliance cases that can be deployed for local adaptation, and possibly, for suggesting more formal GL revisions to be carried out by a committee of expert physicians.

In the hemodialysis domain, we are implementing a case‐based, closed‐loop architecture aimed at configuring temporal abstractions (TA), which will be applied to time series data. The advantage of a case‐based approach is the one of “quickly” obtaining a suitable TA parameter configuration, simply by looking at the most similar already configured case, where configured cases are indexed by means of contextual information. The retrieved configuration, together with the time series data, is then used as an input to a TA processing module, able to provide a set of qualitative states, trends, and significant combinations of both as an output. TA processing results can finally be evaluated, possibly leading to a (human‐supervized) reorganization/revision of the case base content, to ameliorate future TA configuration sessions—thus closing the loop. The work is being integrated with RHENE, a system for case‐based retrieval in hemodialysis, able to work both on raw time series data and on preprocessed (by means of TA) ones.

In this paper, we propose a framework for representing and reasoning about qualitative and quantitative temporal constraints between periodic events. In particular, our contribution is twofold: (i) we provide a formalism to deal with both qualitative and quantitative “periodicity-dependent” constraints between repeated events, considering user-defined periodicities as well; and (ii) we propose an intensional approach to temporal reasoning, which is based on the operations of intersection and composition. Such a comprehensive approach, to the best of our knowledge, represents an innovative contribution that integrates and extends results from both the artificial intelligence and the temporal databases literature. © 2009 Wiley Periodicals, Inc.

The aim of this paper is to formally introduce a fuzzy logic based notion of acceptance and similarity among case features, for case matching and retrieval. In particular, we present an approach where local acceptance relative to a feature can be expressed through fuzzy distributions on its domain, abstracting the actual values to linguistic terms. Furthermore, global acceptance is completely grounded on fuzzy logic, by means of the usual combinations of local distributions through specific defined norms. We propose a retrieval architecture, based on the above notions and implemented through a fuzzy extension of SQL.

This paper presents a software tool allowing the automatic analysis of a dynamic fault tree (DFT) exploiting its conversion to a dynamic Bayesian network (DBN). First, the architecture of the tool is described, together with the rules implemented in the tool, to convert dynamic gates in DBNs. Then, the tool is tested on a case of system: its DFT model and the corresponding DBN are provided and analyzed by means of the tool. The obtained unreliability results are compared with those returned by other tools, in order to verify their correctness.

In this work we propose a case-based architecture tackling the problem of configuring and processing temporal abstractions (trends and qualitative states) produced from raw time series data. The parameter configuration is a critical problem in many temporal abstraction processes; in several application domains (especially in medical ones), contextual knowledge plays a fundamental role in the time series interpretation. Since defining the right configuration for each possible contextual situation may be impractical, we propose to adopt a case-based approach, where the suitable configuration can be obtained by looking at the most similar already configured case, with respect to the current situation. Configured cases are indexed by means of contextual information. The obtained configuration can then be used as input to a temporal abstraction module, providing a set of qualitative states, trends and suitable combination of both as a result. Cases can then be exploited in the processing of such results as well, by providing an evaluation of the whole abstraction processing, possibly leading to the revision of the case base. The approach is illustrated by means of an example taken from a medical application, concerning the monitoring and evaluation of patients undergoing hemodialysis treatment

Time‐varying information embedded in cases has often been neglected and its role oversimplified in case‐based reasoning systems. In several real‐world problems, and in particular in medical applications, a case should capture the evolution of the observed phenomenon over time. To this end, we propose to represent temporal information at two levels: (1) at thecase level, when some features are collected in the form of time series, because they describe parameters varying within a period of time (which corresponds to the case duration), and we aim at analyzing the system behavior within the case duration interval itself; (2) at thehistory level, when we are interested in reconstructing the evolution of the system by retrieving temporally related cases. In this paper, we describe a framework for case representation and retrieval that is able to take into account the temporal dimension, and is meant to be used in any time dependent domain, which is particularly well suited for medical applications. To support case retrieval, we provide an analysis of similarity‐based time series retrieval techniques; to support history retrieval, we introduce possible ways to summarize the case content, together with the corresponding strategies for identifying similar instances in the knowledge base. A concrete application of our framework is represented byRhene, a system for intelligent retrieval in the hemodialysis domain.

Supporting therapy selection is a fundamental task for a system for computerized management of clinical guidelines (GL). To this end, decision theory concepts could provide significant advances. In this article, we propose a systematic analysis of the main GL representation primitives and of how they could be related to decision theory concepts. The knowledge representation contribution we provide can be seen as a basis for implementing a decision support tool within any of the systems described in the literature: As a matter of fact, at a sufficiently abstract level, the GL primitives we treat are shared by all of the systems. Such a tool could be adopted when executing a GL on a single patient (in clinical practice) and for simulation purposes. In particular, a decision theory tool based on this analysis is being implemented in the GLARE system. © 2006 Wiley Periodicals, Inc. Int J Int Syst 21: 585–599, 2006.

In this paper, we focus on an application and extension of artificial intelligence temporal reasoning techniques in order to represent and reason with temporal constraints in clinical guidelines. Particular attention is dedicated to the treatment of repeated (periodic) events, which play a major role in clinical therapies. We also discuss some limitations of our current approach, highlighting possible future enhancements. The work in this paper has been developed in the GLARE project, meant to realize a prototype of a domain-independent manager of clinical guidelines. The GLARE system has been built in cooperation with Azienda Ospedaliera S. Giovanni Battista of Turin, and has been successfully tested on different clinical domains.