Modeling and reasoning over business processes require enterprises to manage and integrate large amounts of information. Despite process designers and engineers may benefit from a unified view of ...process and data models, integrating these two perspectives is challenging, especially when considering conceptual models. In this article, we provide a uniform formal representation of a process model, the schema of a related database, and the data operations connecting them. Then, we show how we can use such a formal representation to identify interesting information during the integrated conceptual modeling and analysis of processes and related databases, from a process (re-)design and improvement perspective. Finally, we discuss the evaluation of the proposed approach through a controlled experiment and a proof-of-concept implementation that considers both relational and XML database technologies.
Acute Kidney Injury is a severe clinical condition with a high risk of multi-organs complications and mortality. For this reason, early recognition is crucial. Our proposal based on a 3-window ...framework discovers all hidden regularities, called Approximate Predictive Functional Dependencies, with the aim to enable early recognition of high-risk patients during hospitalization in the Intensive Care Unit (ICU). We evaluated the different severity stages according to the Kidney Disease Improving Global Outcomes (KDIGO) guidelines, building different pathological state patterns, from admission to the discharge from ICU. According to the clinical practice, for each patient, we examined various characteristics expressed as a temporal history of events that may predict a pathological state pattern. We evaluated our proposal exploiting the MIMIC-IV dataset, a collection of Electronic Medical Records from ICU. The obtained results showed promising possibilities to use this type of dependency to support clinical practice.
The modeling and management of business processes deals with temporal aspects both in the inherent representation of activity coordination and in the specification of activity properties and ...constraints. In this paper, we address the modeling and specification of constraints related to the duration of process activities. In detail, we consider the Business Process Model and Notation (BPMN) standard and propose an approach to define re-usable duration-aware process models that make use of existing BPMN elements for representing different nuances of activity duration at design time. Moreover, we show how advanced event-handling techniques may be exploited for detecting the violation of duration constraints during the process run-time. The set of process models specified in this paper suitably captures duration constraints at different levels of abstraction, by allowing designers to specify the duration of atomic tasks and of selected process regions in a way that is conceptually and semantically BPMN-compliant. Without loss of generality, we refer to real-world clinical working environments to exemplify our approach, as their intrinsic complexity makes them a particularly challenging and rewarding application environment.
•We represent different kinds of duration constraints through re-usable BPMN process models.•The presented processes provide a clear conceptualization of duration-aware process activities.•A formal description of the proposed patterns is provided along with real-world motivating examples.•Being fully BPMN-compliant, the proposed approach benefits of existing tool support.•The soundness of the obtained process models is verified by mapping them to time Petri nets.
Conditional simple temporal networks with uncertainty (CSTNUs) allow for the representation of temporal plans subject to both conditional constraints and uncertain durations. Dynamic ...controllability (DC) of CSTNUs ensures the existence of an execution strategy able to execute the network in real time (i.e., scheduling the time points under control) depending on how these two uncontrollable parts behave. However, CSTNUs do not deal with resources. In this paper, we define conditional simple temporal networks with uncertainty and resources (CSTNURs) by injecting resources and runtime resource constraints (RRCs) into the specification. Resources are mandatory for executing the time points and their availability is represented through temporal expressions, whereas RRCs restrict resource availability by further temporal constraints among resources.
We provide a fully-automated encoding to translate any CSTNUR into an equivalent timed game automaton in polynomial time for a sound and complete DC-checking.
Extracting association rules from large datasets has been widely studied in many variants in the last two decades; they allow to extract relations between values that occur more “often” in a ...database. With temporal association rules the concept has been declined to temporal databases. In this context the “most frequent” patterns of evolution of one or more attribute values are extracted. In the temporal setting, especially where the interference betweeen temporal patterns cannot be neglected (e.g., in medical domains), there may be the case that we are looking for a set of temporal association rules for which a “significant” portion of the original database represents a consistent model for all of them. In this work, we introduce a simple and intuitive form for temporal association rules, called pure evolving association rules (PE-ARs for short), and we study the complexity of checking a set of PE-ARs over an instance of a temporal relation under approximation (i.e., a percentage of tuples that may be deleted from the original relation). As a by-product of our study we address the complexity class for a general problem on Directed Acyclic Graphs which is theoretically interesting per se.
The rapid increase of interest in, and use of, artificial intelligence (AI) in computer applications has raised a parallel concern about its ability (or lack thereof) to provide understandable, or ...explainable, output to users. This concern is especially legitimate in biomedical contexts, where patient safety is of paramount importance. This position paper brings together seven researchers working in the field with different roles and perspectives, to explore in depth the concept of explainable AI, or XAI, offering a functional definition and conceptual framework or model that can be used when considering XAI. This is followed by a series of desiderata for attaining explainability in AI, each of which touches upon a key domain in biomedicine.
•AI in Medicine becomes increasingly ubiquitous, with new concerns and questions:•How does an AI algorithm work — what is it doing?•Does an AI system work as well as an expert?•Does an AI system do what a user would do, were she in the same situation?•Why cannot the system tell a user how it arrived at a conclusion or made a decision?•Here, we deal with the need to address gaps in the explainability of AI in Medicine.
A Simple Temporal Network (STN) consists of time points modeling temporal events and constraints modeling the minimal and maximal temporal distance between them. A Simple Temporal Network with ...Decisions (STND) extends an STN to model temporal plans with decisions. STNDs label time points and constraints by conjunctions of literals saying for which scenarios (i.e., complete truth value assignments to the propositions) they are relevant. In this paper, we deal with the use of STNDs for modeling and synthesizing execution strategies. We propose an incremental hybrid SAT-based consistency checking algorithm for STNDs that is faster than the one previously proposed and allows for the synthesis of all consistent scenarios and related early execution schedules (offline temporal planning). We carry out an experimental evaluation with Kappa, a tool that we developed for STNDs. We also show that any STND can be easily translated into a disjunctive temporal network and vice versa.
Temporal functional dependencies add valid time to classical functional dependencies in order to express data integrity constraints over the flow of time. If the temporal dimension adopted is an ...interval, we have to deal with interval-based temporal functional dependencies (ITFDs for short), which consider different interval relations between tuple valid times. The related approximate problem is when we want to check whether our data satisfy, without any constraint for the schema, a given ITFD under a given error threshold
0
⩽
ϵ
⩽
1
. This can be rephrased as: given a relation instance
r
, is it possible to delete at most
ϵ
·
|
r
|
tuples from it in such a way that the resulting instance satisfies the given ITFD? This optimization problem,
ITFD-Approx
for short, may represent a way to discover (i.e., mine) important dependencies among attribute values in a database. In this paper we analyze the complexity of problem
ITFD-Approx
restricting ourselves to Allen’s interval relations: we shall see how the complexity of such a problem may significantly change, depending on the considered interval relation.
Time is a vital facet of every human activity. Data warehouses, which are huge repositories of historical information, must provide analysts with rich mechanisms for managing the temporal aspects of ...information. In this paper, we (i) propose T+MultiDim, a multidimensional conceptual data model enabling both instant- and interval-based semantics over temporal dimensions, and (ii) provide suitable OLAP (On-Line Analytical Processing) operators for querying temporal information. T+MultiDim allows one to design typical concepts of a data warehouse including temporal dimensions, and provides one with the new possibility of conceptually connecting different temporal dimensions for exploiting temporally aggregated data. The proposed approach allows one to specify and to evaluate powerful OLAP queries over information from data warehouses. In particular, we define a set of OLAP operators to deal with interval-based temporal data. Such operators allow the user to derive new measure values associated to different intervals/instants, according to different temporal semantics. Moreover, we propose and discuss through examples from the healthcare domain the SQL specification of all the temporal OLAP operators we define.
This book constitutes the refereed proceedings of the 13th Conference on Artificial Intelligence in Medicine, AIME 2011, held in Bled, Slovenia, in July 2011.The 42 revised full and short papers ...presented together with 2 invited talks were carefully reviewed and selected from 113 submissions. The papers are organized in topical sections on knowledge-based systems; data mining; special session on AI applications; probabilistic modeling and reasoning; terminologies and ontologies; temporal reasoning and temporal data mining; therapy planning, scheduling and guideline-based care; and natural language processing.