Acromegaly is a rare disease characterized by a diagnostic delay ranging from 5 to 10 years from the symptoms' onset. The aim of this study was to develop and internally validate machine-learning ...algorithms to identify a combination of variables for the early diagnosis of acromegaly. This retrospective population-based study was conducted between 2011 and 2018 using data from the claims databases of Sicily Region, in Southern Italy. To identify combinations of potential predictors of acromegaly diagnosis, conditional and unconditional penalized multivariable logistic regression models and three machine learning algorithms (i.e., the Recursive Partitioning and Regression Tree, the Random Forest and the Support Vector Machine) were used, and their performance was evaluated. The random forest (RF) algorithm achieved the highest Area under the ROC Curve value of 0.83 (95% CI 0.79-0.87). The sensitivity in the test set, computed at the optimal threshold of predicted probabilities, ranged from 28% for the unconditional logistic regression model to 69% for the RF. Overall, the only diagnosis predictor selected by all five models and algorithms was the number of immunosuppressants-related pharmacy claims. The other predictors selected by at least two models were eventually combined in an unconditional logistic regression to develop a meta-score that achieved an acceptable discrimination accuracy (AUC = 0.71, 95% CI 0.66-0.75). Findings of this study showed that data-driven machine learning algorithms may play a role in supporting the early diagnosis of rare diseases such as acromegaly.
A current research problem in the area of business process management deals with the specification and checking of constraints on resources (e.g., users, agents, autonomous systems, etc.) allowed to ...be committed for the execution of specific tasks. Indeed, in many real-world situations, role assignments are not enough to assign tasks to the suitable resources. It could be the case that further requirements need to be specified and satisfied. As an example, one would like to avoid that employees that are relatives are assigned to a set of critical tasks in the same process in order to prevent fraud. The formal specification of a business process and its related access control constraints is obtained through a decoration of a classic business process with roles, users, and constraints on their commitment. As a result, such a process specifies a set of tasks that need to be executed by authorized users with respect to some partial order in a way that all authorization constraints are satisfied. Controllability refers in this case to the capability of executing the process satisfying all these constraints, even when some process components, e.g., gateway conditions, can only be observed, but not decided, by the process engine responsible of the execution. In this paper, we propose
conditional constraint networks with decisions (CCNDs)
as a model to encode business processes that involve access control and conditional branches that may be both controllable and uncontrollable. We define weak, strong, and dynamic controllability of CCNDs as two-player games, classify their computational complexity, and discuss strategy synthesis algorithms. We provide an encoding from the business processes we consider here into CCNDs to exploit off-the-shelf their strategy synthesis algorithms. We introduce
Z
E
T
A
, a tool for checking controllability of CCNDs, synthesizing execution strategies, and executing controllable CCNDs, by also supporting user interactivity. We use
Z
E
T
A
to compare with the previous research, provide a new experimental evaluation for CCNDs, and discuss limitations.
A Flexible Simple Temporal Network with Uncertainty (FTNU) represents temporal constraints between time-points. Time-points are variables that must be set (executed) satisfying all the constraints. ...Some time-points are contingent. It means that they are set by the environment and only observed by the system executing the network. The ranges representing temporal constraints associated with contingent time-points (guarded ranges) can be shrunk during execution only to some extent to have more flexibility in the execution of the network. Subsets of time-points/constraints may be executed/considered in different contexts according to some observed conditions. The main issue here consists of determining whether all the time-points, under the control of the system, are executable in a way that all the specified constraints are satisfied for any possible occurrence of contingent time-points and any possible context. Such property is called controllability. Even though an algorithm was proposed for checking the controllability of such networks, we show that such an algorithm has a limit. Indeed, it does not determine the right bounds for guarded links, and, therefore, it doesn’t permit the system to exploit the potential flexibility of the network. We then propose a new constraint-propagation algorithm for checking controllability, prove that such a new algorithm determines the right guarded ranges, and it is sound-and-complete. Thus, it can be used also for executing the network, by leveraging its flexibility.
Managing temporal process constraints in modularized processes is an important task, both during the design, as it allows the reuse of temporal (child) process models, and during the checking of ...temporal properties of processes, as it avoids the necessity of “unfolding” child processes within the main process model. Taking into account the capability of providing modular solutions, modeling and checking temporal features of processes is still an open problem in the context of process-aware information systems.
In this paper, we present and discuss a novel approach to represent flexible temporal constraints in modularized time-aware BPMN process models.
To support temporal flexibility, allowed task durations are represented through guarded ranges that allow a limited (guarded) restriction of task durations during process execution if it is necessary to guarantee the satisfaction of all temporal constraints. We, then, propose how to derive a compact representation of the overall temporal behavior of such time-aware BPMN models. Such compact representation of child processes allows us to check the dynamic controllability (DC) of a parent time-aware process model without “unfolding” the child process models. Dynamic controllability guarantees that process models can have process instances (i.e., executions) satisfying all the temporal constraints for any possible combination of allowed durations of tasks and child processes. Possible approaches for even more flexibility by solving some kinds of DC violations are then introduced.
We use a real process model from a healthcare domain as a motivating example, and we also present a proof-of-concept prototype confirming the concrete applicability of the solutions we propose, followed by an experimental evaluation.
Highlights • This editorial contains some observations, comments, and desiderata about journal Artificial Intelligence in Medicine (AIIM). • It summarizes what artificial intelligence in medicine is ...about. • The specific role and focus of AIIM is highlighted. • Details about the slightly modified editorial organization of the journal are provided. • This editorial summarizes the publication process and underlines the importance of high level reviews.
Developing countries need telemedicine applications that help in many situations, when physicians are a small number with respect to the population, when specialized physicians are not available, ...when patients and physicians in rural villages need assistance in the delivery of health care. Moreover, the requirements of telemedicine applications for developing countries are somewhat more demanding than for developed countries. Indeed, further social, organizational, and technical aspects need to be considered for successful telemedicine applications in developing countries.
We consider all the major projects in telemedicine, devoted to developing countries, as described by the proper scientific literature. On the basis of such literature, we want to define a specific taxonomy that allows a proper classification and a fast overview of telemedicine projects in developing countries. Moreover, by considering both the literature and some recent direct experiences, we want to complete such overview by discussing some design issues to be taken into consideration when developing telemedicine software systems.
We considered and reviewed the major conferences and journals in depth, and looked for reports on the telemedicine projects.
We provide the reader with a survey of the main projects and systems, from which we derived a taxonomy of features of telemedicine systems for developing countries. We also propose and discuss some classification criteria for design issues, based on the lessons learned in this research area.
We highlight some challenges and recommendations to be considered when designing a telemedicine system for developing countries.
Summary
Objectives
: This survey aims at reviewing the literature related to Clinical Information Systems (CIS), Hospital Information Systems (HIS), Electronic Health Record (EHR) systems, and how ...collected data can be analyzed by Artificial Intelligence (AI) techniques.
Methods
: We selected the major journals (11 journals) collecting papers (more than 7,000) over the last five years from the top members of the research community, and read and analyzed the papers (more than 200) covering the topics. Then, we completed the analysis using search engines to also include papers from major conferences over the same five years.
Results
: We defined a taxonomy of major features and research areas of CIS, HIS, EHR systems. We also defined a taxonomy for the use of Artificial Intelligence (AI) techniques on healthcare data. In the light of these taxonomies, we report on the most relevant papers from the literature.
Conclusions
: We highlighted some major research directions and issues which seem to be promising and to need further investigations over a medium- or long-term period.
Telemedicine for Developing Countries Combi, Carlo; Pozzani, Gabriele; Pozzi, Giuseppe
Applied clinical informatics,
10/2016, Letnik:
7, Številka:
4
Journal Article
Recenzirano
Odprti dostop
Summary
Background
Developing countries need telemedicine applications that help in many situations, when physicians are a small number with respect to the population, when specialized physicians are ...not available, when patients and physicians in rural villages need assistance in the delivery of health care. Moreover, the requirements of telemedicine applications for developing countries are somewhat more demanding than for developed countries. Indeed, further social, organizational, and technical aspects need to be considered for successful telemedicine applications in developing countries.
Objective
We consider all the major projects in telemedicine, devoted to developing countries, as described by the proper scientific literature. On the basis of such literature, we want to define a specific taxonomy that allows a proper classification and a fast overview of telemedicine projects in developing countries. Moreover, by considering both the literature and some recent direct experiences, we want to complete such overview by discussing some design issues to be taken into consideration when developing telemedicine software systems.
Methods
We considered and reviewed the major conferences and journals in depth, and looked for reports on the telemedicine projects.
Results
We provide the reader with a survey of the main projects and systems, from which we derived a taxonomy of features of telemedicine systems for developing countries. We also propose and discuss some classification criteria for design issues, based on the lessons learned in this research area.
Conclusions
We highlight some challenges and recommendations to be considered when designing a telemedicine system for developing countries.
Citation
: Combi C, Pozzani G, Pozzi G. Telemedicine for developing countries: a survey and some design issues.
Highlights • Fifteen Artificial Intelligence in MEdicine (AIME) conferences have been organized over the last 30 years. • We review the main research themes and investigate their scientific impact. • ...Knowledge engeering for medical expert systems dominated the first decade of AIME, while machine learning and data mining prevailed thereafter. • The work on guidelines and protocols has been highly cited, followed by temporal information management and machine learning/data mining. • Promising directions for future research are Big Data, personalized medicine, Evidence Based Medicine, business process modeling, process mining and NLP in social media.