Length of stay prediction for clinical treatment process using temporal similarity

In clinical treatment processes, inpatient length of stay (LOS) is not only a readily available indicator of hospital activity, but also a reasonable proxy of resource consumption. Accurate inpatient LOS prediction has strong implications for health service delivery. Major techniques proposed (statistical approaches or artificial neuronal networks) consider a priori knowledge, such as demographics or patient physical factors, providing accurate methods to estimate LOS at early stages of the patient (admission). However, unexpected scenarios and variations are commonplaces of clinical treatment processes that have a dramatical impact on the LOS. Therefore, these predictors should deal with adaptability, considering the temporal evolution of the patient. In this paper, we propose an inpatient LOS prediction approach across various stages of clinical treatment processes. This proposal relies on a kind of regularity assumption demanding that patient traces of the specific treatment process with similar medical behaviors have similar LOS. Therefore, this approach follows a Case-based Reasoning methodology since it predicts an inpatient LOS of a partial patient trace by referring to the past traces of clinical treatment processes that have similar medical behaviors with the current one. The proposal is evaluated using 284 patient traces from the pulmonary infection CTPs, extracted from Zhejiang Huzhou Central Hospital of China.     

Reprint of “Length of stay prediction for clinical treatment process using temporal similarity”

In clinical treatment processes, inpatient length of stay (LOS) is not only a readily available indicator of hospital activity, but also a reasonable proxy of resource consumption. Accurate inpatient LOS prediction has strong implications for health service delivery. Major techniques proposed (statistical approaches or artificial neuronal networks) consider a priori knowledge, such as demographics or patient physical factors, providing accurate methods to estimate LOS at early stages of the patient (admission). However, unexpected scenarios and variations are common places of clinical treatment processes that have a dramatical impact on the LOS. Therefore, these predictors should deal with adaptability, considering the temporal evolution of the patient. In this paper, we propose an inpatient LOS prediction approach across various stages of clinical treatment processes. This proposal relies on a kind of regularity assumption demanding that patient traces of the specific treatment process with similar medical behaviors have similar LOS. Therefore, this approach follows a Case-based Reasoning methodology since it predicts an inpatient LOS of a partial patient trace by referring to the past traces of clinical treatment processes that have similar medical behaviors with the current one. The proposal is evaluated using 284 patient traces from the pulmonary infection CTPs, extracted from Zhejiang Huzhou Central Hospital of China.     

Intrusion detection for mobile devices using the knowledge-based, temporal abstraction method

In this paper, a new approach for detecting previously unencountered malware targeting mobile device is proposed. In the proposed approach, time-stamped security data is continuously monitored within the target mobile device (i.e., smartphones, PDAs) and then processed by the knowledge-based temporal abstraction (KBTA) methodology. Using KBTA, continuously measured data (e.g., the number of sent SMSs) and events (e.g., software installation) are integrated with a mobile device security domain knowledge-base (i.e., an ontology for abstracting meaningful patterns from raw, time-oriented security data), to create higher level, time-oriented concepts and patterns, also known as temporal abstractions. Automatically-generated temporal abstractions are then monitored to detect suspicious temporal patterns and to issue an alert. These patterns are compatible with a set of predefined classes of malware as defined by a security expert (or the owner) employing a set of time and value constraints. The goal is to identify malicious behavior that other defensive technologies (e.g., antivirus or firewall) failed to detect. Since the abstraction derivation process is complex, the KBTA method was adapted for mobile devices that are limited in resources (i.e., CPU, memory, battery). To evaluate the proposed modified KBTA method a lightweight host-based intrusion detection system (HIDS), combined with central management capabilities for Android-based mobile phones, was developed. Evaluation results demonstrated the effectiveness of the new approach in detecting malicious applications on mobile devices (detection rate above 94% in most scenarios) and the feasibility of running such a system on mobile devices (CPU consumption was 3% on average).     

Expert system problem selection: A domain characteristics approach

The first generation of commercial expert systems based on AI technology are now available in the market place. But in the available literature, one can find hardly any material on expert system problem selection. In this paper a number of popular and successful expert systems are analyzed. Domain-dependent and domain-independent problem characteristics have been identified, based on the analysis. To test our contention that these characteristics significantly contribute to the success of expert systems, a questionnaire survey involving a number of expert system developers was conducted. Based on this, a domain characteristic approach for expert system problem selection is presented.     

Computing the minimal relations in point-based qualitative temporal reasoning through metagraph closure

Computing the minimal representation of a given set of constraints (a CSP) over the Point Algebra (PA) is a fundamental temporal reasoning problem. The main property of a minimal CSP over PA is that the strongest entailed relation between any pair of variables in the CSP can be derived in constant time. We study some new methods for solving this problem which exploit and extend two prominent graph-based representations of a CSP over PA: the timegraph and the series-parallel (SP) metagraph. Essentially, these are graphs partitioned into sets of chains and series-parallel subgraphs, respectively, on which the search is supported by a metagraph data structure. The proposed approach is based on computing the metagraph closure for these representations, which can be accomplished by some methods studied in the paper.In comparison with the known techniques based on enforcing path consistency, under certain conditions about the structure of the input CSP and the size of the generated metagraph, the proposed metagraph closure approach has better worst-case time and space complexity. Moreover, for every sparse CSP over the convex PA, the time complexity is reduced to O(n²) from O(n³), where n is the number of variables involved in the CSP.An extensive experimental analysis presented in the paper compares the proposed techniques and other known algorithms. These experimental results identify the best performing methods and show that, in practice, for CSPs exhibiting chain or SP-graph structure and randomly generated (both sparse and dense) CSPs, the metagraph closure approach is significantly faster than the approach based on enforcing path consistency.     

Towards a temporal coherence management in real-time knowledge-based systems

The multi-agent system paradigm emerges as an interesting approach in the Knowledge-Based System (KBS) field when distributed problem-solving techniques are required. On the other hand, temporal representation and reasoning problems arise in a wide range of KBS application areas where time plays a crucial role. In this paper, we show that when agents run concurrently and access common temporal data, some problems of coherence arise. We analyse the different cases in which an incoherence in temporal information can occur and provide a method to tackle this problem. In this method, conflict management is handled by means of exception handlers and control rules allowing the users to explicitly define their own strategy for temporal coherence solving.     

人工智能应用中基于区间代数的时态推理

时态表示和推理是人工智能领域的重要研究内容之一,它的应用范围分布很广,从逻辑基础研究到知识系统的应用。区间代数是一种独立的与领域无关的时态理论。用区间代数能表示不确定的时态关系,可以很方便的用于时态推理,表达能力强;时态关系的区间表示比较直观,可理解性强;同时区间代数可以进一步扩展到二维空间领域,即将区间代数拓展为矩阵代数,实现二维空间推理。在一维时态推理中,将时态的区间表示和矩阵表示相结合,在提高计算效率的同时,保持了形象直观的时态表示。     

From case-based reasoning to traces-based reasoning

CBR is an original AI paradigm based on the adaptation of solutions of past problems in order to solve new similar problems. Hence, a case is a problem with its solution and cases are stored in a case library. The reasoning process follows a cycle that facilitates “learning” from new solved cases. This approach can be also viewed as a lazy learning method when applied for task classification. CBR is applied for various tasks as design, planning, diagnosis, information retrieval, etc. The paper is the occasion to go a step further in reusing past unstructured experience, by considering traces of computer use as experience knowledge containers for situation based problem solving.     

Knowledge engineering for model-based diagnosis: An experience-based development approach

Falut diagnosis has proved to be one of the most rewarding application areas for the introduction of knowledge-based systems. Initially all diagnostic systems were based upon shallow knowledge, and many proved to be highly effective within a narrow task-specific domain. The current thrust of research, however, is also focusing on the use of model-based reasoning, which provides deeper knowledge of the structure and function of the device under diagnosis. Whilst much has been written with regard to development methods for shallow knowledge-based systems, relatively little has been published specifically relating to model-based approaches. This paper describes the approach adopted for the development of a model-based application for the diagnosis of hydraulic systems, paying particular attention to the lessons learned.     

Process algebras for systems diagnosis

In this paper we propose a new characterization of model-based diagnosis based on process algebras, a framework which is widely used in several areas of computer science. We show that process algebras provide a powerful modelling language which allows us to capture, in an uniform way, different types of models of physical systems, including models of time-varying and dynamic behavior. Then we provide a characterization of diagnosis which is equivalent to the “classical” abductive one. This suggests new interesting opportunities for research on relations between model-based reasoning and process algebras.     

A diagnosis scheme for a large-scale system

This paper presents a method for diagnosis in a large-scale system environment. The method utilizes the theory of hierarchical systems and hybrid diagnostic reasoning from AI (artificial intelligence). In shallow reasoning, which is a part of hybrid reasoning, the concept of entropy is used to determine which component (that might be responsible for a symptom observed) is to be tested next. The procedure is illustrated using a simulated example of a CIM (computer-integrated manufacturing) system, and is implemented on IntelliCorp's knowledge engineering environment (KEE).     

Hierarchical model-based diagnosis for high autonomy systems

Deep reasoning diagnostic procedures are model-based, inferring single or multiple faults from the knowledge of faulty behavior of component models and their causal structure. The overall goal of this paper is to develop a hierarchical diagnostic system that exploit knowledge of structure and behavior. To do this, we use a hierarchical architecture including local and global diagnosers. Such a diagnostic system for high autonomy systems has been implemented and tested on several examples in the domain of robot-managed fluid-handling laboratory.Research supported by NASA-Ames Co-operative Agreement No. NCC 2-525, A Simulation Environment for Laboratory Management by Robot Organization.     

An efficient algorithm for the incremental construction of a piecewise linear classifier

In this paper the problem of finding piecewise linear boundaries between sets is considered and is applied for solving supervised data classification problems. An algorithm for the computation of piecewise linear boundaries, consisting of two main steps, is proposed. In the first step sets are approximated by hyperboxes to find so-called “indeterminate” regions between sets. In the second step sets are separated inside these “indeterminate” regions by piecewise linear functions. These functions are computed incrementally starting with a linear function. Results of numerical experiments are reported. These results demonstrate that the new algorithm requires a reasonable training time and it produces consistently good test set accuracy on most data sets comparing with mainstream classifiers.     

Complexity classification in qualitative temporal constraint reasoning

We study the computational complexity of the qualitative algebra which is a temporal constraint formalism that combines the point algebra, the point-interval algebra and Allen's interval algebra. We identify all tractable fragments and show that every other fragment is NP-complete.     

Pragmatism and purism in artificial intelligence and legal reasoning

The paper identifies and assesses the implications of two approaches to the field of artificial intelligence and legal reasoning. The first — pragmatism — concentrates on the development of working systems to the exclusion of theoretical problems. The second — purism — focuses on the nature of the law and of intelligence with no regard for the delivery of commercially viable systems. Past work in AI and law is classified in terms of this division. By reference to The Latent Damage System, an operational system, the paper articulates and responds to conceivable purist (jurisprudential and AI) objections to such a program. The methods of the pragmatist are also called into question and refined. The author concludes that pragmatism within a purist framework is the only sound approach to developing reliable AI systems in law.     

An expert system for engine fault diagnosis: development and application

The mass production and wider use of automobiles and the incorporation of complex electronic technologies all indicate that the control of faults should be given an integral part of engine design and usage. Today, artificial intelligence (AI) technology is widely suggested for systematic diagnosis of faults where the amount of well-defined diagnosis knowledge is vast and the sequence of steps required to identify the fault is very long. This article describes on an expert system application for automotive engines. A new prototype named EXEDS (expert engine diagnosis system) has been developed using KnowledgePro, an expert system development tool, and run on a PC. The purpose of the prototype is to assist auto mechanics in fault diagnosis of engines by providing systematic and step-by-step analysis of failure symptoms and offering maintenance or service advice. The result of this development is expected to introduce a systematic and intelligent method in engine diagnosis and mai ntenance environments.     

Flexible diagnosis of discrete-event systems by similarity-based reasoning techniques

Diagnosis of discrete-event systems (DESs) may be improved by knowledge-compilation techniques, where a large amount of model-based reasoning is anticipated off-line, by simulating the behavior of the system and generating suitable data structures (compiled knowledge) embedding diagnostic information. This knowledge is exploited on-line, based on the observation of the system behavior, so as to generate the set of candidate diagnoses (problem solution). This paper makes a step forward: the solution of a diagnostic problem is supported by the solution of another problem, provided the two problems are somewhat similar. Reuse of model-based reasoning is thus achieved by exploiting the diagnostic knowledge yielded for solving previous problems. The technique still works when the available knowledge does not fit the extent of the system, but only a partition of it, that is, when solutions are available for subsystems only. In this case, the fragmented knowledge is exploited in a modular way, where redundant computation is avoided. Similarity-based diagnosis is meant for large-scale DESs, where the degree of similarity among subsystems is high and stringent time constraints on the diagnosis response is a first-class requirement.