MoDN-Flip: Optimizing Modular Clinical Decision Support Networks with Decision Flippability Score

BACKGROUND. Clinical Decision Support Systems (CDSS) are point-of-care questionnaires that guide consultations to evidence-based predictions with the aim of standardizing care and optimizing resource allocation. The data collected in these tools contain potentially useful insights to further train its predictive algorithms, however, the questionnaire structure biases data with systematic missingness, making it unusable in traditional models. Further, privacy and interoperability issues make it challenging to synergize with data collected in related CDSS tools. The Modular Decision Support Network (MoDN) was previously proposed by our group to address these issues. It can predict diagnoses at each step in a consultation using sequentially encoded questions. However, it lacks the ability to provide information on unencoded questions, such as predicting their importance, which could potentially optimize questionnaire structure. AIM. In this work, we aim to optimize MoDN by deriving a flippability score (FS) which computes the importance of a question in the form of how likely its answer would flip (change) the predicted diagnoses. METHODS & FINDINGS. The FS is computed with the help of MoDN’s feature decoders that predict unknown feature values in the data. The optimal questionnaire order is then derived by feeding MoDN the question with the highest FS. This approach—-MoDN-flip—- is validated on two independent real world CDSS-derived data sets of pediatric outpatients. We show that FS-optimized question order can achieve the baseline predictive performance 14.71% faster (or with 3.53 fewer questions) compared to MoDN with the original question order. FS-optimized questionnaires are also able to improve the cumulative F1 score by 5.24%. Furthermore, we test the utility of FS-optimization when porting MoDN to an imperfectly interoperable data set (i.e. with slightly different questionnaire structures and partially-overlapping feature sets). The results show that the score is valid in a new dataset and can provide better predictive performance at an earlier stages, albeit a slight cost to final performance. CONCLUSION. With the aim of providing data-driven questionnaire optimization for CDSS tools, we propose the flippability score, which indicates the importance of each potential question in a consultation. The experimental results show that FS can express predictive importance of questions and has the potential to significantly optimize questionnaire structure. It is now necessary to evaluate this ordering against human consultation logic.

Rate allocation and optimized decoding in inter-session network coding

Eirina Bourtsoulatze

Recent advances in data processing and communication systems have led to a continuous increase in the amount of data communicated over today’s networks. These large volumes of data pose new challenges on the current networking infrastructure that only offers a best effort mechanism for data delivery. The emergence of new distributed network architectures, such as peer-to-peer networks and wireless mesh networks, and the need for efficient data delivery mechanisms have motivated researchers to reconsider the way that information is communicated and processed in the networks. This has given rise to a new research field called network coding. The network coding paradigm departs from the traditional routing principle where information is simply relayed by the network nodes towards the destination, and introduces some intelligence in the network through coding at the intermediate nodes. This in-network data processing has been proved to substantially improve the performance of data delivery systems in terms of throughput and error resilience in networks with high path diversity. Motivated by the promising results in the network coding research, we focus in this thesis on the design of network coding algorithms for simultaneous transmission of multiple data sources in overlay networks. We investigate several problems that arise in the context of inter-session network coding, namely (i) decoding delay minimization in inter-session network coding, (ii) distributed rate allocation for inter-session network coding and (iii) correlation-aware decoding of incomplete network coded data. We start by proposing a novel framework for data delivery from multiple sources to multiple clients in an overlay wireline network, where intermediate nodes employ randomized inter-session network coding. We consider networks with high resource diversity, which creates network coding opportunities with possibly large gains in terms of throughput, delay and error robustness. However, the coding operations in the intermediate nodes must be carefully designed in order to enable efficient data delivery. We look at the problem from the decoding delay perspective and design solutions that lead to a small decoding delay at clients through proper coding and rate allocation. We cast the optimization problem as a rate allocation problem, which seeks for the coding operations that minimize the average decoding delay in the client population. We demonstrate the validity of our algorithm through simulations in representative network topologies. The results show that an effective combination of intra- and inter-session network coding based on randomized linear coding permits to reach small decoding delays and to better exploit the available network resources even in challenging network settings. Next, we design a distributed rate allocation algorithm where the users decide locally how many intra- and inter-session network coded packets should be requested from the parent nodes in order to get minimal decoding delay. The capability to take coding decisions locally with only a partial knowledge of the network statistics is of crucial importance for applications where users are organized in dynamic overlay networks. We propose a receiver-driven communication protocol that operates in two rounds. First, the users request and obtain information regarding the network conditions and packet availability in their local neighborhood. Then, every user independently optimizes the rate allocation among different possible intra- and inter-session packet combinations to be requested from its parents. We also introduce the novel concept of equivalent flows, which permits to efficiently estimate the expected number of packets that are necessary for decoding and hence to simplify the rate allocation process. Experimental results indicate that our algorithm is capable of eliminating the bottlenecks and reducing the decoding delay of users with limited resources. We further investigate the application of the proposed distributed rate allocation algorithm to the transmission of video sequences and validate the performance of our system using the NS-3 simulator. The simulation results show that the proposed rate allocation algorithm is successful in improving the quality of the delivered video compared to intra-session network coding based solutions. Finally, we investigate the problem of decoding the source information from an incomplete set of network coded data with the help of source priors in a finite algebraic field. The inability to form a complete decoding system can be often caused by transmission losses or timing constraints imposed by the application. In this case, exact reconstruction of the source data by conventional algorithms such as Gaussian elimination is not feasible; however, partial recovery of the source data may still be possible, which can be useful in applications where approximate reconstruction is informative. We use the statistical characteristics of the source data in order to perform approximate decoding. We first analyze the performance of a hypothetical maximum a posteriori decoder, which recovers the source data from an incomplete set of network coded data given the joint statistics of the sources. We derive an upper bound on the probability of erroneous source sequence decoding as a function of the system parameters. We then propose a constructive solution to the approximate decoding problem and design an iterative decoding algorithm based on message passing, which jointly considers the network coding and the correlation constraints. We illustrate the performance of our decoding algorithm through extensive simulations on synthetic and real data sets. The results demonstrate that, even by using a simple correlation model expressed as a correlation noise between pairs of sources, the original source data can be partially decoded in practice from an incomplete set of network coded symbols. Overall, this thesis addresses several important issues related to the design of efficient data delivery methods with inter-session network coding. Our novel framework for decoding delay minimization can impact the development of practical inter-session network coding algorithms that are appropriate for applications with low delay requirements. Our rate allocation algorithms are able to exploit the high resource diversity of modern networking systems and represent an effective alternative in the development of distributed communication systems. Finally, our algorithm for data recovery from incomplete network coded data using correlation priors can contribute significantly to the improvement of the delivered data quality and provide new insights towards the design of joint source and network coding algorithms.

EPFL2013

Automated analysis of product related data generated from PLM ontology

Ana Milicic

In recent years, ontology for the Product Lifecycle Management domain has raised a lot of interest in research communities, both academic and industrial. It has emerged as a convenient method for supporting the concept of closed lifecycle information loop, which is one of the most important issues of PLM. By modeling relevant aspects collected from all lifecycle stages of a product, within one ontology, a common knowledge structure is created accessible to all actors. Assuming that appropriate mechanisms for updating ontology (or rather, instances that populate it) are provided, ontology becomes a base layer for a knowledge management platform. Useful experience and information from all productsâ life-cycle stages, can influence designerâs decisions and business strategies. The industrial research community has recognized this added value of ontological implementation, and there is an increasing number of developed ontologies for this purpose. Application of ontology contributes to time efficiency by reducing the time required to retrieve information. Furthermore, it allows for the enhancement of design decisions which are supported through additional information at the appropriate moment. Finally, ontology gives an overall perspective on a product's lifecycle, allowing from-the-top optimization. Different domains modeled in ontology, and software platforms that use them as a base layer, become interoperable and convenient to merge. The purpose of ontology as it is today is not to store data, for the most part because there are more efficient data base systems to handle large data amounts. Still, the domain modeled within ontology is composed of structured and un-structured data sets, and ontology itself can give us a top view on relations and dependences between these data sets. In this perspective, it holds a strong similarity to a relational data base, if relations in the data base where defined so that they depicted the real world in the most precise possible manner. In large companies today, handling a growing amount of data generated every day is becoming an increasingly relevant problem. Managing and storing them, although challenging, is still feasible, but holding data without understanding it carries little added value. In an effort to exploit useful information contained in unstructured data sources, a number of decision support systems and enterprise resource planning systems have been developed. They can be very diverse in functionality and efficiency but the one thing that they all have in common is that the user has to be the one making the initiative and defining the queries. This means that the user has to know which information he is looking for, or hoping to extract. As a consequence, the number of relevant correlations and dependencies between different factors of real life captured in the data are left unnoticed, simply because they were not assumed. In the PLM domain, this is particularly present since it involves a number of actors and most of them are interacting only with a small subset of domain concepts. Data mining as a discipline, gives a number of tools for resolving this issue. All of the algorithms are designed to detect correlations, underlying patterns or functions that generated the data. The problem of data mining techniques is that they are still performed mostly manually. Although deterministic steps of data mining procedures can be supported by existing software tools, the others remain an obstac

EPFL2015

Quantum-based approach for laboratory risk assessment and decision-making

Ruoxing Liao

With the rising focus on academic safety, there has been an effort to improve the academic safety climate and develop lab-specific risk assessment tools. Despite the progress made in recent years, there is still a deficit of reliable data statistics on safety events and risk assessment in academia, making it difficult to perform full-scale analysis. Moreover, the rapid turnover of personnel and the highly dynamic research tasks in a laboratory environment impede the implementation of classical and well-established risk management strategies, which are usually time-consuming and resource-intensive. Laboratory safety management is always challenging due to lack of data and effective methods. The end of safety management is usually the selection of risk mitigation measures. In the laboratory risk management process, decisions are often made through discussion and compromise. In this regard, it would be beneficial to provide a tool that can support in resource allocation and prioritization of actions. The goal of this project is to develop a decision support tool to assist in the selection of optimal and appropriate preventive or corrective measures in the lab safety management process. The use of decision tools such as Multi-Criteria Decision Making (MCDM) can effectively abstract complex laboratory management problems into a decision framework. This study focuses on the ranking process of competitive corrective measures. Combining the results of interviews and questionnaires, five evaluation criteria were proposed for the normative process of multi-criteria decision making. They are: Residual Risk, Risk reduction, Personnel reliability, Technical reliability, and Cost. classical methods TOPSIS and WSM have been evaluated during the study, and emerging quantum decision making methods have been explored. All three methods are used to simulate the laboratory safety decision making process, and they all present good consistency. Different weighting methods have also been applied to the model and two case studies have been conducted. The first case study is designed to construct the model and verify its feasibility, and the second model is used to investigate the process of group decision making. By applying different MCDM methods, the obtained results are discussed and compared to verify the stability and accuracy of the model. The approach proposed in this research is a promising tool. It offers the possibility to be compatible with different MCDM methods and risk assessment methods, and the proposed decision model could be used as a decision support system to help lab managers make better decisions, or it can provide a neutral point of view as an aid. Future work may include fine-tuning the model. In the following stage, decision criteria should be precisely defined, and corresponding quantitative formulas should be proposed to serve the flexible and dynamic laboratory environment.

2022