Re-Identification in Differentially Private Incomplete Datasets

Das Risiko von Re-Identifizierung bei der Auswertung medizinischer Routinedaten – Kritische Bewertung und Lösungsansätze

Large and complex data sets are increasingly available for research in critical care. To analyze these data, researchers use techniques commonly referred to as statistical learning or machine learning (ML). The latter is known for large successes in the field of diagnostics, for example, by identification of radiological anomalies. In other research areas, such as clustering and prediction studies, there is more discussion regarding the benefit and efficiency of ML techniques compared with statistical learning. In this viewpoint, we aim to explain commonly used statistical learning and ML techniques and provide guidance for responsible use in the case of clustering and prediction questions in critical care. Clustering studies have been increasingly popular in critical care research, aiming to inform how patients can be characterized, classified, or treated differently. An important challenge for clustering studies is to ensure and assess generalizability. This limits the application of findings in these studies toward individual patients. In the case of predictive questions, there is much discussion as to what algorithm should be used to most accurately predict outcome. Aspects that determine usefulness of ML, compared with statistical techniques, include the volume of the data, the dimensionality of the preferred model, and the extent of missing data. There are areas in which modern ML methods may be preferred. However, efforts should be made to implement statistical frameworks (e.g., for dealing with missing data or measurement error, both omnipresent in clinical data) in ML methods. To conclude, there are important opportunities but also pitfalls to consider when performing clustering or predictive studies with ML techniques. We advocate careful valuation of new data-driven findings. More interaction is needed between the engineer mindset of experts in ML methods, the insight in bias of epidemiologists, and the probabilistic thinking of statisticians to extract as much information and knowledge from data as possible, while avoiding harm.

Comparing conventional statistical models and machine learning in a small cohort of South African cardiac patients

The best algorithm for a computational problem generally depends on the “relevant inputs,” a concept that depends on the application domain and often defies formal articulation. While there is a large body of literature on empirical approaches to selecting the best algorithm for a given application domain, there has been surprisingly little theoretical analysis of the problem. This paper adapts concepts from statistical and online learning theory to reason about application-specific algorithm selection. Our models capture several state-of-the-art empirical and theoretical approaches to the problem, ranging from self-improving algorithms to empirical performance models, and our results identify conditions under which these approaches are guaranteed to perform well. We present one framework that models algorithm selection as a statistical learning problem, and our work here shows that dimension notions from statistical learning theory, historically used to measure the complexity of classes of binary- and re...

Chapter 19 - Statistical (Machine) Learning: Using Complex Models With Large Data Sets

The preponderance of smart devices, such as smartphones, has boosted the development and use of mobile applications (apps) in the recent years. This prevalence induces a large volume of mobile app usage data. The analysis of such information could lead to a better understanding of users' behaviours in using the apps they have installed, even more if these data can be coupled with a given context (location, time, date, sociological data...). However, mobile and apps usage data are very sensitive, and are today considered as personal. Their collection and use pose serious concerns associated with individuals' privacy. To reconcile harnessing of data and privacy of users, we investigate in this paper the possibility to conduct privacy-preserving mobile data usage statistics that will prevent any inference or re-identification risks. The key idea is for each user to encrypt their (private and sensitive) inputs before sending them to the data processor. The possibility to perform statistics on those data is then possible thanks to the use of functional encryption, a cryptographic building block permitting to perform some allowed operations over encrypted data. In this paper, we first show how it is possible to obtain such individuals' usage of their apps, which step is necessary for our use case, but can at the same time pose some security problems w.r.t. those apps. We then design our new encryption scheme, adding some fault tolerance property to a recent dynamic decentralized function encryption scheme. We finally show how we have implemented all that, and give some benchmarks.

Early detection of ankylosing spondylitis using texture features and statistical machine learning, and deep learning, with some patient age analysis

Digital signal processing (DSP) is one of the ‘foundational’ engineering topics of the modern world, without which technologies such the mobile phone, television, CD and MP3 players, WiFi and radar, would not be possible. A relative newcomer by comparison, statistical machine learning is the theoretical backbone of exciting technologies such as automatic techniques for car registration plate recognition, speech recognition, stock market prediction, defect detection on assembly lines, robot guidance and autonomous car navigation. Statistical machine learning exploits the analogy between intelligent information processing in biological brains and sophisticated statistical modelling and inference. DSP and statistical machine learning are of such wide importance to the knowledge economy that both have undergone rapid changes and seen radical improvements in scope and applicability. Both make use of key topics in applied mathematics such as probability and statistics, algebra, calculus, graphs and networks. Intimate formal links between the two subjects exist and because of this many overlaps exist between the two subjects that can be exploited to produce new DSP tools of surprising utility, highly suited to the contemporary world of pervasive digital sensors and high-powered and yet cheap, computing hardware. This book gives a solid mathematical foundation to, and details the key concepts and algorithms in, this important topic.

The​‍​‌‍​‍‌​‍​‌‍​‍‌ rapid evolution of digital healthcare platforms has raised the need for secure and smart methods that can protect patient data while maintaining accurate disease prediction. The present study offers a futuristic e-healthcare system entitled Optimized Multi-Agent Deep Learning Framework for Lung Cancer Image Retrieval Using Medical Imaging Data. The circulated copy intends to focus on the prediction as well as the detection of lung diseases by utilizing machine learning (ML) and deep learning (DL) models to attain high diagnostic accuracy. A web-based front end has been created using the Django framework to facilitate easy user access to predictions and medical insights. In an attempt to preserve the privacy and security of sensitive health records, blockchain technology has been merged for data storage that is decentralized and tamper-proof. Besides that, multi-agent-based privacy metrics have been activated to keep track of, study, and raise the privacy levels through the system, thus providing an adaptive shield against the leakage of data and unauthorized access. The suggested scheme enhances the security of data privacy and at the same time raises the level of trust, transparency, and efficiency in digital healthcare applications. Such a combined system is an excellent example of how healthcare services can be revolutionized by the union of AI-powered disease detection and privacy-preserving ​‍​‌‍​‍‌​‍​‌‍​‍‌methods.

Antibodies are capable of potently and specifically binding individual antigens and, in some cases, disrupting their functions. The key challenge in generating antibody-based inhibitors is the lack of fundamental information relating sequences of antibodies to their unique properties as inhibitors. We develop a pipeline, Antibody Sequence Analysis Pipeline using Statistical testing and Machine Learning (ASAP-SML), to identify features that distinguish one set of antibody sequences from antibody sequences in a reference set. The pipeline extracts feature fingerprints from sequences. The fingerprints represent germline, CDR canonical structure, isoelectric point and frequent positional motifs. Machine learning and statistical significance testing techniques are applied to antibody sequences and extracted feature fingerprints to identify distinguishing feature values and combinations thereof. To demonstrate how it works, we applied the pipeline on sets of antibody sequences known to bind or inhibit the activities of matrix metalloproteinases (MMPs), a family of zinc-dependent enzymes that promote cancer progression and undesired inflammation under pathological conditions, against reference datasets that do not bind or inhibit MMPs. ASAP-SML identifies features and combinations of feature values found in the MMP-targeting sets that are distinct from those in the reference sets.

In order to continuously increase design productivity, engineers and researchers rely on automation frameworks for hardware and firmware design purposes. However, a major problem for optimizing the generated design is retrieving data from which a prediction function (e.g., area, speed) could be learned correctly (since complete generation and synthesis of the hardware design are too computationally expensive). In particular, the data used for learning the prediction function should be representative of valid design possibilities and be generated in an efficient way. As one contribution, this paper describes how Statistical Analysis (SA) and Machine Learning (ML) are used to guarantee the quality of the data. Furthermore, an automatic approach to generate representative and valid configuration samples is proposed, both to improve the efficiency and to avoid manual effort. In order to point out this concept, we implement the generation of data for the estimation of the Hardware Area and Firmware Metrics of a Register Interface (RI) component. As a consequence, the process of learning the RI area through a data-driven ML algorithm guarantees a still accurate (\(R^2= 0.98\)) but 600x faster estimation.

Animals navigate through their ways in various scales ranging from centimeters to thousands of kilometers. How does the brain realize such spatial navigation? Several lines of evidence have suggested that the hippocampal place cell activity in the brain has a potential to answer the question. Although statistical machine learning plays critical roles on precisely deciphering the nature of the place cell activity, some technical issues remain unsolved since the ground truth is missing. By virtue of progressive efforts together with the advance on machine learning, methodologies for tracking and predicting navigational behaviors have been improved. Here we review the popular methodologies based on statistical machine learning that track the animal behavior from images and predict it from place cell activity, and discuss about what the next phase of the analysis tools is to deeply understand the neuronal underpinning of spatial navigation.

Background: The dynamic interplay between statistics and machine learning has emerged as a focal point in contemporary data science research. As the boundaries between these two disciplines blur, it becomes imperative to explore their intersection and discern the synergies that drive advancements in both fields. Objective: This academic article aims to provide a comprehensive analysis of the intersection between statistics and machine learning, shedding light on the evolving relationship between the two disciplines. The primary objective is to elucidate the key areas where statistical methods and machine learning algorithms converge, offering a nuanced understanding of their complementary roles in extracting meaningful insights from complex datasets. Methods: A systematic literature review was conducted to identify seminal works, methodologies, and applications at the intersection of statistics and machine learning. The selected articles were critically analyzed to distill key themes, methodologies, and trends, providing a comprehensive overview of the current state of this interdisciplinary landscape. Results: Our analysis reveals a rich tapestry of collaborations between statistics and machine learning, ranging from foundational principles to innovative applications. Notably, statistical techniques contribute to the interpretability and generalizability of machine learning models, while machine learning algorithms enhance the predictive power of statistical models in diverse domains. Conclusion: This article concludes by highlighting the symbiotic relationship between statistics and machine learning, emphasizing the need for continued interdisciplinary collaboration. Recognizing the shared principles and leveraging the strengths of both disciplines can pave the way for more robust and interpretable data-driven solutions, fostering advancements in the broader field of data science.Statistics

This chapter discusses the application of multivariate techniques and machine learning (ML) to the analysis of data originating from the sensory analysis of dairy products. The main multivariate techniques used in the analysis of sensory data concerning dairy products are principal component analysis (PCA), correspondence analysis (CA), hierarchical cluster analysis (HCA), generalised Procrustes analysis (GPA) and multiple-factor analysis (MFA), allowing us to determine the drivers of liking, characterise the sensory profile, determine sensory acceptance and observe relationships between emotional profiles and sensory acceptance. These techniques can be used to segment consumers or products based on overall liking, type of processing or intra-cultural differences. Comparisons between different sensory methodologies could be made. ML can evaluate the interaction of physical and chemical characteristics with sensory acceptance and predict consumer responses based on descriptive tests. It is essential to observe the peculiarities and limitations of each multivariate statistical techniques or ML, the characteristics of the data set and the objectives of the study, to choose the appropriate analysis to be applied.

The traditional means of extracting information from the Web are keyword-based search and browsing. The Semantic Web adds structured information (i.e., semantic annotations and references) supporting both activities. One of the most interesting recent developments is Linked Open Data (LOD), where information is presented in the form of facts – often originating from published domain-specific databases – that can be accessed both by a human and a machine via specific query endpoints. In this article, we argue that machine learning provides a new way to query web data, in particular LOD, by analyzing and exploiting statistical regularities. We discuss challenges when applying machine learning to the Web and discuss the particular learning approaches we have been pursuing in THESEUS. We discuss a number of applications where the Web is queried via machine learning and describe several extensions to our approaches.