Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set of methods to leverage information about the semantic hierarchy induced by class labels. In the first part of the thesis, we inject label-hierarchy knowledge to an arbitrary classifier and empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance. Taking a step further in this direction, we model more explicitly the label-label and label-image interactions by using order-preserving embedding-based models, prevalent in natural language, and tailor them to the domain of computer vision to perform image classification. Although, contrasting in nature, both the CNN-classifiers injected with hierarchical information, and the embedding-based models outperform a hierarchy-agnostic model on the newly presented, real-world ETH Entomological Collection image dataset.

Cardiovascular Diseases (CVD) and strokes produce immense health and economic burdens globally. Coronary Artery Disease (CAD) is the most common type of cardiovascular disease. Coronary Angiography, which is an invasive treatment, is also the standard procedure for diagnosing CAD. In this work, we illustrate a Medical Decision Support System for the prediction of Coronary Artery Disease (CAD) utilizing Fuzzy Cognitive Maps (FCMs). FCMs are a promising modeling methodology, based on human knowledge, capable of dealing with ambiguity and uncertainty, and learning how to adapt to the unknown or changing environment. The newly proposed MDSS is developed using the basic notions of Fuzzy Logic and Fuzzy Cognitive Maps, with some adjustments to improve the results. The proposed model, tested on a labelled CAD dataset of 303 patients, obtains an accuracy of 78.2% outmatching several state-of-the-art classification algorithms.

The problem of all-relevant feature selection is concerned with finding a relevant feature set with preserved redundancies. There exist several approximations to solve this problem but only one could give a distinction between strong and weak relevance. This approach was limited to the case of linear problems. In this work, we present a new solution for this distinction in the non-linear case through the use of random forest models and statistical methods.

Anomaly detection for time-series data has been an important research field for a long time. Seminal work on anomaly detection methods has been focussing on statistical approaches. In recent years an increasing number of machine learning algorithms have been developed to detect anomalies on time-series. Subsequently, researchers tried to improve these techniques using (deep) neural networks. In the light of the increasing number of anomaly detection methods, the body of research lacks a broad comparative evaluation of statistical, machine learning and deep learning methods. This paper studies 20 univariate anomaly detection methods from the all three categories. The evaluation is conducted on publicly available datasets, which serve as benchmarks for time-series anomaly detection. By analyzing the accuracy of each method as well as the computation time of the algorithms, we provide a thorough insight about the performance of these anomaly detection approaches, alongside some general notion of which method is suited for a certain type of data.

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of available features. In this paper, we propose gOMP, a highly-scalable generalisation of the Orthogonal Matching Pursuit feature selection algorithm to several directions: (a) different types of outcomes, such as continuous, binary, nominal, and time-to-event, (b) different types of predictive models (e.g., linear least squares, logistic regression), (c) different types of predictive features (continuous, categorical), and (d) different, statistical-based stopping criteria. We compare the proposed algorithm against LASSO, a prototypical, widely used algorithm for high-dimensional data. On dozens of simulated datasets, as well as, real gene expression datasets, gOMP is on par, or outperforms LASSO for case-control binary classification, quantified outcomes (regression), and (censored) survival times (time-to-event) analysis. gOMP has also several theoretical advantages that are discussed. While gOMP is based on quite simple and basic statistical ideas, easy to implement and to generalize, we also show in an extensive evaluation that it is also quite effective in bioinformatics analysis settings.

In public media as well as in scientific publications, the term \emph{bias} is used in conjunction with machine learning in many different contexts, and with many different meanings. This paper proposes a taxonomy of these different meanings, terminology, and definitions by surveying the, primarily scientific, literature on machine learning. In some cases, we suggest extensions and modifications to promote a clear terminology and completeness. The survey is followed by an analysis and discussion on how different types of biases are connected and depend on each other. We conclude that there is a complex relation between bias occurring in the machine learning pipeline that leads to a model, and the eventual bias of the model (which is typically related to social discrimination). The former bias may or may not influence the latter, in a sometimes bad, and sometime good way.

A blood test developed and checked using blood samples from 4000 people can accurately detect more than 50 cancer types, often before any symptoms appear. It was most accurate at identifying 12 especially dangerous types, including pancreatic cancers that are usually diagnosed only at a very late stage. Many groups around the world are trying to develop blood tests for cancer, often referred to as "liquid biopsies". Michael Seiden at US Oncology, a company involved in cancer care, and his team explored several ways of testing for cancer based on sequencing the DNA that dying cells release into the bloodstream. The team found that looking at methylation patterns at around a million sites was the most promising.

Effective triage is critical to mitigating the effect of increased volume by accurately determining patient acuity, need for resources, and establishing effective acuity-based patient prioritization. The purpose of this retrospective study was to determine whether historical EHR data can be extracted and synthesized with clinical natural language processing (C-NLP) and the latest ML algorithms (KATE) to produce highly accurate ESI predictive models. An ML model (KATE) for the triage process was developed using 166,175 patient encounters from two participating hospitals. The model was then tested against a gold set that was derived from a random sample of triage encounters at the study sites and correct acuity assignments were recorded by study clinicians using the Emergency Severity Index (ESI) standard as a guide. At the two study sites, KATE predicted accurate ESI acuity assignments 75.9% of the time, compared to nurses (59.8%) and average individual study clinicians (75.3%). KATE accuracy was 26.9% higher than the average nurse accuracy (p-value < 0.0001). On the boundary between ESI 2 and ESI 3 acuity assignments, which relates to the risk of decompensation, KATE was 93.2% higher with 80% accuracy, compared to triage nurses with 41.4% accuracy (p-value < 0.0001). KATE provides a triage acuity assignment substantially more accurate than the triage nurses in this study sample. KATE operates independently of contextual factors, unaffected by the external pressures that can cause under triage and may mitigate the racial and social biases that can negatively affect the accuracy of triage assignment. Future research should focus on the impact of KATE providing feedback to triage nurses in real time, KATEs impact on mortality and morbidity, ED throughput, resource optimization, and nursing outcomes.

Current advances in next generation sequencing techniques have allowed researchers to conduct comprehensive research on microbiome and human diseases, with recent studies identifying associations between human microbiome and health outcomes for a number of chronic conditions. However, microbiome data structure, characterized by sparsity and skewness, presents challenges to building effective classifiers. To address this, we present an innovative approach for distance-based classification using mixture distributions (DCMD). The method aims to improve classification performance when using microbiome community data, where the predictors are composed of sparse and heterogeneous count data. This approach models the inherent uncertainty in sparse counts by estimating a mixture distribution for the sample data, and representing each observation as a distribution, conditional on observed counts and the estimated mixture, which are then used as inputs for distance-based classification. The method is implemented into a k-means and k-nearest neighbours framework and we identify two distance metrics that produce optimal results. The performance of the model is assessed using simulations and applied to a human microbiome study, with results compared against a number of existing machine learning and distance-based approaches. The proposed method is competitive when compared to the machine learning approaches and showed a clear improvement over commonly used distance-based classifiers. The range of applicability and robustness make the proposed method a viable alternative for classification using sparse microbiome count data.

Scientists have developed an artificial intelligence program that can screen people for lung cancer by analysing their blood for DNA mutations that drive the disease. The software is experimental and needs to be verified in a clinical trial, but doctors are hopeful that if it proves its worth at scale, it will boost lung cancer screening rates by making the procedure as simple as a routine blood test. The program works by examining free-floating DNA that circulates in the blood. The majority of this genetic detritus enters the bloodstream when harmless cells in the body break down and spill their molecular innards, but tumours also shed DNA as they form and grow larger. The UK has no national lung cancer screening programme, but is exploring an approach adopted in the US where people who are at high risk, such as older smokers and former smokers, can have low-dose chest X-rays to check their lungs for tumours.