Recent improvements in data collection volume from planetary and space physics missions have allowed the application of novel data science techniques. The Cassini mission for example collected over 600 gigabytes of scientific data from 2004 to 2017. This represents a surge of data on the Saturn system. Machine learning can help scientists work with data on this larger scale. Unlike many applications of machine learning, a primary use in planetary space physics applications is to infer behavior about the system itself. This raises three concerns: first, the performance of the machine learning model, second, the need for interpretable applications to answer scientific questions, and third, how characteristics of spacecraft data change these applications. In comparison to these concerns, uses of black box or un-interpretable machine learning methods tend toward evaluations of performance only either ignoring the underlying physical process or, less often, providing misleading explanations for it. We build off a previous effort applying a semi-supervised physics-based classification of plasma instabilities in Saturn's magnetosphere. We then use this previous effort in comparison to other machine learning classifiers with varying data size access, and physical information access. We show that incorporating knowledge of these orbiting spacecraft data characteristics improves the performance and interpretability of machine learning methods, which is essential for deriving scientific meaning. Building on these findings, we present a framework on incorporating physics knowledge into machine learning problems targeting semi-supervised classification for space physics data in planetary environments. These findings present a path forward for incorporating physical knowledge into space physics and planetary mission data analyses for scientific discovery.

Alzheimer's Disease (AD) ravages the cognitive ability of more than 5 million Americans and creates an enormous strain on the health care system. This paper proposes a machine learning predictive model for AD development without medical imaging and with fewer clinical visits and tests, in hopes of earlier and cheaper diagnoses. That earlier diagnoses could be critical in the effectiveness of any drug or medical treatment to cure this disease. Our model is trained and validated using demographic, biomarker and cognitive test data from two prominent research studies: Alzheimer's Disease Neuroimaging Initiative (ADNI) and Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL). We systematically explore different machine learning models, pre-processing methods and feature selection techniques. The most performant model demonstrates greater than 90% accuracy and recall in predicting AD, and the results generalize across sub-studies of ADNI and to the independent AIBL study. We also demonstrate that these results are robust to reducing the number of clinical visits or tests per visit. Using a metaclassification algorithm and longitudinal data analysis we are able to produce a "lean" diagnostic protocol with only 3 tests and 4 clinical visits that can predict Alzheimer's development with 87% accuracy and 79% recall. This novel work can be adapted into a practical early diagnostic tool for predicting the development of Alzheimer's that maximizes accuracy while minimizing the number of necessary diagnostic tests and clinical visits.

Clinical researchers often select among and evaluate risk prediction models using standard machine learning metrics based on confusion matrices. However, if these models are used to allocate interventions to patients, standard metrics calculated from retrospective data are only related to model utility (in terms of reductions in outcomes) under certain assumptions. When predictions are delivered repeatedly throughout time (e.g. in a patient encounter), the relationship between standard metrics and utility is further complicated. Several kinds of evaluations have been used in the literature, but it has not been clear what the target of estimation is in each evaluation. We synthesize these approaches, determine what is being estimated in each of them, and discuss under what assumptions those estimates are valid. We demonstrate our insights using simulated data as well as real data used in the design of an early warning system. Our theoretical and empirical results show that evaluations without interventional data either do not estimate meaningful quantities, require strong assumptions, or are limited to estimating best-case scenario bounds.

In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we call the feature-weighted elastic net ("fwelnet"), uses these "features of features" to adapt the relative penalties on the feature coefficients in the elastic net penalty. In our simulations, fwelnet outperforms the lasso in terms of test mean squared error and usually gives an improvement in true positive rate or false positive rate for feature selection. We also apply this method to early prediction of preeclampsia, where fwelnet outperforms the lasso in terms of 10-fold cross-validated area under the curve (0.86 vs. 0.80). We also provide a connection between fwelnet and the group lasso and suggest how fwelnet might be used for multi-task learning.

The process of fertilizing a human egg outside the body in order to help those suffering from infertility to conceive is known as in vitro fertilization (IVF). Despite being the most effective method of assisted reproductive technology (ART), the average success rate of IVF is a mere 20-40%. One step that is critical to the success of the procedure is selecting which embryo to transfer to the patient, a process typically conducted manually and without any universally accepted and standardized criteria. In this paper we describe a novel data-driven system trained to directly predict embryo implantation probability from embryogenesis time-lapse imaging videos. Using retrospectively collected videos from 272 embryos, we demonstrate that, when compared to an external panel of embryologists, our algorithm results in a 12% increase of positive predictive value and a 29% increase of negative predictive value.

We develop a general non-asymptotic analysis of learning rates in kernel ridge regression (KRR), applicable for arbitrary Mercer kernels with multi-dimensional support. Our analysis is based on an operator-theoretic framework, at the core of which lies two error bounds under reproducing kernel Hilbert space norms encompassing a general class of kernels and regression functions, with remarkable extensibility to various inferential goals through augmenting results. When applied to KRR estimators, our analysis leads to error bounds under the stronger supremum norm, in addition to the commonly studied weighted $L_2$ norm; in a concrete example specialized to the Mat\'ern kernel, the established bounds recover the nearly minimax optimal rates. The wide applicability of our analysis is further demonstrated through two new theoretical results: (1) non-asymptotic learning rates for mixed partial derivatives of KRR estimators, and (2) a non-asymptotic characterization of the posterior variances of Gaussian processes, which corresponds to uncertainty quantification in kernel methods and nonparametric Bayes.

Amazon's controversial facial recognition technology has incorrectly matched more than 100 photos of politicians in the UK and US to police mugshots, new tests have revealed. Amazon Rekognition uses artificial intelligence software to identify individuals from their facial structure. Customers include law enforcement and US government agencies like Immigration and Custome Enforcement (ICE). It is not the first time the software's accuracy has been called into question. In July 2018, the American Civil Liberties Union (ACLU) found 28 false matches between US Congress members and pictures of people arrested for a crime.

Unnecessary restrictions on blood donors should be removed to maximize the blood and plasma available for use. With a vaccine for coronavirus disease 2019 (COVID-19) likely more than a year away, we must identify effective therapies for patients now. One promising approach is the use of plasma from patients who have recovered from COVID-19 (1, 2). To facilitate this strategy, the U.S. Food and Drug Administration (FDA) recently revised some of the restrictions on blood donation, including a decrease in deferral time for men who have sex with men (MSM) to 3 months (3). This is a positive change to an outdated guideline, but it does not go far enough.

Electroencephalograms (EEG) are a noninvasive longstanding medical modality that measures the brain's activity by recording the electromagnetic field at the scalp. Since its creation, EEG has played a fundamental role in understanding several major neurological disorders, by analyzing their manifestation into brain rhythms. For example, the study of deceases such as depression, age-related cognitive deterioration, epilepsy, anxiety disorders and subnormal brain development in children have benefited from this technology. The typical brain rhythms are distinguished by their different frequency ranges, called delta (δ) within the range 0.5 to 4Hz, theta (θ) within the range 4 to 7.5Hz, alpha (α) within the range 8 to 13Hz, beta (β) within the range 14 to 30Hz, and gamma (γ) within the range 30 to 64Hz. In this study, we focus on the brain rhythm called mu (µ) within the range 7.5 to 11.5Hz. Mu-waves are considered to emerge naturally and may convey information about what the functioning of brain hierarchies [1]. According to [2], there exist three historical theoretical hypotheses to explaining the mu-brain rhythm: i) the neuronal hyperexcitability related to the rolandic cortex; ii) the superficial cortical inhibition explaining its suppression with motor activity; and iii) the somatosensory cortical idling, related to the afference-dependent phenomenon.

Given the surge in popularity of mutual funds (including exchange-traded funds (ETFs)) as a diversified financial investment, a vast variety of mutual funds from various investment management firms and diversification strategies have become available in the market. Identifying similar mutual funds among such a wide landscape of mutual funds has become more important than ever because of many applications ranging from sales and marketing to portfolio replication, portfolio diversification and tax loss harvesting. The current best method is data-vendor provided categorization which usually relies on curation by human experts with the help of available data. In this work, we establish that an industry wide well-regarded categorization system is learnable using machine learning and largely reproducible, and in turn constructing a truly data-driven categorization. We discuss the intellectual challenges in learning this man-made system, our results and their implications.