The state of clinical data is a barrier to the development of machine learning models to improve healthcare. Uncontrolled clinical freetext is common in both the patient and clinical trials: the resulting spelling, grammatical errors, phrasing variation, and other resulting variability results in difficult-to-leverage data. As part of our effort to harmonize the Aggregate Analysis of ClinicalTrials.gov (AACT) drop-withdrawal reasons to a controlled vocabulary, we explored two solutions. Elastic's fuzzy matching capability matched entries in the AACT Drop-Withdrawal table to a list of user-specified terms (74.6% coverage). The second approach was a custom pipeline employing NLP preprocessing, Levenshtein Distance (Fuzzy Matching), and semantic similarity mapping using a pre-trained FastText Model (98% coverage). Although manual oversight is still required, the amount of effort to harmonize with a controlled vocabulary is notably reduced. This work enables the rapid harmonization of clinical databases, allowing them to be leveraged for machine learning and analytics.

Prostate cancer is a complex disease which advances in stages. While clinical failure (including metastasis) is a significant endpoint following a radical prostatectomy, it can often take years to manifest, usually too late to be optimistically treated. Instead the earlier endpoint of PSA Recurrence is frequently used as a surrogate in prognostic modeling. The central issue in these models is managing censored observations which challenge traditional regression techniques. The true target times of a majority of instances are unknown, what is known is a censored target representing some earlier indeterminate time. In this work we apply a novel transduction approach for semi-supervised survival analysis which has previously been shown to be powerful in medical prognosis. The approach considers censored samples as semi-supervised regression targets leveraging the partial nature of unsupervised information. In this work, the approach leads to a significant increase in performance for predicting advanced prostate cancer from earlier endpoints and may also be useful in other diseases for predicting advanced endpoints from earlier stages.

The central challenge in predictive modeling for survival analysis in medical prognostics is managing censored observations. Traditional regression techniques are challenged by these censored samples. In such problems the true target times of a majority of instances are unknown; what is known is a censored target representing some earlier indeterminate time. Such censored samples can be considered as semi-supervised targets; however most efforts in semi-supervised regression do not take into account the partial nature of unsupervised information; samples are treated as either fully labelled or unlabeled. In this work we extend a novel transduction approach for semi-supervised survival analysis to neural networks. The true target times are approximated from the censored times through transduction. For prostate and breast cancer applications, this semi-supervised regression framework yields a significant improvement in performance.

Parkinson's disease is a complex condition currently monitored at home with paper diaries which rely on subjective and unreliable assessment of motor function at nonstandard time intervals. We present an innovative wearable and unobtrusive monitoring system for patients which can help provide physicians with significantly improved assessment of patients' responses to drug therapies and lead to better-targeted treatment regimens. In this paper we describe the algorithmic development of the system and an evaluation in patients for assessing the onset and duration of advanced PD motor symptoms.

Many machine learning algorithms require a single value per feature per record for modeling. However, there are applications, in the medical domain particularly, where a single record may have multiple observations for the same feature. For example, a patient could have the same gene analyzed in multiple tissue slides of a biopsy, or could have the same genetic test performed on multiple subsequent biopsies. The challenge in these applications is how to integrate multiple observations of the same predictor feature per record. In this paper, two data aggregation methods are compared, one method is a simple median aggregation of feature values, while the other is a novel method which constructs intervals of values for each feature. The aggregated features are passed as input to a novel support vector regression method for modeling survival data in a prostate cancer setting. The performance of both methods was similar in predicting prostate cancer progression on three data cohorts.

A crucial challenge in predictive modeling for survival analysis is managing censored observations in the data. The Cox proportional hazards model is the standard tool for the analysis of continuous censored survival data. We propose a novel machine learning algorithm, support vector regression for censored data (SVRc) for improved analysis of medical survival data. SVRc leverages the high-dimensional capabilities of traditional SVR while adapting it for use with censored data through a modified asymmetric loss/penalty function which allows censored (left and right censored) data to be processed. We applied the new algorithm to predict the recurrence and disease progression of prostate cancer, breast cancer and lung cancer. Compared with the traditional Cox model, SVRc achieves significant improvement in overall accuracy as well as in the ability to identify high-risk and low-risk patient populations.

In this paper we present an analysis of the minimal hardware precision required to implement support vector machine (SVM) classification within a logarithmic number system architecture. Support vector machines are fast emerging as a powerful machine-learning tool for pattern recognition, decision-making and classification. Logarithmic number systems (LNS) utilize the property of logarithmic compression for numerical operations. Within the logarithmic domain, multiplication and division can be treated simply as addition or subtraction. Hardware computation of these operations is significantly faster with reduced complexity. Leveraging the inherent properties of LNS, we are able to achieve significant savings over double-precision floating point in an implementation of a SVM classification algorithm.