Data Derived Disease Diagnostics

Microscopic haematuria is a common incidental finding in childhood which often resolves on its own. However, it can be an early marker of genetic kidney disease. It is best practice to repeat testing to ensure resolution. Using data from the electronic medical record, we set out to find children without follow up, offer testing, and look for genetic kidney disease.

CHEER: Rich Model Helps Poor Model via Knowledge Infusion

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in rich-data environments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in a poor-data environments (e.g., at home), which often results in predictive models with poor performance. How can we boost the performance of models learned from such poor-data environment by leveraging knowledge extracted from existing models trained using rich data in a related environment? To address this question, we develop a knowledge infusion framework named CHEER that can succinctly summarize such rich model into transferable representations, which can be incorporated into the poor model to improve its performance. The infused model is analyzed theoretically and evaluated empirically on several datasets. Our empirical results showed that CHEER outperformed baselines by 5.60% to 46.80% in terms of the macro-F1 score on multiple physiological datasets.

The CrowdHEALTH project and the Hollistic Health Records: Collective Wisdom Driving Public Health Policies

Introduction:

With the expansion of available Information and Communication Technology (ICT) services, a plethora of data sources provide structured and unstructured data used to detect certain health conditions or indicators of disease. Data is spread across various settings, stored and managed in different systems. Due to the lack of technology interoperability and the large amounts of health-related data, data exploitation has not reached its full potential yet.

Aim:

The aim of the CrowdHEALTH approach, is to introduce a new paradigm of Holistic Health Records (HHRs) that include all health determinants defining health status by using big data management mechanisms.

Methods:

HHRs are transformed into HHRs clusters capturing the clinical, social and human context with the aim to benefit from the collective knowledge. The presented approach integrates big data technologies, providing Data as a Service (DaaS) to healthcare professionals and policy makers towards a “health in all policies” approach. A toolkit, on top of the DaaS, providing mechanisms for causal and risk analysis, and for the compilation of predictions is developed.

Results:

CrowdHEALTH platform is based on three main pillars: Data & structures, Health analytics, and Policies.

Conclusions:

A holistic approach for capturing all health determinants in the proposed HHRs, while creating clusters of them to exploit collective knowledge with the aim of the provision of insight for different population segments according to different factors (e.g. location, occupation, medication status, emerging risks, etc) was presented. The aforementioned approach is under evaluation through different scenarios with heterogeneous data from multiple sources.

Challenges of Health Analytics Utilization: A Review of Literature

The last four decades witnessed a huge progress in digitizing health information, representing an unmatched opportunity for utilizing health analytics in improving the quality of healthcare and reducing its costs. To learn more about different challenges facing the successful utilization of health analytics, a careful review of literature was conducted, and a qualitative analysis was used to explore and classify these challenges. Three main categories of challenges were identified. 1) Technological challenges; hardware, software, and data content, 2) Human challenges; knowledge, experiences, beliefs and attitudes, and end user behaviors, and 3) Organizational challenges; managerial, financial, and legal barriers to optimal utilization of health analytics. The non-technological problems seem to be harder to solve as well as more time consuming, including the existence of a specific business need and a clear vision to guide the project. In addition, health analytics should always be built with the end users in mind.

Distributed Tensor Decomposition for Large Scale Health Analytics

In the past few decades, there has been rapid growth in quantity and variety of healthcare data. These large sets of data are usually high dimensional (e.g. patients, their diagnoses, and medications to treat their diagnoses) and cannot be adequately represented as matrices. Thus, many existing algorithms can not analyze them. To accommodate these high dimensional data, tensor factorization, which can be viewed as a higher-order extension of methods like PCA, has attracted much attention and emerged as a promising solution. However, tensor factorization is a computationally expensive task, and existing methods developed to factor large tensors are not flexible enough for real-world situations. To address this scaling problem more efficiently, we introduce SGranite, a distributed, scalable, and sparse tensor factorization method fit through stochastic gradient descent. SGranite offers three contributions: (1) Scalability: it employs a block partitioning and parallel processing design and thus scales to large tensors, (2) Accuracy: we show that our method can achieve results faster without sacrificing the quality of the tensor decomposition, and (3) FlexibleConstraints: we show our approach can encompass various kinds of constraints including l2 norm, l1 norm, and logistic regularization. We demonstrate SGranite's capabilities in two real-world use cases. In the first, we use Google searches for flu-like symptoms to characterize and predict influenza patterns. In the second, we use SGranite to extract clinically interesting sets (i.e., phenotypes) of patients from electronic health records. Through these case studies, we show SGranite has the potential to be used to rapidly characterize, predict, and manage a large multimodal datasets, thereby promising a novel, data-driven solution that can benefit very large segments of the population.

Health Analytics Types, Functions and Levels: A Review of Literature

Health analytics is a business-driven term that encompasses a wide spectrum of aspects and dimensions of business intelligence applications and big data analysis. Healthcare organizations recently are eager to know whether they are getting the full value from the massive amounts of data and information they already have, to achieve their strategic effectiveness goals and operational efficiency objectives. It is very crucial to learn more about the diverse functions, types and levels through which health analytics can support such tasks. A careful review of literature was conducted, and a qualitative analysis was used to classify health analytics. Five main types of analytics could be identified; these are descriptive, diagnostic, predictive, prescriptive and discovery analytics, each has its own distinct role in improving healthcare. In addition to the five types, health analytics could also be classified into three levels of performance and engagement, these are the operational, tactical and strategic health analytics.