Advances in Sharing Multi-sourced Health Data on Decision Support Science 2016-2017

Introduction: Clinical decision support science is expanding to include integration from broader and more varied data sources, diverse platforms and delivery modalities, and is responding to emerging regulatory guidelines and increased interest from industry. Objective: Evaluate key advances and challenges of accessing, sharing, and managing data from multiple sources for development and implementation of Clinical Decision Support (CDS) systems in 2016-2017. Methods: Assessment of literature and scientific conference proceedings, current and pending policy development, and review of commercial applications nationally and internationally. Results: CDS research is approaching multiple landmark points driven by commercialization interests, emerging regulatory policy, and increased public awareness. However, the availability of patient-related “Big Data” sources from genomics and mobile health, expanded privacy considerations, applications of service-based computational techniques and tools, the emergence of “app” ecosystems, and evolving patient-centric approaches reflect the distributed, complex, and uneven maturity of the CDS landscape. Nonetheless, the field of CDS is yet to mature. The lack of standards and CDS-specific policies from regulatory bodies that address the privacy and safety concerns of data and knowledge sharing to support CDS development may continue to slow down the broad CDS adoption within and across institutions. Conclusion: Partnerships with Electronic Health Record and commercial CDS vendors, policy makers, standards development agencies, clinicians, and patients are needed to see CDS deployed in the evolving learning health system.

Download Full-text

A Description of Clinical Decision Support Framework Prediction in Heterogeneous Data Sources

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f1090.0886s19 ◽

2019 ◽

Vol 8 (6S) ◽

pp. 425-427

Keyword(s):

Decision Support ◽

Clinical Decision Support ◽

Clinical Decision ◽

Heterogeneous Data ◽

Scientific Discipline ◽

Work Environments ◽

Data Sources ◽

Heterogeneous Data Sources ◽

Decision Support Framework ◽

Different Sources

To keep pace with the updates in obliging scientific discipline, thriving recuperating knowledge is being assembled incessantly. Regardless, inferable from the not too appalling gathering of its categories and sources, therapeutic knowledge has over up being significantly hugger-mugger in numerous specialist's work environments that it currently wants Clinical call Support (CDS) system for its affiliation. To reasonably utilize the party flourishing knowledge, we tend to propose a CDS structure which will distort mixed thriving knowledge from totally different sources, for example, take a goose at workplace check works out as planned, important info of patients and action records into a joined depiction of options everything thought-about. Victimization the electronic roaring healing knowledge therefore created, multi-name delineation was accustomed endorse a layout of afflictions and so facilitate consultants in diagnosis or treating their patients' therapeutic problems a lot of competently. Once the ace sees the contamination of a patient, the running with organize is to contemplate the conceivable complexities of that disarray, which may impel a lot of infections

Download Full-text

A Clinical Decision Support Framework for Heterogeneous Data Sources

IEEE Journal of Biomedical and Health Informatics ◽

10.1109/jbhi.2018.2846626 ◽

2018 ◽

Vol 22 (6) ◽

pp. 1824-1833 ◽

Cited By ~ 12

Author(s):

Mengxing Huang ◽

Huirui Han ◽

Hao Wang ◽

Lefei Li ◽

Yu Zhang ◽

...

Keyword(s):

Decision Support ◽

Clinical Decision Support ◽

Clinical Decision ◽

Heterogeneous Data ◽

Data Sources ◽

Heterogeneous Data Sources ◽

Decision Support Framework

Download Full-text

Patient Representation Learning from Heterogeneous Data Sources and Knowledge Graphs using Deep Collective Matrix Factorization: Evaluation Study (Preprint)

10.2196/preprints.28842 ◽

2021 ◽

Author(s):

Sajit Kumar ◽

Alicia Nanelia Tan Li Shi ◽

Ragunathan Mariappan ◽

Adithya Rajagopal ◽

Vaibhav Rajan

Keyword(s):

Decision Support ◽

Clinical Decision Support ◽

Matrix Factorization ◽

Representation Learning ◽

Clinical Decision ◽

Heterogeneous Data ◽

Biomedical Literature ◽

Data Sources ◽

Heterogeneous Data Sources ◽

Knowledge Graphs

BACKGROUND Patient Representation Learning aims to learn features, also called representations, from input sources automatically, often in an unsupervised manner, for use in predictive models. This obviates the need for cumbersome, time- and resource-intensive manual feature engineering, especially from unstructured data such as text, images or graphs. Most previous techniques have used neural network based autoencoders to learn patient representations, primarily from clinical notes in Electronic Medical Records (EMR). Knowledge Graphs (KG), with clinical entities as nodes and their relations as edges, can be extracted automatically from biomedical literature, and provide complementary information to EMR data that have been found to provide valuable predictive signals. OBJECTIVE We evaluate the efficacy of Collective Matrix Factorization (CMF) - both classical variants and a recent neural architecture called Deep CMF (DCMF) - in integrating heterogeneous data sources from EMR and KG to obtain patient representations for Clinical Decision Support Tasks. METHODS Using a recent formulation of obtaining graph representations through matrix factorization, within the context of CMF, we infuse auxiliary information during patient representation learning. We also extend the DCMF architecture to create a task-specific end-to-end model that learns to simultaneously find effective patient representations and predict. We compare the efficacy of such a model to that of first learning unsupervised representations and then independently learning a predictive model. We evaluate patient representation learning using CMF-based methods and autoencoders for two clinical decision support tasks on a large EMR dataset. RESULTS Our experiments show that DCMF provides a seamless way to integrate multiple sources of data to obtain patient representations, both in unsupervised and supervised settings. Its performance in single-source settings is comparable to that of previous autoencoder-based representation learning methods. When DCMF is used to obtain representations from a combination of EMR and KG, where most previous autoencoder-based methods cannot be used directly, its performance is superior to that of previous non-neural methods for CMF. Infusing information from KGs into patient representations using DCMF was found to improve downstream predictive performance. CONCLUSIONS Our experiments indicate that DCMF is a versatile model that can be used to obtain representations from single and multiple data sources, and to combine information from EMR data and Knowledge Graphs. Further, DCMF can be used to learn representations in both supervised and unsupervised settings. Thus, DCMF offers an effective way of integrating heterogeneous data sources and infusing auxiliary knowledge into patient representations.

Download Full-text

Cloud-Based System for Effective Surveillance and Control of COVID-19: Useful Experiences From Hubei, China

Journal of Medical Internet Research ◽

10.2196/18948 ◽

2020 ◽

Vol 22 (4) ◽

pp. e18948 ◽

Cited By ~ 11

Author(s):

Mengchun Gong ◽

Li Liu ◽

Xin Sun ◽

Yue Yang ◽

Shuang Wang ◽

...

Keyword(s):

Decision Support ◽

Mobile Devices ◽

Clinical Decision Support ◽

Syndromic Surveillance ◽

Improve Patient Care ◽

Clinical Effectiveness ◽

Clinical Decision ◽

Effective Control ◽

Multiple Sources ◽

Related Data

Background Coronavirus disease (COVID-19) has been an unprecedented challenge to the global health care system. Tools that can improve the focus of surveillance efforts and clinical decision support are of paramount importance. Objective The aim of this study was to illustrate how new medical informatics technologies may enable effective control of the pandemic through the development and successful 72-hour deployment of the Honghu Hybrid System (HHS) for COVID-19 in the city of Honghu in Hubei, China. Methods The HHS was designed for the collection, integration, standardization, and analysis of COVID-19-related data from multiple sources, which includes a case reporting system, diagnostic labs, electronic medical records, and social media on mobile devices. Results HHS supports four main features: syndromic surveillance on mobile devices, policy-making decision support, clinical decision support and prioritization of resources, and follow-up of discharged patients. The syndromic surveillance component in HHS covered over 95% of the population of over 900,000 people and provided near real time evidence for the control of epidemic emergencies. The clinical decision support component in HHS was also provided to improve patient care and prioritize the limited medical resources. However, the statistical methods still require further evaluations to confirm clinical effectiveness and appropriateness of disposition assigned in this study, which warrants further investigation. Conclusions The facilitating factors and challenges are discussed to provide useful insights to other cities to build suitable solutions based on cloud technologies. The HHS for COVID-19 was shown to be feasible and effective in this real-world field study, and has the potential to be migrated.

Download Full-text

Cloud-Based System for Effective Surveillance and Control of COVID-19: Useful Experiences From Hubei, China (Preprint)

10.2196/preprints.18948 ◽

2020 ◽

Cited By ~ 2

Author(s):

Mengchun Gong ◽

Li Liu ◽

Xin Sun ◽

Yue Yang ◽

Shuang Wang ◽

...

Keyword(s):

Decision Support ◽

Mobile Devices ◽

Clinical Decision Support ◽

Syndromic Surveillance ◽

Improve Patient Care ◽

Clinical Effectiveness ◽

Clinical Decision ◽

Effective Control ◽

Multiple Sources ◽

Related Data

BACKGROUND Coronavirus disease (COVID-19) has been an unprecedented challenge to the global health care system. Tools that can improve the focus of surveillance efforts and clinical decision support are of paramount importance. OBJECTIVE The aim of this study was to illustrate how new medical informatics technologies may enable effective control of the pandemic through the development and successful 72-hour deployment of the Honghu Hybrid System (HHS) for COVID-19 in the city of Honghu in Hubei, China. METHODS The HHS was designed for the collection, integration, standardization, and analysis of COVID-19-related data from multiple sources, which includes a case reporting system, diagnostic labs, electronic medical records, and social media on mobile devices. RESULTS HHS supports four main features: syndromic surveillance on mobile devices, policy-making decision support, clinical decision support and prioritization of resources, and follow-up of discharged patients. The syndromic surveillance component in HHS covered over 95% of the population of over 900,000 people and provided near real time evidence for the control of epidemic emergencies. The clinical decision support component in HHS was also provided to improve patient care and prioritize the limited medical resources. However, the statistical methods still require further evaluations to confirm clinical effectiveness and appropriateness of disposition assigned in this study, which warrants further investigation. CONCLUSIONS The facilitating factors and challenges are discussed to provide useful insights to other cities to build suitable solutions based on cloud technologies. The HHS for COVID-19 was shown to be feasible and effective in this real-world field study, and has the potential to be migrated.

Download Full-text

Report: Evaluating the ability of the TMA Clinical Decision Support platform to identify interventions in a clinical setting.

10.1101/2021.05.24.21257617 ◽

2021 ◽

Author(s):

Joshua Resnikoff ◽

Yessica M Giraldo ◽

Lina Williamson

Keyword(s):

Decision Support ◽

Clinical Decision Support ◽

Complex Disease ◽

Clinical Decision ◽

Small Sample ◽

Care Plan ◽

Sample Population ◽

Multiple Sources ◽

Personalized Care ◽

Care Plans

The TMA Precision Health Clinical Decision Support system is a commercially available software platform focused on the confirmation of a precision diagnosis and generation of a personalized care plan to rapidly deliver therapeutic optionality and improve quality of life for rare and complex disease patients. For this study, we worked with our partners in Medellin, Colombia to evaluate the efficacy of the platform in identifying previously unexplored modes of care within a small sample population of adult patients suffering from a diverse set of rare diseases. Although challenges were encountered during the curation of data from multiple sources, personalized care plans and medication options were identified successfully for 94% of cases, suggesting a high level of impact for deployment at scale.

Download Full-text