A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis

Automated analysis of cardiac structure and function using machine learning (ML) has great potential, but is currently hindered by poor generalizability. Comparison is traditionally against clinicians as a reference, ignoring inherent human inter- and intraobserver error, and ensuring that ML cannot demonstrate superiority. Measuring precision (scan:rescan reproducibility) addresses this. We compared precision of ML and humans using a multicenter, multi-disease, scan:rescan cardiovascular magnetic resonance data set.

One hundred ten patients (5 disease categories, 5 institutions, 2 scanner manufacturers, and 2 field strengths) underwent scan:rescan cardiovascular magnetic resonance (96% within one week). After identification of the most precise human technique, left ventricular chamber volumes, mass, and ejection fraction were measured by an expert, a trained junior clinician, and a fully automated convolutional neural network trained on 599 independent multicenter disease cases. Scan:rescan coefficient of variation and 1000 bootstrapped 95% CIs were calculated and compared using mixed linear effects models.

Clinicians can be confident in detecting a 9% change in left ventricular ejection fraction, with greater than half of coefficient of variation attributable to intraobserver variation. Expert, trained junior, and automated scan:rescan precision were similar (for left ventricular ejection fraction, coefficient of variation 6.1 [5.2%–7.1%], P=0.2581; 8.3 [5.6%– 10.3%], P=0.3653; 8.8 [6.1%–11.1%], P=0.8620). Automated analysis was 186× faster than humans (0.07 versus 13 minutes).

Automated ML analysis is faster with similar precision to the most precise human techniques, even when challenged with realworld scan:rescan data. Assessment of multicenter, multi-vendor, multifield strength scan:rescan data (available at www.thevolumesresource. com) permits a generalizable assessment of ML precision and may facilitate direct translation of ML to clinical practice.

The full article can be downloaded below.  

Slides from eHI's 9.25.19 Data Analytics Task Force: Non-Traditional Sources of Data (Genetic and Genomics Data) Meeting providing an overview on the topic: Definitions, applications, value, challenges attaining value, trends, and resources.

Slides from eHI's 9.25.19 Data Analytics Task Force: Non-Traditional Sources of Data (Genetic and Genomics Data) Meeting presentation by Robert Freimuth, PhD​. Dr. Freimuth is Assistant Professor of Biomedical Informatics, Mayo Clinic; Co-chair on the HL7 Clinical Genomics workgroup; Co-chair of the Global Alliance for Genomics and Health’s “Genomic Knowledge Standards” work stream​; Co-chair of the Clinical Pharmacogenetics Implementation Consortium Informatics work group​; and Technical Director, ONC Sync for Genes project​.

Presentation covered many areas within the topic of genetic and genomics data, including pharmacogenomics, clinical decision support, data standards, data governance, and regulatory impacts.

eHI members may request a recording of the call by emailing Kayli.Davis@ehidc.org and Claudia.Ellison@ehidc.org.

A link to a recording of the webinar can be found below. To request a PDF of the presentation slides, please email contactus@inovalon.com.

Data-driven healthcare plays an integral role enabling access to patient data, but the industry still lacks broad connectivity between stakeholders invested in improving a patient’s health. This has proven to be particularly challenging for high-cost, high-touch patients who receive a large amount of their care through specialty pharmacies.

As one of the fastest growing capabilities to standardize healthcare data exchange, HL7® FHIR® is providing greater opportunities for data sharing and enabling organizations to leverage their existing systems to improve care delivery and patient outcomes.

Join industry experts to learn how leveraging provider Electronic Health Record (EHR) connectivity and real-time, bi-directional API / FHIR®-based clinical data exchange allows for greater transparency into the patient’s journey as he/she tackles the complicated nature of his/her diagnoses. This clinical data exchange can be further enhanced by layering on clinical intelligence which ensures that only the data that is most relevant to each patient’s unique clinical situation is exchanged.

Attendees will gain insight into the newest technology innovations that are meaningfully reducing time-to-fill, costs, and error rates, while empowering advanced functionality and focus on clinical and quality outcomes

Speakers:
-Rick Miller, Vice President, Clinical Services & Professional Services, AllianceRx Walgreens Prime
-Sean Creehan, President & General Manager, ScriptMed® Cloud, Inovalon
-Kate Eshelman, MD, MPH, Vice President, Clinical Enterprise Tools, Inovalon

Physician Suicide: A Call to Action

Physician suicide is topic of growing professional and public health concern. Despite working to improve the health of others, physicians often sacrifice their own well-being to do so. Furthermore, there are systemic barriers in place that discourage self-care and help-seeking behaviors among physicians. This article will discuss the relevant epidemiology, risk factors, and barriers to treatment, then explore solutions to address this alarming trend.

The full article can be downloaded below.  

Nursing Our Way to Better Health

Nurses have always been on the front lines of health care provision. Increasingly, they are on the front lines of health care reform. Almost all of the ideas put forward for US health care reform, from reducing treatment costs to improving patient safety to moving care into the community, involve a significant role for nurses.

There are real questions, however, about whether the economics will support the needed nursing care. Done right, nursing can be the lynchpin for a better, cheaper health system. But if we make the same mistakes with nurses as we did with physicians, we will have wasted another shot at health care improvement.

The full article can be downloaded below.  

Detecting conversation topics in primary care office visits from transcripts of patient-provider interactions

Amid electronic health records, laboratory tests, and other technology, office-based patient and provider communication is still the heart of primary medical care. Patients typically present multiple complaints, requiring physicians to decide how to balance competing demands. How this time is allocated has implications for patient satisfaction, payments, and quality of care. We investigate the effectiveness of machine learning methods for automated annotation of medical topics in patient-provider dialog transcripts.

We used dialog transcripts from 279 primary care visits to predict talk-turn topic labels. Different machine learning models were trained to operate on single or multiple local talk-turns (logistic classifiers, support vector machines, gated recurrent units) as well as sequential models that integrate information across talk-turn sequences (conditional random fields, hidden Markov models, and hierarchical gated recurrent units).

Evaluation was performed using cross-validation to measure 1) classification accuracy for talk-turns and 2) precision, recall, and F1 scores at the visit level. Experimental results showed that sequential models had higher classification accuracy at the talk-turn level and higher precision at the visit level. Independent models had higher recall scores at the visit level compared with sequential models.

Incorporating sequential information across talk-turns improves the accuracy of topic prediction in patient-provider dialog by smoothing out noisy information from talk-turns. Although the results are promising, more advanced prediction techniques and larger labeled datasets will likely be required to achieve prediction performance appropriate for real-world clinical applications.

The full article can be downloaded below.  

Distributed representation of patients and its use for medical risk adjustment

Efficient representation of patients is very important in the healthcare domain and can help with many tasks such as medical risk prediction. Many existing methods, such as Diagnostic Cost Groups (DCG), rely on expert knowledge to build patient representation from medical data, which is resource consuming and non-scalable. Unsupervised machine learning algorithms are a good choice for automating the representation learning process. However, there is very little research focusing on patient-level representation learning directly. In this paper, we proposed a novel patient vector learning architecture that learns high quality, fixed-length patient representation from claims data. In addition, our model can learn meaningful medical visit representation and medical code representation at the same time. We conducted several experiments to test the quality of our learned representation, and the empirical results show that our learned patient vectors are superior to vectors learned through other methods. We also used our patient vector on a real-world application, and it outperforms a popular commercial model. Lastly, we provide potential clinical interpretation for using our representation on predictive tasks, as interpretability is vital in the healthcare domain.

The full article can be downloaded below.  

A review on intelligent wearables: Uses and risks

Intelligent wearable technology is becoming very popular in application fields such as clinical medicine and healthcare, health management, workplaces, education, and scientific research. Using the four-element model of technological behavior, the first part of this review briefly introduces issues related to the uses of intelligent wearables, including the technologies (i.e., what kind of intelligent wearables are used?), the users (i.e., who use intelligent wearables?), the activities involving the technologies (i.e., in what activities or fields intelligent wearables are used?), and the effects of technology usages (i.e., what benefits intelligent wearables bring?). The second part of this review focuses on the risks of using intelligent wearables. This part summarized five common risks (i.e., privacy risks, safety risks, performance risks, social and psychological risks, and other risks) in the use of intelligent wearables. The review ends with a discussion of future research.

The full article can be downloaded below.