Slides by Rashi Venkataraman, Executive Director, Prevention & Population Health, AHIP, presented at eHI's December 4, 2018 Healthcare Data Governance Board Executive Roundtable on putting Social Determinants of Health Data into action.

A US National Study of the Association Between Income and Ambulance Response Time in Cardiac Arrest

Our analysis demonstrated that EMS responding to low-income communities had a lower likelihood of meeting 8-minute and 15-minute national benchmarks compared with EMS responding to highincome communities and showed that the mean EMS response time, on-scene time, and transport time were longer in low-income communities, even after controlling for observable differences. Given that whether or not a patient survives cardiac arrest can depend on a matter of minutes, even small delays in EMS response times may negatively alter patient outcomes. Our findings are disturbing given that poorer neighborhoods have higher rates of disease and other structural disparities in health care access that further compound their risk for worse outcomes. Our study shows that these structural disparities begin as early as the initial EMS activation and the resulting services, which is an area previously more traditionally administered by public services and considered less vulnerable to market forces. Recent trends in the financing and delivery of prehospital care suggest that these disparities are likely to worsen unless fewer economically driven forces are introduced. Understanding where gaps exist can help guide improvements in policies and develop interventions to address prehospital care disparities and ultimately disparities in patient outcomes.

The full article can be downloaded below.  

Prevalence of and Factors Associated With Patient Nondisclosure of Medically Relevant Information to Clinicians

In this research we examined what information patients are most likely to avoid telling a clinician, with a focus on types of information that are basic and essential to health care (eg, medication use, health behaviors, disagreement with recommendations, or lack of understanding of instructions). We also examined the characteristics that are associated with withholding information from clinicians and the reasons for this nondisclosure, distinguishing between, for example, nondisclosure due to embarrassment vs privacy reasons.

The full article can be downloaded below.  

Predictive Modeling of 30-Day Emergency Hospital Transport of Patients Using a Personal Emergency Response System: Prognostic Retrospective Study

This study showed that remotely collected patient data using a PERS service can be used to predict 30-day hospital transport. Furthermore, linking these data to clinical observations from the EHR showed that predicted high-risk patients had nearly four times higher rates of emergency encounters in the year following the prediction date compared with low-risk patients. Health care providers could benefit from our validated predictive model by estimating the risk of 30-day emergency hospital transport for individual patients and target timely preventive interventions to high-risk patients. We are testing this hypothesis in a randomized clinical trial where risk predictions are combined with a stepped intervention pathway. This approach could lead to overall improved patient experience, higher quality of care, and more efficient resource utilization. Future studies should explore the impact of combined EHR and PERS data on predictive accuracy.

The full article can be downloaded below.  

Why Should You Care About Amazon's New Medical Language Processing Service

This week Amazon announced a new service called AWS Comprehend Medical at AWS Re:Invent 2018 that can potentially impact the whole medical records ecosystem. Although electronic health records (EHR) exist for more than a decade, the majority of historical patient data is still stored today as unstructured medical text, such as medical notes, prescriptions, audio interview transcripts, and printed pathology and radiology reports. Extracting meaningful information from these is still a time-consuming process, and either requires data entry by high skilled medical experts, or teams of developers writing custom code.

Comprehend Medical leverages Amazon’s AI technology to build a health record industry-specific solution, that uses natural language processing (NLP) to extract health-related text and data from virtually any medical record. Comprehend Medical empowers developers to process unstructured medical text and identify information such as patient diagnosis, treatments, dosages, symptoms and signs, and more. This will, in turn, help health care providers such as hospitals, insurers, and clinical trial investigators to improve clinical decision support, streamline revenue cycle and clinical trials management. Since Comprehend Medical has built-in HIPAA compliance, health care providers will be able to better address data privacy and protected health information (PHI) requirements. Other startups such as Mendel is building similar AI-powered medical data extraction platform for clinical data relevant to cancer research.

The full Forbes article can be viewed at this link.  

The First Frontier for Medical AI Is the Pathology Lab

Trained on vast troves of digitized slides showing an enormous variety of tumors, artificial-intelligence (AI) systems will likely provide more accurate diagnoses than human pathologists, at least on fairly rote diagnostic tasks. They may even pick up on subtle features that the best-trained human eyes could never see. In this crucial, high-stakes branch of medicine, AI tools may soon offer diagnoses—and treatment recommendations—that are as close to infallible as we’re likely to get in the foreseeable future. And they’ll do so in a matter of seconds.

Lately, dazzlingly high success rates for AI-based systems in recognizing the presence of certain specific illnesses have prompted speculation that such tools will replace doctors. But the developments in pathology show us a more likely outcome: that machines will make the ever-increasing complexity of modern medicine manageable for human beings. This human-machine combination will outperform what either could do individually. At first, the improvement will be small. But eventually, it will be great.

The full IEEE Spectrum article can be viewed at this link.  

How Blockchain Technology Could Disrupt Healthcare

From managing patient data to tracking drugs through the supply chain, blockchain could solve some of the healthcare industry’s biggest problems.

The healthcare industry is plagued by inefficiencies, errors, bureaucracy, and high administrative costs.

Could blockchain technology help solve some of these challenges?

For all the hype, there’s no question that blockchain’s distributed ledger technology can offer real value for the healthcare industry.

Blockchain could help solve some of the industry’s most pressing compliance, interoperability, and data security issues, as well as enable new patient-centric business models.

But unlocking blockchain’s potential for healthcare will be a slow process, and change is unlikely to come fast.

In this report, we analyze where blockchain is likely to be integrated into healthcare in the short, medium, and long term, based on known stakeholders, scalability requirements, and necessary safeguards.

The full CB Insights report can be viewed at this link.  

AI, working with standard CT scans, could help predict under-diagnosed conditions

Israeli healthcare system Calit Health System teamed with analytics company Zebra Medical Vision to develop ways artificial intelligence could be leveraged to help predict two major under-diagnosed medical conditions: osteoporotic fractures and coronary vascular events. Using CT scan data, the AI tools showed improvements in predicting instances of both.

In each case, when AI was paired with existing predictive and diagnostic measures it was able to improve both the "sensitivity and specificity" of the clinical predictions, leading to much better predictions of future health events, said Calit Health and Zebra Medical officials.

The full Healthcare IT News article can be viewed at this link.  

Precision immunoprofiling by image analysis and artificial intelligence

Clinical success of immunotherapy is driving the need for new prognostic and predictive assays to inform patient selection and stratification. This requirement can be met by a combination of computational pathology and artificial intelligence. Here, we critically assess computational approaches supporting the development of a standardized methodology in the assessment of immune-oncology biomarkers, such as PD-L1 and immune cell infiltrates. We examine immunoprofiling through spatial analysis of tumor-immune cell interactions and multiplexing technologies as a predictor of patient response to cancer treatment. Further, we discuss how integrated bioinformatics can enable the amalgamation of complex morphological phenotypes with the multiomics datasets that drive precision medicine. We provide an outline to machine learning (ML) and artificial intelligence tools and illustrate fields of application in immune-oncology, such as pattern-recognition in large and complex datasets and deep learning approaches for survival analysis. Synergies of surgical pathology and computational analyses are expected to improve patient stratification in immuno-oncology. We propose that future clinical demands will be best met by (1) dedicated research at the interface of pathology and bioinformatics, supported by professional societies, and (2) the integration of data sciences and digital image analysis in the professional education of pathologists.

The full article can be downloaded below.