Slides and recording from 11.20.18 webinar.

The healthcare industry is in the midst of various challenges, including high costs, provider shortages, and protecting the privacy of sensitive patient information. New developments in Artificial Intelligence (AI) technologies provide organizations with exciting opportunities to address these challenges, especially as AI solutions become more advanced, available, and affordable. Is AI just what healthcare needs to rescue healthcare?

Join us for a webinar highlighting eHI’s recent AI initiatives with Booz Allen Hamilton and Cerner, including two reports, one summarizing our September Artificial Intelligence and Machine Learning Executive Roundtable Meeting and a report offering guidance to providers hoping to use these technologies. Speakers will breakdown the essentials of AI, provide specific examples of how and where AI is implemented today, review its potential to reshape pieces of healthcare entirely, and reveal what might stand in the way of reaching its full potential in healthcare. 

Speakers:

-- Lindsey Jarrett, Lead Strategist, Cerner's Intelligence Organization, Cerner

-- David Cohen, Division VP, Cerner

-- Matthew Keating, Director, Health accounts, Booz Allen Hamilton

Rural Individuals’ Telehealth Practices: An Overview

Telehealth—i.e., health services or activities conducted via phone, Internet, and other technologies—has emerged as a new way for consumers to meet their health care needs. The benefits of telehealth may be greater in rural areas, where remoteness and provider shortages may make accessing health care more difficult for rural residents. Using detailed 2015 household data, the report analyzes three basic telehealth activities as practiced by consumers age 15 or older: (1) online health research; (2) online health maintenance (communication with health providers, including communicating with medical practitioners, maintaining records, and paying bills); and (3) online health monitoring via devices that exchange data remotely with medical personnel. Rural residents were less likely than urban people to engage in the telehealth activities, with 17 percent of rural people conducting online health research, 7 percent engaging in online health maintenance, and 1.3 percent using online health monitoring (compared with 20 percent, 11 percent, and 2.5 percent of urban residents, respectively). Use of all of these telehealth activities increased among individuals with higher levels of education. Generally, use increased among individuals with higher household income, but income’s effect varied across the telehealth activities.

The full report from the U.S. Department of Agriculture's Economic Research Service can be downloaded below.  

FHIR Tools for Healthcare Interoperability

Electronic Health Records (EHR) is an essential element in human healthcare monitoring systems these days. As a large amount of data continues being archived and uploaded to healthcare repositories, virtually every second across the globe, vast amount of data mining tasks continue being modelled and modified to extract valuable decision support information. The Health Level 7 (HL7) consortium provides the framework and related standards for the exchange, integration, sharing, and retrieval of electronic health information that supports clinical practice, management and delivery. With the large number of Internet of Things (IoT) health care kits becoming available it has become increasingly difficult to log the realtime patient monitoring information to healthcare repositories. As patients continue being monitored in real-time it has become essential that the trauma events information such as stroke or cardiac arrhythmia be uploaded to the EHR in real-time. Currently available monitoring devices can monitor and analyse an abnormal condition but may not be able to upload these events in real-time. The proposed research focused on developing real-time interoperability tools and services, which can enable wearable IoT devices to interact with the EHR in real-time and can provide real-time decision support.

The Fast Healthcare Interoperability Resources (FHIR) specification was used to develop and encode trauma related information in terms of FHIR resources, conceptual and logical models using clinFHIR tools. A HAPIFHIR application was implemented on an IoT device which could upload real-time ECG, PPG and relevant trauma information on a test FHIR server. The HAPIFHIR application code could encapsulate ECG arrhythmia, vital signs and trauma events in a single observation and could upload it to the HAPIFHIR server. Several such observations could be linked to a patient context and could be observed in real time in EHR. The ECG, the PPG, vital signs and trauma events were encoded according to Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT) specifications. The alerts and alarms mechanism could assist the emergency response teams at the hospitals to prepare for an emergency well in time. An analogue front-end biomedical device was used for data acquisition and signal processing and the IoT devices were networked over wireless network to upload the events and observations to the FHIR server in real time. The system focussed on ‘preventive care’ as the next generation personalized health-care monitoring devices continue becoming available.

The full article can be downloaded below.  

Toward Addressing Social Determinants of Health: A Health Care System Strategy

In the US, there is growing recognition that social factors (eg, financial hardship, food insecurity, housing instability) influence individual and population health. This has led to increased efforts to address these social determinants of health (SDH) within the delivery system. Yet, limited information exists about the strategies health care systems employ to identify and address SDH. Kaiser Permanente Northwest (KPNW) is an integrated health care delivery system that has implemented a comprehensive approach toward addressing its patients’ SDH. This article describes the tools and processes used at KPNW for identifying and addressing SDH.

Tools included use of electronic health record-based data elements, International Classification of Diseases, Tenth Revision social diagnostic codes (Z codes), and the development of novel workflows via nonclinical patient navigators to address patients’ SDH through community resource referrals. Between March 31, 2016, and March 25, 2018, KPNW patient navigators screened patients with SDH.

Patient navigators screened 11,273 patients with SDH, identifying and documenting 47,911 SDH in the electronic health record. During the same 2-year period, 18,284 community resource referrals were made for 7494 patients.

The novel electronic health record-based tools developed by KPNW have led to standardized, measurable, and actionable SDH data being used to tailor and target specific resources to meet the identified needs of our patients. By disseminating information about these efforts at KPNW, we aim to help build an evidence basis of different approaches for addressing SDH within the health care system as well as defining opportunities to improve care efficiency for patients with SDH.

The full article can be downloaded below.  

What If AI Could Uber The Healthcare Industry?

Yes, it may seem like a stretch to imagine our complicated and flawed healthcare system changing overnight due to developments from AI startups. However, this is what’s meant by “little things add up.” In our lifetimes we have seen how the entrenched retail industry has morphed, taking down once seemingly invincible bastions, such as Sears. We have watched Uber challenge the taxi transportation model and Airbnb upset the regal hotels of yore. What might AI medical startups accomplish for the health industry? That future is uncertain. However, what's true is that change is in the air and that little things can add up ­— sometimes for good.

The full Forbes article can be viewed at this link.  

AI and the NHS: How artificial intelligence will change everything for patients and doctors

The current UK government has made its vision for artificial intelligence use in the NHS very clear. It wants AI, data and innovation to "transform the prevention, early diagnosis and treatment of chronic diseases by 2030", with the UK to be "at the forefront of the use of AI and data in early diagnosis, innovation, prevention and treatment".

Under this vision, AIs could ultimately become the first point of contact for the sick instead of a human doctor, could help healthcare professionals to diagnose medical conditions, and even monitor individuals' health by analysing data from their wearable devices or smart-home sensors.

It's a huge ambition for a set of technologies that are still developing, and whose use is relatively restricted in the health service today. Can AI really make a difference to the future of the NHS?

The full ZDNet article can be viewed at this link.  

Statement by FDA Commissioner Scott Gottlieb, M.D., on the FDA’s efforts to hold industry accountable for fulfilling critical post-marketing studies of the benefits, safety of new drugs

The FDA remains committed to ensuring that FDA-approved drugs are safe and effective for Americans. As part of this commitment, we require evidence from premarket clinical trials that the medicine will be both effective and safe for use when prescribed according to its labeling. However, it’s not unusual for the FDA to identify issues that need additional evaluation either at the time of initial approval or later, once the drug has been marketed. These issues are evaluated through the conduct of additional post-marketing studies.

Today we’re announcing our FY 2017 Report on the Performance of Drug and Biologics Firms in Conducting Postmarketing Requirements and Commitments. This report provides an update on how we’re doing at holding companies accountable for completing these important studies on time to ensure that our understanding of a drug’s safety and efficacy keeps pace with its use in all relevant populations once a product is approved. We’re committed to ensuring that PMRs and PMCs are conducted and reported as required, and to providing transparent access to the progress of these studies for the public.

The full statement can be viewed at this link.  

The 2017 report can be downloaded below.  

Burnout, Cognitive Overload, and Metacognition in Medicine

The number of physicians reportedly suffering from burnout, a phenomenon where the individual appears overwhelmed by tasks usually within their competence, has been increasing internationally. Burnout represents a large burden for the medical profession, from undergraduate training to the postgraduate world. The impact of burnout has effects on physician productivity, although the exact effect remain difficult to quantify. By extension, a physician suffering from burnout is likely to have ramifications to the wider team of colleagues. Evidence suggests that, independent to level of experience, the extent of the relationship between burnout and work extends beyond total capacity and directly affects patient safety. The widespread impact on burnout on both the providers and recipients of healthcare is therefore a critical aspect of clinical practice.

Factors affecting the phenomenon of physician burnout have been considered in literature, with reported risk factors being younger age, longer working hours with high workload, low job satisfaction, negative or poor personal relationships and interpersonal demands, job insecurity, and female gender, as well as a weak association with specialty. These findings place physicians in common with other healthcare professions. However, healthcare professions as a group stand apart as particularly prone to burnout. The implication of this suggests that risk factors are shared within the healthcare professions. This may also imply that risk reduction and prevention strategies can be applied across the spectrum. Prior to considering the prevention, it is invaluable to evaluate the stressors associated with healthcare that serve to predispose these professions to burnout.

The full commentary can be downloaded below.  

Using Aggregate Data on Health Goals, Not Disease Diagnoses, to Develop and Implement a Healthy Aging Group Education Series

The Healthy Aging Group Education Series was developed by interprofessional primary healthcare team members and researchers to address the health needs and goals of nutrition, fitness and function, and advance care planning identified using data from a randomized controlled trial. Older adults from one family practice were invited to attend the series and participate in the descriptive evaluation. The series was developed based on aggregated patient-reported data on health goals, risks, and needs gathered using a structured process. Surveys which included open-ended feedback and rated items of content and delivery evaluated the series. Program delivery expenses were itemized. Of 69 people invited, a range of 26 to 37 people attended sessions. The overall series was rated positively with respect to meeting attendees’ expectations and being well-organized; 69.2% and 76.9% of attendees gave a positive rating respectively. Individual session feedback indicated a range of positive ratings (82.8-100%) for categories of effective and engaging presenters and providing new and relevant information. The majority of attendees (76.9%) indicated they would recommend the series to friends. The series continues to be offered regularly in the family practice. The health goal information (and not disease diagnosis) that was used to develop and deliver the program resulted in a program that was well received by participants and sustainable in the family practice.

The full article can be downloaded below.  

Primary care physicians’ attitudes to the adoption of electronic medical records: a systematic review and evidence synthesis using the clinical adoption framework

Recent decades have seen rapid growth in the implementation of Electronic Medical Records (EMRs) in healthcare settings in both developed regions as well as low and middle income countries. Yet despite substantial investment, the implementation of EMRs in some primary care systems has lagged behind other settings, with piecemeal adoption of EMR functionality by primary care physicians (PCPs) themselves. We aimed to review and synthesise international literature on the attitudes of PCPs to EMR adoption using the Clinical Adoption (CA) Framework. MEDLINE, PsycINFO, and EMBASE were searched from 1st January 1996 to 1st August 2017 for studies investigating PCP attitudes towards EMR adoption. Papers were screened by two independent reviewers, and eligible studies selected for further assessment. Findings were categorised against the CA Framework and the quality of studies assessed against one of three appropriate tools. Out of 2263 potential articles, 33 were included, based in North and South America, Europe, Middle East and Hong Kong. Concerns about the accessibility, reliability and EMR utility exerted an adverse influence on PCPs’ attitudes to adoption. However many were positive about their potential to improve clinical productivity, patient safety and care quality. Younger, computer-literate PCPs, based in large/multi-group practices, were more likely to be positively inclined to EMR use than older physicians, less-skilled in technology use, based in solo practices. Adequate training, policies and procedures favourably impacted on PCPs’ views on EMR implementation. Financial factors were common system level influencers shaping EMR adoption, from start-up costs to the resources required by ongoing use. By using the CA Framework to synthesise the evidence, we identified a linked series of factors influencing PCPs attitudes to EMR adoption. Findings underline the need to involve end-users in future implementation programmes from the outset, to avoid the development of an EMR which is neither feasible nor acceptable for use in practice.

The full article can be downloaded below.