Challenges of developing a digital scribe to reduce clinical documentation burden

Clinicians spend a large amount of time on clinical documentation of patient encounters, often impacting quality of care and clinician satisfaction, and causing physician burnout. Advances in artificial intelligence (AI) and machine learning (ML) open the possibility of automating clinical documentation with digital scribes, using speech recognition to eliminate manual documentation by clinicians or medical scribes. However, developing a digital scribe is fraught with problems due to the complex nature of clinical environments and clinical conversations. This paper identifies and discusses major challenges associated with developing automated speech-based documentation in clinical settings: recording high-quality audio, converting audio to transcripts using speech recognition, inducing topic structure from conversation data, extracting medical concepts, generating clinically meaningful summaries of conversations, and obtaining clinical data for AI and ML algorithms.

The full article can be downloaded below.  

Resident-led organizational initiatives to reduce burnout and improve wellness

Professional burnout among medical trainees has been identified as a national concern in need of attention. A significant challenge for residency programs is designing and implementing effective strategies to promote resident wellness and reduce burnout. Emerging evidence highlights the importance of developing organizational changes targeting physician burnout.

To address this critical need, Harvard South Shore (HSS) Psychiatry Residency Training Program aimed to assess burnout among residents, identify areas for wellness-related growth, and implement strategies for organizational change to reduce burnout and increase wellness. We aligned closely to the Standards for Quality Improvement Reporting Excellence (SQUIRE) 2.0 guidelines to systematically approach planning, conducting, and evaluating this quality improvement effort. We developed a wellness action team and assessed burnout using the Copenhagen Burnout Inventory (CBI). We also conducted a survey to investigate high opportunity areas for wellness-related growth and using this data we designed and implemented four organizational initiatives to (i) improve residents’ on-call experience, (ii) increase social activities, (iii) support preventative care, and (iv) promote wellness education. We then re-assessed burnout 1 year after implementation and performed two-sample t-tests to compare CBI scores. We additionally gathered and analyzed feedback from residents on the implemented organizational initiatives’ relevance to wellness and their well-being.

There was an overall clinically meaningful reduction in burnout averaged among all residents that participated. Participants indicated that fitness-oriented activities were most likely to lead to change in wellness habits.

Our implemented wellness program was resident-led and involved continuous feedback from both residents and leadership. Given that there may be multiple factors that affect resident burnout, future studies involving a control group could help reveal whether our intervention contributed to the change in burnout scores we observed.

The full article can be downloaded below.  

A crisis brewing for the healthcare system and a crisis already happening for our students

Working in medicine has always been a stressful job for a number of reasons. Long hours, dealing with life and death situations day and night, lack of time to build personal relationships and stressors related to work-life balance contribute to personal stress. This is compounded by putting oneself second to the needs of others combined with changes in practice of medicine, technical advances and changing patient expectations among other factors. Furthermore, organisational and institutional pressures and structures can add to the burden of practising medicine. Medical students (doctors-in-training) carry with them a number of stress-inducing factors. First and foremost, they are in that vulnerable age group where two thirds of psychiatric disorders begin. Secondly, stressors of all types can contribute to the development of mental ill-health. The history of medicine tells us that doctors would often work hard and in relative isolation, but enjoyed extremely high social status and other rewards. This social contract with medicine has shifted significantly over recent decades, with doctors almost ubiquitously working in teams with other doctors, nurses, social workers and others. Indeed, health care overall is becoming much more collaborative and patients themselves are increasingly seen as a crucial part of the overall team in their care. This is undoubtedly welcome. At the same time, societal and financial rewards for doctors have lessened in many places alongside marked changes in patient expectations and changes in laws with clear emphasis on health as a commodity which can be bought and sold and patients being consumers who have greater understanding and can communicate widely using social media and other methods.

The full article can be downloaded below.  

Data exchanges based on blockchain in m-Health applications

The most important aspect of handling data in the healthcare industry is its seamless and secure transition across intercepting nodes. Effective elimination of third-party entities and ensuring direct links between patient and healthcare provider can result in the transmission of error-free, unduplicated data. The use of blockchains can open up opportunities to counter the current requirements due to their ability to safely share information across nodes and networks from the access point and secure the safety of transactions. Currently, sharing medical data is observed to be slow, incomplete, insecure, and provider-centric. These shortcomings prevent data interoperability and are a consequence of lack of foundational, structural, and semantic inoperability. By applying the blockchain technologies with appropriate markers, the safety of patient data can be ensured during data transmission. This paper evaluates the potential use of blockchain technology in association with mobile-based healthcare applications.

The full article can be downloaded below.  

Development of the mHealth App Trustworthiness checklist

Mobile health applications (mHealth apps) currently lack a consensus on substantial quality and safety standards. As such, the number of individuals engaging with untrustworthy mHealth apps continues to grow at a steady pace.

The purpose of this study was to investigate end-users’ opinions on the features or actions necessary for trustworthy mHealth apps; and to convey this information to app developers via a succinct but informative checklist: the mHealth app trustworthiness checklist.

The checklist was formulated in three stages: (a) a literature review of studies identified the desirable features of the most prolific mHealth apps (health and fitness apps); (b) four focus group sessions with past or current users of these apps (n ¼ 20); and (c) expert feedback on whether the checklist items are conceivable in a real-life setting (n ¼ 6).

Five major themes emerged from the focus group discussions: informational content, organizational attributes, societal influence, technology-related features, and user control factors. The mHealth app trustworthiness checklist was developed to incorporate these five themes and subsequently modified following expert consultation. In addition to the trustworthiness themes, we identified features that lie between trust and mistrust (limited digital literacy and indifference) as well as 10 features and actions that cause end-users to mistrust mHealth apps.

This study contributes to the evidence base on the attributes of trustworthy mHealth apps. The mHealth app trustworthiness checklist is a useful tool in advancing continued efforts to ensure that health technologies are trustworthy.

The full article can be downloaded below.  

How AI Is Helping Diagnose Rare Genetic Diseases

400 million people globally suffer from a rare disease. This is greater than the population of the United States, yet the ominous figures don't end there. According to the Global Genes organization, eight out of ten rare diseases are caused by a faulty gene, yet it takes an average of 4.8 years to arrive at an accurate diagnosis. This is part of the reason why 30% of children with a rare disease won't live to see their fifth birthday.

Neither is this situation helped by the fact that 95% of rare diseases lack an FDA-approved treatment. However, while the rarity of rare diseases means they're often neglected by the medical establishment, artificial intelligence and machine learning have been emerging in recent years as new, promising tools in the fight against uncommon pathology. Several companies are developing platforms that harness AI as a means to identify genetic variants at the roots of rare diseases, while medical researchers and practitioners are using these platforms or developing their own.

The full Forbes article can be viewed at this link.  

 Concrete Problems: Experts Caution on Construction of Digital Health Superhighway

If you’re used to health tech meetings filled with go-go entrepreneurs and the investors who love them, a conference of academic technology experts can be jarring.

Speakers repeatedly pointed to portions of the digital health superhighway that sorely need more concrete – in this case, concrete knowledge. One researcher even used the word “humility.”

The gathering was the annual symposium of the American Medical Informatics Association (AMIA). AMIA’s founders were pioneers. Witness the physician featured in a Wall Street Journal story detailing his use of “advanced machines [in] helping diagnose illness” – way back in 1959.

That history should provide a sobering perspective on the distinction between inevitable and imminent (a difference at least as important to investors as intellectuals), even on hot-button topics such as new data uses involving the electronic health record (EHR). 

The full Forbes article can be viewed at this link.  

Can Synthetic Biology Inspire The Next Wave Of AI?

In building the world’s first airplane at the dawn of the 20th century, the Wright Brothers took inspiration from the “insightful” movements of birds. They observed and reverse-engineered aspects of the wing in nature, which in turn helped them make important discoveries about aerodynamics and propulsion. 

Similarly, to build machines that think, why not seek inspiration from the three pounds of matter that operates between our ears? Geoffrey Hinton, a pioneer of artificial intelligence and winner of the Turing Award, seemed to agree: “I have always been convinced that the only way to get artificial intelligence to work is to do the computation in a way similar to the human brain.” 

So what’s next for artificial intelligence (AI)? Could the next wave of AI be inspired by rapid advances in biology? Can the tools for understanding brain circuits at the molecular level lead us to a higher, systems-level understanding of how the human mind works? 

The answer is likely yes, and the flow of ideas between learning about biological systems and developing artificial ones has actually been going on for decades. 

The full Forbes article can be viewed at this link.  

Top 10 Health Care Industry Predictions For The Year 2020

Here is how I see the dialog around our nation’s health care system evolving in 2020.

1. The push to deliver home-based care will continue
2. The balance of power will begin to shift from hospital systems back to physician groups
3. Drug pricing will continue to be a front-page issue; at the same time, pharmaceutical innovation will also dominate headlines
4. Medicare-for-All will quickly morph into “Medicare Advantage-for-All
5. Big Tech and Silicon Valley will continue to play in health care, but they won’t upend the system anytime soon
6. On a related note, big box retailers and other atypical organizations will attempt to enter the health care market with a big splash
7. Amid revelations about data privacy, companies that are transparent and ethical will come out ahead
8. When it comes to social determinants of health, expect more talk than action
9. Mental health conditions and substance abuse disorders will take the main-stage
10. The public will begin to examine the behaviors and practices of “non-profit” health systems

The full Forbes article can be viewed at this link.  

Artificial Intelligence Could Help Solve America's Impending Mental Health Crisis

Five years from now, the U.S.’ already overburdened mental health system may be short as many as 15,600 psychiatrists as the growth in demand for their services outpaces supply, according to a 2017 report from the National Council for Behavioral Health. But some proponents say that, by then, an unlikely tool—artificial intelligence—may be ready to help mental health practitioners mitigate the impact of the deficit.

The full TIME article can be viewed at this link.