The digital health space refers to the integration of technology and health care services to improve the overall quality of health care delivery. It encompasses a wide range of innovative and emerging technologies such as wearables, telehealth, artificial intelligence, mobile health, and electronic health records (EHRs). The digital health space offers numerous benefits such as improved patient outcomes, increased access to health care, reduced costs, and improved communication and collaboration between patients and health care providers. For example, patients can now monitor their vital signs such as blood pressure and glucose levels from home using wearable devices and share the data with their doctors in real-time. Telehealth technology allows patients to consult with their health care providers remotely without having to travel to the hospital, making health care more accessible, particularly in remote or rural areas. Artificial intelligence can be used to analyze vast amounts of patient data to identify patterns, predict outcomes, and provide personalized treatment recommendations. Overall, the digital health space is rapidly evolving, and the integration of technology in health

Sunday, January 22, 2023

Medical Command Centers Take Flight

Hospitals have always been challenged with improving patient flow from emergency rooms, elective admissions to final discharge.  Inefficient utilization increases cost by decreasing reimbursements. 

Whether it is fee-for-service or managed care, the lack of proper utilization has the same effect. Computer guidance coupled with a command and control center helps hospital administrators to address this challenge.



January 16, 2023



The command center is abuzz as more than a dozen experts monitor the constant flow of real-time information. When alerts emerge on one of the 32 computer screens, team members jump into action to resolve problems that range from minor obstacles to mission-critical challenges.

This sleek, high-tech room looks like the  fabled site NASA uses to keep astronauts safe, but it is located inside Michigan Medicine’s University South Hospital in Ann Arbor.

Seven years in the making, this state-of-the-art facility – officially known as the M2C2: The Michigan Medicine Capacity Operations and Real Time Engagement Center – is improving patient care by leveraging real-time data and predictive analytics to not only identify bottlenecks and other barriers hindering care but also to get ahead of potential problems. Building on the success of similar initiatives at other cutting-edge hospitals, including Johns Hopkins and Yale in the United States and several medical centers outside the US, Michigan’s M2C2 reflects the innovative use of technology to enhance care and reduce costs.

The relationship between doctors, nurses and patients has always been at the heart of medicine and M2C2 is designed to improve outcomes by streamlining the complex behind-the-scenes logistical challenges that have profound impacts on the care they deliver.

In addition to expert caregivers, patients need hospital beds, MRI machines, surgical theaters, and recovery rooms and so much more available as needed so their treatment is a steady flow. The command center is designed to optimize these and other resources so that logistics do not impede care.

Hospitals have, of course, always addressed logistics. But they have typically been handled by separate units that did not have clear and easy channels of communication to seamlessly coordinate their actions. The rise of electronic health records during last decade, which greatly facilitates access to and the sharing of information across a hospital’s sprawling operations,  makes it not only possible but necessary to unify these efforts which impact patient experience and outcomes.

Command centers such as Michigan Medicine’s M2C2 bring together a broad range of trained experts, including patient flow coordinators, admission triage coordinators, admission triage associates, clinical expediters, data analysts, management and support staff who monitor and analyze data entered into the electronic health records system to improve capacity decision making. A few examples:

  • It is not uncommon for patients to remain in the hospital awaiting a test or lab result. Specially designed software alerts the command center to such instances, allowing staff to address the cause of the delay and, whenever possible, expedite care which allows patients to more quickly receive the care they need and be discharged, freeing up rooms and caregivers for others.
  • Traditionally, Mondays and Tuesdays have been slower days for surgeries, with demand building toward the end of the week. The command center deploys advanced analytics that help guide OR schedulers so they can smooth out these scheduling bumps, relieving pressure on surgical teams and facilities.
  • Advanced algorithms built into the command center dashboards enable staff to analyze a wide range of data to determine which patients might be vulnerable to deterioration and to get ahead of the situation.

As real-time information appears on the command centers dashboards, the team identifies issues that require further attention and work with various teams — including nursing, physicians, pharmacy, physical and occupational therapy, and radiology, to name a few – to address them.

Michigan’s M2C2 just began operating on Nov. 29 but similar initiatives at other institutions have shown significant benefits in patient care covering the full spectrum of services from admission to discharge. After opening its command center, Johns Hopkins Hospital in Baltimore reported that its critical care team was dispatched 63 minutes sooner to pick up patients via ambulance from outside hospitals and “a  60 percent improvement in the ability to accept patients with complex medical conditions from other hospitals around the region and country.” Patients were assigned to a bed “30 percent faster after a decision was made to admit him or her from the Emergency Department” and transfer delays from the operating room after a procedure was reduced by 70 percent. Hopkins also reported that “twenty-one percent more patients were discharged before noon.”

These are game-changing results. As my colleague Vikas Parekh, M.D., associate chief medical officer for U-M Health and an executive sponsor of the M2C2 project, put it, “If we get the right information at the right time to the right people, that will drive the right outcome for our patients.”

Marschall S. Runge, MD, PhD, is Executive Vice President for Medical Affairs and Dean of the Medical School for the University of Michigan. He serves on the Board of Directors for Eli Lilly and Company.

This article was originally published by RealClearHealth and made available via RealClearWire.

Sunday, January 15, 2023

Google Launches MedPaLM—the AI-Based Healthcare Answer System

Google Launches MedPaLM—the AI-Based Healthcare Answer System

Google Research and DeepMind have launched MedPaLM, an open-sourced large language model platform that is geared toward the medical domain.

According to Interesting Engineering, “It is meant to generate safe and helpful answers in the medical field. It combines HealthSearchQA, a new free-response dataset of medical questions sought online, with six existing open-question answering datasets covering professional medical exams, research, and consumer queries.

MedPaLM addresses multiple-choice questions and questions posed by medical professionals and non-professionals through the delivery of various datasets. These datasets come from MedQA, MedMCQA, PubMedQA, LiveQA, MedicationQA, and MMLU. A new dataset of curated, frequently searched medical inquiries called HealthSearchQA was also added to improve MultiMedQA.

The HealthsearchQA dataset consists of 3375 frequently asked consumer questions. It was collected by using seed medical diagnoses and their related symptoms. This model was developed on PaLM, a 540 billion parameter LLM, and its instruction-tuned variation Flan-PaLM to evaluate LLMs using MultiMedQA.

Med-PaLM currently claims to perform particularly well especially compared to Flan-PaLM. It still, however, needs to outperform a human medical expert’s judgment. Up to now, a group of healthcare professionals determined that 92.6 percent of the Med-PaLM responses were on par with clinician-generated answers (92.9 percent).

This is surprising as only 61.9 percent of the long-form Flan-PaLM answers were deemed to be in line with doctor assessments. Meanwhile, only 5.8 percent of Med-PaLM answers were deemed to potentially contribute to negative consequences, compared to 6.5 percent of clinician-generated answers and 29.7 percent of Flan-PaLM answers. This means that Med-PaLM replies are much safer...

This isn’t the first time Google ventured into AI-based healthcare. In May of 2019, Google joined up with medical researchers to train its deep learning AI to detect lung cancer in CT scans, performing as well as or better than trained radiologists, achieving just over 94 percent accuracy.

In May of 2021, Google rolled out a diagnostic AI for skin conditions on smartphones, which would allow every smartphone owner to have an idea of what their diagnosis might be. The app did not replace the role of a professional dermatologist, but it was a significant step forward for the field of AI healthcare.”

According to a physician blog published on Medium, “While the MedPaLM model performance was impressive and certainly superior to other NLP models investigated to date, it was still inferior to clinicians, particularly in incorrect retrieval of information (16.9% for MedPaLM vs 3.6% for human clinicians), evidence of incorrect reasoning (10.1% vs 2.1%) and inappropriate/incorrect content of responses (18.7% vs. 1.4%).

Bottomline, a huge step forward both in moving the needle towards a viable LLM that can be used for clinical knowledge, as well as in establishing frameworks to evaluate such models.

The high bar of safety that will be expected of such models before they can be used in practice, along with the fact that we need to investigate and shed light on bias and fairness in their functioning, means more work needs to be done. However, health-data trained LLMs, such as MedPaLM and the amusingly-named GatorTron, are paving the way.”


Thursday, January 12, 2023

ChatGPT for healthcare: Google / DeepMind’s MedPaLM and predictions for 2023 | by Puneet Seth | Jan, 2023 | Medium

As of December 13, 2022, ChatGPT, the new language processing AI from OpenAI, is making waves in the tech industry. The advanced model, which is trained to generate human-like text, is already being hailed as a game-changer for businesses that rely on natural language processing.

ChatGPT’s ability to understand and respond to a wide range of topics has been particularly impressive, with some even suggesting that it has the potential to revolutionize the way we interact with technology. Many experts believe that ChatGPT’s advanced capabilities will be a valuable asset for companies in fields such as customer service, online education, and market research.

One of the key advantages of ChatGPT is its ability to learn and adapt quickly to new information. This means that it can be trained to handle new topics and tasks without the need for extensive retraining. Additionally, ChatGPT is highly scalable, which makes it well-suited for use in large-scale applications.
So far, the response to ChatGPT has been overwhelmingly positive, with many praising its advanced capabilities and ease of use. It remains to be seen how ChatGPT will be used in the coming years, but it’s clear that it has the potential to be a major player in the world of natural language processing.





While #chatgpt has been hogging the limelight as of late on all matters associated with AI and LLM (large language models), the research teams at Google and DeepMind quietly published a paper last week outlining their impressive work in developing an open source LLM tool called Med-PaLM. Unlike ChatGPT, which is trained on an extraordinarily massive but broad range of datasets for the purpose of serving as a general natural language tool, #MedPaLM was designed to respond to medical questions, either from medical professionals or consumers (i.e. patients).

To do this, the team created a new dataset of medical questions (to serve as a benchmark) by combining 6 existing datasets. They then evaluated the performance of the model by analyzing its responses to questions based on factuality, precision, possible harm and bias.

What did they find?

While the MedPaLM model performance was impressive and certainly superior to other NLP models investigated to date, it was still inferior to clinicians, particularly in incorrect retrieval of information (16.9% for MedPaLM vs 3.6% for human clinicians), evidence of incorrect reasoning (10.1% vs 2.1%) and inappropriate/incorrect content of responses (18.7% vs. 1.4%).

Bottomline, MedPalM is a huge step forward both in moving the needle towards a viable LLM that can be used for clinical knowledge, as well as in establishing frameworks to evaluate such models.










ChatGPT for healthcare: Google / DeepMind’s MedPaLM and predictions for 2023 | by Puneet Seth | Jan, 2023 | Medium

Wednesday, January 4, 2023

Protecting users of digital mental health apps | World Economic Forum


The impact of using digital mental health apps.

The COVID-19 crisis has uncovered an enduring mental health epidemic globally.

New ethical questions about the safety, efficacy, equity and sustainability of digital mental healthcare – online and through apps – are being raised around the world, and businesses are being held to account over their creation and endorsement of services.

Over 10,000 mental health apps are currently on the market, yet regulations do not fully protect against the sharing of sensitive consumer data or ensure a standard quality of, for example, chatbot psychologists. Telehealth has contributed to solving the paucity of mental health providers.  This was even more apparent during the COVID pandemic. The pandemic fueled a large uptake in the use of telehealth during the necessity of social distancing. 


Not only is telehealth used for telemedicine there are also numerous mental health apps available for patients.


Best overall: Moodkit

Best for therapy: Talkspace

Best for meditation: Headspace

Best for suicide awareness: Better Stop Suicide

Best for stress: iBreathe

Best for anxiety: MindShift CBT

Best for addiction: Quit That!

Best for boosting your mood: Happify

Best for eating disorders: Recovery Record

Best for OCD: NOCD

Best for sleep: Calm

Best for drinking less alcohol: Reframe

Best for quitting alcohol: I Am Sober



Mental Health the Trillion Dollar Challenge (Spotify)

What’s the challenge?

Between a quarter and half of the global population is affected by a mental disorder at some point in their life. Between 2011 and 2030, the cumulative economic output loss associated with mental disorders is projected to be $16.3 trillion worldwide.

Disruptive technologies – such as artificial intelligence and machine learning, digital reality, blockchain, and the cloud – are ushering in a new era for consumers, industries, and organizations. There are more than 10,000 mental health apps in the Apple App Store and the Google Play Store alone. Many of these 10,000 apps are not currently evidence-based, placing users at significant risk in some cases. Deloitte analyzed 190 global high-traction use cases for the toolkit, revealing 89% of the apps are not clinically validated.


Web 3.0, Virtual Reality, and the Metaverse will also contribute to new online therapies.


Online platforms have the potential to engage patients in a patient-centric manner.



Try Healium



The uptick in VR meditation parallels an avalanche of smartphone apps for mental health, which total about 20,000. VR is more immersive than smartphones and, some say, can enable feelings of awe, relaxation, mindfulness, and connection with fellow meditators— or their avatars, at least





Protecting users of digital mental health apps | World Economic Forum