Mayo Clinic launches AI startup program to help early-stage companies get market-ready

Mayo Clinic launched its artificial intelligence startup program this week with four early-stage health tech companies. The program also features additional expert assistance from Google and electronic health records giant Epic.

This is a 20-week program called Mayo Clinic Platform_Accelerate. The aims are to help AI-based startups get market-ready by offering access to Mayo Clinic experts in regulatory, clinical, technology and business domains with a focus on AI model validation and clinical readiness.

According to John Halamka, M.D., president of the Mayo Clinic Platform, “Health tech startups are critical contributors to the cycle of innovation. We are excited to collaborate with these innovators to solve some of the most complex problems in medicine today.”

Mayo Clinic says its AI startup program is different from other typical accelerator programs. It focuses on helping drive a company’s success with valuable in-kind investments—from data sets to validation tools and from mentorship to clinical workflow planning, the company said on the program website.

As part of this in-kind investment, Mayo Clinic Platform will take an equity position in participating startups based on most recent valuations or a convertible note or SAFE, the organization said.

The four participating companies will work with data science experts to delineate AI model requirements, check for fairness and bias in their AI models and gain an understanding of the Food and Drug Administration clearance pathways.

The startups also will gain access to de-identified Mayo Clinic patient data, conduct model validation with guidance from data science experts, plan clinical validation studies such as clinical simulation or clinical trials and explore the potential to partner with Mayo.

Link: Mayo Clinic Platform_Accelerate

Predicting Early Antidepressant Outcomes For Children and Adolescents with MDD Using AI

Mayo Clinic researchers have taken the first step in using artificial intelligence (AI) to predict early outcomes with antidepressants in children and adolescents with major depressive disorder, in a study published in The Journal of Child Psychology and Psychiatry.

In the study, researchers identified variation in six depressive symptoms: difficulty having fun, social withdrawal, excessive fatigue, irritability, low self-esteem and depressed feelings.

They assessed these symptoms with the Children’s Depression Rating Scale-Revised to predict outcomes to 10 to 12 weeks of antidepressant pharmacotherapy:

  • The six symptoms predicted 10- to 12-week outcomes at four to six weeks in fluoxetine testing datasets, with an average accuracy of 73%.
  • The same six symptoms predicted 10- to 12-week outcomes at four to six weeks in duloxetine testing datasets, with an average accuracy of 76%.
  • In placebo-treated patients, predicting response and remission accuracy was significantly lower than for antidepressants at 67%.

According to the researchers, ‘these outcomes show the potential of AI and patient data to ensure children and adolescents receive treatment that has the highest likelihood of delivering therapeutic benefits with minimized side effects. We designed the algorithm to mimic a clinician’s logic of treatment management at an interim time point based on their estimated guess of whether a patient will likely or not benefit from pharmacotherapy at the current dose,” says Dr. Athreya, lead author. “Hence, it was essential for me as a computer engineer to embed and observe the practice closely to not only understand the needs of the patient, but also how AI can be consumed and useful to the clinician to benefit the patient.”

This preliminary work suggests that AI has promise for assisting clinical decisions by informing physicians on the selection, use and dosing of antidepressants for children and adolescents with major depressive disorder,” says Paul Croarkin, D.O., a Mayo Clinic psychiatrist and senior author of the study. “We saw improved predictions of treatment outcomes in samples of children and adolescents across two classes of antidepressants.”

Key points from the study

  • The optimal treatment of depression in children and adolescent is a substantial public health problem.
  • Machine learning and probabilistic graphical models were used to predict treatment outcomes with antidepressants in a training and testing databases.
  • Variation in six depression symptoms predicted outcomes with fluoxetine or duloxetine.
  • Future work should augment probabilistic graphical models with biological data to refine tools to assist decision making in clinical practice.

This work was a collaborative effort between the departments of Molecular Pharmacology and Experimental Therapeutics, and Psychiatry and Psychology, at Mayo Clinic, with support from Mayo Clinic’s Center for Individualized Medicine.

Study:
Athreya AP, Vande Voort JL, Shekunov J, et al. The Journal of Child Psychology and Psychiatry. 15 March 2022

Long-term Risks of Mental Health Outcomes Post-Covid-19

The short-term consequences from COVID-19 have been described after the initial “acute” infection passes. These have included not only a variety of physical symptoms, but also psychiatric symptoms have been reported. A team of VA researches has been shining a light on various dangerous and enduring consequences that can arise following the initial COVID bout. These COVID complications include mental health disorders.

A study published this week in the British Medical Journal (BMJ) by researchers with the VA St. Louis Health Care System focused on mental health disorders following COVID-19 infection.  They found that, even in people not needing hospitalization while infected with COVID-19, serious health issues related to mental health could persist, or pop up, in the weeks and months following the acute stage. They describe that the reasons for the increased mental health risks after COVID are not completely clear. Biologic changes may occur in the body that affect the brain, and nonbiologic changes such as social isolation and trauma may also be at play.

The researchers analyzed medical records in a database within VA, which operates the largest integrated health care system in the United States. The analysis included nearly 154,000 patients who had tested positive for COVID-19 in a defined time frame from March 2020 into January 2021. (The time frame predated the delta and omicron variants, as well as wide availability of vaccines.) A comparison was made of these patients’ health information with data from more than 11 million people who had not had COVID-19 infection—about half of them from the same time frame and the other half from a pre-pandemic timespan.

The research group compared the mental health risks for those who had COVID-19 and survived the first 30 days of infection with the same health outcomes among those who were not infected. Over a study period of about a year, the researchers identified elevated risks for issues such as anxiety, depression, stress disorders, opioid use, substance use disorders, and sleep conditions. 

“We’ve all suffered some sort of distress from this pandemic—maybe a measure of anxiety or difficulty sleeping,” says lead investigator Al-Aly. “But these challenges are magnified, especially in those who were admitted to the hospital during the acute part of their COVID battle but also in many who experienced only mild or moderate symptoms.”

Compared to those who did not have COVID, those in the COVID group had a 60 percent higher risk of having any mental health disorder or mental health-related prescriptions.

Findings by the type of mental health issue were:

  • Anxiety: 35 percent higher risk in the COVID-19 group
  • Depression: 39 percent higher risk
  • Sleep disorder: 41 percent higher risk
  • Opioid use: 76 percent higher risk
  • Opioid use disorder: 34 percent higher risk
  • Non-opioid substance use disorders: 20 percent higher risk.
Hospitalized COVID-19 patients fared the worst. (BMJ 2022)

Given the large number of people with COVID-19, these findings could translate into a huge impact in the United States and around the world, the authors point out. A strength of our research was the large number of patients and the ability to leverage the breadth and depth of the VA’s electronic health records system,” highlights Al-Aly. As a pioneer in the use of electronic health records, VA “can offer answers to questions about areas including the pandemic that would be hard for others to address.”

The researchers were a multidisciplinary research team for making the rigorous analysis possible brought together public health experts from across disciplines, successfully marrying the medical and research perspectives. An Editorial in the BMJ by lead researcher points out that mental health disorders represent one part of the multifaceted nature of long covid which can affect nearly every organ system (including the brain, heart, and kidneys). Our results should be used to promote awareness of this risk among people with covid-19 and to guide efforts for the early identification and treatment of affected individuals.

Research Article: Xie Y, Xu E, Al-Aly Z. Risks of mental health outcomes in people with covid-19: cohort study. BMJ 2022; 376 (Published 16 February 2022)

Research shows that gender, specialty, geography are among the top factors contributing to EHR overtime work for clinicians

The amount of time spent on after-hours EHR documentation is one of the main factors driving clinicians’ burnout. Clinicians’ specialty, gender, region and organizational structure are the four main factors determining how much time they spend on this after-hours work, according to study results released Jan. 25 by EHR company Athenahealth.

This new research from athenahealth on the time clinicians spend documenting in the EHR finds that the ongoing stressors of the pandemic and a critical staffing shortage make now a more important time than ever to address the related factors that are likely to impact clinicians’ satisfaction and wellbeing.

The research team analyzed 8.1 million hours of active EHR work completed by 14,520 clinicians using Athenahealth software over a five-month period in the first half of 2021.

Four major issues were highlighted by the research team:

1. Healthcare organizations requiring more complex documentation have clinicians who spend more time in the EHR, both during and outside patient hours. These organizations tend to be larger and have more detailed policies on charting, as well as a more varied mix of payer contracts and fee structures, according to the study.

2. The weekly number of hours a clinician spends in the EHR varies by specialty. The study found adult primary care clinicians spend the most time in the EHR per week, followed by neurologists. Mental Health clinicians are not far behind in the number of hours.

3. Female and male clinicians spend the same amount of time cumulatively on EHR documentation per week. However, female clinicians spend more time on documentation on a per-patient basis, scheduling an average of 60 visits per week, compared with their male counterparts, who schedule an average of 73. Gender differences in documentation minutes per visit is at least 20 percent across most clinician specialties, according to the study.

4. Given female clinicians’ likelihood to spend more time in the EHR and the more equal clinician gender ratio in New England and the Middle Atlantic, clinicians in the Northeast spend more time on EHR documentation than other regions in the U.S.

One major difference between specialties is in the number of patient visits they schedule each week. Despite data showing that orthopedic surgeons schedule the most patients weekly, they spend the least amount of time in the EHR as compared to other top specialties. Mental health clinicians see the fewest patients, as they tend to have longer, more conversational encounters that are one-on-one.

Determining the reasons why burnout is correlated with specialty may ultimately lead to how to solve – or at least better address – some of healthcare’s most pressing challenges. The volume of quality measures that clinicians must meet if their organizations are involved in risk-based contracts can vary widely. Primary care physicians, for instance, typically have more quality measures to account for versus orthopedists. Other factors contributing both to EHR time and burnout include regional market competition and gender, for instance.

This new research from Athenahealth on the time clinicians spend documenting in the EHR finds that the ongoing stressors of the pandemic and a critical staffing shortage make now a more important time than ever to address the related factors that are likely to impact clinicians’ satisfaction and wellbeing.

Source: Athenahealth Survey of how much time clinicians spend in the EHR. Publ: Jan 26, 2022

A Virtual Reality Shopping Environment Could Help Evaluate Cognitive Deficits or Decline in Adults

New research published in the Journal of Medical Internet Research, uses a novel virtual reality shopping task called “VStore” to measure cognition, which asks participants to take part in tests designed to mirror the real world. Researchers hope that it will be able to test for age-related cognitive deficits and future cognitive decline.

In the ‘VStore’, participants “go to the shops” to navigate a shopping scenario as a way of assessing functional cognition, as well as the thinking and processing skills needed to accomplish complex everyday activities. The immersive environment (a virtual shop) mirrored actiities encountered in everyday life and meant that participants were better able to engage brain structures that are associated with spatial navigation, such as the hippocampus and entorhinal cortex, both of which can be affected in the early stages of Alzheimer disease.

The trial recruited 142 healthy individuals aged 20-79 years. Each participant was asked to “go to the shops,” first verbally recalling a list of 12 items, before being assessed for the amount of time it took to collect the items, as well as select the corresponding items on a virtual self-checkout machine, pay, and order coffee.

Cognition tests, such as those used to measure the deficits present in several neuropsychiatric disorders including Alzheimer’s disease, schizophrenia, and depression, are traditionally time-consuming and onerous. Vstore—the technology that the researchers used in this study—is designed to overcome these limitations to provide a more accurate, engaging, and cost-effective process to explore a person’s cognitive health.

Researchers were able to establish that Vstore effectively engages a range of key neuropsychological functions simultaneously, suggesting that the functional tasks embedded in virtual reality may engage a greater range of cognitive domains than standard assessments.

Reference:
Lilla Alexandra Porffy, Mitul A. Mehta, Joel Patchitt, Celia Boussebaa, Jack Brett, Teresa D’Oliveira, Elias Mouchlianitis, Sukhi S. Shergill. A Novel Virtual Reality Assessment of Functional Cognition (VStore): Validation Study (Preprint)Journal of Medical Internet Research, 2021; DOI: 10.2196/27641

Non-Invasive Vagus Nerve Stimulation for Treatment of Posttraumatic Stress Disorder

A Vagus Nerve Stimulation(nVNS) device called gammaCore™, this week has received a Breakthrough Designation from the U.S. Food and Drug Administration (FDA) for the treatment of posttraumatic stress disorder (PTSD) after showing a reduction of symptoms of PTSD by 31% when compared to sham treatment.

The Breakthrough Device Designation was supported, in part, by research from an Emory-Georgia Tech team led by J. Douglas Bremner, M.D., in the Departments of Psychiatry and Radiology at the Emory University School of Medicine, and Omer T. Inan, Ph.D., from the School of Electrical and Computer Engineering and the Coulter Department of Biomedical Engineering at the Georgia Institute of Technology in Atlanta, Georgia. Their research, built upon a strong mechanistic rationale and animal studies, shows nVNS blocks sympathetic and inflammatory responses to memories of traumatic events in patients with PTSD, modulates brain responses to traumatic memory, and reduces symptoms of PTSD by 31% when compared to a sham stimulation.

The Breakthrough Devices Program is a voluntary program for certain medical devices and device-led combination products for more effective treatment or diagnosis of life-threatening or irreversibly debilitating diseases or conditions.

The goal of the Breakthrough Devices Program is to provide patients and health care providers with timely access to critical medical devices by speeding up their development, assessment, and review, while preserving the statutory standards for premarket approval, 510(k) clearance, and De Novo marketing authorization, consistent with the FDA’s mission to protect and promote public health.

Why PTSD?

PTSD is a highly prevalent and disabling disorder with limited approved treatment options. According to the U.S. Department of Veterans Affairs National Center for PTSD, approximately 15 million adults in the U.S. experience PTSD each year. In the Military and Veterans Administration alone, PTSD is reported to affect between 10-20% of veterans who served in each Operations Iraqi Freedom (OIF) and Enduring Freedom (OEF), the Gulf War (Desert Storm), and the Vietnam War. More than half of all patients with PTSD report severely impaired quality of life in areas including mood, social and family relationships, leisure activities, sense of well-being and life satisfaction.

According to one of the investigators, Dr. Douglas Bremner commented, “Current treatments for PTSD involving medication and psychotherapy have limitations due to limited efficacy, possible side effects, and the unwillingness of many PTSD patients to engage in therapies that involve reliving traumatic memories. gammaCore represents a new class of treatment separate from medication or psychotherapy that is safe, relatively free of side effects, and does not involve costly and invasive procedures for implantation, like previous VNS devices approved by the FDA for treatment of refractory depression.”

Gammacore device has been previously approved by the FDA for: (Source: https://www.gammacore.com/)

Migraine – Clinically proven to treat and prevent migraines in users ages 12 and up. Help reduce migraines days without additional drugs.

Cluster Headache – The only clinically proven device to treat and prevent cluster headache attacks, while providing fast, reliable relief for those suffering with cluster headache.

Hemicrania Continua (HC) & Paroxysmal Hemicrania (PH) – 1st and ONLY device for HC and PH treatment, proven to reduce pain severity or headache frequency.

COVID-19 – Emergency Use Authorization to treat users with known or suspected COVID-19 and experiencing reduced airflow.

Sources:

FDA
Fact sheet for healthcare workers

Instructions for use of gammaCore

gammaCore™ Press release

Exploring problematic smartphone use during pandemic

Smartphones have become people’s daily companions and an integral part of our lives and interactions with information and other people. Through mobile Internet access, smartphones allow quick access and provide up-to-date news around the globe and in the life of family and friends.  In addition to the active online interaction, one can passively observe the online behavior of others by checking their updates and depending on privacy settings, we can track when our friends are online, and whether they have read our recent messages. 

Essentially “smartphones not only satisfy our need for belonging; they also can contribute to the satisfaction of another important human need—the sense of control.” Previous research has demonstrated that smartphone use has significantly increased during the COVID-19 pandemic. While smartphones can enhance daily routines and social connection, studies has also shown that smartphone use can become problematic and negatively affect relationships, work, and mental or physical health. A more complete understanding of factors that may contribute to problematic smartphone use (PSU) could help inform efforts to prevent and manage such behavior.

To provide new insights, researchers from the University of Bochum in Germany conducted an online survey of 516 smartphone users aged 18 and over in Germany in April and May of 2021. The survey included questions to evaluate self-reported smartphone use as well as sense of control, fear of missing out, and repetitive negative thinking—three factors that the researchers hypothesized could contribute to problematic smartphone use, particularly during the COVID-19 pandemic. 

Statistical analysis of the survey results found that those individuals who reported experiencing low sense of control, fear of missing out, and repetitive negative thinking,and indeed, all were associated with greater severity of problematic smartphone use.

Moderating effect of repetitive negative thinking on the connection between fear of missing out and problematic smartphone use (N = 516).

While the findings do not prove causation, the statistical analysis also suggested possible interactions between the four factors. For one, fear of missing out may be a key mechanism by which low sense of control could lead to problematic smartphone use. Meanwhile, a higher degree of repetitive negative thinking was associated with a stronger relationship between fear of missing out and problematic smartphone use.

The sample was comprised of mostly female and rather young participants; the authors suggest that the study should be replicated in more age and gender balanced samples from other countries, to ensure the results are generalizable to other populations. Furthermore, the study was conducted during the pandemic when participants’ usual daily routines may have been disrupted, possibly affecting the participants’ sense of control. Nonetheless, the findings are in line with the hypothesis that loss of control—as experienced by some during the pandemic—could boost the risk of problematic smartphone use.

Source: Brailovskaia J, Stirnberg J, Rozgonjuk D, Margraf J, Elhai JD (2021) From low sense of control to problematic smartphone use severity during Covid-19 outbreak: The mediating role of fear of missing out and the moderating role of repetitive negative thinking. PLoS ONE 16(12): e0261023. https://doi.org/10.1371/journal.pone.0261023

Social media use shown to be linked to depression in adults

Data shows that individuals over age 35 were mostly likely to be negatively affected by highly visual apps, such as TikTok and Snapchat.

A number of recent studies have focused on adolescents and young adults being negatively affected by frequent use of social media. Symptoms of diminished well-being and greater levels of anxiety and depression were commonly reported. A research question asked if these same symptoms might apply to older consumers of social media.

To investigate this question, data from multiple waves of an ongoing 50-state US survey as used. The surveys, conducted from May 2020 through May 2021, were initially focused on learning more about how adults were coping during the Covid-19 pandemic. Over time, researchers increasingly became interested in whether social media use might be linked to changes in mental health.

The survey initially asked people who were not expressing depressed feelings about their social media use, with subsequent queries to see if the people who were using certain kinds of social media were more likely to be depressed. The research does not prove social media causes depression. Indeed, it is possible that people already prone to feeling sad were more likely to log on to such sites.

Compared to adults who did not use social media, “people who were using Facebook, people who were using TikTok, and people who were using Snapchat were substantially more likely to come back and tell us they felt depressed the next time they filled out the survey,” reported Roy H Perlis, MD, a professor of psychiatry at Harvard Medical School and Massachusetts General Hospital.

The research also found age differences in how certain platforms impacted mental health. Depressive symptoms were more commonly reported among Facebook users under age 35 than older adults. The opposite was true for users of Snapchat and TikTok more depressive symptoms were reported among people over age 35.

The reasons for such findings were unclear. It could be that because Snapchat and TikTok are more visual mediums, perhaps affecting older adults differently. Or it could suggest that a person is out of sync with his or her peers. Perlis said more research is needed to interpret the results appropriately. Ultimately, experts recommend remaining mindful of time spent on social media.

The authors concluded that  “Among survey respondents who did not report depressive symptoms initially, social media use was associated with greater likelihood of subsequent increase in depressive symptoms after adjustment for sociodemographic features and news sources. These data cannot elucidate the nature of this association, but suggest the need for further study to understand how social media use may factor into depression among adults.”

Mitch Prinstein, PhD, chief science officer for the American Psychological Association commenting on this research pointed out that “Our brains were not built for this kind of social interaction. And social media is kind of hijacking the need for social interaction with something very artificial and insufficient,” he said. “Social media is the empty calories of social interaction.”

Sources:

Perils RH, Green J, Simonsson M, et al. Association Between Social Media Use and Self-reported Symptoms of Depression in US Adults. JAMA Netw Open. 2021;4(11):e2136113. doi:10.1001/jamanetworkopen.2021.36113

NBC News

FCC Votes to Allow Texting ‘988’ to Reach the National Suicide Prevention Lifeline Beginning July 2022

On July 16, 2020, the FCC adopted rules to establish 988 as the new, nationwide, easy-to-remember 3-digit phone number for Americans in crisis to connect with suicide prevention and mental health crisis counselors.

Texting will be able to access suicide hotline help

This week, U.S. communications regulators will require that phone companies allow people to text as well as call a new “988” number for the suicide-prevention hotline. In recognition of the changing trend in technology use by youth, texting 988 will also be a way to reach the hotline. This would also benefit those who are deaf, have hearing loss or speech disabilities.

According to FCC Acting Chairwoman Jessica Rosenworcel, “For millions of us, especially young people and those with disabilities — they are more likely to text than they are to call when they are in crisis. The bottom line is it should not matter when you make a voice call or send a text message, because we should connect people in crisis to the resources they need, no matter how they communicate.”

Currently, the National Suicide Prevention Lifeline uses a 10-digit number, 800-273-TALK (8255), which routes calls to about 170 crisis centers. Phone companies have until July 2022 to implement the 988 number for both calling and texting. The FCC said Thursday that the country’s largest cellphone companies already support calling 988. The implementation of a three-digit number for the National Suicide Prevention Lifeline comes as suicide is a growing public health problem in the United States, with risk factors compounded by the Covid-19 pandemic.

It is estimated that nearly 6,000 Americans call the Lifeline on an average day. The most recent report (2020) by the National Center for Health Statistics, describes more than 45,000 suicide deaths in the US. While there was an overall decrease in suicides by 3% from 2019 to 2020 — suicide rates increased for non-Hispanic Black, non-Hispanic American Indian and Alaska Native, and Hispanic men, according to the NCHS report

Sources:

FCC News

FCC Report and Order

NCHS suicide report 2020

988 Fact Sheet: [ English | Spanish ]

FDA’s Breakthrough Device Designation for rapid-acting technology to treat major depression

Non-invasive neurostimulation technology to rapidly treat major depressive disorder (MDD) 

The FDA has awarded Breakthrough Device Designation to Magnus Medical’s non-invasive technology to rapidly treat major depressive disorder (MDD) in adults who have not responded to existing treatments. The Magnus System is based on the SAINT technology (Stanford Accelerated Intelligent Neuromodulation Therapy), a form of transcranial magnetic stimulation which was licensed exclusively to Magnus Medical from Stanford University for commercialization.

An advance online article published in the American Journal of Psychiatry, describe the results from an investigational double-blinded randomized controlled trial (RCT) evaluating SAINT suggest that the novel approach has the potential to be a reproducible, rapid, and highly effective treatment for severe, refractory depression in a broader clinical setting. Fourteen study participants received active treatment, and another 15 received sham (placebo) treatment. The clinical trial results show that 79% of people in the active treatment arm entered remission—that is, experienced near elimination of their depression symptoms based on the Montgomery-Åsberg Depression Rating Scale (MADRS)—compared to people in the sham treatment arm, where only 13% entered remission. In an earlier pilot trial evaluating SAINT, 19 of 21 study participants (90%) entered remission. The restoration of healthy neural activity for the responders was life-changing as indicated by improvement in quality of life measures, and within five days, symptoms (including thoughts of suicide) improved dramatically. Data collected during both studies were evaluated by the FDA as part of the criteria for granting Breakthrough Device designation. 

The SAINT technology is described as having breakthrough algorithms that can identify optimal, personalized targets to affect brain circuitry based on structural and functional neuroimaging. Therefore, utilizing precise patterns of stimulation that can leverage recent advances in neuroscience and restore these neural circuits.

According to Magnus Medical, this system is a novel innovation with the potential to have a significant positive impact on the treatment of severe depression. For the first time, advanced imaging technologies combined with personalized neural targeting and novel stimulation patterns have the potential to yield a new form of individualized, non-invasive neurostimulation for people with treatment-resistant depression. This new approach is designed to be delivered on an accelerated timeline and is precisely tailored to each person’s brain connectivity.

The Magnus System, currently an investigational device, is expected to require 501(k) clearance from the U.S. FDA and is not yet commercially available.

Sources:

Cole EJ, Phillips AL, Bentzley BS, et al. Stanford Neuromodulation Therapy (SNT): A Double-Blind Randomized Controlled Trial. AJP Published Online:29 Oct 2021

Magnus Medical Press Release

Stanford University News