Connect with us

AI Research

AI Wonder Material? – Brownstone Research

Published

2 months ago

on


 

I hope that all of my readers in the Northern Hemisphere are enjoying their summer.  Mine has been extremely busy, intense, and full of challenges.

To that end, I’ll be taking some time off next week to recover.

I won’t be writing any issues of The Bleeding Edge, but we will still be producing content for you.  My team will step in and be writing for me next week about a bunch of interesting topics consistent with our mission here at Brownstone Research.

I will be in touch with my team daily, though, as we monitor the markets and our model portfolio positions in real time, as always.  I’m fortunate to have a fantastic team around me where I don’t have to worry about all the right things getting done.

Have a great week next week, keep in touch with The Bleeding Edge, and I’ll be writing to you next on Monday, July 28.

Sincerely,

Jeff

Graphene for AI?

Dear Jeff

What are your thoughts on whether graphene chips, with layers of indium selenide, will dramatically reduce the energy consumption of AI?

Will the technology be in mass production in the early part of the 2030s?

Regards.

– Robert A.

Hi Robert,

Thanks for writing in. I’ve actually written quite a lot about graphene in previous Bleeding Edge issues. This material is often looked at as a breakthrough material for semiconductors.

For the benefit of new readers or for anyone who wants a refresher, graphene is an incredibly thin, light, and highly conductive material made of pure carbon.

It’s 200 times stronger than steel and five times lighter than aluminum. It’s especially popular for its conductivity – it can handle heat up to 1,300 degrees Fahrenheit.

Graphene comes up in conversation a lot when we talk about heat management in semiconductors. The main problem with graphene is that, economically, it’s not a good solution. There are some technical issues as well that make it difficult to use in semiconductor manufacturing.

Here’s what I wrote recently in The Bleeding Edge – Reason to Be Optimistic About Nuclear Energy…

Graphene production as of now is just too expensive and too energy-intensive to apply it widely in the industries where we’d hypothetically see the most use of it, among other issues. I previously wrote…

Graphene can cost as much as $200,000 per ton. The industry is, of course, working towards a breakthrough that could radically reduce the costs of producing graphene. But until that happens, it is very difficult to scale production for commercial manufacturing.

And not to get too technical, but one of the reasons that graphene is so good at conducting electricity is because it doesn’t have an energy band gap.

There is an energy band gap in silicon, which is the difference between the valence band (which is filled with electrons) and the conduction band (which is an empty state). And without a band gap – as is the case with graphene’s natural state – graphene can’t stop conducting electricity.

This makes it hard to use for applications like transistors and thus semiconductors.

There are some solutions to this problem, but they have not been commercialized. And it would make the manufacturing process more complex, which means even more expensive.

It’s an incredible material, no doubt. I’m still very excited about future applications. But as of now, the economics just don’t make a lot of sense.

However, I’m always keeping an eye on the materials science industry as any breakthroughs directly impact a wide range of industries we follow here at Brownstone Research.

With that understanding, Robert, I’d like to now get to your question.  Given your specificity, I’m sure you know the purpose of indium selenide is to potentially solve the band gap problem I mentioned above.

Indium selenide (InSe) is one of a handful of materials that shows promise for semiconductors at an extremely small scale, below 3-nanometer manufacturing.  This is possible because of indium selenide’s low effective mass, high mobility, and highly tunable band gap.

These properties could theoretically result in a two-dimensional semiconductor capable of outperforming silicon.  That’s why we hear a lot of buzz about graphene, or some combination of new materials, from time to time.

In the case of indium selenide, there are two major issues that negatively impact the manufacturing of InSe semiconductor wafers.  There is a lot of phase diversity with InSe, which is difficult to control and results in significant deviation across the material, as well as degradation.

The second major problem is that it is hard to manufacture high-quality crystallinity of InSe films.  This is due to the vapor pressure of selenide being about seven orders of magnitude greater than that of indium.  That makes it very hard to find a balance between the two materials.

To be fair, a lot could happen within the next five years that could address these challenges. But one thing that I’m sure of is that the issue of economics will almost certainly not be solved.

Because of that, I predict that if graphene with layers of InSe is used in 2030, it will only be used for niche applications where cost is not a concern.

The reality is that current semiconductor manufacturing materials and technologies continue to make significant improvements in terms of reducing energy consumption per unit of compute.

I believe that this progress will be significant enough, and at low cost, which will mean that it is unlikely that the current course will be changed by 2030.

To unseat a technological approach, it would take a radical improvement in total performance in addition to much lower costs of manufacturing.

At the moment, working with InSe for semiconductor applications is nothing more than a laboratory experiment.  But I’ll continue to watch this space and those of other promising materials, always looking for a breakthrough that just might cause an inflection point in the industry.

When it happens, you can be sure I’ll be writing about it. 

What’s Going on With Day One Investor?

Mr. Brown, are you still doing your Day One Investor service? I signed up as a lifetime member of Brownstone to receive this service. I tried contacting you through Brownridge, but the voicemail box was full. I have not seen any news for some time now.

Regards.

– Jerry P.

Hi Jerry,

I appreciate you writing in to ask about that.  I have been meaning to put out an update, in addition to updates on portfolio companies.  I have been keeping in touch with the portfolio company CEOs, as well as speaking with new potential Day One Investor companies.

Unfortunately, I’ve had a bit of a challenging time with my health the last several months as I’m trying to cure myself from my cancer.  My therapeutic protocol has been much more difficult than I expected in terms of side effects, and that has limited my productivity.  I hope to have some good news on that front in a few weeks or so.

I still have some heavy lifting to do with returning Day One Investor to full health, which I am committed to doing.  I hope to have some updates for you soon.  Please bear with me as I put the right infrastructure in place and return to health and my normal levels of super-productivity.

Any News on Cerebras?

Your major sales pitch in late May about the possible IPO of Cerebras was the main reason I subscribed to Exponential Tech Investor. Unless I’ve overlooked something, I have not seen any updates on the status of the IPO as to whether you think it’s still on the company’s drawing board and simply postponed, or if the company has dropped pursuit of it. I strongly suggest you periodically update subscribers on this matter. I await your response. Thank you.

– John W.B.

Hi John,

Thanks for joining us at Exponential Tech Investor. Happy to have you on board.

We’ve had quite a few people writing in wondering about the Cerebras IPO. I’m glad to see so many readers as excited about it as we are.

I wrote about this in a recent AMA issue when someone wrote in wondering What’s Up With Cerebras…

[Cerebras] will be one of the largest and most important IPOs of 2025.

It has already chosen its underwriters, namely Citi, Barclays, and UBS.  I know that the demand is through the roof, and Cerebras is carefully picking its window to go public.

There haven’t been any recent filings with the SEC that would provide us with specific details, so I can only speculate on timing and reasoning.  I’ve been at this for a few decades, so I have a pretty good feel for what’s likely going on.

Companies as prominent, promising, and in a very hot sector like AI are in the best position to maximize their public offering.  Good timing allows them to raise more capital – exactly the amount they want to raise.

Executives looking to take their company public tend to avoid highly volatile markets and windows with a lot of negative “noise.”  There was a lot of that in the first half of the year with the new Trump administration, DOGE, Ukraine/Russia, the breakout of conflict in the Middle East, tariff negotiations, and persistently high interest rates.

Put simply, the last six months have not been ideal for taking a company public.  There has been too much risk and too many distractions with everything that was happening.

But we did see some positive progress in the IPO markets this quarter, with 42 IPO’s raising about $7 billion. Two exciting tech companies, Circle (crypto) and Chime (fintech), received particularly strong demand.

If it were my decision, I’d wait until the Federal Reserve starts cutting interest rates.

This is long overdue, and a cut of at least 50 basis points is warranted at the next meeting. But then, that’s been the case for a while now, and so long as Fed Chair Jay Powell continues his misguided campaign against rate cuts, we don’t know if that will happen yet.

But if it were me at Cerebras, I’d be looking for the sector rotation into smaller capitalization stocks, which will only happen when rates start to come down.

The next FOMC meetings are July 29–30 and September 16–17.  If I had to make a prediction, I would say we might look forward to an IPO in the September/October time frame.

My team and I are tracking its progress closely. The timing for this IPO is so critical, and it makes sense that the team over at Cerebras would wait for the opportune moment to go public. I stand by my initial forecast. This fall seems the ideal window for a Cerebras IPO. But, as always, we’ve got our eyes and ears on anything that might signal an earlier move.

We’ll absolutely keep you posted of any changes and alert our readers over at Exponential Tech Investors as soon as it’s time to move.

Deep Access Update

Message for Jeff —

Don’t give up on Deep Access!

Actually, keep refining it… once the current “melt-up” is finished, probably in the next 2-4 years, the downturn will be historic. And just like the dot-com bust, with the next downturn, I’ll be looking for the most over-hyped, worthless companies (probably in the AI frenzy, I’m guessing this time) to short.

Hopefully, you’ll have those already discovered in Deep Access!

And the next step… I’m counting on you to already know the solid companies that will survive the carnage to become the next massive winners (like the Amazons) for the next market cycle. Thanks for all the work you and your team are doing!

– James R.

Hi James,

Don’t worry! Deep Access isn’t going anywhere.

We’re just holding back on new recommendations for a couple of weeks or so, looking for an opportunity to stack the deck in our favor for our next trades. Markets are overextended, and everything’s running pretty hot at the moment, which means even trades in companies with questionable fundamentals or bad news can still climb higher.

As it goes, a rising tide lifts all boats.

But the Deep Access AI is tirelessly seeking our next opportunity. As my senior analyst Nick Rokke and I wrote in our recent update to Deep Access readers…

Deep Access isn’t about swinging for the fences on every trade. It’s about staying in the game long enough to capture the big winners that come when the Deep Access AI picks up massive institutional short positions in a company, signaling that the smart money knows something is going to crack.

So for now, we’ll let this rally run.  The markets are already overextended right now, and they definitely could go higher given the potential positive catalysts mentioned earlier.

We continue to track new signals daily.  We’re going to be very picky in this environment.  And when the time is right and market conditions simply return to more normal trading conditions, we’ll be ready.

And if there is a silver lining when conditions do get this overextended, it’s that they tend to snap back sharply when there is bad news, especially for individual equities.  And larger swings downward mean larger profits on trades.

Deep Access has been years in the making, and it’s a fantastic neural network.  And just in the last couple of days, we’ve seen the signal strength on several assets start to climb.  We believe that this indicates that some institutional capital believes many assets are way overvalued now, and they are building their short positions.

There will definitely be major pullbacks even during bull markets.  And there will always be companies that take a turn for the worse and get it all wrong.  We’ll still be able to build profitable trades when that happens.  And the Deep Access AI will be working night and day to spot those patterns for high probability signals.

We’re just getting started… And just a reminder, we’re never going to put out a trade just to put out a trade.  When the Deep Access AI has a high probability signal that we believe in, we’ll get it out to you as quickly as we can.

Have a great weekend,

Jeff

Want more stories like this one?

The Bleeding Edge is the only free newsletter that delivers daily insights and information from the high-tech world as well as topics and trends relevant to investments.



Source link

Related Topics:
Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

AI Research

Research has shown that people who do not use AI technology more than those who are well aware of ar..

Published

2 hours ago

on

September 4, 2025

By


According to a study by the University of Southern California in the United States, “The less AI you understand, the more magical AI you feel.”

AI-generated image of a college student who is disappointed with low grades [Production = Gemini]

Research has shown that people who do not use AI technology more than those who are well aware of artificial intelligence (AI) technology. In addition, there are studies showing that excessive use of Generative AI tools such as ChatGPT is linked to lower academic achievement, and it is analyzed that dependence on AI should be vigilant.

According to a study by researchers at the University of Southern California in the United States and the University of Bocconi in Italy on the 4th, the lower the understanding of AI, the more often they accept it as magic and use it.

The researchers evaluated 234 university undergraduate students with their understanding of AI (literacy), then gave them writing tasks on a specific topic and investigated whether to use Generative AI tools.

As a result, students with lower scores in AI understanding showed a stronger tendency to use AI for tasks. The researchers analyzed, “People with low understanding of AI perceive AI like magic,” and “They are likely to be in awe when AI performs tasks that were thought to be a unique attribute of humans.”

Conversely, people with a high understanding of AI know that AI works based on computer algorithms, not magic, so they don’t rely too much on it.

In March this year, a study found that sincere students use fewer Generative AI tools, and that AI dependence can lead to a decrease in self-efficacy and academic achievement. The researchers investigated and analyzed the frequency of AI learning and self-efficacy of learning after the end of the semester in 326 undergraduate students.

Sundas Azim, a professor at SZABIST University in Pakistan who conducted the study, said, “In the case of tasks conducted by students relying on Generative AI, AI produced similar responses, resulting in less classroom participation or discussion activities.” As a result, students with more AI use tended to have relatively lower average GPA.

It is analyzed that services such as ChatGPT can be effective when they need immediate help in their studies, but can have a negative impact on long-term learning and achievement.



Source link

Continue Reading

AI Research

Alberta Follows Up Its Artificial Intelligence Data Centre Strategy with a Levy Framework

Published

2 hours ago

on

September 4, 2025

By


Alberta is introducing a levy framework for data centres powering artificial intelligence technologies, the Province recently announced.

Effective by the end of 2026, a 2% levy on computer hardware will apply to grid-connected data centres of 75 megawatts or greater, according to a statement from Alberta.

The levy will be fully offset against provincial corporate income taxes, the government says. Once a data centre becomes profitable and pays corporate income tax in Alberta, the levy will not result in any additional tax burden.

Data centres of 75MW or greater will be recognized as designated industrial properties, with property values assessed by the province. Land and buildings associated with data centres will be subject to municipal taxation.

The framework was forged through a six-week consultation with industry stakeholders, according to Nate Glubish, Minister of Technology and Innovation.

“Alberta’s government has a duty to ensure Albertans receive a fair deal from data centre investments,” the provincial minister remarked. “This approach strikes a balance that we believe is fair to industry and Albertans, while protecting Alberta’s competitive advantage.”

Glubish added that the Alberta government is also exploring other options. This includes a payment in lieu of taxes program that would allow companies to make predictable annual payments instead of fluctuating levy amounts, as well as a deferral program to ease cash-flow pressures during construction and early years of operation.

“After working closely with industry, we’re introducing a fair, predictable levy that ensures data centres pay their share for the infrastructure and services that support them,” commented Nate Horner, Minister of Finance.

“This approach provides stability for businesses while generating new revenue to support Alberta’s future,” he posits.

The decision builds on the Alberta Artificial Intelligence Data Centre Strategy, introduced in 2024.

The strategy aims to capture a larger share of the global AI data centre market, which is expected to exceed $820 billion by 2030 as Alberta becomes a data centre powerhouse within Canada.

However, the Province’s tactics have not gone uncriticized.



Source link

Continue Reading

AI Research

Reimagining clinical AI: from clickstreams to clinical insights with EHR use metadata

Published

2 hours ago

on

September 4, 2025

By


  • Harnessing EHR data for health research | Nature Medicine. https://www.nature.com/articles/s41591-024-03074-8.

  • Acosta, J. N., Falcone, G. J., Rajpurkar, P. & Topol, E. J. Multimodal biomedical AI. Nat. Med. 28, 1773–1784 (2022).

    CAS 
    PubMed 

    Google Scholar     

  • Adler-Milstein, J. et al. Meeting the Moment: Addressing Barriers and Facilitating Clinical Adoption of Artificial Intelligence in Medical Diagnosis. NAM Perspect. https://doi.org/10.31478/202209c. (2022)

  • Aquino, Y. S. J. et al. Utopia versus dystopia: Professional perspectives on the impact of healthcare artificial intelligence on clinical roles and skills. Int. J. Med. Inf. 169, 104903 (2023).


    Google Scholar     

  • Pavuluri, S., Sangal, R., Sather, J. & Taylor, R. A. Balancing act: the complex role of artificial intelligence in addressing burnout and healthcare workforce dynamics. BMJ Health Care Inf. 31, e101120 (2024).


    Google Scholar     

  • Rule, A. et al. Guidance for reporting analyses of metadata on electronic health record use. J. Am. Med. Inform. Assoc.31, 784–789 (2023).

    PubMed Central 

    Google Scholar     

  • Adler-Milstein, J., Adelman, J. S., Tai-Seale, M., Patel, V. L. & Dymek, C. EHR audit logs: A new goldmine for health services research?. J. Biomed. Inform. 101, 103343 (2020).

    PubMed 

    Google Scholar     

  • Kannampallil, T. & Adler-Milstein, J. Using electronic health record audit log data for research: insights from early efforts. J. Am. Med. Inform. Assoc. 30, 167–171 (2023).


    Google Scholar     

  • Rule, A., Melnick, E. R. & Apathy, N. C. Using event logs to observe interactions with electronic health records: an updated scoping review shows increasing use of vendor-derived measures. J. Am. Med. Inform. Assoc. 30, 144–154 (2023).


    Google Scholar     

  • Rule, A., Chiang, M. F. & Hribar, M. R. Using electronic health record audit logs to study clinical activity: a systematic review of aims, measures, and methods. J. Am. Med. Inform. Assoc.27, 480–490 (2020).

    PubMed 

    Google Scholar     

  • Physician time spent using the electronic health record during outpatient encounters: a descriptive study. Ann Intern. Med 172, No 3. https://www.acpjournals.org/doi/10.7326/M18-3684.

  • Rotenstein, L. S., Holmgren, A. J., Downing, N. L. & Bates, D. W. Differences in total and after-hours electronic health record time across ambulatory specialties. JAMA Intern. Med. 181, 863–865 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Tai-Seale, M. et al. Association of physician burnout with perceived EHR work stress and potentially actionable factors. J. Am. Med. Inform. Assoc. 30, 1665–1672 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Chen, Y. et al. Modeling care team structures in the neonatal intensive care unit through network analysis of EHR Audit Logs. Methods Inf. Med. 58, 109–123 (2019).

    PubMed 

    Google Scholar     

  • Yakusheva, O. et al. An electronic health record metadata-mining approach to identifying patient-level interprofessional clinician teams in the intensive care unit. J. Am. Med. Inform. Assoc. 32, 426–434 (2025).

    PubMed 

    Google Scholar     

  • Chen, Y., Patel, M. B., McNaughton, C. D. & Malin, B. A. Interaction patterns of trauma providers are associated with length of stay. J. Am. Med. Inform. Assoc.25, 790–799 (2018).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Lou, S. S. et al. Effect of clinician attention switching on workload and wrong-patient errors. Br. J. Anaesth. 129, e22–e24 (2022).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rose, C. et al. Team is brain: leveraging EHR audit log data for new insights into acute care processes. J. Am. Med. Inform. Assoc. 30, 8–15 (2023).


    Google Scholar     

  • Melnick, E. R. et al. Analysis of electronic health record use and clinical productivity and their association with physician turnover. JAMA Netw. Open 4, e2128790 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Tran, B., Lenhart, A., Ross, R. & Dorr, D. A. Burnout and EHR use among academic primary care physicians with varied clinical workloads. AMIA Summits Transl. Sci. Proc. 2019, 136–144 (2019).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rossetti, S. C. et al. Real-time surveillance system for patient deterioration: a pragmatic cluster-randomized controlled trial. Nat. Med. 1–8. https://doi.org/10.1038/s41591-025-03609-7. (2025)

  • Rossetti, S. C. et al. Healthcare process modeling to phenotype clinician behaviors for exploiting the signal gain of clinical expertise (HPM-ExpertSignals): Development and evaluation of a conceptual framework. J. Am. Med. Inform. Assoc.28, 1242–1251 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Zhang, X., Yan, C., Malin, B. A., Patel, M. B. & Chen, Y. Predicting next-day discharge via electronic health record access logs. J. Am. Med. Inform. Assoc.28, 2670–2680 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Bhaskhar, N., Ip, W., Chen, J. H. & Rubin, D. L. Clinical outcome prediction using observational supervision with electronic health records and audit logs. J. Biomed. Inform. 147, 104522 (2023).

    PubMed 

    Google Scholar     

  • Zhang, X. et al. Optimizing large language models for discharge prediction: best practices in leveraging electronic health record audit logs. AMIA Annu. Symp. Proc. 2024, 1323–1331 (2025).

  • Kim, S., Warner, B. C., Lew, D., Lou, S. S. & Kannampallil, T. Measuring cognitive effort using tabular transformer-based language models of electronic health record-based audit log action sequences. J. Am. Med. Inform. Assoc.31, 2228–2235 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rossetti, S. C. et al. Leveraging clinical expertise as a feature – not an outcome – of predictive models: evaluation of an early warning system use case. Amia. Annu. Symp. Proc. 2019, 323–332 (2020).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Duggan, M. J. et al. Clinician experiences with ambient scribe technology to assist with documentation burden and efficiency. JAMA Netw. Open 8, e2460637 (2025).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Garcia, P. et al. Artificial intelligence–generated draft replies to patient inbox messages. JAMA Netw. Open 7, e243201 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Sinsky, C. A., Rotenstein, L., Holmgren, A. J. & Apathy, N. C. The number of patient scheduled hours resulting in a 40-hour work week by physician specialty and setting: a cross-sectional study using electronic health record event log data. J. Am. Med. Inform. Assoc. 32, 235–240 (2025).

    PubMed 

    Google Scholar     

  • Holmgren, A. J., Sinsky, C. A., Rotenstein, L. & Apathy, N. C. National comparison of ambulatory physician electronic health record use across specialties. J. Gen. Intern. Med. 39, 2868–2870 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rotenstein, L. et al. Virtual scribes and physician time spent on electronic health records. JAMA Netw. Open 7, e2413140 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rotenstein, L. S. et al. Association of primary care physicians’ Electronic Inbox activity patterns with patients’ likelihood to recommend the physician. J. Gen. Intern. Med. 39, 150–152 (2024).

    PubMed 

    Google Scholar     

  • Li, H. et al. Quantifying EHR and policy factors associated with the gender productivity gap in ambulatory, general internal medicine. J. Gen. Intern. Med. 39, 557–565 (2024).

    PubMed 

    Google Scholar     

  • Jay Holmgren, A., Steitz, B., Lou, S. & Apathy, N. Using Electronic Health Record Metadata to Understand Clinician Work and Behavior. In Reengineering Clinical Workflow in the Digital and AI Era: Toward Safer and More Efficient Care (eds. Zheng, K., Westbrook, J. & Patel, V. L.) 299–317 (Springer Nature Switzerland, Cham, https://doi.org/10.1007/978-3-031-82971-0_15. 2025).

  • Rotenstein, L. & Jay Holmgren, A. COVID exacerbated the gender disparity in physician electronic health record inbox burden. J. Am. Med. Inform. Assoc. 30, 1720–1724 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Gupta, K. et al. Differences in ambulatory EHR use patterns for male vs. female physicians. Catal. Carryover 5, (2019).

  • Rotenstein, L. S. et al. System-level factors and time spent on electronic health records by primary care physicians. JAMA Netw. Open 6, e2344713 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Holmgren, A. J., Thombley, R., Sinsky, C. A. & Adler-Milstein, J. Changes in physician electronic health record use with the expansion of telemedicine. JAMA Intern. Med. 183, 1357–1365 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Tawfik, D. et al. Emerging domains for measuring health care delivery with electronic health record metadata. J. Med. Internet Res. 27, e64721 (2025).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Yan, C. et al. Differences in health professionals’ engagement with electronic health records based on inpatient race and ethnicity. JAMA Netw. Open 6, e2336383 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Cox, M. L. et al. Documenting or operating: where is time spent in general surgery residency?. J. Surg. Educ. 75, e97–e106 (2018).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Read-Brown, S. et al. Time requirements for electronic health record use in an Academic Ophthalmology Center. JAMA Ophthalmol. 135, 1250–1257 (2017).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Dziorny, A. C. et al. Automatic detection of front-line clinician hospital shifts: a novel use of electronic health record timestamp data. Appl. Clin. Inform. 10, 28–37 (2019).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Hribar, M. R. et al. Secondary use of EHR timestamp data: validation and application for workflow optimization. Amia. Annu. Symp. Proc. 2015, 1909–1917 (2015).

    PubMed Central 

    Google Scholar     

  • Hribar, M. R. et al. Secondary use of electronic health record data for clinical workflow analysis. J. Am. Med. Inform. Assoc. JAMIA 25, 40–46 (2018).

    PubMed 

    Google Scholar     

  • Sinsky, C. A. et al. Metrics for assessing physician activity using electronic health record log data. J. Am. Med. Inform. Assoc. 27, 639–643 (2020).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Avdagovska, M. et al. Exploring the impact of in basket metrics on the adoption of a new electronic health record system among specialists in a tertiary hospital in alberta: descriptive study. J. Med. Internet Res. 26, e53122 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Akbar, F. et al. Physicians’ electronic inbox work patterns and factors associated with high inbox work duration. J. Am. Med. Inform. Assoc. 28, 923–930 (2021).

    PubMed 

    Google Scholar     

  • Arndt, B. G. et al. Tethered to the EHR: Primary care physician workload assessment using EHR event log data and time-motion observations. Ann. Fam. Med. 15, 419–426 (2017).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Amroze, A. et al. Use of electronic health record access and audit logs to identify physician actions following noninterruptive alert opening: descriptive study. JMIR Med. Inform. 7, e12650 (2019).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Cutrona, S. L. et al. Primary care providers’ opening of time-sensitive alerts sent to commercial electronic health record inBaskets. J. Gen. Intern. Med. 32, 1210–1219 (2017).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rumlow, Z. et al. The impact of diagnosis-specific plan templates on admission note writing time: a quality improvement initiative. J. Grad. Med. Educ. 16, 581–587 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Nguyen, O. T. et al. Primary care physicians’ electronic health record proficiency and efficiency behaviors and time interacting with electronic health records: a quantile regression analysis. J. Am. Med. Inform. Assoc. JAMIA 29, 461–471 (2021).


    Google Scholar     

  • Chen, B. et al. Mining tasks and task characteristics from electronic health record audit logs with unsupervised machine learning. J. Am. Med. Inform. Assoc. 28, 1168–1177 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Lou, S. S., Liu, H., Harford, D., Lu, C. & Kannampallil, T. Characterizing the macrostructure of electronic health record work using raw audit logs: an unsupervised action embeddings approach. J. Am. Med. Inform. Assoc. 30, 539–544 (2023).

    PubMed 

    Google Scholar     

  • Tiase, V. L., Sward, K. A. & Facelli, J. C. A scalable and extensible logical data model of electronic health Record Audit Logs for Temporal Data Mining (RNteract): model conceptualization and formulation. JMIR Nurs. 7, e55793 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Zhang, X., Zhao, Y., Yan, C., Derr, T. & Chen, Y. Inferring EHR utilization workflows through audit logs. Amia. Annu. Symp. Proc. 2022, 1247–1256 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Chen, Y., Adler-Milstein, J. & Sinsky, C. Measuring and maximizing undivided attention in the context of electronic health records. Appl. Clin. Inform. https://doi.org/10.1055/a-1892-1437. (2022)

  • Moy, A. J. et al. Characterizing multitasking and workflow fragmentation in electronic health records among emergency department clinicians: using time-motion data to understand documentation burden. Appl. Clin. Inform. 12, 1002–1013 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Jones, B., Zhang, X., Malin, B. A. & Chen, Y. Learning tasks of pediatric providers from electronic health record audit logs. Amia. Annu. Symp. Proc. 2020, 612–618 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Li, P. et al. Measuring collaboration through concurrent electronic health record usage: network analysis study. JMIR Med. Inform. 9, e28998 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Mannering, H. et al. Assessing neonatal intensive care unit structures and outcomes before and during the COVID-19 pandemic: network analysis study. J. Med. Internet Res. 23, e27261 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Chen, Y., Yan, C. & Patel, M. B. Network analysis subtleties in ICU structures and outcomes. Am. J. Respir. Crit. Care Med. 202, 1606–1607 (2020).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Chen, Y., Lorenzi, N. M., Sandberg, W. S., Wolgast, K. & Malin, B. A. Identifying collaborative care teams through electronic medical record utilization patterns. J. Am. Med. Inform. Assoc. JAMIA 24, e111–e120 (2017).

    PubMed 

    Google Scholar     

  • Yan, C. et al. Collaboration structures in COVID-19 critical care: retrospective network analysis study. JMIR Hum. Factors 8, e25724 (2021).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Kelly Costa, D., Liu, H., Boltey, E. M. & Yakusheva, O. The structure of critical care nursing teams and patient outcomes: a network analysis. Am. J. Respir. Crit. Care Med. 201, 483–485 (2020).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Kim, C. et al. Provider Networks in the Neonatal Intensive Care Unit Associate with Length of Stay. In 2019 IEEE 5th International Conference on Collaboration and Internet Computing (CIC) 127–134. https://doi.org/10.1109/CIC48465.2019.00024. (2019)

  • Apathy, N. C., Holmgren, A. J. & Cross, D. A. Physician EHR time and visit volume following adoption of team-based documentation support. JAMA Intern. Med. 184, 1212–1221 (2024).

    PubMed 

    Google Scholar     

  • Tang, M., Holmgren, A. J., Huckman, R. S., Pany, M. J. & McWilliams, J. M. Modalities, Mo Problems: impacts of provider modality switching in hybrid outpatient clinics. Acad. Manag. Proc. 2024, 13107 (2024).


    Google Scholar     

  • Jiang, S. Y., Hum, R. S., Vawdrey, D. & Mamykina, L. In search of social translucence: an audit log analysis of handoff documentation views and updates. Amia. Annu. Symp. Proc. 2015, 669–676 (2015).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Lyles, C. R. et al. Using electronic health record portals to improve patient engagement: research priorities and best practices. Ann. Intern. Med. 172, S123–S129 (2020).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Zhang, X. et al. Association between patient portal engagement and weight loss outcomes in patients after bariatric surgery: longitudinal observational study using electronic health records. J. Med. Internet Res. 26, e56573 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Davis, S. E., Embí, P. J. & Matheny, M. E. Sustainable deployment of clinical prediction tools—a 360° approach to model maintenance. J. Am. Med. Inform. Assoc. 31, 1195–1198 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Guo, L. L. et al. EHR foundation models improve robustness in the presence of temporal distribution shift. Sci. Rep. 13, 3767 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar     

  • Brown, K. E. et al. Large language models are less effective at clinical prediction tasks than locally trained machine learning models. J. Am. Med. Inform. Assoc. ocaf038. https://doi.org/10.1093/jamia/ocaf038. (2025)

  • Wornow, M. et al. The shaky foundations of large language models and foundation models for electronic health records. Npj Digit. Med. 6, 1–10 (2023).


    Google Scholar     

  • Moor, M. et al. Foundation models for generalist medical artificial intelligence. Nature 616, 259–265 (2023).

    CAS 
    PubMed 

    Google Scholar     

  • Zhou, Y. et al. A foundation model for generalizable disease detection from retinal images. Nature 622, 156–163 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar     

  • Guo, L. L. et al. A multi-center study on the adaptability of a shared foundation model for electronic health records. Npj Digit. Med. 7, 1–9 (2024).


    Google Scholar     

  • Peng, C. et al. A study of generative large language model for medical research and healthcare. NPJ Digit. Med. 6, 210 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Krishnan, R., Rajpurkar, P. & Topol, E. J. Self-supervised learning in medicine and healthcare. Nat. Biomed. Eng. 6, 1346–1352 (2022).


    Google Scholar     

  • Katsoulakis, E. et al. Digital twins for health: a scoping review. NPJ Digit. Med. 7, 77 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Embí, P. J., Rhew, D. C., Peterson, E. D. & Pencina, M. J. Launching the Trustworthy and Responsible AI Network (TRAIN): A Consortium to Facilitate Safe and Effective AI Adoption. JAMA https://doi.org/10.1001/jama.2025.1331. (2025)

  • Maddox, T. M. et al. Generative AI in Medicine — Evaluating Progress and Challenges. N. Engl. J. Med. 0

  • You, J. G., Hernandez-Boussard, T., Pfeffer, M. A., Landman, A. & Mishuris, R. G. Clinical trials informed framework for real world clinical implementation and deployment of artificial intelligence applications. Npj Digit. Med. 8, 1–5 (2025).


    Google Scholar     

  • McCoy, A. B. et al. Clinician collaboration to improve clinical decision support: the Clickbusters initiative. J. Am. Med. Inform. Assoc. 29, 1050–1059 (2022).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Baxter, S. L., Apathy, N. C., Cross, D. A., Sinsky, C. & Hribar, M. R. Measures of electronic health record use in outpatient settings across vendors. J. Am. Med. Inform. Assoc. JAMIA 28, 955–959 (2021).

    PubMed 

    Google Scholar     

  • Cohen, G. R., Boi, J., Johnson, C., Brown, L. & Patel, V. Measuring time clinicians spend using EHRs in the inpatient setting: a national, mixed-methods study. J. Am. Med. Inform. Assoc. JAMIA 28, 1676–1682 (2021).

    PubMed 

    Google Scholar     

  • Wu, D. T. Y. et al. Using EHR audit trail logs to analyze clinical workflow: A case study from community-based ambulatory clinics. Amia. Annu. Symp. Proc. 2017, 1820–1827 (2018).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Sinsky, C. et al. Allocation of physician time in ambulatory practice: a time and motion study in 4 specialties. Ann. Intern. Med. 165, 753–760 (2016).

    PubMed 

    Google Scholar     

  • Were, M. C. et al. Role and use of race in artificial intelligence and machine learning models related to health. J. Med. Internet Res. 27, e73996 (2025).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Rajkomar, A. et al. Scalable and accurate deep learning with electronic health records. Npj Digit. Med. 1, 1–10 (2018).


    Google Scholar     

  • Grabowska, M. E. et al. Developing and evaluating pediatric phecodes (Peds-Phecodes) for high-throughput phenotyping using electronic health records. J. Am. Med. Inform. Assoc. 31, 386–395 (2024).

    PubMed 

    Google Scholar     

  • Hripcsak, G. & Albers, D. J. Next-generation phenotyping of electronic health records. J. Am. Med. Inform. Assoc. 20, 117–121 (2013).

    PubMed 

    Google Scholar     

  • Yasrebi-de Kom, I. A. R. et al. Electronic health record-based prediction models for in-hospital adverse drug event diagnosis or prognosis: a systematic review. J. Am. Med. Inform. Assoc. 30, 978–988 (2023).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Dos Santos, F. C. et al. The effect of a combined mHealth and community health worker intervention on HIV self-management. J. Am. Med. Inform. Assoc. 32, 510–517 (2025).

    PubMed 

    Google Scholar     

  • Liu, S. et al. Leveraging explainable artificial intelligence to optimize clinical decision support. J. Am. Med. Inform. Assoc. 31, 968–974 (2024).

    PubMed 
    PubMed Central 

    Google Scholar     

  • Ozkaynak, M., Ponnala, S. & Werner, N. E. Patient-Oriented Workflow Approach. In Reengineering Clinical Workflow in the Digital and AI Era: Toward Safer and More Efficient Care (eds. Zheng, K., Westbrook, J. & Patel, V. L.) 213–229 (Springer Nature Switzerland, Cham, https://doi.org/10.1007/978-3-031-82971-0_11. 2025).

  • Sánchez-Salmerón, R. et al. Machine learning methods applied to triage in emergency services: A systematic review. Int. Emerg. Nurs. 60, 101109 (2022).

    PubMed 

    Google Scholar     



    • Source link

    Continue Reading

    Trending