What happened in health care technology this week, and why it’s important.

AI technique narrowed to only propose candidate molecules that can be produced in a lab
Pharmaceutical companies are using artificial intelligence to streamline the discovery of new medicines. Machine-learning models can propose new molecules with specific properties that could fight certain diseases, doing in minutes what might take humans months to achieve manually. Adam Zewe reports on a new approach from MIT researchers that constrains a machine-learning model, so it only suggests molecular structures that can be synthesized. The method guarantees that molecules are composed of materials that can be purchased and that the chemical reactions between those materials follow the laws of chemistry.
Why it’s important – Compared to other methods, their model proposed molecular structures that scored as high and sometimes better using popular evaluations but were guaranteed to be synthesizable. Their system also takes less than one second to present a synthetic pathway, while other methods that separately propose molecules and then evaluate their synthesizability can take several minutes. In a search space that can include billions of potential molecules, those time savings add up. The work is fascinating because it could eventually enable a new paradigm for computer-aided synthesis planning.
Infographic of the week – I love this graphic representation of how technology disrupts the human needs equation from Rock Health.

A multi-organ chip with matured tissue niches linked by vascular flow
Engineered tissues can be used to model human pathophysiology and test the efficacy and safety of drugs. Yet, to model whole-body physiology and systemic diseases, engineered tissues with preserved phenotypes need to communicate physiologically. In an article in Nature Biomedical Engineering, the authors reported on the development and applicability of a tissue-chip system in which matured human heart, liver, bone, and skin tissue niches are linked by recirculating vascular flow to allow for the recapitulation of interdependent organ functions.
Why it’s important – The development of multi-organ chips is another move forward in developing whole-body digital twins that will model and predict responses to drugs and therapies in the future. In this case, the interlinked tissues maintained their molecular, structural, and functional phenotypes over four weeks of culture, recapitulated the pharmacokinetic and pharmacodynamic profiles of doxorubicin in humans, allowed for the identification of early miRNA biomarkers of cardiotoxicity, and increased the predictive values of clinically observed miRNA responses relative to tissues cultured in isolation and to fluidically interlinked tissues in the absence of endothelial barriers.
Cartoon of the week – Everyone’s exhausted with the COVID-19 pandemic. I love this cartoon from Wiley Miller.

U.K. Hospital Trials Brain Implant to Treat Parkinson’s
A hospital in the U.K. is the first to implant a brain device to reverse the symptoms of Parkinson’s – and its test patient calls it “amazing.” Surgeons at Southmead Hospital in Bristol, England, are implementing a tiny deep brain stimulation (DBS) device into the skull. An article in Newsweek and provided by Zenger News reported on the project in which the implant overrides the abnormal brain-cell firing patterns caused by Parkinson’s.
Why it’s important – Traditional operations for Parkinson’s involve implanting a reasonably large battery into the chest with wires that run under the skin through to the top of the head. The new DBS system, the smallest that has ever been created, involves a tiny battery system for the device implanted into the skull. It takes just three hours to carry out the new operation, about half the time it used to with the larger battery. For more on technology and Parkinson’s disease, read my post from last week.
Many hospital executives don’t have a digital strategy
Many healthcare organizations are spending a great deal of time on finding new digital solutions, but many aren’t sure about the options they have chosen. That’s a key takeaway from a new report on healthcare technology by Panda Health, a digital marketplace for health systems. The company, which evaluates health vendors to help hospitals find the right partners, was founded by CentraCare, Gundersen Health System, and ThedaCare.

Why it’s important – The hospitals that had digital health strategies found themselves better able to pivot during the COVID-19 pandemic, the report suggested. Hospitals with comprehensive digital plans were more likely to move forward with digital health solutions during the pandemic than those without strategies (71% to 41%).
How Google could own healthcare
Google’s response to the pandemic is a microcosm of how the company intends to lead the entire healthcare industry: helping people stay as healthy as possible through wellness care and managing the journey to receive care when needed. Adam Dorfman reports on Google’s strategy in his article on VentureBeat. Google, like Apple, has an advantage in personal healthcare: a data platform tied to devices. Hardware, though, is the key to Google’s foray into health. Devices, ranging from Chromebooks to Pixel phones to home devices, provide the means for Google users to manage their data and for Google to monetize it. The second part of Google’s healthcare strategy is to own the patient journey to getting care. And here, Google is the undisputed Big Tech leader. The company has positioned itself as the default resource for people to research symptoms and access care. Google influences every phase of the patient journey, from awareness to consideration.
Why it’s important – I’ve written on the challenges Big Tech faces in targeting healthcare earlier. Google will continue to move into healthcare using devices and software/data analytics to expand its reach. Google will also benefit by attracting more advertisers (engagement and volume are like gold to online advertisers).
Researchers create AI model to predict pediatric no-shows
Kat Jercich from Healthcare IT News reports that a team from Boston Children’s Hospital and Yonsei University used local weather information to help forecast the possibility of patients missing scheduled appointments. By adopting a data imputation method for patients with missing information in their records, developing an interpretable approach that explains how a prediction is made, and exploiting local weather information, the team created a model identifying 83% of no-shows at the time of scheduling.

Why it’s important – No-shows cost the industry approximately $150 Billion per year in the U.S. alone. And as the researchers pointed out, “no-shows” can negatively impact patient health and hospital and clinics’ resource utilization. For this study, researchers noted that their model showed minimal predictive performance differences across racial groups. And of course, other health system leaders have pointed out that no-shows can be reduced via different technologies such as telemedicine and patient engagement platforms.