Moneyball Medicine

Computers can interpret the text we type, and they’re getting better at understanding the words we speak. But they’re only starting to understanding the emotions we feel—whether that means anger, amusement, boredom, distraction, or anything else. This week Harry talks with Rana El Kaliouby, the CEO of a Boston-based company called Affectiva that’s working to close that gap.El Kaliouby and her former MIT colleague Rosalind Picard are the inventors of the field of emotion AI, also called affective computing. The main product at Affectiva, which Picard and El Kaliouby co-founded in 2009, is a media analytics system that uses computer vision and machine learning to help market researchers understand what kinds of emotions people feel when they view ads or entertainment content. But the company is also active in other areas such as safety technology for automobiles that can monitor a driver’s behavior and alert them if they seem distracted or drowsy. Ultimately, Kaliouby predicts, emotion AI will become an everyda

Rapid and cheap DNA sequencing technology can tell us a lot about which genes a patient is carrying around, but it can't tell us when and where the instructions in those genes get carried out inside cells. Resolve Biosciences—headed by this week's guest, Jason Gammack—aims to solve that problem by scaling up a form of intracellular imaging it calls molecular cartography.Gammack says the technology offers a high-resolution way to see the geography of gene transcription in single cells, that is, where specific messenger RNA molecules congregate once they’ve left the nucleus. The technology can trace up to 100 gene transcripts simultaneously. Right now it only works for mRNA, but the company says it plans to add the ability to track DNA, proteins, and “metabolic data layers.” The big idea is to make it easier to see how gene expression translates into normal tissue development and, by extension, the pathology of genetic or infectious diseases."We can go in and identify specific RNA molecules that code for a know

Pek Lum, co-founder, and CEO of Auransa believes that a lot fewer drugs would fail in Phase 2 clinical trials if they were tested on patients predisposed to respond. The problem is finding the sub-populations of likely high-responders in advance and matching them up with promising drug compounds. That’s Auransa's specialty.The Palo Alto, CA-based drug discovery startup, formerly known as Capella Biosciences, has a pipeline of novel compounds for treating cancer and other conditions identified through machine learning analysis of genomic data and other kinds of data. It’s closest to the clinical trial stage with a gene expression modulator for liver cancer (AU-409) and is also working on drugs for prostate cancer and for protecting the heart against chemotherapy drugs. The company says it discovered AU-409 as part of a broad evaluation of data sets on a range of close to 30 diseases. The company’s discovery process uses a platform called the SMarTR Engine that uses hypothesis-free machine learning to identify

This week Harry talks with Matteo Franceschetti, founder and CEO of the Khosla Ventures-backed startup Eight Sleep. The company' smart mattress, called the Pod, is one of the latest (and largest) entries in the burgeoning market for home digital-health devices.The Pod is designed to counteract body heat and provide a surface that stays cool all night, on the theory that people sleep better when it’s cool or cold. It includes four layers of foam topped by an “Active Tech Grid Cover” that includes sensors to detect body temperature, breathing patterns, heartbeat, and tossing and turning, as well as a network of tubes that silently carry water through the cover, regulating temperature for each side of the mattress. The New York, NY-based company  has raised more than $70 million from big Silicon Valley firms including Khosla Ventures, Founders Fund, and Y Combinator and has roughly 60 employees around the world. Franceschetti, a former competitive ski racer, tennis player, race car driver, and attorney, has said

Michael Geer is co-founder and CSO (Chief Strategy Officer) of Humanity Health, a London-based startup that's building an iPhone app and subscription service designed to help users slow or reverse their rate of aging. Geer's co-founder Pete Ward has described the app as like “Waze for maximizing health span," or years of healthy functioning. The Humanity iPhone app, which is currently being beta-tested by users in the UK, is designed to track various types of health-related data for free, such as exercise levels. At various premium subscription levels users will be able to track biomarkers in their blood samples and even track the levels of methylation in their DNA. The app’s machine learning algorithms pull together all of this data to produce what the company calls an “H Score.” The big idea is to show well users are doing at slowing their aging—compared to others who have similar profiles or have taken similar actions—and to advise users on what else they could be doing to increase their H Score and their

This week on MoneyBall Medicine, Harry takes a field trip (literally!) into farming and agriculture. His guests are Al Eisaian co-founder and CEO of crop intelligence IntelinAir, and the company’s director of machine learning, Jennifer Hobbs. Intelinair’s AGMRI platform uses customized computer vision and deep learning algorithms to sift through terabytes of aerial image data, to help farmers identify problems like weeds or pests that can go undetected from the ground. The parallels to the digital transformation in healthcare aren't hard to spot.Harry has talked with scores of guests about advanced computer science techniques like neural networks, computer vision, and machine learning and how they’re changing the way healthcare providers can find patterns in genomic data or radiology images. But the fact is, these same techniques are being used to generate new kinds of actionable insights in many other areas, including agriculture. In fact, today’s farmers are almost overwhelmed by the volume of imaging avail

What if there were a single company that could connect hospital electronic health record systems to a massive genomic testing and analytics platform? It would be a little like Amazon Web Services (AWS) for healthcare—an enabling platform for anyone who wants to deploy precision medicine at scale. That's exactly what Joel Dudley says he's now helping to build at Tempus.When Harry last spoke with Dudley in January 2019, he was a tenured professor of genetics and genomics at the Icahn School of Medicine at Mount Sinai Medical Center and director of the Institute for Next Generation Healthcare. But later that same year, Dudley was lured away to Tempus, founded in 2015 by Eric Lefkofsky, the billionaire co-founder of Groupon. Tempus is building an advanced genomic testing platform to document the specific gene variants present in patients with cancer (and soon other diseases) in order to match them up with the right drugs or clinical trials and help physicians make faster, better treatment decisions. In this week'

This week Harry catches up with Christine Lemke from Evidation Health, a startup in San Mateo, CA, that helps drug developers and other organizations analyze the effectiveness of smart devices and wearables in new types of therapies. Lemke is Evidation's co-CEO.Our Fitbits and Apple Watches are with us so much of the time that the data they collect can go way beyond telling us whether we’ve completed our 10,000 steps for the day. They can also help doctors diagnose cardiovascular problems, and even provide early signs of cognitive changes like the onset of dementia. But the data comes in so many forms from so many sources that it’s a real chore to set up population-wide studies and keep the incoming data organized and anonymized. That’s Evidation's specialty.The company came together in its current form when a company Lemke helped to start, The Activity Exchange, merged with another company called Evidation. (Harry helped to incubate Evidation at GE Ventures with colleagues Rowan Chapman and Deborah Kilpatric

Thomas Chittenden, chief data science officer at Genuity Science, says what's keeping the genomics revolution from turning into an equivalent revolution in drug discovery is that most of our domain knowledge about the molecular biology of disease has come from a hunt-and-peck approach, focused on one gene at a time. Find some gene relevant to a disease, knock it out, and you see what happens. Such experiments are always revealing, but the reality is that human biology is the product of the interactions of huge networks of thousands of genes—which means most diseases are the product of dysregulation across these networks. Which means, in turn, that to figure out where to intervene with a drug, you really need to identify the patterns that cascade through the whole network. That’s where AI and machine learning come in, and that’s why Genuity has tasked Chittenden to lead R&D at its Advanced Artificial Intelligence Research Laboratory. Chittenden's team is pioneering new applications of old ideas from the wo

This week Harry interviews the head of Etiometry, a Boston-based startup building visualization systems and decision support software for hospital intensive care units. Shane Cooke says critical care "is an incredibly complex environment where speed matters and information matters." By aggregating real-time data, lab results, and historical patient records on a single screen, Cooke says, Etiometry hopes to show caregivers that they can glean more value from the data that's already collected by intensive care units but seldom unified.Etiometry's visualizations run on any hospital-approved web browser, and can therefore be used to monitor patients remotely. Not only does this unified visual presentation of input from monitoring devices and medical records can increase the effectiveness and efficiency of ICU care, Cooke says—it also enables real-time, risk-based analytics that help medical staff anticipate a patient's course.Cooke joined Etiometry in 2019 as the president and CEO, bringing over 20 years of exper

Charles Fisher is the founder and CEO at Unlearn, a San Francisco company using purpose-built machine learning algorithms that use historical clinical trial data to create "digital twins" of actual participants in controlled drug trials to help predict how each participant would have fared if they'd been given a placebo. By comparing a patient's actual record to their digital twin, Fisher says, the company can pinpoint the treatment effect at the patient level and conduct trials with fewer placebo patients. Fisher tells Harry that Unlearn's software can help drug companies run clinical trials "twice as fast, using half as many people." Fisher's own history is somewhat unconventional for someone in the pharmaceutical business. He holds a  B.S. in biophysics from the University of Michigan and a Ph.D. in biophysics from Harvard University. He was a postdoctoral scientist in biophysics at Boston University and a Philippe Meyer Fellow in theoretical physics at École Normale Supérieure in Paris, France, then went

What if all our everyday assumptions about economics are wrong? This week Harry speaks with author and entrepreneur Jeff Booth, who says the most powerful force for change in the future will be deflation: getting more for less. Even the healthcare industry will feel the effects, he says. Listen to find out how.Booth is the author of The Price of Tomorrow: Why Deflation is the Key to an Abundant Future. The book argues that the most powerful force for innovation and change is not endless investment and growth, based on an inflationary idea that everything always gets more expensive, but technology-driven abundance, powered by exponential, deflationary trends in computing and storage that drive the price of everything down. Booth says governments should stop striving to ward off deflation and recognize that economic systems built around credit, debt, and eternal inflation only reinforce radical inequality and class resentment. As the deflationary force of technology spreads to even more industries—including hea

How does an expert in pharmacokinetics, whose only exposure to computers was taking one semester of programming in college to meet a language requirement, become an advocate for the new AI-driven style of drug discovery? This week Harry finds out from Mark Eller, who helped to invent Allegra at Hoechst Marion Roussel (now Sanofi), spent 12 years at Jazz Pharmaceuticals, and is now senior vice president of research and development at twoXAR, an AI-driven drug discovery startup.In our previous episode from August 31, 2020, Harry spoke with twoXAR founder and CEO Andrew A. Radin, who confessed to being a computer nerd and lamented that it's been hard finding colleagues who are willing and able to help him bridge the gap between software and biology. He told the story of Mark Eller, who started out as a consultant at twoXAR but ended up telling Radin "I want you to offer me a job." Eller told Radin that the twoXAR project had finally convinced him that AI is good for more than just winning games of chess or Go, a

Harry welcomes back Andrew A. Radin, CEO of the drug discovery startup twoXAR, where scientists model pathogenesis computationally to identify potential drug molecules, ideally shaving years off the drug development process.Harry first spoke with Radin two years ago at the AI Applications Summit—Biopharma. (Listen back to MoneyBall Medicine Episode 9 from November 2018 for more details about the company's innovations.) Since then, the company has begun to use what Radin calls twoXAR's "discovery engine" to test hypotheses about new drug leads in 18 different treatment areas, counting a dozen internal programs."We go after complex disease where we think there is not only an unmet medical need, but where we believe discovery of new biology can  unlock some opportunity for new therapy," Radin tells Harry. He says the company's approach compresses the time-consuming early steps of basic science, literature search,  hypothesis formulation, and high-throughput screening into a single computational step. "We're goin

In this week's show Harry interviews Rayid Ghani, a computer scientist at Carnegie Mellon University who studies how to use AI and data science to model and influence people's behavior in realms like politics, healthcare, education, and criminal justice.Ghani tell Harry he grew up hating coding, since the very need for it showed that "computers are really stupid and dumb." But Ghani says he eventually realized that machine learning can change that by allowing programmers to teach computers the rules of the game, at which point they can improve on their own and learn to solve real problems.Ghani went on to become chief data scientist for the 2012 Obama campaign, and he has since used what he learned  about data analytics to study applications of AI to large-scale social problems in many areas, including healthcare. He's currently Distinguished Career Professor in the Machine Learning Department at Carnegie Mellon University's School of Computer Science.In political campaigns, Ghani says, machine learning and o

This week Harry speaks with Oura Health CEO Harpreet Rai, who's leading an effort to explore how a wearable sleep-monitoring device—the Oura Ring—can pick up patterns that may help diagnose covid-19 infections and other problems.The ring is equipped with sensors that measure heart rate and body temperature, as well as a tiny Bluetooth radio that syncs the data it collects with a smartphone app. The Finland-based company designed the ring primarily to measure sleep quality, but it also contains an accelerometer and a gyroscope that can measure daytime movement and activity.  Together, the data is used to calculate a "readiness score" indicating whether the wearer is fully rested and prepared for the day.Now Oura is collaborating with the West Virginia University Rockefeller Neuroscience Institute to study whether data from the ring can also be used to detect the early symptoms of covid-19 and predict whether wearers will be officially diagnosed with the virus.  The hypothesis is that systematic changes in a we

David Sable got his start in reproductive medicine in the late 1980s, a time when he says fertility treatments were "very primitive." But by the mid-2000s, he says, new procedures and new insights into the genetics of development had changed everything. His subsequent time observing (and investing in) the field has convinced him that reproductive medicine is "the most interesting area of medicine this century."Sable is a medical and entrepreneurial chameleon who trained in obstetrics and gynecology, worked as a reproductive endocrinologist, co-founded the Institute for Reproductive Medicine and Science fertility clinic, co-founded the embryo genetic testing firm Reprogenetics, and now works as portfolio manager of the Special Situations Life Sciences Fund and the Life Sciences Innovation Fund while also writing for Forbes and teaching biotech entrepreneurship at Columbia University. Intriguingly, Sable says his earliest inspiration to become a medical entrepreneur came from the brief scene at the end of The E

This week Harry speaks with molecular geneticist Elli Papaemmanuil about how newly available genomic data could lead to major improvements in the standard of care for cancer patients, leading to an age of true precision medicine.Papaemmanuil is an assistant professor of computational oncology at Memorial Sloan Kettering Cancer Center in New York. Her lab's research is built around the idea that the genetic sequences of tumor cells reveal distinctive acquired mutations that can allow doctors to predict the course of the disease in specific patients and help them to design individualized treatments. That idea isn't new—but it isn't yet standard practice in oncology, a situation Emmanuil is working to change, in part by using AI and data-driven approaches to analyze the vast number of genetic variations in diseases like leukemia and reduce them to a manageable number of classes amenable to customized treatment approaches.Papaemmanuil says she decided to become a cancer geneticist from the moment she learned abou

This week Harry interviews Gregory Bowman, an associate professor in the department of biochemistry and molecular biophysics in the School of Medicine at Washington University in St. Louis. Bowman is the current director of Folding@home, a distributed computing project currently focused on analyzing the structures of coronavirus proteins to find targets for new drug therapies that could help end the pandemic.Understanding and modeling the 3D structures of tiny, ever-shifting protein molecules is a notoriously complex problem. Folding@home cuts through it by sending crystallography data and other information to thousands of home computers and using it to model possible protein configurations—effectively creating a large, networked supercomputer. The project has been underway in various forms since 2000, but has recently concentrated fully on the SARS-CoV-2 virus that causes covid-19. The hope is that the work will reveal locations on viral proteins where small-molecule drugs could bind, disrupting the virus's

Harry's guest this week is the founder and CEO of a New Zealand firm, SaferMe, that had developed proximity-based smartphone apps for worker safety. When the coronavirus came along, their apps turned out to be a great way to help companies build their own "contact tables" to identify, test, and isolate SARS-CoV-2 carriers.In epidemiology, contact tracing is the art of determining who has crossed paths with an infected individual, so that those exposed can be alerted and can take appropriate action, such as self-isolating. Health agencies around the world are building public smartphone apps to assist with contact tracing, but they're being deployed at a national scale, whereas many businesses need more detailed information to protect their workers. Van Marrewijk says SaferMe had already built technology that creates a "virtual safety bubble" around each worker—issuing an alert, for example, if lightning is approaching or if they come too close to a hazard such as a mine shaft. "We already had this technology g