All Segments
a16z Podcast | Health Data -- A Feedback Loop for Humanity
24 segments available
"We live in a world where we use millions of variables to predict which ad you're going to click on. Whether or not you deserve to get a loan. What movie you might watch next. But when it comes to our bodies and even serious diseases, we want to reduce things down to just one or two variables." It's insane that we actually collect so little data about our bodies. The modern day physical is downright spartan in what it captures, not to mention that we're using 200-year old tools to capture that very limited data. Which is why we need to borrow from other domains of science and data and apply that to our bodies, in more ways than one, argues Q founder and CEO Jeffrey Kaditz with a16z bio fund general partner Vijay Pande (in conversation with Sonal Chokshi) on this episode of the a16z Podcast. But how do we get there? What would data "rights" look like -- and could we possibly donate data much like we currently donate organs? And for catching diseases like prostate or breast cancer early, how can we use data captured over multiple points in time -- something not really done right now in medicine -- to be more predictive, sensitive, and specific beyond so-called "representative" population samples? What IS a 'diagnostic', really, anyway?
Segments Timeline
Welcome to the Future of Health Data
In this segment, Sonal introduces the podcast and the guests, Vijay Pande and Jeffrey Kaditz, discussing the intersection of machine learning and biology. They highlight the importance of collecting comprehensive health data to improve our understanding of human physiology.
"hi everyone welcome to the a six in Z podcast I am sonal and I'm here today with our general partner for our bio friend Vijay Pandey and we have a special guest joining us we're just really talking a ..."
The Limitations of Current Health Assessments
Jeff Kaditz critiques the current state of annual physicals, noting the lack of correlation between these assessments and health outcomes. He contrasts this with dental care, which utilizes standardized metrics to track health over time, emphasizing the need for a similar approach in general healthcare.
"Aemon matter well I think we live in an era where the amount of information we actually collect about our physiology is like exceedingly small if you think about what the annual physical goal consists..."
Reinventing Preventative Healthcare
Kaditz shares his vision for a future where healthcare is preventative and continuously improving. He argues that no one should die from treatable diseases, advocating for a shift in how diagnostics are understood and applied in medicine.
"hundreds of millions of Americans nobody goes dentist twice a year for the record you know I think if you look at the trends by most metrics even adjusted for inflation the cost of dental care is stay..."
Understanding Diagnostics in Medicine
The discussion turns to the definition of diagnostics, with Kaditz explaining that they are predictive models. He critiques the reliance on point measurements and the outdated methods of comparing them to historical clinical studies, advocating for a time-series approach to diagnostics.
"yeah that's a great point because you think about you go to a dentist you get x-rays and you get them you know once every few years and you have this record over time and so you can see things develop..."
The Flaws of Representative Populations
Kaditz argues against the concept of representative populations in medical studies, emphasizing that individual physiological changes over time are unique. He highlights the importance of understanding personal health trajectories rather than relying solely on genetic information.
"Diagnostics you mean just tests that measure disease well that's actually I think an interesting question because we have specific opinions about what a diagnostic is but in general a diagnostic is a ..."
The Need for Continuous Monitoring
The conversation shifts to the current healthcare system's reliance on retrospective models. Kaditz discusses the challenges of transitioning to a value-based care model that emphasizes continuous monitoring and preventative measures to improve patient outcomes.
"standard test for determining if a man has prostate cancer but it has a very high false positive rate now you know I think if you look at this as a time series right series you mean like more than one..."
Challenges in Capturing Longitudinal Data
Kaditz and Pande discuss the difficulties in capturing a person's longitudinal health trajectory with current clinical data. They highlight the limitations of episodic testing and the need for a more comprehensive approach to health monitoring.
"so that effectively from our perspective that means that human physiology is a long-tailed distribution so your genetic code cannot be the kind of you know silver bullet that is magically going to bri..."
The Cost of Preventative Care
The segment addresses the financial implications of preventative care and the issue of false positives in diagnostics. Kaditz explains how costs and the potential for false positives hinder the adoption of more frequent and comprehensive health screenings.
"last ten years they've gotten sick at this rate and it cost us much for these drugs and these drugs are going up and so look at it more like well we know we have therapeutics for these certain disease..."
Defining False Positives in Diagnostics
Kaditz defines false positives and discusses their significance in medical diagnostics. He emphasizes the need for accurate predictive models to avoid misdiagnoses and improve patient care.
"we're being value-based versus just fee-for-service based it actually will create the opportunity where this actually makes a ton of sense because the total value to the patient the value to the payer..."
The Need for Longitudinal Health Data
In this segment, the discussion revolves around the necessity of quantifying health metrics to shift towards value-based care. The speakers highlight the current limitations in capturing a person's health trajectory through clinical data and the importance of early detection of diseases. They emphasize that most lethal diseases are often diagnosed too late, underscoring the need for a more comprehensive approach to health data collection.
"unless we have a way to quantify what it means to get healthier we can't even develop a metric for what value-based care is and so I think that not only does it does this make sense from it in terms o..."
Understanding False Positives in Diagnostics
This segment delves into the concept of false positives in medical diagnostics, explaining their implications for patient care. The speakers discuss how false positives can lead to unnecessary invasive procedures and the associated costs. They also touch on the importance of improving diagnostic accuracy to reduce the occurrence of false positives, particularly in the context of prostate and breast cancer screenings.
"wouldn't we figure out a way to use that more frequently and and I think the answer actually is costs right and false positive problems two aspects are cost right so cost is one thing and false positi..."
The Challenge of Diagnostic Accuracy
The conversation shifts to the challenges surrounding the accuracy of diagnostic tests, particularly mammograms. The speakers argue that while mammograms provide some predictive power, the high rate of false positives raises concerns about their utility. They advocate for a longitudinal approach to diagnostics, suggesting that tracking data over time could enhance the accuracy and effectiveness of these tests.
"there's the cost of any incremental test and that's one thing I think that's part is actually less concerning than the part that where a person's health is negatively affected because of the false pos..."
Redesigning Healthcare Through Data Science
In this segment, the speakers propose a redesign of healthcare delivery, emphasizing the importance of longitudinal data in improving patient outcomes. They draw parallels between healthcare and other scientific fields that successfully utilize longitudinal studies. The discussion highlights the potential for better health outcomes through a positive feedback loop of information, particularly in primary care settings.
"if you think of this test from a one-off point of view it may look less useful but if you think of her from a longitudinal point of view or longitudal in my context of many other tests suddenly now th..."
Identifying Key Biomarkers for Health
The final segment focuses on the identification of critical biomarkers for health monitoring. The speakers discuss how current practices may overlook essential indicators of health, using gum disease as an example of a correlated factor for cardiovascular issues. They challenge the audience to consider what first-order biomarkers should be tracked and how this could lead to significant improvements in early disease detection and prevention.
"from predicting population growth or deforestation we use longitudinal data predict what the climate is going to be in a hundred years we use it to predict what the weather is gonna be like next week ..."
Patient Rights and Data Ownership
The speakers discuss the ethical implications of patient rights regarding their health data. They argue for a shift in perspective, advocating that patients should have greater access to and control over their health information, especially as it pertains to non-invasive data collection methods. This segment raises questions about the paternalistic attitudes of medical organizations towards patient information.
"just patients but actual doctors who believe that a patient has a lot more rights to information about their body right now there is a to some degree there is a paternal position taken by you know org..."
Outdated Medical Tools and Technology
In this segment, the conversation critiques the reliance on outdated medical tools, such as the stethoscope, which has remained largely unchanged for 200 years. The speakers argue that modern medicine lacks the technological advancements necessary for comprehensive health assessments, highlighting the need for innovation in medical diagnostics.
"solution I'm still not clear though on where this data is coming from how is this data gonna get into the system this longitudinal tracking and how does it affect say a concrete case like prostate can..."
The Complexity of Physiological Data
This segment delves into the vast complexity of physiological data compared to genomic data. The speakers discuss how the information contained within a person's physiological state is exponentially greater than that of their genome, emphasizing the need for advanced methods to capture and analyze this data for better health outcomes.
"that we use to assess our general physical health if you think about when that was that we did not have the technology there tools to non-invasively measure anything about our physiology we didn't hav..."
Methylation and Its Impact on Health
The discussion focuses on the role of methylation in gene expression and how environmental factors can alter genetic behavior over time. The speakers argue that understanding these changes is crucial for predicting health outcomes and that the complexity of physiological states must be considered in medical assessments.
"Jesus like every voxel that describes you although you could argue it's really the diffs right so the genome the the you know maybe there's a million base pairs not a billion in the you know are actua..."
Improving Predictive Healthcare Models
In this concluding segment, the speakers propose methods to enhance the sensitivity and specificity of health tests by analyzing individual changes over time in relation to population data. They advocate for a more personalized approach to healthcare that considers both individual history and broader population trends to improve diagnostic accuracy.
"state that accumulate over time so and and we would argue that it really is part of the explanation so for why twins diverge you were constantly interacting with your environment in accumulating compl..."
Data-Driven Health Insights
This segment discusses the irony of using complex data models in everyday decisions while simplifying health metrics to one or two variables. The speakers argue for a more nuanced approach to health data, advocating for the integration of multiple variables over time to better understand individual health conditions.
"know a you know a you know a noble goal but you know I think we definitely know how to set up systems that have this positive information feedback we can get better and better I mean Facebook and Goog..."
The Need for Comprehensive Data
The speakers stress the necessity of applying advanced data modeling techniques from other scientific domains to healthcare. They argue that the complexity of human physiology requires a more sophisticated approach to data collection and analysis, moving beyond outdated methods.
"part of this is so you can add time as another dimension to any specific biomarker and increase the sensitivity specificity the other thing you can do is have multivariate models for pathology it's ki..."
The Case for Data Donors
In this thought-provoking segment, the idea of 'data donors' is introduced, suggesting that individuals could contribute their health data anonymously to improve medical research. The speakers compare this to organ donation, emphasizing the potential impact of shared health data on future generations.
"there's a little bit of reticence to do that because people think oh our bodies are so complex you know we'll never understand it and I think we have to decouple our thinking part of our body from the..."
Building a Public Data Repository
The discussion shifts to the logistics of creating a public data repository for health information. The speakers propose a system where individuals can opt to donate their health data, similar to organ donation, to foster a feedback loop that benefits humanity and advances medical research.
"every day it's more sophisticated by the way just a really interesting example of this I read this amazing article on Landsat and how over the last like 30 years they've been you know obviously collec..."
Ethics of Health Data Donation
In the concluding segment, the ethical implications of health data donation are explored. The speakers advocate for a structured approach to data donation, ensuring anonymity and privacy while highlighting the potential for significant advancements in healthcare through collective data sharing.
"me and that's a network effect that's how you as a person can improve the health of every generation after you yep that's amazing and how do you then control for the fact that the sample because you'r..."