"hi and welcome to the a 16z podcast I'm Hannah and today we're talking about AI in medicine but we want to talk about it in a really practical way what it means to use it in practice and in a medical ..."

"maybe just do a quick breakdown of what we're actually talking about when we talk about introducing AI to medicine what does that actually mean how will we actually start to see AI intervene in medici..."

"so basically doing what hypochondriacs do Yeah right so so Google isn't as in some ways an AI expression of that where it's actually used ongoing inputs in classification to do that over time much mor..."

"you think about kind of a hospital from the CFO's perspective misdiagnosis actually earns them more money because when you miss diagnose you do follow-up tests right and those and our billing system i..."

"of physicians going crazy and where it's going to be very very hard and that I think is the challenge in terms of both building developing these technologies commercializing them and seeing how they s..."

"there's some inherent challenges in the nature of the beast yeah healthcare is unpredictable it's stochastic you can predict a cumulative probability like a probability of getting condition X or diagn..."

"think that's where we've seen AI really pick up in imaging like studies it's a closed loop diagnosis you know there is a nodule on an x-ray that is you know cancer based on a biopsy proven later in th..."

"reinvent the entire medical system with this assumption that we have a lot of data intelligence is artificial and therefore they're for cheap so we can do continuous monitoring so one of the things I ..."

"which seems astonishingly low but that's that's kind of the fact there's kind of a gap right about a third of people with diabetes don't realize they have it about a fifth of people with hypertension ..."

"a last mile ai problem so that if you want to scale the ability so to get this stuff okay so let's say we get to a point where our bathroom tiles have built-in EKG sensors and scales and the data just..."

"the convolutional neural networks and to actually break that down for a second so are those confusion matrix so the confusion matrix is a way to graph the errors and which directions they go and so fo..."

"technical hurdle at this point right well and you can imagine just as for less a self-driving cars you have different levels of autonomy it's not nothing versus everything you know in convention level..."

"computer it is very natural but I think we need a couple things to get there we need really dense high-quality data to train and the more data you put in a model I mean so much gene learning by defini..."

"a nice thing about wearable data is it fitbit's are the same all over the world this legal problem though is is interesting because you know in our context each label represents a human life at risk r..."

"and so don't complicate your models unnecessarily and don't build models that are overly complicated for the amount of data you have right because if you have the case where you're doing so much bette..."

"fundamentally a data quality problem if you collect data from all over the world you can address this but but you have to be a while for that to happen as we start gathering the data in different ways..."

"the initial version of versions of the apps weren't engaging so this isn't in ads an interesting new dimension as a medical researcher you might not think about building an engaging well-designed app ..."

"entity whoever that may be whether its employer based programs insured based programs accountable care organizations are they going to be willing to take on risk to see the rewards of cost and scale a..."

"version you could version every day every week every month it's browner's what you want to do is to the point that we're talking about earlier you want to bring in new validation sets things that it h..."

"early companies used expert systems to just ease the pain points of me having to write out and code out every single diagnosis the super low-hanging fruit yeah can you improve the accuracy of physicia..."

"clinical setting you know the tools that we might see our doctor actually use with us or not I think it's going to be these adjacencies around treatment with management there are a lot of things that ..."

"the AI inputs over time could be like well you can really truly know which physicians are quick and speedy which ones over there are a lot of times which patient cases might be high-risk which ones ma..."