<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Saud Siddiqui M.D. on Medium]]></title>
        <description><![CDATA[Stories by Saud Siddiqui M.D. on Medium]]></description>
        <link>https://medium.com/@saudsiddiquiMD?source=rss-d7759d0d2387------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*oxQOjqfIrS7JXKLjdE4UTg.jpeg</url>
            <title>Stories by Saud Siddiqui M.D. on Medium</title>
            <link>https://medium.com/@saudsiddiquiMD?source=rss-d7759d0d2387------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 15:03:56 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@saudsiddiquiMD/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[My Deep Dive into Deep Learning — What I Learned as a Physician]]></title>
            <link>https://medium.com/swlh/my-deep-dive-into-deep-learning-what-i-learned-as-a-physician-ad81295c6e13?source=rss-d7759d0d2387------2</link>
            <guid isPermaLink="false">https://medium.com/p/ad81295c6e13</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[medicine]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[healthcare]]></category>
            <dc:creator><![CDATA[Saud Siddiqui M.D.]]></dc:creator>
            <pubDate>Sat, 16 Dec 2017 17:52:07 GMT</pubDate>
            <atom:updated>2017-12-17T12:55:20.913Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*Oxnn96iIiIPykAK3QGHlVg.jpeg" /><figcaption>Neurons depicted by Santiago Ramón y Cajal, courtesy of Nature.com</figcaption></figure><p>“You’re doing what?” my colleague exclaimed. I wondered, did he think I was insane, or just stupid?</p><p>I recently embarked on a journey to learn about machine learning and deep learning. We hear the words machine learning, artificial intelligence, and deep learning echoed often, but I wanted to know the mechanics behind these processes and figure out if there were real applications to healthcare.</p><p>I took a course on deep learning which covered supervised learning through Artificial Neural Networks, Convoluted Neural Networks, and Recurrent Neural Networks, as well as unsupervised learning through Self-Organizing Maps, Boltzmann Machines, and Auto-Encoders. Through this course, we created models in the programming language Python using deep learning libraries Tensorflow and PyTorch. Here’s what I learned in the process.</p><h4>Different Models Can Solve Different Problems</h4><p>Before taking this course, I had heard the buzzwords and seen the headlines — “AI! Machine Learning! The robots are coming!”…but I actually had no idea how the mechanisms worked. I found that there were many different learning models that had been developed, each serving its own purpose. If we take a generalized approach, one could say neural networks and deep learning are modeled to mimic the neurons and neuronal connections in a brain. Taking this course opened my eyes to the different ways you could approach real world problems with these models inspired by neuroscience.</p><p>For example, an Artificial Neural Network, at its most basic level, takes numbers as inputs, feeds them through nodes contained in hidden layers, and provides a predicted output. While the model is being trained, this output is compared with the ground truth, or the actual value. Through an algorithm the weights or importance of each node in the hidden layers are changed and the model again tries to predict an outcome with the adjusted weights. This could be helpful in creating predictive models for disease processes and probabilities for differential diagnosis for example.</p><p>A Convoluted Neural Network, on the other hand, is tailored towards using images as inputs, which through a series of steps are flattened into numerical inputs that can be fed into the same type of system. This is how much of the image recognition software works, and could be applied to medical imaging to aid physicians in diagnosis.</p><p>As you learn more, you find more models, and you can imagine how each model can serve to solve a different need. The possibilities are vast and there is incredible room for creative solutions.</p><h4>As a Physician, Focus on the Concepts</h4><p>Lines and lines of code- for a physician, sometimes it’s almost as scary as a variceal bleeder. I dove right into this course with no prior python experience. Having learned Javascript in the past, I found that having a basic understanding of data types, objects, and arrays was very helpful. Nevertheless, understanding all of the nuts and bolts proved to be difficult.</p><p>Not only can the code be daunting, but so can the mathematics behind the algorithms and models. I believe you can take two different approaches here. The first route is to continue to learn as much as you can, and to become a master in deep learning, and then later apply it to medicine. Though this is a valiant goal, I fear it may be impossible for most, given that we spend most of our time becoming masters of our respective medical fields. The second, and I think more practical route, is to leverage the fact that you are a domain expert in medicine, and then focus on understanding the concepts of deep learning to then be in a position to come up with and apply solutions to your field.</p><p>I am a believer in the latter approach, though the question of how much understanding is enough understanding is debatable. I think in the discovery phase when you are learning about the different neural networks, you will easily come up with many different applications to healthcare. Once you do, focus on what you need to understand to bring those applications to reality. Try not to get bogged down or quit if the code and mathematics are difficult, as you can always team up with people who are experts in this area, who have spent their time learning this the same way you have spent your time learning medicine.</p><h4>This Is the Future -Be a Part of It</h4><p>Whether you like it or not, artificial intelligence, machine learning, and deep learning will make their way into medicine. In fact, there are applications being developed worldwide already. For example, researchers at Stanford University demonstrated that a deep learning algorithm could diagnose a skin lesion as cancerous just as accurately as a board certified dermatologist. Alphabet’s life sciences team and Nikon are using algorithms to detect causes of blindness in diabetics. At the Szechwan People’s Hospital in China, deep learning and image recognition is being developed to help where there are shortages of radiologists.</p><p>I believe that as physicians, we must accept and open our eyes to this technology, and should have a grasp of their mechanics and potential applications. As experts in our field, we are in the best position to come up with the great ideas that could impact healthcare and improve patient care. So go ahead, dive right in. A little bit of curiosity can go a long way.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6gfnVvkMRFtjVsWF7vkClA.png" /></figure><h4>This story is published in <a href="https://medium.com/swlh">The Startup</a>, Medium’s largest entrepreneurship publication followed by 275,057+ people.</h4><h4>Subscribe to receive <a href="http://growthsupply.com/the-startup-newsletter/">our top stories here</a>.</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6gfnVvkMRFtjVsWF7vkClA.png" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ad81295c6e13" width="1" height="1" alt=""><hr><p><a href="https://medium.com/swlh/my-deep-dive-into-deep-learning-what-i-learned-as-a-physician-ad81295c6e13">My Deep Dive into Deep Learning — What I Learned as a Physician</a> was originally published in <a href="https://medium.com/swlh">The Startup</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>