![\"\"](\"http:\/\/www.washingtonpost.com\/wp-apps\/imrs.php?src=http:\/\/img.washingtonpost.com\/blogs\/innovations\/files\/2014\/09\/Copy-of-google-datac2346enter-tech-221363877103_image_982w.jpg&w=1484\")
<\/div>\nImagine if your doctor could compare your physical health, diet and lifestyle to a thousand Americans with similar characteristics, and realize that you need treatment to prevent heart failure next month.<\/p>\n
What if an analysis of your genome could help a physician give you a customized cancer treatment that saves your life?<\/p>\n
Unleashing the modern power of computers, data crunching and artificial intelligence could revolutionize health care, improving and extending lives.<\/p>\n
It\u2019s the kind of potential Google chief executive Larry Page hinted at when he told the New York Times<\/a> earlier this year that \u201cwe\u2019d probably save 100,000 lives next year,\u201d if we data mined health care data.<\/p>\n \u201cImagine you had the ability to search people\u2019s medical records in the U.S.,\u201d Page said in another interview<\/a> this summer. \u201cI imagine that would save 10,000 lives in the first year.\u201d<\/p>\n Page\u2019s numbers sound impressive, but are speculative and unfounded, according to many in the medical industry.<\/p>\n Interviews with more than a dozen\u00a0health care professionals and data scientists found no evidence backing Page\u2019s specific claims. While they universally agree that data mining \u2014 the examination and analysis of huge batches of information\u00a0\u2013 could invigorate health care, they caution that any sort of accurate estimate would be impossible.<\/p>\n \u201cUsually when I see someone put a number on it and throw around saving lives it usually means one, they aren\u2019t usually a clinician or someone who provides care, or No. 2\u00a0it\u2019s someone who really knows better, but is trying to grab a headline,\u201d said Nicholas Marko, the department head of data science at the Geisinger Medical Center.<\/p>\n A Google spokeswoman declined to offer an explanation of Page\u2019s numbers, or make him available for comment.<\/p>\n In one other instance where Page has used an unsubstantiated health care statistic, he\u00a0told Time Magazine <\/a>\u00a0last year that solving cancer would only \u201cadd about three years to people\u2019s average life expectancy.\u201d That\u2019s a figure the American Cancer Society and National Cancer Institute had never heard of before. A Google spokeswoman didn\u2019t have an answer when asked for an explanation.<\/p>\n To a cynic, Page is a shrewd businessman twisting facts to shape the national dialogue so that he can profit from absorbing our health data into\u00a0the Google cloud, where his world-class engineers will find ways to make money off all of that information.<\/p>\n An optimist might remember Page\u2019s assertion<\/a> that Google is a company devoted to solving \u201chuge problems for hundreds of millions of people,\u201d and offer him the benefit of the doubt.<\/p>\n \u201cHealth care has been pretty archaic. We\u2019re pretty behind the curve on things,\u201d said Lorren Pettit, a vice president for the Healthcare Information and Management Systems Society, which aims to improve health care through information technology. \u00a0\u201cWe need the innovation of people from outside health care to come in and take\u00a0a look and challenge this industry, and yes with data mining there\u2019s a great world of possibility.\u201d<\/p>\n Shaking up industries is part of Google\u2019s DNA. Its self-driving car project could in theory eliminate the 1.24 million<\/a> fatalities a year on global roads. If Page can soften a country\u2019s fears about sharing our health data \u2014 which ends up saving lives \u2014 does the end justifies his means of fuzzy math?<\/p>\n \u201cThere\u2019s tremendous opportunity if we start taking individualized genomic data and health histories and assuming you can perfectly de-identify it, my gosh, if you can mine that and look for patterns between genomic sequences and types of illnesses and effects of treatment on those illnesses you could potentially do a tremendous amount for society and the health of our individuals,\u201d said Christopher Jaeger, Sutter Health\u2019s chief medical information officer.<\/p>\n The average person might spend a few hours a year with their physician, during which data about their health (blood pressure, alcohol consumption, weight, etc.) is written down. If a patient\u2019s health data was tracked 24-7 \u2014 as devices such as smartwatches are making realistic \u2014 there would be an exponential leap\u00a0in the amount of data about someone\u2019s health. More information \u2014 and the comparison of that information to other patients \u2014 should lead to better treatments.<\/p>\n \u201cIt would be great if when the patient walked in our Bluetooth sensors picked up their phone and it pushed in all their exercise and diet history, and then there were analytics that were performed in real time,\u201d said Thomas Graf, chief medical officer at Geisinger Health System. \u201cWhen the doc walked in the room they can say \u2018Oh, looks like you\u2019re exercising at 80 percent of what we were talking about.\u2019 \u201d<\/p>\n But fear of litigation, privacy concerns, regulations and the challenge of collecting and standardizing data all stand in the way of realizing this health care utopia. Still, there are some early examples that hint at what could be done.<\/p>\n Researchers at the University of Bern in Switzerland have built a computer program to better measure the size of brain tumors.<\/p>\n Traditionally radiologists look at MRI scans and measure in two dimensions the size of a tumor. The computer program \u2014 called BraTumIA \u2014 is capable of a 3D analysis of the tumor\u2019s volume, which better measures whether it\u2019s shrinking or growing. Getting measurements right is crucial as physicians determine the best treatment plan for a patient.<\/p>\n \u201cIf I ask two radiologists to do the same job, you will see differences,\u201d said researcher Mauricio Reyes. \u201cThe computer has the ability to be more consistent and more objective over time. Even if you have an error in the computer this error is consistent over time. What really matters is the trend.\u201d<\/p>\n Here\u2019s how the program works.\u00a0A set\u00a0of annotated brain scans \u2014 in which different parts of a tumor are labeled \u2014 are preloaded into the program. The program uses those as a guide to\u00a0teach itself to identify different parts of future brain scans as a tumor or not.<\/p>\n The end result is being able to run a scan for five minutes on a laptop and having a better understanding of a tumor. If more medical images made their way into databases such as BraTumIA, those services would get even better.<\/p>\n But what if health data we think is anonymous gets identified or hacked? The threat of being sued deters health organizations from sharing data and embracing the full potential of data mining.<\/p>\n For example, MRI exams and CT scans of a patient\u2019s head could\u00a0be used to reconstruct a person\u2019s face. A hacker with access to such a database could use face-detection software to crosscheck the scans with a Web site where users post photos of themselves.<\/p>\n \u201cIf the same person has a Facebook account there\u2019s a good chance that you could identify this person. If I had access to such a database I could give you a list of people in Facebook with names of who has a brain tumor,\u201d cautioned Bjoern Menze, a computer science professor at TU Munchen who researches medical imaging.<\/p>\n \u201cThere will be criminals. There will be people who are bad actors. At some point something is going to get out,\u201d Graf said. \u201cIt\u2019s not an irrational fear. At the same time, people die driving every year and we still choose to drive cars, or most of us do. It\u2019s a risk every person has to decide where they fall on the line.\u201d<\/p>\n Many of those I interviewed anticipated a situation where patients could decide whether to opt into data mining of their health records. A tax benefit might even be given to encourage involvement.<\/p>\n If health records are ever going to be data mined, it\u2019ll happen when consumers are convinced the perks outweigh the costs. The world has already seen dramatic changes to privacy norms as services such as Facebook grow in popularity. It\u2019s incredibly popular Newsfeed \u2014 which funnels the latest information about friends into a feed \u2014 was initially met with uproar<\/a> by users concerned about their privacy.<\/p>\n But as users saw the utility of the feed, the tradeoff in privacy became acceptable.<\/p>\n \u201cThe goal in health care is not to protect privacy, the goal is to save lives. We need to have that as starting point,\u201d said David Castro, director of the Center for Data Innovation. \u201cIs the doctor treating me based on the last couple patients he saw, or is he treating me based on the rigorous analysis of millions of patents and finding the 5,000 that are actually just like me, and treating me in a much more accurate way?\u201d<\/p>\n For data mining to succeed would also require recruiting top data scientists to health care, which isn\u2019t easy given the demand in the hot field<\/a>.<\/p>\n \u201cIt\u2019s hard,\u201d said John Weinstein, chair of bioinformatics and\u00a0computational biology at MD Anderson Cancer Center. \u201cYou really have to battle with Silicon Valley and the Boston academic scene.\u201d<\/p>\n \u201cWhy would someone who is really really good at analyzing data come to work for a health care organization and make X dollars when they could go to Google and make 10X dollars?\u201d Marko added.<\/p>\n<\/article>\n \u201cThe goal in health care is not to protect privacy, the goal is to save lives. We need to have that as starting point,\u201d said David Castro, director of the Center for Data Innovation. \u201cIs the doctor treating me based on the last couple patients he saw, or is he treating me based on the … Continue reading data mining health records<\/span> ![\"\"](\"http:\/\/www.washingtonpost.com\/wp-apps\/imrs.php?src=http:\/\/img.washingtonpost.com\/blogs\/innovations\/files\/2014\/09\/Un2346236titled.png&w=1484\")
\nA screenshot of BraTumIA in action. (Mauricio Reyes)<\/span><\/div>\n![\"\"](\"http:\/\/img.washingtonpost.com\/wp-apps\/imrs.php?src=http:\/\/wp-eng-static.washingtonpost.com\/author_images\/mcfarlandmh.jpg?ts=1402601608910&h=90&w=90\")
<\/a><\/p>\n