Illness and Big Data

Richard Barker is director of the Center for the Advancement of Sustainable Medical Innovation, Oxford. He states, 'Illness just became another big-data problem'.

Cameron was Alissa Lundfelt's first child, so initially she didn't realize anything was wrong. He would demand milk constantly, but she thought that wasn't unusual. But when his fingers and toes started to go cold, his eyes rolled back in his head and his skin turned grey, he was taken to the emergency room and diagnosed with Type 1 diabetes. At five months old, he was the youngest person ever to receive this diagnosis in his home state of Alaska.

This meant testing his blood sugar every two to four hours and giving frequent insulin injections, since -- in Type 1 diabetics -- the insulin-producing beta cells in the pancreas are attacked by the body's own immune system, stopping the production of insulin that the body needs.

But even with this regimen, Cameron didn't thrive. When he was two years old, Ian Glass, associate professor of paediatrics and medicine at the University of Washington, and visiting Alaska from Seattle, ordered a test. This revealed that Cameron's diabetes was caused by a mutation in the KCNJ11 gene. Lundfelt went online and read about a group of scientists who had discovered that, in this rare form of diabetes, the beta cells produced plenty of insulin, but it couldn't get out of the cells. All Cameron needed was to take a single pill three times a day to restore his glucose levels to normal.

So diabetes isn't just diabetes: it's a cluster of diseases with different causes and different remedies. This story is just a glimpse of a quiet medical revolution: from defining diseases by the symptoms they cause or the part of the body affected, to the underlying molecular mechanism.

Everything from the situation in the womb to the way someone lives their life can result in a set of molecular patterns that appear as symptoms, which often hides more than they reveal
Richard Barker
The tools we have to power this revolution are being added to daily. We are testing cancers that arise in the skin, the colon and the lungs and finding that a proportion of all of them have mutations of the BRAF gene, suggesting they will all respond to the same medication. And often we can work backwards from different responses to a drug to find that superficially similar diseases have different mechanisms -- as in many autoimmune diseases, for example.

It isn't just genetics that influence the existence of a disease, or the form that it takes. Only one of a pair of identical twins may have schizophrenia, for example. Everything from the situation in the womb to the way someone lives their life can result in a set of molecular patterns that appear as symptoms, which often hides more than they reveal.

This redefinition of disease will also set us a fascinating semantic challenge. Your doctor might tell you that your swollen joints are symptomatic of a TLR and IL-1R signalling pathway imbalance: or instead perhaps she will just say you have arthritis type 13-2. Or perhaps your doctor is not aware of this new precision medicine and simply says you've got rheumatoid arthritis. So when you search for "molecular mechanisms of rheumatoid arthritis", you find over 2,270,000 results.

We'll discover a lot about ourselves and our diseases from big data -- assessing the outcomes of different therapies and finding out in retrospect what works best for who. We will then match that against our gene sequences, which may be stored confidentially at birth. If Cameron Lundfelt had been born a few years later, his parents and doctors would perhaps have known before his symptoms had even appeared that he had monogenic diabetes type KCNJ11. And they would have known immediately what to do.


Click here for the article on the web.



<< Click here to see more recent news articles >>

 

Latest Jobs

Salary

US$120000 - US$130000 per annum + Additional Benefits

Location

Cincinnati, Ohio

Description

My client in Ohio are looking for big data engineering experts looking to join a learning-based cutting edge environment to grow technically!

Salary

US$400 - US$560 per day

Location

San Francisco, California

Description

Salary

US$150000 - US$160000 per annum

Location

New York

Description

Looking for a Salesforce Developer to join a Data Intelligence consulting firm that provides innovative solutions to meet business goals.

Salary

US$170000 - US$200000 per annum + Additional Benefits

Location

New York

Description

A Data-centric Tech Start Up client of mine are looking for a Full Time Lead Data Engineer and Technical Consultant to join their NYC team!

Salary

US$170000 - US$200000 per annum + Additional Benefits

Location

New York

Description

A Data-centric Tech Start Up client of mine are looking for a Full Time DataOps and Presales Engineer to join their NYC team!

Salary

US$100000 - US$115000 per annum + Additional Benefits

Location

New York

Description

Please check out this great local Senior Business Intelligence opportunity I am working on in the exciting eMarketing industry!

Salary

US$150000 - US$175000 per year

Location

New York

Description

Are you a Data Engineer who lives and breathes Marketing?

Salary

US$100000 - US$115000 per annum + Additional Benefits

Location

New York

Description

Please check out this great local Senior Business Intelligence opportunity I am working on in the exciting eMarketing industry!

Salary

US$130000 - US$140000 per annum + Additional Benefits

Location

Hartford, Connecticut

Description

An insurance business is looking for a data engineer to join their CT headquarters or work remotely!

Salary

US$140000 - US$150000 per annum

Location

Cincinnati, Ohio

Description

Are you the type of person who likes a challenge? Do you like learning new technologies?

Salary

US$180000 - US$220000 per annum

Location

San Francisco, California

Description

A cybersecurity business with their own innovative technology that is saving its users thousands of dollars.

Salary

US$100000 - US$115000 per annum + Additional Benefits

Location

New York

Description

Please check out this great local Senior Business Intelligence opportunity I am working on in the exciting eMarketing industry!

Harnham blog & news

With over 10 years experience working solely in the Data & Analytics sector our consultants are able to offer detailed insights into the industry.

Visit our Blogs & News portal or check out our recent posts below.

Business Intelligence Is About Asking The Right Questions

You’ve dotted all the ‘Is’, crossed all the ‘Ts’. You’ve ensured your business priorities were aligned with your mission and objectives. But, how can you know if you’re on the right path, especially in light of today’s uncertainties. Your crystal ball may be in the cloud, but to find its clarity, you have to be asking the right questions. Below are three questions to consider moving forward. 1. How Collaborative Are We? As businesses shift online and teams expand globally, collaborative business intelligence streamlines decision-making. A combination of BI tools, software, and social technologies to inform, engage, analyze, and form insights of what customers want and need. This form of collaboration takes decision-making out of its siloes. Not unlike the Socratic method, collaborative business intelligence solves problems through shared information to find common ground. Using business intelligence software to provide opportunities for predictive modeling, visual analysis of data and business metrics, businesses analysts can interpret and inform, in a more efficient streamlined process. 2. How Secure is Our Data? Whether big business, small business, or medium business, no one is immune to cyberattacks. The ever- increasing rise of these attacks pinpoints just how important keeping data secure is for all businesses. Breaches cause not only monetary loss, but ultimately, consumer trust leading to more loss. The importance of Data security cannot be overstated.  Now that a majority of businesses are making flexible and remote work options available, it’s imperative businesses work to keep data secure. Consumers today are much more concerned today about how and why their Data is used, and many may decline to offer it, not wanting to put themselves at risk of a possible cyberattack.  3. What’s the Best Platform to Drive Actionable Insights from Our Analytics? Much like the trend of collaborative BI, businesses are focused on combining business processes and workflows into one platform, so everyone has access to the same Data. It’s within these platforms, that businesses cannot only determine what action to take and implement those actions all in one place. Platforms become the hub of the wheel and the spokes are analytics of a particular industry, business, or department in which insights can be implemented. Some platforms on the move include Sisense and Sharepoint. Google Analytics Intelligence (GAI) might be the most well-known especially if you’re just getting started asking the right questions for your business.  If you want insight into the state of your business, know any major consumer traffic changes, or want to know the probable conversion rate of web browsers to customers, GAI can help you get those answers. Because it uses machine learning to help, it’s important to know not necessarily what questions to ask, but how to ask them. How to Ask a Computer the Right Questions If you’ve been working in a collaborative BI team and asking each other questions based on the data you’ve collected, it may be a bit of a mindset shift for asking questions of a computer. So, how you phrase your question, what you want to know, and how you ask may require a bit of thought to find the answers you’re looking for. Below are a few guidelines to consider when posing the questions.Follow the TrendIf you want to know what’s trending in your business, you might ask: How many products were sold last week?How many customers did I have today?Where are my customers located?What time were the most customers shopping?  Which is Best? When you want to know what product is selling the most and through which means. Follow the performance. These questions might include: Which channel converted the most customers?Which product sold the most? Which product sold the least?Which hour was best for customer traffic? Compare and Contrast These are questions or commands that enable you to compare two sets of data side by side, such as how your business performed week to week, day to day, or year to year. While most questions begin with ‘which’ or ‘how’, the compare and contrast questions can get a bit more complex. In these questions, you begin with what you want to know such as conversion rate, revenue shares, traffic, or trend.  As this year comes to a close, what questions will you ask of yourself? Are you ready for a change? A new role? If you’re a business, what questions will you ask to move your company forward in the new year? If you’re interested in Big Data & Analytics, we may have a role for you. Check out our current opportunities or contact one of our expert consultants to learn more.  For our West Coast Team, contact us at (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.  For our Mid-West and East Coast teams contact us at (212) 796-6070 or send an email to newyorkinfo@harnham.com.  

How Machine Learning and AI Can Help Us See the Forest for the Trees

In the early days of 2020, Johns Hopkins, the CDC, the WHO, and a host of other public organizations banded together in collaboration. They were on a mission to ensure the world had real-time information to a virus that would forever chance the course of this year and the years to come. Which is great for those families with a computer in every home or every person with smartphone access. But what about the rest of the world? How do you ensure those people without access to basic needs lives can be improved? A health non-profit using AI and Machine Learning is aiming to do just this. But the Data is vast and the sheer numbers of people need to be corralled by someone into something the computers can read and make decisions on. Who would have thought Public Research and Data Science would come together in such a manner and in such an important time? Three Benefits of Data Science and Machine Learning in Healthcare According to a seminar given in September 2019, two research scientists explained to the CDC the promises and challenges using Big Data for public health initiatives. After explaining a few definitions and making correlations, the focus was soon on the benefits. The focus of Machine Learning is to learn data patterns.From the initial focus, patterns can then be validated to ensure they make sense.These patterns and validation of patterns can find links between seemingly uncorrelated factors such as the relationship between one’s environment and their genetics. To the scientists working with these scenarios, the decisions seem simple. Yet, when it comes to explaining them to laymen like policymakers, there can be a shift in understanding. This shift can lead to arbitrary and different findings which can affect medical decision making. Why? Could it be using Random Forests in linking the data could be confusing?  Data Classification is Not as Cut-and-Dried as a Work Flow or Org Chart If someone shows us a work flow or organizational chart, we understand immediately each task to be done in which order or who reports to whom. But in trying to link uncorrelated bits of information using decision trees, it can seem more like abstract art, more subjective than direct. Yet, it is those correlations which answer the bigger questions brought to bear by Research Scientists, Public Health Researchers, the Data Scientists, and AI working together to see the bigger picture. Decision trees, ultimately, are the great classifier. But there are a few things which need to be in place first. Yet, in the random forest model it’s not just one decision tree, it’s many. This is definitely a case where, if you done right, you will see the forest for the trees and at the same time be able to determine patterns in those trees. A bit counter-intuitive, but this is what stretches our minds to see correlations and patterns we might not see otherwise, don’t you think? So, what do you need to help make predictions?  Two Important Needs to Help Make Predictions Predictive power. The features you employ should make some sense. For example, without a basic knowledge of cooking, you can’t just throw random items from your refrigerator into a pot and expect it taste good. Unless of course, you’re making soup and all you have to do is add water.The trees and their predictions should be uncorrelated. If you’ve ever seen M. Night Shymalan’s Lady in the Water, there’s a little boy who can ‘read’ cereal boxes and tell a coherent story. A predictive coherent story. This is the layman’s version of random forests, their predictive nature, and ultimately, the scientists who can ‘read’ and explain the patterns. If you're looking for your first or next role in Big Data, Web Analytics, Marketing & Insight, Life Science Analytics, and more, check out our current vacancies or contact one of our recruitment consultants to learn more.   For our West Coast Team, contact us at (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.   For our Mid-West and East Coast teams contact us at (212) 796-6070 or send an email to newyorkinfo@harnham.com.  

Recently Viewed jobs