Although the area of genomics has not been developing at an exponential rate that experts expected when the Human Genome Project was announced to be completed, more and more ways of potential use of genomic data in medicine have showed how it might transform our lives. A few months ago, it was published that so-called “genetic mugshots” can be recreated from DNA. By only using a person’s DNA, a face can be generated which sounds like pure science fiction.
Now researchers at Oxford University have developed a computer program that can diagnose rare genetic disorders in children simply by analyzing family photos.
One day we might be able to sequence the genomes of newborns immediately after birth (or even before) to tell parents what major conditions the child might have to deal with in the future. As an additional feature, children without genomic sequences made available could get an instant diagnosis only by looking into the camera of a computer using this algorithm.
An excerpt about how it works:
The program works by recognising certain characteristic facial structures that can be present with certain conditions, including Down’s syndrome, Teacher Collins, Progeria, Fragile X and Angelman syndrome. It combines computer vision and machine learning to scan pictures for similarities to a database of pictures of people with known conditions, and then returns matches ranked by likelihood.
The New Scientist published a very interesting report about a new idea and technology that will be showcased at the upcoming Human-Computer Interaction conference in Toronto, Canada.
At the Museum of Arts and Crafts in Paris, a couple wandered in front of a set of dark screens. Staring back at them was an image of themselves – but with the skin stripped away, revealing organs, bones and muscle. Surprised, the woman gasped and covered her breasts, trying to shield herself from view.
Here’s how it works: an individual undergoes a PET scan, X-ray and MRI scan to capture high-resolution images of their bones and organs. Altogether, it takes about three-and-a-half hours to collect this data. Then when you step in front of the mirror, a Microsoft Kinect’s motion-capture camera tracks the movement of two dozen different joints, including the knees, elbows and wrists. That means the medical images can be animated with the help of graphical processing units so you can see your body inside out in real time.
A new study analyzing the role of IBM’s supercomputer named Watson in medical decision making was just published in Artificial Intelligence in Medicine. While the most acclaimed medical professionals might keep some studies in mind, Watson can check millions of them quickly. Instead of fighting them, doctors should realize we need to include such solutions in the everyday medical decision-making processes.
Using 500 randomly selected patients from that group for simulations, the two compared actual doctor performance and patient outcomes against sequential decision-making models, all using real patient data. They found great disparity in the cost per unit of outcome change when the artificial intelligence model’s cost of $189 was compared to the treatment-as-usual cost of $497.
“This was at the same time that the AI approach obtained a 30 to 35 percent increase in patient outcomes,” Bennett said. “And we determined that tweaking certain model parameters could enhance the outcome advantage to about 50 percent more improvement at about half the cost.”
I’m very glad they added this message at the end:
“Let humans do what they do well, and let machines do what they do well. In the end, we may maximize the potential of both.”
Being a medical futurist means I work on bringing disruptive technologies to medicine & healthcare; assisting medical professionals and students in using these in an efficient and secure way; and educating e-patients about how to become equal partners with their caregivers.
Based on what we see in other industries, this is going to be an exploding series of changes and while redesigning healthcare takes a lot of time and efforts, the best we can do is to prepare all stakeholders for what is coming next. That was the reason behind creating The Guide to the Future of Medicine white paper which you can download for free.
Please use the Twitter hashtag #MedicalFuture for giving feedback.
In the white paper, there is an infographic featuring the main trends that shape the future of medicine visualized from 3 perspectives:
- Which stage of the delivery of healthcare and the practice of medicine is affected by that (Prevent & Prepare; Data Input & Diagnostics; Therapy & Follow-up; and Outcomes & Consequences);
- Whether it affects patients or healthcare professionals;
- The practicability of it (already available – green boxes; in progress – orange boxes; and still needs time – red boxes)
Click here to see the infographic in the original size.
I hope you will find the guide useful in your work or in preparing your company and colleagues for the future of medicine.
I might be too optimistic about the advances of technologies in medicine, but I believe we live in a great era. Here is how third generation computers or cognitive computers can help cancer centers fight different forms of cancer.
FlowingData, one of my favourite blogs, just featured an entry focusing on how data will be organized in the future.
If there’s anything uniform across all the ideas, it’s ubiquity. In the future, computers won’t feel like computers, and data will not just flow alongside the physical world. Instead, data will intertwine with your day-to-day like threads in a fabric.
They come up with many examples, but I liked this one below the most. Imagine a totally transparent healthcare system in which you see all the relevant data about doctors, procedures, hospitals (success rates, costs), etc. You can really make a wise decision because you will know all the details and data you need.
Microsoft envisioned what 2019 would look like:
And here is a great talk from Minority Report science adviser and inventor John Underkoffler who presents g-speak – the real-life version of the film’s eye-popping, tai chi-meets-cyberspace computer interface.
Just a few articles focusing on the recent H1N1 outbreak.
I’ve come across a great new feature, Autocite, on the blog of Labmeeting.
If you’re reading a document with a big long bibliography, you can copy and paste the bibliography into Autocite and immediately have a list of links to abstracts and full text for all the articles. Or, if you have a webpage of your own with a list of your own past published works, you can automatically convert the plain text list into the HTML that you would use to link to the abstracts so that people who read your page can more easily find things out about your work.
Let’s give it a try. It works quite easily:
1. Copy and paste the references on your website
2. Click Autocite
3. Preview the linked version of your citations
4. Copy and paste the HTML of the linked citations
We’ve been organizing medical and scientific events in the virtual world of Second Life for years now. Just imagine how great it would be to do the same simulations and case presentations in 3D and with touch screen. Case presentations would become more realistic than ever.
An excerpt from the press release:
3Di, Inc. , a Tokyo-based company providing 3D Internet solutions and services (representative director and CEO Satoshi Koike), has released the world’s first commercially available OpenSim-based(*) viewer software “3Di OpenViewer”, which allows end users to view and interact with multi-user 3D virtual worlds using a web browser. The launch of the 3Di OpenViewer original software accompanies the simultaneous product release of “3Di OpenSim Enterprise Version 1.0″, the company’s server software for large-scale construction of 3D virtual worlds. 3Di OpenViewer and 3Di OpenSim Enterprise Version 1.0 are aimed at business use and are commercially available starting April 15, 2009.
Recently, Ves Dimov at Clinical Cases and Images has come up with a great post on How to deal with the information overload from blogs, RSS and Twitter so I thought I would share my thoughts with you about time-management lifehacks.
The main concept is to centralize the flow of information into one or two sites. For me, these are GMail and Google Reader. It means I can control anything I’m interested in by visiting these places online.
How to keep up with Twitter?
I follow more than 1000 users and have more than 1500 followers, so I receive thousands of tweets every day. Here are a few things that save me time and effort.
- I use Tweetdeck and created several groups on Tweetdeck that let me filter useful information (e.g. Health 2.0, genetics, bloggers groups, etc.).
- I check Friendfeed Best of the day because it will filter the best discussions for me (though not all of my Twitter contacts are on Friendfeed).
- Microplaza automatically filters the most interesting discussions and links mentioned in my Twitter community. I get the updates through RSS so it’s quite easy to see what I miss when I’m not online.
How to follow the content you want to track?
- Google Alerts helps me track the content that is published about me, my blog or my service online.
- Twilerts and Tweetbeep do the same but via Twitter. Whenever a Twitterer mentions my name, blogs, favourite search terms, I will be notified via e-mail.
How to write posts fast on your blog?
I often use the Quickpress function on WordPress that lets me write a post from the admin dashboard in just seconds. I always have a huge backlog on Scienceroll so I created clearly defined directories in Firefox bookmarks and tag all the links I save there. It helps me organize the thousands of bookmarks I have and I always get a clear picture of what I should write about.
As I’m working on different computers, Foxmarks synchronizes my bookmarks automatically.
How to work on Wikipedia?
As an administrator, I have some duties, so I built a long watchlist to keep track of the changes in the entries I’m interested in. I also use Huggle to fight vandalism. With Huggle, reverting hundreds of vandalisms and notify vandals on their talk pages take only minutes and a few clicks.
How to use RSS?
I created categories based on priorities in Google Reader. I always know which category of feeds to check depending on how much time I have and whether I’m looking for blog topics or just interesting pieces of information.
I also receive the updates of my favourite Youtube channels, Pubmed search terms and Del.icio.us tags.
And you may also find the slideshow from Joshua Schwimmer interesting
If you have more tips on how to be productive online, please let me know.