A very interesting use of AI and digital twin technology may offer new insights into the infamous sinking of the Titanic.

A digital twin is an AI-driven computer simulation of a real-world object. Cognitive digital twinning or “CDT” technology has been used to create digital twins for the maintenance and diagnostics of everything from sophisticated jet fighters to human organs! Now, CDT may solve one of the most enduring mysteries of modern times, how did the Titanic actually sink?

The RMS Titanic sank to the bottom of the North Atlantic in 1912, but the fate of the ship and its passengers has fascinated the popular imagination for more than a century. Now we have the first full-size 3D digital scan of the complete wreckage—a “digital twin” that captures Titanic in unprecedented detail. Magellan Ltd, a deep-sea mapping company, and Atlantic Productions — which is making a documentary film about the project – conducted the scans over a six-week expedition last summer.

“Great explorers have been down to the Titanic… but actually, they went with really low-resolution cameras, and they could only speculate on what happened,” Atlantic Productions CEO Andrew Geffen told BBC News. “We now have every rivet of the Titanic, every detail, we can put it back together, so for the first time, we can actually see what happened and use real science to find out what happened.”

The ship split apart as it sank, with the bow and stern sections lying roughly one-third of a mile apart.

When the first divers made it to the wreck in 1985, the bow proved to be surprisingly intact, while the stern showed severe structural damage, likely flattened from the impact as it hit the ocean floor. There is a debris field spanning a 5-by-3-mile area, filled with furniture fragments, dinnerware, shoes and boots, and other personal items.

The joint mission by Magellan and Atlantic Productions deployed two submersibles nicknamed Romeo and Juliet to map every millimeter of the wreck, including the debris field spanning some three miles. The result was a whopping 16 terabytes of data, along with over 715,000 still images and 4K video footage. That raw data was then processed to create the 3D digital twin. The resolution is so good one can make out part of the serial number on one of the propellers.

“This model is the first one based on a pure data cloud that stitches all that imagery together with data points created by a digital scan, and with the help of a little artificial intelligence, we are seeing the first unbiased view of the wreck,” historian and Titanic expert Parks Stephenson told BBC News. “I believe this is a new phase for underwater forensic investigation and examination.”

Time is running out for what’s left of the famous shipwreck. Damage from previous salvage operations and deterioration due to iron-munching bacteria feasting on the ship’s hull will mean the wreck may soon be lost to history. These full-size 3D scans will preserve all the minute details for further study, giving researchers fresh insight into what really happened in April 1912—so people can finally have some definitive answers.

Other Applications Benefiting From Digital Twin Technology

In addition to such esoteric applications as providing amazing new insights into unsolved mysteries such as the sinking of the great ship Titanic, AI and digital twinning are revolutionizing many other industries, chief among them transportation. Just as CDT can create a digital duplicate of a ship like the Titanic, cognitive digital twin technologies are proving invaluable for the predictive maintenance of high-value military vehicles, airplanes, ships, and even passenger cars. Digital twin solutions like those developed by CarTwin extend the lifespan of cars and other vehicles by monitoring the vehicle’s “health” through its “digital twin.”

Basically, CarTwin can provide diagnostic and predictive models for all vehicle systems for which data is available (either directly or indirectly) onboard the vehicle.

Virtually any part of the vehicle that has sensors or that sensors can be developed for can be “twinned.” These data sets are then enhanced and augmented with design and manufacturing data that is already available by the OEM.

Primarily designed for use in fleets of vehicles, in combination with powerful AI models, CarTwin predicts breakdowns, monitors and improves performance, and measures and records real-time greenhouse gas emissions, which reduces expensive maintenance costs and avoids lost revenue associated with fleet downtime.

You can read much more about how AI and digital twin technology in my new book Quantum Care: A Deep Dive into AI for Health Delivery and Research. While the book’s primary focus is on healthcare delivery, it also takes a deep dive into digital twin tech, with an entire chapter devoted to CDT and the development and launch of CarTwin!

Rohit Mahajan is a Managing Partner at BigRio and the President and Co-Founder of Citadel Discovery. He has particular expertise in the development and design of innovative AI and machine learning solutions for clients in Healthcare, Financial Services, Retail, Automotive, Manufacturing, and other industry segments.

CarTwin has leveraged AI and Digital Twin technologies to create a digital, cloud-based clone of a physical vehicle designed to detect, prevent, predict, and optimize through AI and real-time analytics. If you would like to benefit from our expertise in these areas or if you have further questions on the content of this article, please do not hesitate to contact us.

A cognitive digital twin is an AI-driven representation of a real-world system. The objects being twinned can be mechanical such as vehicles, ships, and airplanes, or biological, such as organs and biological processes. It is the latter that is radically altering pharmaceutical research and may very well change the nature of clinical drug trials forever.

Traditional drug discovery is a long and complex process that can take years and millions and millions of dollars. The long and intensive process of bringing a new drug through all phases of clinical trials and to market starts with recruiting the right candidates and then proceeds through many steps and phases of testing the drugs vs. placebos in the candidates that have been recruited for the trial.

Finding those patients is one of the most time-consuming aspects of the process. But that is all changing thanks to AI and, specifically, cognitive digital twin (CDT) technologies.

Cognitive digital twins behave virtually the same way, statistically, as their physical counterparts, which makes them ideal for the powerful ability of AI to assimilate massive amounts of data and make remarkably accurate predictions.

Digital twins have been used quite effectively for monitoring health and providing preventive maintenance for some very highly complex systems, such as high-performance sports cars to military aircraft.

Now, they are changing the very landscape of drug discovery by modeling perhaps the most complex system of all organs and even complete human beings. For example, digital twins of patients are now being used to find ideal candidates in that all-important recruitment phase of a drug trial. The twin is created using AI algorithms and machine learning to create a “virtual patient” by leveraging data from previous clinical trials and from individual patient records. The model predicts how the patient’s health would progress during the course of the trial.

This kind of CDT technology is also being used to create “virtual patients” who are “stand-ins” for the control group – the ones getting a placebo – in the typical double-blind drug trial protocol. The digital twin patient predicts how that individual patient would react if they were given a placebo, essentially creating a simulated control group for a particular patient. Think of it as splitting yourself into two distinct exact copies of yourself, one given the actual drug and the other given the placebo as a control. This makes for an even more accurate control group than just splitting all those in the trial into two groups as in typical trials, because the control group is now exactly the same as the group getting the drug. The digital twin virtually eliminates any variance between the drug group and the placebo group that could be based on genetic, physical, and lifestyle differences between the two groups.

Furthermore, replacing or augmenting control groups with digital twins could help patient volunteers as well as researchers. Most people who join a trial do so, hoping to get a new drug that might help them when already-approved drugs have failed. But there’s a 50/50 chance they’ll be put into the control group and won’t get the experimental treatment. Replacing control groups with digital twins could mean more people have access to experimental drugs.

In Silico Research

And finally, another area where CDT technology is making a tremendous difference in drug discovery is in the emerging area of “in silico” research, where digital twinning is used to create so-called “organs on a chip.” Digital twins of the human heart, lungs, and other organs are already being used to hyper-accelerate drug discovery.

One of the promises of CDT is to make complete in silico drug trials from start to finish a reality. Early successes occurring now are paving the way to a time in the not-so-distant future where no humans, nor animals, not even a single living cell will be required for drug discovery — and yet the impact of any given therapeutic or treatment option on a targeted organ, system or even an individual cell can be perfectly charted.

Citadel and AI for Drug Discovery

AI and machine learning are having a tremendous impact on healthcare in America, from streamlining hospital operations, to improved diagnostics and more intuitive telemedicine applications. However, AI’s greatest impact will likely be in the way digital twins and other AI solutions are revolutionizing pharmaceutical research.

To that end, Citadel Discovery was launched in 2021 with the purpose of giving a kind of “open access” to the data and technology that will drive the future of pharma research streamlining and lowering the costs of drug discovery and biological research.

The costs of drug discovery continue to rise, with current estimates exceeding $2 Billion. Not to mention that bringing a drug successfully through all clinical trial phases takes, on average, 10-12 years in research and development. Artificial intelligence and machine learning in drug discovery hold the key to reducing these costs and timelines.

Rohit Mahajan is the President and Co-Founder of Citadel Discovery. He has a particular expertise in the development and design of innovative solutions for clients in Healthcare, Financial Services, Retail, Automotive, Manufacturing, and other industry segments.

Citadel Discovery is dedicated to leveraging AI and MI for the purpose of democratizing access to the data and technology that will drive the future of biological exploration, drug discovery, and health technologies. If you would like to benefit from our expertise in these areas or if you have further questions on the content of this article, please do not hesitate to contact us.