This might be a tough pill to swallow, but the future of medicine is all about ingestible sensors. Things like cameras to scope out your bowels and electronics that detect if you've taken your medicine (recently FDA-approved, by the way). Researchers at MIT have developed a frozen gizmo made of pig intestine that you drop down the hatch. As it thaws in your stomach, it unfolds. Using a magnetic field, a doctor could theoretically lead the device to something you've gone and swallowed but really shouldn't have--batteries aren't as tasty as they look--and hurry the offending object out of your system.

"Given an example of presence and absence of a specific concept, computers would use storage to memorize examples exactly as they appear from a shallow learning concept – classic memorization," Dreyer said. Humans adjust neural weighting to solve for current and future examples, so we don't have to see a future example to know what something is. If you show a computer a picture of a bunch of oranges and then show it an apple, the computer wouldn't know what the apple was because it hadn't seen it before. Humans exploit deep learning by classifying new objects, recognizing faces, and recognizing language, Dreyer said. We see examples every day of facial recognition technology (for example, used by Facebook and Twitter).

Identification of patients with overt cardiorespiratory insufficiency or at high risk of impending cardiorespiratory insufficiency is often difficult outside the venue of directly observed patients in highly staffed areas of the hospital, such as the operating room, intensive care unit (ICU) or emergency department. And even in these care locations, identification of cardiorespiratory insufficiency early or predicting its development beforehand is often challenging. The clinical literature has historically prized early recognition of cardiorespiratory insufficiency and its prompt correction as being valuable at minimizing patient morbidity and mortality while simultaneously reducing healthcare costs. Recent data support the statement that integrated monitoring systems that create derived fused parameters of stability or instability using machine learning algorithms, accurately identify cardiorespiratory insufficiency and can predict their occurrence. In this overview, we describe integrated monitoring systems based on established machine learning analysis using various established tools, including artificial neural networks, k?nearest neighbor, support vector machine, random forest classifier and others on routinely acquired non?invasive and invasive hemodynamic measures to identify cardiorespiratory insufficiency and display them in real?time with a high degree of precision.

The experimental Smart Tissue Autonomous Robot (STAR) recently sewed a piglet's gut together using a computer program and camera-based guidance, overseen by a team of doctors and computer scientists from the Children's National Health System in Washington DC and Johns Hopkins University. The procedure took 50 minutes, as opposed to 8 minutes when performed by a surgeon, but (unfortunately for doctors) resulted in more evenly spaced sutures and less leakage from the gut. And with iterative improvements, it's likely that the time difference can be shrunk. Meanwhile, FDA-approved robotic surgery on humans is making strides as well, though it requires a surgeon to operate the mechanical arm. The potential treatment paradigm, highlighted by The Economist this month, raises questions about whether patients will trust robots with their lives, and who is liable if something goes wrong. Another question robots pose: Are doctors in line for a string of layoffs?

The future of health care is wearable devices that transmit our vitals to our physicians. Instead of self-reported data, which is often inaccurate (no offense, but your memory just kind of sucks), doctors will have real numbers to form the basis for diagnoses and treatment plans. In the wake of Apple's CareKit launch, connected medical device maker Qardio is launching a platform to share health data from its hardware with your doctor. QardioArm is a medical-grade smart blood pressure monitor that can send data to your doctor. The company has two FDA-approved products for consumers: the smart blood pressure monitor QardioArm and wireless scale QardioBase.

Jeet Raut's mom was told she no longer had breast cancer. But it turned out to be a false diagnosis and she had to undergo further treatment. She's okay now, but that medical mistake could have cost her life and it gave Raut the idea to build a better way to catch medical abnormalities in the body. He and his co-founder Peter Wakahiu Njenga created Behold.ai to speed up the process of finding cancers and minimize human error. "The idea behind Behold.ai is to increase efficiency," Raut told TechCrunch.

The Smart Tissue Autonomous Robot (STAR) can autonomously perform 60 percent of bowel anastomosis on pig intestines. Robots are a growing presence in operating rooms throughout the U.S. as surgeons embrace the technology to help them remove damaged organs or cancerous tissue. These systems have improved greatly in recent years but still need hands-on surgeons to guide their instruments and make critical decisions. Turning a robot loose on its own to cut and sew delicate tissue inside a human body would be a massively complex undertaking requiring advanced imaging, sensor and artificial intelligence technologies--not to mention a lot more acceptance from the medical community and federal regulators. But those hurdles have not stopped scientists at Children's National Medical Center's (CNMC) Sheikh Zayed Institute from developing a robotic system that has successfully sutured and reconnected portions of pig intestine in a living animal with little or no human intervention, according to a report in the May 4 Science Translational Medicine. Soft tissue surgeries like this one, which is called intestinal anastomosis, are especially challenging for robotic systems because the tissue changes shape and moves around during the procedures.

In a small startup space just down the street from UC Berkeley's campus, robotics pioneer Homayoon Kazerooni is bragging about how no-frills his invention is. "We're trying to make the Honda," he says, "not the sportscar." Kazerooni is showing me his latest robotic exoskeleton that gives paraplegics and people with mobility problems the ability to stand up from their wheelchairs and walk again. He's been building such bionic systems for more than a decade, and back in 2005 he cofounded Ekso Bionics, the current market leader for exoskeletons. So it's no surprise that Kazerooni says the new device from his new company, SuitX, is the most advanced yet.

One of the most frustrating elements of the current healthcare environment is the administrative burden of prior authorizations for medications and procedures. It is a frustration for providers, for patients, and for payers. Is there any way to solve this dilemma? For physicians, an estimated 20 hours per week is spent in prior authorization activities, costing an average of 83,000 in excess annual overhead per physician. Is there an actual benefit for this effort? Most physicians say that payers (commercial, Medicare, Medicaid, and pharmacy benefit managers (PBMs)) use prior authorizations to keep costs down.

Artificial intelligence and concerns over the long term consequences has come up again in the news week in the form of a Scientific American blog musing over how artificial intelligence will evolve -- "Is AI Dangerous? It Depends…" There is a certain amount of hand wringing over AI and, to a lesser extent, its branches such as machine learning and natural language processing. It also drew attention to notables who have voiced concern over AI including Bill Gates, Stephen Hawking and Elon Musk. The concerns tend to emerge from worst case scenarios and assume that even though AI can be used for beneficial purposes, what if the technology is turned against us? But many people applying AI to make healthcare delivery more efficient and automated don't see it that way.