Once a week.
Subscribe to our weekly newsletter.
Collective intelligence out-diagnoses even professionals
The Human Diagnosis Project project is building the world's "open medical intelligence" system.
- The Human Diagnosis Project can develop medical diagnoses with startling accuracy.
- The platform combines the knowledge of medical professionals and artifical intelligence.
- The goal of the project is to provide open, readily available high-level guidance and training to health care professionals across the globe.
The world-class Mayo Clinic is often the place patients go for a second opinion on a medical diagnosis. It's a good thing they do. According to a report issued by the clinic in 2017, 88 percent of them return home with either a completely different diagnosis or a significantly altered one. Only 12 percent receive confirmation of their doctors' original conclusions.
It's hard to overstate the life-and-death importance of medical misdiagnoses, and with all the artificial intelligence and data collection tools out there, you'd think there might be a way to improve on these statistics. This said, the goal of the Human Diagnosis project, or "Human Dx," (a triple pun their site explains) is to create the world's open medical intelligence system, a "collective intelligence" that can produce vastly improved diagnostic accuracy.
In early March, JAMA published the results of an experiment conducted by Human Dx in cooperation with Harvard, and the results were impressive. Where 54 individual human medical specialists correctly diagnosed 156 test cases 66.3 percent of the time, collective intelligence achieved an 85.5 percent accuracy rate. Nine medical professionals contributed to the collective intelligence conclusions.
Human Dx founder Jayanth Komarneni tells Big Think that, "We can get numbers in the 97th, 98th [percentile], and even — if we have sufficiently large numbers of participants — we can get to super intelligent results. That means that it outperforms 100 percent of individual participants."
About Human Dx
The Human Dx project is a partnership between the social, public, and private sectors — in the U.S., it's a 501 (c)(3) not-for-profit/public-benefit corporation. According to Komarneni, Human Dx's business model is as free of cost to users as possible while still generating enough income to be self-sustaining. There are now nearly 20,000 medical professionals in almost 80 countries contributing. Among Human Dx's partners are, as the company states: the American Medical Association, the Association of American Medical Colleges, American Board of Medical Specialties, and the American Board of Internal Medicine. They're also working in collaboration with researchers at Harvard, Johns Hopkins., University of California San Francisco, Berkeley, and MIT.
While diagnoses produced by Human Dx do bring together the opinions of multiple medical professionals, it's far from a simple voting system. It incorporates its own massive data set, machine learning, and artificial intelligence in addition to the input from medical professionals to develop its diagnoses. In designing their collective intelligence, says Komarneni, Human Dx had to first re-think the idea of open intelligence itself.
"We believe that open intelligence is the third form of open knowledge," he explains. The first was open source-protocols such as those on which the internet is based, as well as operating systems such as Linux. These protocols enabled the second form, open content: Wikipedia, data libraries, and so on. Open intelligence combines the first two: "And when you think about A.I. in the context of software," says Komarneni, "it really is code which is smartly delivering content to you based on what you put into the system."
The importance of open intelligence is that without it being available at low cost or free, the cost of A.I. is going to be so prohibitive that it'll "exacerbate, as opposed to close, income, health, and other disparities in society," warns Komarneni. Nowhere will the ramification be more serious than in health care, since "there is nothing we care more about than the well-being of the people we love and ourselves."
How Human Dx collective intelligence works
Collective intelligence in the Human Dx project is not unlike a panel of participants, when are referred to as "agents." Some of these are medical professionals, but they may also include the outputs of other systems. For example, Komarneni mentions that it's entirely possible IBM's Watson could be one of these agents, or even a data set from the National Institutes of Health.
Of course, individual agents, even the human participants, express themselves in their own ways — is a lump "blue" or "blueberry-colored," for example — not to mention that contributions from some agents such as A.I. or datasets may be in the form of raw data. Before any meaningful synthesis of all these opinions can be performed, the first step is to convert them all into a common language of some sort. Human Dx's AI uses natural language processing, text prediction, and medical ontologies to derive these translations as the process's first step.
Human Dx establishes the capability, or CQ ("clinical quotient"), of each agent. To do this they rank agents' skills using test cases with known diagnoses, including "some of the most wickedly complex cases," says Komarneni. This allows Human Dx to determine how accurate agents' diagnoses can be expected to be, and how heavily they should be weighted against other participants' contributions in solving the current case.
A.I. joins the panel
At this point, the agents' inputs are synthesized to derive the most likely diagnosis, and this is combined in an A.I. model with all of the aggregated case data that's ever been captured by Human Dx — interactions in the "tens of millions" — including how "lots of other participants over many other cases have solved these cases." This A.I. model then joins the panel in arriving at the final diagnosis.
"And those [agents] combined," says Komarneni, "are how we can get to results that outperform the vast majority of individual participants."
The Harvard and Johns Hopkins studies
The Harvard study published in JAMA is the first public demonstration of the Human Dx system as a diagnostic tool. Working with an international cohort of medical students and professionals, the results were unquestionably amazing. There were 2069 users working 1572 cases — again, these were cases with known correct answers — from the Human Dx data set. About 60 percent of the participants were residents or fellows, 20 percent were attending physicians, and another 20 percent were medical students. In the study, as more medical professionals were added to the collective intelligence "panel," up to nine individuals, its accuracy consistently rose. Physicians who weren't specialists in their test-case areas achieved just a 62.5 percent accuracy score.
A previous study published in JAMA in January, and done in cooperation with Johns Hopkins, looked at Human Dx as an automatic platform for assessing the diagnostic abilities of health care professionals and students. That the scores of participants looking at 11,023 case simulations were consistent with their training level shows, in Komarneni words, "that we provided a valid, quantitative, scalable measure of medical reasoning." While he admits this doesn't sound like a big deal, it is, since it offers a far more accurate and scalable option to current multiple-choice assessments, which have been shown to correspond poorly to real-world diagnostic skills.
The future of health care and Human Dx
Komarneni says that there are basically only two ways to provide global universal health care, a pressing need since, "Almost half the world has no access to essential health services." One way, he says, would be to create a God-like A.I. system to provide health care to everyone, but, "We know that's not going to happen." God-like AI is just too hard, potentially requiring having to know everything about a patient from the tiniest details — say, the quantum behavior of electrons in mitochondria — to the huge, as in the kind of environment a patient lived in as a child.
In addition, Komarneni says, "In a world where data is locked up in many disparate silos, there isn't going to be a single collective agent. There's going to be a collective of many intelligent agents, both human and machine. The key is how do you integrate intelligence into larger buckets of intelligence than can solve the world's hardest problems."
This is where the Human Dx project, and the second approach, comes in. It actually has two components:
- The first is the expansion of existing medical professionals' diagnostic accuracy skills by providing them access to the Human Dx platform and its collective intelligence as a diagnostic tool.
- The second is helping to train new professionals, and Human Dx Training is already offering this on the Human Dx site.
For those concerned with privacy in a system such as Human Dx, Komarneni says it'll be a non-issue, explaining with an example. When two people converse, "We don't have access to the underlying data of each others' minds. We're agents that are interacting with each other to gain relevant and useful information from each other." Similarly, Human Dx's system of interacting agents doesn't require the exposure of patients' personal data. What's shared with Human Dx are the conclusions agents draw from that data, not the data itself. In the case of a dataset operating as an agent, the data would be anonymized.
Human Dx's interest in all this is developing a platform it hopes others find uses for. "We believe we're just building the enabling technology that many other stakeholders could use." As examples, Komarneni imagines, "The VA could implement their own version of this. Kaiser Permanente could implement their own version. Employers could contract with us or with their own insurers. You could even also have individual and group practices use Human Dx software to serve patients directly."
Human Dx is currently looking at ways to open up as much of the project for non-professionals as possible, and they've already made a start: On their home page is a diagnosis cloud — mouse over the various blue bubbles to see different conditions, and then click for further details. In addition, just beneath the cloud is a search field with which you can look up diseases and symptoms.
- A new day is coming in healthcare, where AI will help diagnose and ... ›
- How deep medicine will revolutionize health care - Big Think ›
Welcome to the world's newest motorsport: manned multicopter races that exceed speeds of 100 mph.
- Airspeeder is a company that aims to put on high-speed races featuring electric flying vehicles.
- The so-called Speeders are able to fly at speeds of up to 120 mph.
- The motorsport aims to help advance the electric vertical take-off and landing (eVTOL) sector, which could usher in the age of air taxis.
Airspeeder, the world's newest motorsport, is set to debut its first race in 2021.
What can you expect to see? Something like a mix between Red Bull's air racing and the pod-racing scenes from "Star Wars: The Phantom Menace" — manned electric cars flying close together in the desert at 120 mph, nose-diving off cliffs, and racing over lakes, all while hopefully avoiding collisions.
Airspeeder calls its vehicles flying electric cars, but it's probably easier to think of the wheelless multicopters as car-sized drones. Powered by electric batteries, the carbon-fiber craft use eight propellers to fly, and the tiltable motors are designed to allow pilots to navigate through the course's pylons at high speeds.
To prevent crashes, Airspeeder is working with the companies Acronis and Teknov8 to develop "high-speed collision avoidance" systems for its Speeders.
"As they compete, Speeders will utilise cutting-edge LiDAR and Machine Vision technology to ensure close but safe racing, with defined and digitally governed no-fly areas surrounding spectators and officials," Airspeeder wrote in a blog post.
Beyond motorsports, Airspeeder hopes to help advance the electric vertical take-off and landing (eVTOL) sector. This sector is where companies like Uber, Hyundai, and Airbus are working to develop air taxis, which could someday take the ridesharing industry into the skies. By 2040, the autonomous urban aircraft industry could be worth $1.5 trillion, according to a 2019 report from Morgan Stanley.
Still, many technical and regulatory hurdles remain. Matt Pearson, Airspeeder's founder and CEO, thinks the futuristic motorsport will help to not only speed up that process, but also pave the way for self-driving cars.
"Even with autonomous vehicles on the ground, it's a difficult thing to get right because computers have to make decisions very fast," Airspeeder's founder and CEO, Matt Pearson, told GQ." But in a racing environment, you have a pretty controlled course and you have the ability to make all the vehicles cooperate with each other. You have a whole load of vehicles talking to each other, so if there's an incident or a pilot slows down or there's a traffic jam on the course they're all aware of each other. This is something we think will revolutionise autonomous vehicles on the ground. It's technology that will make flying cars a reality in our cities in the future."
Airspeeder has yet to announce a date for the first race, but Pearson said he hopes to put on three races over the first season. The company is developing two courses: one in California's Mojave Desert, and one near Coober Pedy in South Australia.
The way you speak might reveal a lot about you, such as your willingness to engage in casual sex.
- A new study finds a deeper voice is associated with self-reported extraversion, dominance, and casual sex.
- It was the first study on the topic to objectively measure voice pitch.
- The authors suggest that hormones like testosterone might explain their findings.
We make snap decisions about other people based on information that we can gather quickly. One of the many ways that we do this is by making bold conclusions about other people's personalities based on their voices alone. Various studies demonstrate that people associate a deep voice with dominance, but those with higher pitched voices are perceived as nervous or neurotic. Popular culture seems to agree with and reinforce these stereotypes.
Are these perceptions accurate? Maybe. A new study by an international team of researchers with the goal of more accurately determining what our voices reveal about us has demonstrated that there is some connection between how we sound and who we think we are.
The voice-personality connection
Lead author Dr. Julia Stern of the University of Göttingen explained:
"Even if we just hear someone's voice without any visual clues — for instance on the phone — we know pretty soon whether we're talking to a man, a woman, a child, or an older person. We can pick up on whether the person sounds interested, friendly, sad, nervous, or whether they have an attractive voice. We also start to make assumptions about trust and dominance. The first step was to investigate whether voices are, indeed, related to people's personality."
The study included data from 2,000 people from four countries involved in eleven previous independent studies focused on other questions. Each of these studies involved some kind of self-reporting of personality traits and vocal recordings. The recordings were analyzed with Praat, software that determined the frequencies of the participants' speaking voices.
The study is the largest ever conducted on the topic and the first to use an objective measure of pitch rather than subjective rankings such as "high pitched" or "deep." Each participant's vocal pitch was then compared to the self-reported personality data they provided.
The findings associated self-reported levels of dominant tendencies, extroversion, and increased interest in and acceptance of sociosexuality (casual sex or sex outside of a relationship) with a lower pitched voice. This was true for men and women of any age. The findings were in line with the previous, less robust studies on the subject.
Other stereotypes, like if a higher pitched voice hints at neuroticism, openness to new experiences, or agreeableness, were impossible to determine with the data at hand.
Voice isn't everything
It should be remembered that the personality traits that this study associates with vocal pitch are self-reported, so there are some serious limitations. For instance, it is entirely possible that vocal pitch is associated with thinking you're extroverted when you actually aren't. Furthermore, all four countries in the study are WEIRD, so the findings probably cannot be universalized.
Additionally, there are plenty of examples of people for whom the voice-personality link doesn't apply. For example, Teddy Roosevelt, an extremely extroverted, dominating man, had a fairly high pitched voice.
The authors do speculate that there could be a connection between testosterone levels in men, their vocal pitch, and their perceived level of dominance that would be supported by previous studies. However, they have no hypothesis explaining why that same relationship exists for women.
The authors suggest that further studies in this area could focus on finding a possible physical connection between these traits and vocal pitch and to determine if they hold for traits which are not self-reported.
Who needs steroids when you have the placebo effect?
- A study suggests that the effectiveness of sports drinks may depend in part on their color.
- Runners who rinsed with a pink liquid ran better than those who consumed the same but colorless drink.
- Improvement in their performance is likely due to a placebo effect.
The "placebo effect" is real. It's the name for a strange phenomenon that most notably occurs during clinical trials. People who are given an inactive substance, like a sugar pill, often experience the same therapeutic benefit as those who are given actual medicine. It's not their imagination — it really happens. (Even better, recent research suggests that therapeutic benefits occur even when the person knows that they were given a placebo.)
Now, a new study from the University of Westminster (UOW) Centre for Nutraceuticals in London and published in Frontiers in Nutrition suggests that the placebo effect may explain yet another phenomenon: Athletic performance.
The research showed that treadmill runners who rinsed their mouths with a pink liquid increased their performance over runners who swished with exactly the same liquid but without the coloring. Why pink? The color is generally linked to sweetness, and the researchers wondered if that association would subconsciously trick the runners into an expectation of more carbohydrates and thus energy.
Author Sanjoy Deb explains:
"The influence of color on athletic performance has received interest previously, from its effect on a sportsperson's kit to its impact on testosterone and muscular power. Similarly, the role of color in gastronomy has received widespread interest, with research published on how visual cues or color can affect subsequent flavor perception when eating and drinking."
Running for science
Credit: Ryan De Hamer / Unsplash
For the study, the researchers recruited ten healthy adults — six men, four women. All were regular exercisers, with an average age of 30. The participants were told that they would be testing the relative benefits of two commercial sports drinks after watching a brief video explaining the value of such beverages. Previous research found that mid-exercise rinsing with such drinks can reduce the perceived intensity of exercise.
The drinks consisted of 0.12 grams of sucralose dissolved in 500 mL of plain water — an artificially sweetened rinse low in calories. The liquids contained no other additives common to sports drinks such as caffeine. The pink version had non-caloric coloring added but was otherwise identical.
After a 12-minute warmup phase of jogging followed by running, the athletes ran at a difficult pace for 30 minutes, rinsing with their drinks as they ran. Following a brief cool-down, they were interviewed to capture their impressions of the exercise session. (Each runner tested both drinks.)
The researchers found that when the volunteers used the pink rinse, they ran an average of 212 meters farther and 4.4 percent faster. They also enjoyed the exercise more.
Deb said, "The findings from our study combine the art of gastronomy with performance nutrition, as adding a pink colorant to an artificially sweetened solution not only enhanced the perception of sweetness, but also enhanced feelings of pleasure, self-selected running speed, and distance covered during a run."
The researchers also plan to dig deeper into the phenomenon by investigating the possibility that the pinkness of the beverage is somehow directly activating the brain's reward areas.