More stories

  • in

    What is the impact of predictive AI in the health care setting?

    Models built on machine learning in health care can be victims of their own success, according to researchers at the Icahn School of Medicine and the University of Michigan. Their study assessed the impact of implementing predictive models on the subsequent performance of those and other models. Their findings — that using the models to adjust how care is delivered can alter the baseline assumptions that the models were “trained” on, often for worse — were detailed in the October 9 online issue of Annals of Internal Medicine.
    “We wanted to explore what happens when a machine learning model is deployed in a hospital and allowed to influence physician decisions for the overall benefit of patients,” says first and corresponding author Akhil Vaid, M.D., Clinical Instructor of Data-Driven and Digital Medicine (D3M), part of the Department of Medicine at Icahn Mount Sinai. “For example, we sought to understand the broader consequences when a patient is spared from adverse outcomes like kidney damage or mortality. AI models possess the capacity to learn and establish correlations between incoming patient data and corresponding outcomes, but use of these models, by definition, can alter these relationships. Problems arise when these altered relationships are captured back into medical records.”
    The study simulated critical care scenarios at two major health care institutions, the Mount Sinai Health System in New York and Beth Israel Deaconess Medical Center in Boston, analyzing 130,000 critical care admissions. The researchers investigated three key scenarios:
    1. Model retraining after initial use
    Current practice suggests retraining models to address performance degradation over time. Retraining can improve performance initially by adapting to changing conditions, but the Mount Sinai study shows it can paradoxically lead to further degradation by disrupting the learned relationships between presentation and outcome.
    2. Creating a new model after one has already been in use
    Following a model’s predictions can save patients from adverse outcomes such as sepsis. However, death may follow sepsis, and the model effectively works to prevent both. Any new models developed in the future for prediction of death will now also be subject to upset relationships as before. Since we do not know the exact relationships between all possible outcomes, any data from patients with machine-learning influenced care may be inappropriate to use in training further models. More

  • in

    AI language models could help diagnose schizophrenia

    Scientists at the UCL Institute for Neurology have developed new tools, based on AI language models, that can characterise subtle signatures in the speech of patients diagnosed with schizophrenia.
    The research, published in PNAS, aims to understand how the automated analysis of language could help doctors and scientists diagnose and assess psychiatric conditions.
    Currently, psychiatric diagnosis is based almost entirely on talking with patients and those close to them, with only a minimal role for tests such as blood tests and brain scans.
    However, this lack of precision prevents a richer understanding of the causes of mental illness, and the monitoring of treatment.
    The researchers asked 26 participants with schizophrenia and 26 control participants to complete two verbal fluency tasks, where they were asked to name as many words as they could either belonging to the category “animals” or starting with the letter “p,” in five minutes.
    To analyse the answers given by participants, the team used an AI language model that had been trained on vast amounts of internet text to represent the meaning of words in a similar way to humans. They tested whether the words people spontaneously recalled could be predicted by the AI model, and whether this predictability was reduced in patients with schizophrenia.
    They found that the answers given by control participants were indeed more predictable by the AI model than those generated by people with schizophrenia, and that this difference was largest in patients with more severe symptoms. More

  • in

    Researchers create a neural network for genomics — one that explains how it achieves accurate predictions

    A team of New York University computer scientists has created a neural network that can explain how it reaches its predictions. The work reveals what accounts for the functionality of neural networks — the engines that drive artificial intelligence and machine learning — thereby illuminating a process that has largely been concealed from users.
    The breakthrough centers on a specific usage of neural networks that has become popular in recent years — tackling challenging biological questions. Among these are examinations of the intricacies of RNA splicing — the focal point of the study — which plays a role in transferring information from DNA to functional RNA and protein products.
    “Many neural networks are black boxes — these algorithms cannot explain how they work, raising concerns about their trustworthiness and stifling progress into understanding the underlying biological processes of genome encoding,” says Oded Regev, a computer science professor at NYU’s Courant Institute of Mathematical Sciences and the senior author of the paper, which appears in the Proceedings of the National Academy of Sciences. “By harnessing a new approach that improves both the quantity and the quality of the data for machine-learning training, we designed an interpretable neural network that can accurately predict complex outcomes and explain how it arrives at its predictions.”
    Regev and the paper’s other authors, Susan Liao, a faculty fellow at the Courant Institute, and Mukund Sudarshan, a Courant doctoral student at the time of the study, created a neural network based on what is already known about RNA splicing.
    Specifically, they developed a model — the data-driven equivalent of a high-powered microscope — that allows scientists to trace and quantify the RNA splicing process, from input sequence to output splicing prediction.
    “Using an ‘interpretable-by-design’ approach, we’ve developed a neural network model that provides insights into RNA splicing — a fundamental process in the transfer of genomic information,” notes Regev. “Our model revealed that a small, hairpin-like structure in RNA can decrease splicing.”
    The researchers confirmed the insights their model provides through a series of experiments. These results showed a match with the model’s discovery: Whenever the RNA molecule folded into a hairpin configuration, splicing was halted, and the moment the researchers disrupted this hairpin structure, splicing was restored.
    The research was supported by grants from the National Science Foundation (MCB-2226731), the Simons Foundation, the Life Sciences Research Foundation, an Additional Ventures Career Development Award, and a PhRMA Fellowship. More

  • in

    Twisted science: New quantum ruler to explore exotic matter

    A single-atom-thick sheet of carbon known as graphene has remarkable properties on its own, but things can get even more interesting when you stack up multiple sheets. When two or more overlying sheets of graphene are sightly misaligned — twisted at certain angles relative to each other — they take on a plethora of exotic identities.Depending on the twist angle, these materials, known as moiré quantum matter, can suddenly generate their own magnetic fields, become superconductors with zero electrical resistance, or conversely, turn into perfect insulators.
    Joseph A. Stroscio and his colleagues at the National Institute of Standards and Technology (NIST), along with an international team of collaborators, have developed a “quantum ruler” to measure and explore the strange properties of these twisted materials. The work may also lead to a new, miniaturized standard for electrical resistance that could calibrate electronic devices directly on the factory floor, eliminating the need to send them to an off-site standards laboratory.
    Collaborator Fereshte Ghahari, a physicist from George Mason University in Fairfax, Virginia, took two layers of graphene (known as bilayer graphene) of about 20 micrometers across and twisted them relative to another two layers to create a moiré quantum matter device. Ghahari made the device using the nanofabrication facility at NIST’s Center for Nanoscale Science and Technology. NIST researchers Marlou Slot and Yulia Maximenko then chilled this twisted material device to one-hundredth of a degree above absolute zero, reducing random motions of atoms and electrons and heightening the ability for electrons in the material to interact. After reaching ultralow temperatures, they examined how the energy levels of electrons in the layers of graphene changed when they varied the strength of a strong external magnetic field. Measuring and manipulating the energy levels of electrons is critical for designing and manufacturing semiconductor devices.
    To measure the energy levels, the team used a versatile scanning tunneling microscope that Stroscio designed and built at NIST. When the researchers applied a voltage to the graphene bilayers in the magnetic field, the microscope recorded the tiny current from the electrons that “tunneled” out from the material to the microscope probe tip.
    In a magnetic field, electrons move in circular paths. Ordinarily, the circular orbits of the electrons in solid materials have a special relationship with an applied magnetic field: The area enclosed by each circular orbit, multiplied by the applied field, can only take on a set of fixed, discrete values, due to the quantum nature of electrons. In order to maintain that fixed product, if the magnetic field is halved, then the area enclosed by an orbiting electron must double. The difference in energy between successive energy levels that follow this pattern can be used like tick marks on a ruler to measure the material’s electronic and magnetic properties. Any subtle deviation from this pattern would represent a new quantum ruler that can reflect the orbital magnetic properties of the particular quantum moiré material researchers are studying.
    In fact, when the NIST researchers varied the magnetic field applied to the moiré graphene bilayers, they found evidence of a new quantum ruler at play. The area enclosed by the circular orbit of electrons multiplied by the applied magnetic field no longer equaled a fixed value. Instead, the product of those two numbers had shifted by an amount dependent on the magnetization of the bilayers.
    This deviation translated into a set of different tick marks for the energy levels of the electrons. The findings promise to shed new light on how electrons confined to twisted sheets of graphene give rise to new magnetic properties. More

  • in

    AI-driven earthquake forecasting shows promise in trials

    A new attempt to predict earthquakes with the aid of artificial intelligence has raised hopes that the technology could one day be used to limit earthquakes’ impact on lives and economies. Developed by researchers at The University of Texas at Austin, the AI algorithm correctly predicted 70% of earthquakes a week before they happened during a seven-month trial in China.
    The AI was trained to detect statistical bumps in real-time seismic data that researchers had paired with previous earthquakes. The outcome was a weekly forecast in which the AI successfully predicted 14 earthquakes within about 200 miles of where it estimated they would happen and at almost exactly the calculated strength. It missed one earthquake and gave eight false warnings.
    It’s not yet known if the same approach will work at other locations, but the effort is a milestone in research for AI-driven earthquake forecasting.
    “Predicting earthquakes is the holy grail,” said Sergey Fomel, a professor in UT’s Bureau of Economic Geology and a member of the research team. “We’re not yet close to making predictions for anywhere in the world, but what we achieved tells us that what we thought was an impossible problem is solvable in principle.”
    The trial was part of an international competition held in China in which the UT-developed AI came first out of 600 other designs. UT’s entry was led by bureau seismologist and the AI’s lead developer, Yangkang Chen. Findings from the trial are published in the journal Bulletin of the Seismological Society of America.
    “You don’t see earthquakes coming,” said Alexandros Savvaidis, a senior research scientist who leads the bureau’s Texas Seismological Network Program (TexNet) — the state’s seismic network. “It’s a matter of milliseconds, and the only thing you can control is how prepared you are. Even with 70%, that’s a huge result and could help minimize economic and human losses and has the potential to dramatically improve earthquake preparedness worldwide.”
    The researchers said that their method had succeeded by following a relatively simple machine learning approach. The AI was given a set of statistical features based on the team’s knowledge of earthquake physics, then told to train itself on a five-year database of seismic recordings. More

  • in

    New open-source method to improve decoding of single-cell data

    Researchers at Memorial Sloan Kettering Cancer Center (MSK) have developed a new open-source computational method, dubbed Spectra, which improves the analysis of single-cell transcriptomic data.
    By guiding data analysis in a unique way, Spectra can offer new insights into the complex interplay between cells — like the interactions between cancer cells and immune cells, which are critical to improving immunotherapy treatments.
    The team’s approach and findings were recently published in Nature Biotechnology.
    Spectra, the researchers note, can cut through technical “noise” to identify functionally relevant gene expression programs, including those that are novel or highly specific to a particular biological context.
    The algorithm is well suited to study data from large patient cohorts and to suss out clinically meaningful patient characteristics, the MSK team writes in a research briefing that accompanies the study, adding that Spectra is ideal for identifying biomarkers and drug targets in the burgeoning field of immuno-oncology.
    Additionally, the MSK team has made Spectra freely available to researchers around the world.
    “I’m trained as a computer scientist,” says study senior author Dana Pe’er, PhD, who chairs the Computational and Systems Biology Program at MSK’s Sloan Kettering Institute. “Every single tool I build, I strive to make robust so it can be used in many contexts, not just one. I also try and make them as accessible as possible.”
    “I’m happy to discover new biology,” she continues. “And I’m just as happy — perhaps happier — to build a foundational tool that can be used by the wider community to make many biological discoveries.” More

  • in

    Comfort with a smaller carbon footprint

    As organizations work to reduce their energy consumption and associated carbon emissions, one area that remains to be optimized is indoor heating and cooling. In fact, HVAC — which stands for Heating, Ventilation, and Air Conditioning — represents, on average, about 40% of a building’s total energy use. Methods that conserve electricity while still providing a comfortable indoor environment for workers could make a significant difference in the fight against climate change.
    Now, researchers from Osaka University have demonstrated significant energy savings through the application of a new, AI-driven algorithm for controlling HVAC systems. This method does not require complex physics modelling, or even detailed previous knowledge about the building itself.
    During cold weather, it is sometimes challenging for conventional sensor-based systems to determine when the heating should be shut off. This is due to thermal interference from lighting, equipment, or even the heat produced by the workers themselves. This can lead to the HVAC being activated when it should not be, wasting energy.
    To overcome these obstacles, the researchers employed a control algorithm that worked to predict the thermodynamic response of the building based on data collected. This approach can be more effective than attempting to explicitly calculate the impact of the multitude of complex factors that might affect the temperature, such as insulation and heat generation. Thus, with enough information, ‘data driven’ approaches can often outperform even sophisticated models. Here, the HVAC control system was designed to ‘learn’ the symbolic relationships between the variables, including power consumption, based on a large dataset.
    The algorithm was able to save energy while still allowing the building occupants to work in comfort. “Our autonomous system showed significant energy savings, of 30% or more for office buildings, by leveraging the predictive power of machine learning to optimize the times the HVAC should operate.” says lead author Dafang Zhao. “Importantly, the rooms were comfortably warm despite it being winter.”
    The algorithm worked to minimize the total energy consumed, the difference between the actual and desired room temperature, and change in the rate of power output at peak demand. “Our system can be easily customized to prioritize energy conservation or temperature accuracy, depending on the needs of the situation,” adds senior author Ittetsu Taniguchi.
    To collectively achieve the goal of a carbon-neutral economy, it is highly likely that corporations will need to be at the vanguard of innovation. The researchers note that their approach may enjoy rapid adoption during times of rising energy costs, which makes their findings good for both the environment as well as company viability. More

  • in

    New technology could reduce lag, improve reliability of online gaming, meetings

    Whether you’re battling foes in a virtual arena or collaborating with colleagues across the globe, lag-induced disruptions can be a major hindrance to seamless communication and immersive experiences.
    That’s why researchers with the University of Central Florida’s College of Optics and Photonics (CREOL) and the University of California, Los Angeles, have developed new technology to make data transfer over optical fiber communication faster and more efficient.
    Their new development, a novel class of optical modulators, is detailed in a new study published recently in the journal Nature Communications. Modulators can be thought of as like a light switch that controls certain properties of data-carrying light in an optical communication system.
    “Carrying torrents of data between internet hubs and connecting servers, storage elements, and switches inside data centers, optical fiber communication is the backbone on which the digital world is built,” says Sasan Fathpour, the study’s co-author and CREOL professor. “The basic constituents of such links, the optical fiber, semiconductor laser, optical modulator and photoreceiver, all place limits on the bandwidth and the accuracy of data transmission.”
    Fathpour says particularly the dispersion of optical fibers, or signal distortion over long distances, and noise of semiconductor lasers, or unwanted signal interference, are two fundamental limitations of optical communication and signal processing systems that affect data transmission and reliability.
    He says their research has invented a unique class of optical modulators that simultaneously address both limitations by taking advantage of phase diversity, or varied timing of signals, and differential operations, or comparison of light signals.
    By doing so, the researchers have created an advanced “light switch” that not only controls data transmission but does so while comparing the amount and timing of data moving through the system to ensure accurate and efficient transmission. More