Pathological speech analysis has been of interest in the detection of certain diseases like depression and Alzheimer's disease and attracts much interest from researchers. However, previous pathological speech analysis models are commonly designed for a specific disease while overlooking the connection between diseases, which may constrain performance and lower training efficiency. Instead of fine-tuning deep models for different tasks, prompt tuning is a much more efficient training paradigm. We thus propose a unified pathological speech analysis system for as many as three diseases with the prompt tuning technique. This system uses prompt tuning to adjust only a small part of the parameters to detect different diseases from speeches of possible patients. Our system leverages a pre-trained spoken language model and demonstrates strong performance across multiple disorders while only fine-tuning a fraction of the parameters. This efficient training approach leads to faster convergence and improved F1 scores by allowing knowledge to be shared across tasks. Our experiments on Alzheimer's disease, Depression, and Parkinson's disease show competitive results, highlighting the effectiveness of our method in pathological speech analysis.

Multi-modal fusion is crucial in medical data research, enabling a comprehensive understanding of diseases and improving diagnostic performance by combining diverse modalities. However, multi-modal fusion faces challenges, including capturing interactions between modalities, addressing missing modalities, handling erroneous modal information, and ensuring interpretability. Many existing researchers tend to design different solutions for these problems, often overlooking the commonalities among them. This paper proposes a novel multi-modal fusion framework that achieves adaptive adjustment over the weights of each modality by introducing the Modal-Domain Attention (MDA). It aims to facilitate the fusion of multi-modal information while allowing for the inclusion of missing modalities or intrinsic noise, thereby enhancing the representation of multi-modal data. We provide visualizations of accuracy changes and MDA weights by observing the process of modal fusion, offering a comprehensive analysis of its interpretability. Extensive experiments on various gastrointestinal disease benchmarks, the proposed MDA maintains high accuracy even in the presence of missing modalities and intrinsic noise. One thing worth mentioning is that the visualization of MDA is highly consistent with the conclusions of existing clinical studies on the dependence of different diseases on various modalities. Code and dataset will be made available.

Thomas Fuchs, the Dean of Artificial Intelligence and Human Health at Mount Sinai in NYC, said AI will be needed to retain the standard of care in the U.S. Glioblastoma is one of the deadliest types of brain cancer, with the average patient living only eight months after diagnosis, according to the National Brain Tumor Society, a nonprofit. Two ambitious high school students -- Andrea Olsen, 18, from Oslo, Norway, and Zachary Harpaz, 16, from Fort Lauderdale, Florida -- are looking to change that. The teens partnered with Insilico Medicine, a Hong Kong-based medical technology company, to identify three new target genes linked to glioblastoma and aging. They used Insilico's artificial intelligence platform, PandaOmics, to make the discovery -- and now, they plan to continue researching ways to fight the disease with new drugs. Their findings about target genes were published on April 26 in Aging, a peer-reviewed biomedical academic journal.

AI shows tremendous promise in discovering new patterns buried in mountains of data. Yet, some data remains isolated across various silos for technical, ethical and commercial reasons. A promising new AI and machine learning technique called amalgamated learning might help overcome these silos to find new cures for diseases, prevent fraud and improve industrial equipment. It may also provide a way to construct digital twins from inconsistent forms of data. At the Imec Future Summits conference, Roel Wuyts detailed how amalgamated learning works and how it compares to related techniques like federated learning and homomorphic encryption in an exclusive interview with VentureBeat.

How, he asks, do we complete this pattern? Now a student might say that the next term is 12. When the teacher asks him why, he says, "I looked out the window and saw the number 12 bus go by." One thing you might say is that there's a metarule, a rule about rules, and the metarule is: The only valid rules are ones that don't involve anything specific about the classroom in which the question is asked. So then the student says, fine, the next number in the series is 5. And this time, when you ask him why, he says it's because it's the fifth term in the series.

In response to the coronavirus health crisis, USC researchers have made a hard pivot, adapting labs and lessons learned from treating other diseases to help check the virus and save lives. At their disposal are numerous technologies that give a human advantage, despite the fast-break spread of COVID-19 once it exited central China and spread across the globe. The disease has afflicted thousands of Californians and poses a serious risk to public health and the world economy. Tools such as supercomputers, software apps, virtual reality, big data and algorithms are now in play. They are using the tools to find ways to search and destroy coronavirus DNA, turn smartphones into personal protection devices and use people-friendly simulators to help cope with the crush of medical cases.

A group of Australian researchers have recently developed an AI-powered smartphone app that can diagnose respiratory disorders by "listening" to the user's cough. This technology was developed by researchers at Curtin University and The University of Queensland, Australia, whose findings were published June 6 in the journal Respiratory Research. The researchers created an algorithm that can analyze coughs for features that are unique to five different diseases. This technique is similar to speech recognition technologies in that the software examines the auditory cough for characteristics specific to these conditions. This is typically done by a physician during a clinical exam, with a stethoscope being used to listen to sound produced while breathing or coughing (auscultation). The downside to this is that the patient must be in the presence of a trained professional to have their respiration sounds analyzed.

Our breath contains a slew of information about our health in the form of molecules whose existence and concentration can serve as biomarkers for disease. Typically breath sensors focus on a single biomarker and therefore are limited in their scope and screening ability. A worldwide scientific collaboration headed by a team from Technion Israel Institute of Technology has developed a breath sensor capable of detecting many different molecules and correlated these biomarkers to 17 different diseases. The device consists of an array of specially prepared gold nanoparticle sensors and ones based on a random network of single-walled carbon nanotubes. While it is impressive on its own, what gave it special powers was to use it to collect breath samples from thousands of patients with different diseases and to use artificial intelligence software to find correlations in the data.

Scientists have developed experimental breath analyzers, but most of these devices only focused on a single type of disease, such as cancer. Researchers from the Israel Institute of Technology have created a device that can identify 17 different diseases, including lung cancer or Parkinson's disease. The researchers developed an array of nanoscale sensors to detect the components in breath samples from more than 1,400 patients who were either healthy or had one of 17 different diseases, such as kidney cancer, Parkinson's disease, pulmonary hypertension and other diseases. Each sample was then passed through the breathalyzer, which could detect the types of chemicals and in what quantities. As the researchers report in the journal ACS Nano, the data from the breathalyzer could detect if a person is suffering from diseases almost nine out of ten times.

Elucidating the genetic basis of human diseases is a central goal of genetics and molecular biology. While traditional linkage analysis and modern high-throughput techniques often provide long lists of tens or hundreds of disease gene candidates, the identification of disease genes among the candidates remains time-consuming and expensive. Efficient computational methods are therefore needed to prioritize genes within the list of candidates, by exploiting the wealth of information available about the genes in various databases. Here we propose ProDiGe, a novel algorithm for Prioritization of Disease Genes. ProDiGe implements a novel machine learning strategy based on learning from positive and unlabeled examples, which allows to integrate various sources of information about the genes, to share information about known disease genes across diseases, and to perform genome-wide searches for new disease genes. Experiments on real data show that ProDiGe outperforms state-of-the-art methods for the prioritization of genes in human diseases.