AI double-checks ventilator tube placemen, Injectable Cardiac Monitor Can Now Look for Signs of Fever, FDA clears Zebra Medical Vision…
May 1, 2022
Backpropagation Basics
May 1, 2022Mental Health
AI to deliver best mental health treatments
The Black Dog Institute and The University of New South Wales, also known as UNSW Sydney, have implemented AI techniques to determine which psychological treatments work best in various groups. UNSW data proposes that mental health problems, including depression and anxiety, are the largest health disorders globally, affecting around 792 million people. The project also addresses the immense strain on young people’s mental health during university. AI-powered adaptive trial strategies will be used to decide which of a series of therapeutic interventions led to the best results in specific sub-groups.(1)
AI to deliver best mental health treatments
The Black Dog Institute and The University of New South Wales, also known as UNSW Sydney, have implemented AI techniques to determine which psychological treatments work best in various groups. UNSW data proposes that mental health problems, including depression and anxiety, are the largest health disorders globally, affecting around 792 million people.
The project also addresses the immense strain on young people’s mental health during university. AI-powered adaptive trial strategies will be used to decide which of a series of therapeutic interventions led to the best results in specific sub-groups.(1)
Microsoft Pilots Voice AI-Based Senior Mental Healthcare Program in South Korea
Microsoft created a mental healthcare assistance program for older people utilizing artificial intelligence, voice assistants, and wearable tech in South Korea. Powered by Microsoft’s Azure Kinect, the program comprises a sensor kit connected to artificial intelligence. Kinect combines a high-end camera and microphone with other sensors to detect human movement. Smart speakers will allow participants to interact directly with the AI by voice or typing on a keyboard. Azure Kinect, equipped with one camera, a 360-degree microphone, and sensors, can precisely detect human motions and collect data. AI speakers will provide verbal guides to alleviate mental illnesses such as geriatric depression. When information is analyzed, it will be managed via a simple dashboard interface that allows healthcare workers to provide tailored advice or services.(2)
Microsoft Pilots Voice AI-Based Senior Mental Healthcare Program in South Korea
Microsoft created a mental healthcare assistance program for older people utilizing artificial intelligence, voice assistants, and wearable tech in South Korea. Powered by Microsoft’s Azure Kinect, the program comprises a sensor kit connected to artificial intelligence. Kinect combines a high-end camera and microphone with other sensors to detect human movement. Smart speakers will allow participants to interact directly with the AI by voice or typing on a keyboard.
Azure Kinect, equipped with one camera, a 360-degree microphone, and sensors, can precisely detect human motions and collect data. AI speakers will provide verbal guides to alleviate mental illnesses such as geriatric depression. When information is analyzed, it will be managed via a simple dashboard interface that allows healthcare workers to provide tailored advice or services.(2)
A new generation of mental health drugs designed with artificial intelligence
Drug therapy for psychiatric illness has been stagnant with no modification in the last decade, with patients often requiring multiple medications to achieve disease control. Entheogenix Biosciences is a new project created by Cyclica, an AI drug discovery company, collaborating with Biotech ATAI Life Sciences, a German biotech enterprise.
The project intends to design and develop the next generation of mental health treatment drugs for depression, bipolar disorder, and schizophrenia inspired by previously developed psychoactive compounds. The new drugs are expected to be more effective, with fewer side effects and fewer administration issues.
The drug, known as BXCL501, comes from BioXcel, one of the slates of biotechs that holds promise of using artificial intelligence and other advanced computational techniques to speed up the sluggish pace of drug development. The new drug reduced patients’ “excitement” scores on the Positive and Negative Syndrome Scale for schizophrenia and bipolar disorder in phase III. (3)
A new generation of mental health drugs designed with artificial intelligence
Drug therapy for psychiatric illness has been stagnant with no modification in the last decade, with patients often requiring multiple medications to achieve disease control. Entheogenix Biosciences is a new project created by Cyclica, an AI drug discovery company, collaborating with Biotech ATAI Life Sciences, a German biotech enterprise. The project intends to design and develop the next generation of mental health treatment drugs for depression, bipolar disorder, and schizophrenia inspired by previously developed psychoactive compounds. The new drugs are expected to be more effective, with fewer side effects and fewer administration issues.
The drug, known as BXCL501, comes from BioXcel, one of the slates of biotechs that holds promise of using artificial intelligence and other advanced computational techniques to speed up the sluggish pace of drug development. The new drug reduced patients’ “excitement” scores on the Positive and Negative Syndrome Scale for schizophrenia and bipolar disorder in phase III. (3)
AI in psychiatry: detecting mental illness with artificial intelligence
A team of investigators from the University of Colorado Boulder, a public research university in Boulder, Colorado, is working to spread machine-learning AI in psychiatry with a speech-based mobile app. Studies suggest that the app can outperform human assessment to categorize a patient’s mental health status. The new portable app asks patients a 10-minute series of questions over their phones. They’re asked about their emotional state, asked to tell a short story, listen to a story and repeat it, and given a series of touch-and-swipe motor skills tests.
The team requested clinicians to listen to and assess speech samples of 300 participants, half with intense psychiatric issues and half healthy volunteers. The team developed an AI system that sets the speech samples, compares them to earlier models by the same patient and the overall population, and then rates the patient’s mental state.(4)
AI in psychiatry: detecting mental illness with artificial intelligence
A team of investigators from the University of Colorado Boulder, a public research university in Boulder, Colorado, is working to spread machine-learning AI in psychiatry with a speech-based mobile app. Studies suggest that the app can outperform human assessment to categorize a patient’s mental health status. The new portable app asks patients a 10-minute series of questions over their phones. They’re asked about their emotional state, asked to tell a short story, listen to a story and repeat it, and given a series of touch-and-swipe motor skills tests. The team requested clinicians to listen to and assess speech samples of 300 participants, half with intense psychiatric issues and half healthy volunteers. The team developed an AI system that sets the speech samples, compares them to earlier models by the same patient and the overall population, and then rates the patient’s mental state.(4)
Potential of voice in serving as a deep phenotype for Parkinson’s Disease
Detection of Parkinson’s Disease (PD) symptoms typically requires an exam by a movement disorder specialist and can often be hard to assess, primarily due to inconsistent findings. A digital vocal biomarker could potentially supplement the existing manual exam by detecting and quantifying symptoms to guide treatment.Specifically, vocal biomarkers of PD are a potentially effective method of assessing symptom severity, which is the focus of the current research. The researchers analyzed a database of PD patients and non-PD subjects containing voice recordings used to extract paralinguistic features, which served as inputs to machine learning models to predict PD severity.(5)
Potential of voice in serving as a deep phenotype for Parkinson’s Disease
Detection of Parkinson’s Disease (PD) symptoms typically requires an exam by a movement disorder specialist and can often be hard to assess, primarily due to inconsistent findings. A digital vocal biomarker could potentially supplement the existing manual exam by detecting and quantifying symptoms to guide treatment.
Specifically, vocal biomarkers of PD are a potentially effective method of assessing symptom severity, which is the focus of the current research. The researchers analyzed a database of PD patients and non-PD subjects containing voice recordings used to extract paralinguistic features, which served as inputs to machine learning models to predict PD severity.(5)
Facebook language predicts depression in medical records
Depression, the most prevalent mental illness, is still underdiagnosed and undertreated, emphasizing the need to increase effective screening methods. Researchers from the University of Pennsylvania analyzed language from Facebook posts of consenting individuals to predict depression as recorded in electronic medical records. They accessed the history of Facebook statuses posted by 683 patients visiting a large urban educational emergency department, 114 of whom had a diagnosis of depression in their medical records. Using only the vocabulary preceding their first documentation of a diagnosis of depression, the researchers identified depressed patients. Their method matches the accuracy of screening surveys when compared with medical records. Restricting Facebook data to only the six months immediately preceding the first documented diagnosis of depression yielded a higher prediction accuracy for those users who had sufficient Facebook data.(6)
Healthcare Looks to AI-Powered Chatbots to Ease COVID-19 Anxiety
Institutions are exploring the use of AI-powered chatbots to support people during COVID-19, resulting in enhanced patient experiences and better outcomes. Researchers from the Indiana University Kelley School of Business directed an online investigation with participants who viewed a COVID-19 screening session between a chatbot and a user with COVID-19 manifestations.
The team studied whether the chatbots were seen as persuasive, provided satisfying information, and were likely to be followed. The outcomes showed a slight negative bias against chatbots’ ability. However, when the perceived ability is the same, participants reported that they viewed chatbots more positively than human agents. At the University of California Los Angeles, a public land-grant research university, and Mattel Children’s Hospital, leaders are also investigating using AI-driven chatbots to support patients during the pandemic. The association uses a robot named Robin to ease pediatric patients’ loneliness while physically isolated in the hospital. Robin is powered by emotional learning technology, allowing the tool to engage realistically with children. (7)
Healthcare Looks to AI-Powered Chatbots to Ease COVID-19 Anxiety
Institutions are exploring the use of AI-powered chatbots to support people during COVID-19, resulting in enhanced patient experiences and better outcomes. Researchers from the Indiana University Kelley School of Business directed an online investigation with participants who viewed a COVID-19 screening session between a chatbot and a user with COVID-19 manifestations. The team studied whether the chatbots were seen as persuasive, provided satisfying information, and were likely to be followed. The outcomes showed a slight negative bias against chatbots’ ability. However, when the perceived ability is the same, participants reported that they viewed chatbots more positively than human agents.
At the University of California Los Angeles, a public land-grant research university, and Mattel Children’s Hospital, leaders are also investigating using AI-driven chatbots to support patients during the pandemic. The association uses a robot named Robin to ease pediatric patients’ loneliness while physically isolated in the hospital. Robin is powered by emotional learning technology, allowing the tool to engage realistically with children. (7)
The therapists using AI to make therapy better
Investigators have tried to study verbal therapies for years to unlock the secrets of why some therapists get more valuable outcomes than others. It can be as much art as science to blend competent therapists’ experience and gut instinct. It has been virtually impossible to quantify what works best and why clearly.
Nonetheless, AI is giving us some hope. Natural Language processing, the class of machine learning that carries out automated translation, can quickly analyze extensive amounts of language. A US-based company called Lyssn is developing technology to pursue this endeavor.
Lyssn was cofounded by Zac Imel and David Atkins (current CEO), who researches psychology and machine learning at the University of Washington. The AI models were developed from annotations from hundreds of transcripts, accentuating the role therapists’ and customers’ words play at any point in the session. The technology works resembling a sentiment-analysis algorithm that can tell whether film reviews are favorable or not or a translation tool that learns to map between languages. In this scenario, the AI translates from natural language into various bar codes or fingerprints of a therapy session that reveals the role of different utterances.(8)
The therapists using AI to make therapy better
Investigators have tried to study verbal therapies for years to unlock the secrets of why some therapists get more valuable outcomes than others. It can be as much art as science to blend competent therapists’ experience and gut instinct. It has been virtually impossible to quantify what works best and why clearly. Nonetheless, AI is giving us some hope. Natural Language processing, the class of machine learning that carries out automated translation, can quickly analyze extensive amounts of language. A US-based company called Lyssn is developing technology to pursue this endeavor.
Lyssn was cofounded by Zac Imel and David Atkins (current CEO), who researches psychology and machine learning at the University of Washington. The AI models were developed from annotations from hundreds of transcripts, accentuating the role therapists’ and customers’ words play at any point in the session. The technology works resembling a sentiment-analysis algorithm that can tell whether film reviews are favorable or not or a translation tool that learns to map between languages. In this scenario, the AI translates from natural language into various bar codes or fingerprints of a therapy session that reveals the role of different utterances.(8)
References