Alphabet’s “x lab” posted a new blog post on Monday about project amber, which it has been working on for the past three years – and it is now open-source for other mental health research communities to learn from, and hope to build on. The project tried to identify a specific biomarker for depression – it didn’t do it (researchers now think that a single biomarker for depression and anxiety probably doesn’t exist), but lab x still hopes that its work with electroencephalogram (EEG) combined with machine learning to find a biomarker can help others. The researchers in the laboratory believe that depression, like other diseases, may have a clear biomarker to help medical staff diagnose depression more easily and objectively, and then hope to make it easier and more sustainable to treat depression. In terms of electroencephalogram, there are some precedents. Through the use of specially designed games in the laboratory, depressive patients seem to have consistently shown low EEG activity in order to “win” games effectively. < / P > < p > these studies seem to provide a path to potential biomarkers, but in order to make them really useful in real-world diagnostic environments, such as clinics or public health laboratories, the team at lab X has begun to improve the process of EEG collection and interpretation to make it easier for users and technicians to understand. < / P > < p > What’s most remarkable about this pursuit, and the post that alphabet posted on Monday detailing its research, is perhaps that it’s essentially a story of years of unsuccessful research – rather than the side you usually hear from big technology companies about projects that are unlikely to happen. < / P > < p > the X lab team has summed up what it has learned from years of research projects into three key points of its user research, each of which touches to some extent the shortcomings of purely objective biomarker detection methods (even if they have worked), especially when it comes to mental illness. The following is from the researchers: < / P > < p > 1. Mental health measurement is still an unsolved problem. Although there are many mental health surveys and scales, they are not widely used, especially in primary health care and counseling settings. The reasons range from burden (“I don’t have time to do this”) to doubt (“using the scale is no better than using my clinical judgment”) to a lack of trust (“I don’t think my client filled in this truthfully” and “I don’t want to disclose so much to my consultant”). These findings are consistent with the literature on measurement based mental health care. Any new measurement tool must overcome these obstacles and create clear value for people with life experience and clinicians. It is valuable to combine subjective and objective data. People with life experience and clinicians welcome the introduction of objective measures, but they cannot replace subjective assessment and asking about people’s experiences and feelings. The combination of subjective and objective indicators is considered particularly powerful. Objective indicators may validate subjective experience, or if there is a divergence between the two, it is an interesting insight in itself and provides a starting point for dialogue. There are many use cases of new measurement technology. Our initial hypothesis was that clinicians might use “brain wave tests” as diagnostic aids. However, the concept has received a lukewarm response. Mental health professionals, such as psychiatrists and clinical psychologists, are confident in their ability to diagnose through clinical interviews. Primary care physicians believe that an EEG test may be useful, but only if it is performed by a medical assistant before consultation with the patient, similar to a blood pressure test. Counselors and social workers do not make a diagnosis in their practice and therefore have nothing to do with them. Some people with life experience don’t like being labeled depression by machines. In contrast, there is a clear strong interest in using technology as a tool for continuous monitoring – capturing changes in mental health status over time – to understand what happened between visits. Many clinicians ask if they can send the EEG system home so that their patients and clients can repeat the tests themselves. They were also interested in the potential predictability of EEG, such as predicting who might become more depressed in the future. More research is needed to determine how best to deploy tools such as EEG in clinical and consulting settings, including how to combine with other measurement technologies such as digital phenotype. < / P > < p > laboratory x is opening up Amber’s hardware and software on GitHub, and has also released a “patent undertaking” to ensure that lab x will not bring any legal proceedings against users of amber’s EEG patents through the use of open source materials. It is not clear that if amber succeeds in finding a single biomarker of depression, it will be a result, but perhaps in the wider community’s hands, the team’s work in making EEG more accessible to professional testing institutions will lead to other interesting findings. Privacy Policy