Predicting Alzheimer’s 10 years in advance is now a scientific reality. The challenge now is to prevent healthcare from collapsing

Alzheimer’s is a devastating disease that is undoubtedly a true ghost, since it only It becomes visible when the damage is already irreparable and that, despite trying to stop it, it is becoming difficult to control it. And historically, the medical diagnosis comes when memory begins to fail, but by then the brain has been suffering in silence for years, even decades. Now science focuses on the need for early diagnosis so that treatments can work. A new analysis. One of the ways to detect this disease before it begins to show the classic symptoms such as memory loss is through a blood test. This is the milestone that has been collected in The Lancet magazine recently thanks to research from the University of California, and that could generate a large population screening that is not free of controversy. What they did. The researchers followed 1,350 people aged between 56 and 69, without any type of dementia, for more than 35 years. And here the key was to look for specific proteins circulating in the blood that increased in the earliest phases of Alzheimer’s, as occurs with others marked in other diseases such as PSA in prostate cancer. And they found two biomarkers. The first of them is Aβ42/40, which is an early indicator that warns of the accumulation of hateful beta-amyloid plaques in the brain. But they also found the protein p-tau217, which is considered today the most precise marker for the pathology. The results. The 6% of participants who tested positive for these biomarkers showed a four-fold increased risk of developing verbal memory problems and a decline in their cognitive speed a decade later. But science has been trying to refine this tool for years, looking for markers such as GFAP, which rises about ten years before symptoms appear. See the invisible. The blood test does not walk alone in this diagnostic revolution, since on the same day, The Lancet published a second study based on nearly 800 participants from the US and Canada that tests a new and sophisticated neuroimaging technology: the MK6240 PET plotter. Until now, visualizing the tau protein, which is one of those responsible for Alzheimer’s by accumulating in neurons, was a great challenge. But this new tracer promises to be much more sensitive, detecting twice as many positive cases in healthy people with amyloid accumulation compared to the standard used today. You have to wait. Before throwing the bells in the air, it should be noted that experts point out that this test not ready to be used as general population screening. The reason lies in mathematics, since the prevalence of asymptomatic Alzheimer’s in healthy middle-aged people remains low in absolute terms, so applying this test to everyone would generate a very high volume of false positives. That is, an increase in this protein that is not actually related to early Alzheimer’s. But logically, the fear, anxiety and the resulting cascade of confirmatory tests would collapse the health services that are already stressed, and furthermore, the drugs we have, despite the fact that they stop the effects of the disease in its earliest phases, are not yet definitive. That is why we must remain on the right path, but there is still a long way to go to get this disease under control. Images | Robina Weermeijer Testalize.me In Xataka | Alzheimer’s no longer seems irreversible: science allows brains with advanced damage to recover for the first time in animals

Predicting a drought six months in advance was a utopia. The UPV has achieved this with a system that uses AI

In recent years drought episodes have intensified in some regions and fear of a global drought flies over the environment. In this scenario, a team of researchers from the Polytechnic University of Valencia have created a system that can predict whether there will be a drought six months in advance. The system. The work has been carried out by the team from the Institute of Water and Environmental Engineering (IIAMA) of the UPV and has been published in the journal Earth Systems and Environment. The method integrates predictions from four reference climate systems (ECMWF-SEAS5, Météo-France System8, DWD-GCF2.1 and CMCC-SPSv3.5) and are processed using artificial intelligence techniques. From this data, the team calculated two of the most important international drought indices (the Standardized Precipitation Index and the Standardized Precipitation-Evapotranspiration Index), using data windows of 6, 12, 18 and 24 months. The method has been applied in the Júcar River basin, which usually goes through stages of recurrent and quite intense droughts. Why is it important. The novelty of this system is that it is not limited to using a single climate model or index, but rather it merges three pieces that are usually used separately and adds AI processing to correct biases and adapt the models to a regional scale. This allows the prediction to be more reliable since it does not depend on a single model. Furthermore, all of this has been integrated into an operational web toolintended to be used in water management and not only as an academic exercise. Results. The system is correct with a reliability of 90% when the prediction is made for that same month. If they want to obtain predictions three months in advance, the reliability is 60%, while for longer periods (12, 18 and 24 months) they do not give a percentage, but they affirm that the model is still useful for predicting what will happen up to six months in advance. Héctor Macián, co-author of the study, states that “The results confirm that the system is especially effective in reinforcing early warning of droughts, a fundamental aspect to anticipate management measures, reduce socioeconomic impacts and increase resilience to climate change.” Action window. As we said, the methodology has been developed in the Júcar river basin, which is a semi-arid area with long, dry and very hot summers, although researchers highlight that it is transferable to other drought-prone areas. Being able to foresee these episodes with up to six months of margin opens a window to implement the drought management plans much more in advance and thus be able to mitigate the effects. Image | UPV In Xataka | The remains of an ancient Mayan city leave us lessons for the future: an amazing system against drought

Predicting dementia seven years in advance seemed impossible. An AI with Spanish participation has just achieved it

The diagnosis of the neurodegenerative diseases You face a problem at the time the diagnosis is made, since in many cases it is diagnosed when the symptoms are already evident and this makes the brain damage irreversible. But… What if we could peer into the future of the brain years before the disease shows its face? This is precisely what a Spanish team has done with a new biomarker. The study. The future of medicine involves making increasingly earlier diagnoses so that the success of treatments is much greater, and now in a recent published article in Science Report The door opens for this to be a reality in dementia. To get here, what the researchers propose, where have you participated Rubén Armañanzas, from the DATAI Institute of the University of Navarra, is the use of a test such as the electroencephalogram together with artificial intelligence to develop a biomarker capable of predicting the risk of dementia with up to seven years in advance. Your methodology. To understand the magnitude of this advance, we must look at the population on which the study was carried out, which are people with subjective cognitive impairment. These are patients who go to the doctor because they notice that their memory is failing, but when they undergo standard cognitive tests, the results are completely normal, so they cannot be given a clear diagnosis even though it seems that something is not right. Until now, medicine found a blind spot in this phase as there was no way to know if these ‘complaints’ in memory were the prelude to Alzheimer’s or simply confusion. But now, the study with 88 older adults with this situation has shown that the brain emits alarm signals long before psychological tests detected them. You just had to know how to ‘read’ them. A new method. Here the research has unified different metrics to be able to read these warning signs. The first thing of all is to use an electroencephalogram to measure brain activity, which is a cheap, quick and non-invasive test. From here, the BrainScope technology platform analyzes this data by looking for 14 specific features related to neuronal connectivity and brain wave behavior. Once these characteristics are ‘found’, an AI algorithm comes in that processes the patterns and determines whether the patient analyzed can progress towards mild cognitive impairment or dementia such as Alzheimer’s. And the results are spectacular, since it has demonstrated outstanding precision when separating patients who develop the disease from those who do not. The future. The great value of this biomarker is not only technological, but also clinical, since the most reliable current tests to predict pathologies such as Alzheimer’s require painful lumbar punctures or scans that are not cheap. A system based on EEG and AI could be easily integrated into primary care clinical protocols or routine neurological consultations as it does not have a very high cost and, above all, is not invasive. The important thing here is to detect neurodegeneration in the earliest phases in order to gain golden time so that new drugs can act at the beginning of the disease and gain years of quality of life. Images | Robina Weermeijer In Xataka | We have a new “theory of everything” to understand Alzheimer’s. Its key is in some small granules

We needed more than ever a way of predicting better storms and hurricanes. AI has solved the problem

Among the areas in which Google Deepmind works, Meteorological prediction It is one of the most precision is obtaining thanks to the refinement of artificial intelligence tools designed for it. And the company has just demonstrated that AI can overcome traditional methods in hurricane prediction. And is that your model Weather Lab managed to forecast more accurately The trajectory and intensity of Hurricane Erinwhich went from tropical storm to Category 5 in less than 24 hours A few days ago. The first real exam. Until now, the meteorological models were a promise. Hurricane Erin became the first real -time fire test for the Google system. During the first three critical prediction, the artificial intelligence model exceeded the official forecast so much of the National Center for American Hurricanes such as several traditional physical models, including the most reliable Europeans and American. How it works. Traditional models are based on complex physical equations that recreate current atmospheric conditions: humidity, pressure, temperature. Google’s approach It is radically different. Its AI has been trained with a massive data set that includes historical weather information of the entire land and a specialized database with details of almost 5,000 cyclones observed during the last 45 years. “They match these long historical data with details about how hurricanes behave and statistically combine them to see patterns that the human eye could not detect,” Explain James Franklin, former head of the Hurricane Specialists Unit of the National Hurricane Center. Why does it matter so much. The precise prediction of hurricanes is vital to know what type of measures are needed to protect themselves from them in case of emergencies. The three to five forecast days are crucial to make decisions about evacuations and preparation measures. In Google’s internal tests With storms of 2023 and 2024, its model managed to predict the final location of the cyclones with about 140 kilometers more precision than the European model (ECMWF), considered the most exact available. Exceptional performance. Franklin stands out The performance of the Google system: “It really surpassed the other guides in terms of intensity. It captured the general form of the change of the life cycle almost exactly. practically without error.” The model not only succeeded in the trajectory, but predicted with surprising precision how Erin’s intensity would evolve throughout his life cycle. Still in development. Despite success, the Google model is not ready for public use. Weather Lab includes a warning that recommends trusting the official forecasts of the National Hurricane Center. However, Franklin It is optimistic About the future: “For next year, you will receive a very serious look and will really play a role in the forecasts that leave the Hurricane Center.” Cover image | Brian McGowan In Xataka | It is no longer necessary to pay to transform our photos into what we want. The latest Google offers it for free for everyone

Log In

Forgot password?

Forgot password?

Enter your account data and we will send you a link to reset your password.

Your password reset link appears to be invalid or expired.

Log in

Privacy Policy

Add to Collection

No Collections

Here you'll find all collections you've created before.