--This paper presents a multitask learning approach based on long-short-term memory (LSTM) networks for the joint prediction of arboviral outbreaks and case counts of dengue, chikungunya, and Zika in Recife, Brazil. Leveraging historical public health data from DataSUS (2017-2023), the proposed model concurrently performs binary classification (outbreak detection) and regression (case forecasting) tasks. A sliding window strategy was adopted to construct temporal features using varying input lengths (60, 90, and 120 days), with hyperparameter optimization carried out using Keras T uner . Model evaluation used time series cross-validation for robustness and a held-out test from 2023 for generalization assessment. The results show that longer windows improve dengue regression accuracy, while classification performance peaked at intermediate windows, suggesting an optimal trade-off between sequence length and generalization. The multitask architecture delivers competitive performance across diseases and tasks, demonstrating the feasibility and advantages of unified modeling strategies for scalable epidemic forecasting in data-limited public health scenarios.

By Karina Toledo Agência FAPESP – A platform that can diagnose several diseases with a high degree of precision using metabolic markers found in patients' blood has been developed by scientists at the University of Campinas (UNICAMP) in Brazil. The method combines mass spectrometry, which can identify tens of thousands of molecules present in blood serum, with an artificial intelligence algorithm capable of finding patterns associated with diseases of viral, bacterial, fungal and even genetic origin. The results have been published in Frontiers in Bioengineering and Biotechnology. "We used infection by Zika virus as a model to develop the platform and showed that in this case, diagnostic accuracy exceeded 95%. One of the main advantages is that the method doesn't lose sensitivity even if the virus mutates," said Melo's supervisor Rodrigo Ramos Catharino, principal investigator for the project.

Washington: Scientists have developed an artificial intelligence system that can accurately diagnose Zika virus and several other viral, bacterial and even genetic diseases from the patient's blood. The platform developed by scientists at the University of Campinas (UNICAMP) in Brazil, can identify tens of thousands of molecules present in blood serum, with an artificial intelligence algorithm. "We used infection by Zika virus as a model to develop the platform and showed that in this case, diagnostic accuracy exceeded 95%. One of the main advantages is that the method doesn't lose sensitivity even if the virus mutates," said Rodrigo Ramos Catharino, principal investigator at UNICAMP. Another strength of the platform, he added, is the capacity to identify positive cases of Zika even in blood serum analysed 30 days after the start of infection, when the acute phase of the disease is over.

A platform that can diagnose several diseases with a high degree of precision using metabolic markers found in patients' blood has been developed by scientists at the University of Campinas (UNICAMP) in Brazil. The method combines mass spectrometry, which can identify tens of thousands of molecules present in blood serum, with an artificial intelligence algorithm capable of finding patterns associated with diseases of viral, bacterial, fungal and even genetic origin. The results have been published in Frontiers in Bioengineering and Biotechnology. "We used infection by Zika virus as a model to develop the platform and showed that in this case, diagnostic accuracy exceeded 95%. One of the main advantages is that the method doesn't lose sensitivity even if the virus mutates," said Melo's supervisor Rodrigo Ramos Catharino, principal investigator for the project.

It could be the plot of a post-apocalyptic science fiction film – a tech firm is set to release 20 million bacteria-filled mosquitoes in the heart of California. But, the experts spearheading the effort say it could finally provide a way to take on the'deadliest animal in the world,' preventing mosquito-borne illnesses and ultimately saving lives. Unlike other modern approaches to eradicate'bad bugs,' the technique launched today by Verily's Debug project doesn't rely on genetic engineering; instead, it uses a naturally occurring bacteria that causes them to produce dud eggs. A tech firm is set to release 20 million bacteria-filled mosquitos in the heart of California. The technique launched today by Verily's Debug project uses a naturally occurring bacteria that causes them to produce dud eggs Smart traps - Roughly the size of large birdhouses, these smart traps use robotics, infrared sensors, machine learning and cloud computing to help health officials keep tabs on potential disease carriers.

Verily partnered with MosquitoMate, a Kentucky-based sterile mosquito breeder, and Fresno's local authority, the Consolidated Mosquito Abatement District, to release a million insects a week through the end of 2017. His team used a sieve-like device to sort the sexes by size in their pupal stage, and then gave each mosquito another look under a microscope before shipping them from Kentucky to California, where district officials released the bugs by hand, shaking them out of cardboard tubes. If this summer's trial proves effective, Mulligan and Dobson hope they could expand to other places in California and wipe out the existing pockets of Aedes aegypti before they become a permanent feature of the landscape. Its ultimate goal is to be able to make more mosquito factories, ready to ship all over the world whenever a new mosquito-borne disease strikes.

"It's really 1,000 times better," said Mustapha Debboun, the director of Harris County Public Health's mosquito control division. The prototype trap, part of Microsoft's broader Project Premonition research project, is designed to automatically do things entomologists previously had to do manually or not at all. For example, this new trap, which is being deployed in the Houston area for the first time this month as part of a pilot project, is designed to only collect the type of mosquito an entomologist wants to track, instead of a hodgepodge of mosquitoes, flies, moths and other critters that scientists then need to manually sort through. The trap also can tell researchers what time each mosquito was trapped, as well as what the temperature, wind and humidity was when the mosquito flew in. And it's designed to withstand the rain, wind and other elements that can batter traditional traps and take them out of commission.