Foodborne gastrointestinal (GI) illness is a common cause of ill health in the UK. However, many cases do not interact with the healthcare system, posing significant challenges for traditional surveillance methods. The growth of publicly available online restaurant reviews and advancements in large language models (LLMs) present potential opportunities to extend disease surveillance by identifying public reports of GI illness. In this study, we introduce a novel annotation schema, developed with experts in GI illness, applied to the Yelp Open Dataset of reviews. Our annotations extend beyond binary disease detection, to include detailed extraction of information on symptoms and foods. We evaluate the performance of open-weight LLMs across these three tasks: GI illness detection, symptom extraction, and food extraction. We compare this performance to RoBERTa-based classification models fine-tuned specifically for these tasks. Our results show that using prompt-based approaches, LLMs achieve micro-F1 scores of over 90% for all three of our tasks. Using prompting alone, we achieve micro-F1 scores that exceed those of smaller fine-tuned models. We further demonstrate the robustness of LLMs in GI illness detection across three bias-focused experiments. Our results suggest that publicly available review text and LLMs offer substantial potential for public health surveillance of GI illness by enabling highly effective extraction of key information. While LLMs appear to exhibit minimal bias in processing, the inherent limitations of restaurant review data highlight the need for cautious interpretation of results.

For rapidly spreading diseases where many cases show no symptoms, swift and effective contact tracing is essential. While exposure notification applications provide alerts on potential exposures, a fully automated system is needed to track the infectious transmission routes. To this end, our research leverages large-scale contact networks from real human mobility data to identify the path of transmission. More precisely, we introduce a new Infectious Path Centrality network metric that informs a graph learning edge classifier to identify important transmission events, achieving an F1-score of 94%. Additionally, we explore bidirectional contact tracing, which quarantines individuals both retroactively and proactively, and compare its effectiveness against traditional forward tracing, which only isolates individuals after testing positive. Our results indicate that when only 30% of symptomatic individuals are tested, bidirectional tracing can reduce infectious effective reproduction rate by 71%, thus significantly controlling the outbreak.

Source separation is the process of isolating individual sounds in an auditory mixture of multiple sounds [1], and has a variety of applications ranging from speech enhancement and lyric transcription [2] to digital audio production for music. Furthermore, Automatic Music Transcription (AMT) is the process of converting raw music audio into sheet music that musicians can read [3]. Historically, these tasks have faced challenges such as significant audio noise, long training times, and lack of free-use data due to copyright restrictions. However, recent developments in deep learning have brought new promising approaches to building low-distortion stems and generating sheet music from audio signals [4]. Using spectrogram masking, deep neural networks, and the MuseScore API, we attempt to create an end-to-end pipeline that allows for an initial music audio mixture (e.g...wav file) to be separated into instrument stems, converted into MIDI files, and transcribed into sheet music for each component instrument.

AFTER dodging covid-19 for several years, I finally tested positive for one of the leading causes of death where I live in the US. I'm vaccinated, but also in a statistically vulnerable group: I'm over 50, and I used to smoke. For people like me, the US Centers for Disease Control and Prevention recommends treatments including the new drug Paxlovid.

Older Americans face a growing loneliness epidemic. Startups are finding ways technology can help. The hard part is bringing them together. The U.S. globally has the highest percentage of older adults living alone, according to Pew Research Center. The Centers for Disease Control and Prevention have long warned that social isolation contributes to numerous health problems, including dementia and depression.

Neglected tropical diseases (NTDs) continue to affect the livelihood of individuals in countries in the Southeast Asia and Western Pacific region. These diseases have been long existing and have caused devastating health problems and economic decline to people in low- and middle-income (developing) countries. An estimated 1.7 billion of the world's population suffer one or more NTDs annually, this puts approximately one in five individuals at risk for NTDs. In addition to health and social impact, NTDs inflict significant financial burden to patients, close relatives, and are responsible for billions of dollars lost in revenue from reduced labor productivity in developing countries alone. There is an urgent need to better improve the control and eradication or elimination efforts towards NTDs. This can be achieved by utilizing machine learning tools to better the surveillance, prediction and detection program, and combat NTDs through the discovery of new therapeutics against these pathogens. This review surveys the current application of machine learning tools for NTDs and the challenges to elevate the state-of-the-art of NTDs surveillance, management, and treatment.

We present a new challenging dataset, CPPE - 5 (Medical Personal Protective Equipment), with the goal to allow the study of subordinate categorization of medical personal protective equipments, which is not possible with other popular data sets that focus on broad level categories (such as PASCAL VOC, ImageNet, Microsoft COCO, OpenImages, etc). To make it easy for models trained on this dataset to be used in practical scenarios in complex scenes, our dataset mainly contains images that show complex scenes with several objects in each scene in their natural context. The image collection for this dataset focusing on: obtaining as many non-iconic images as possible and making sure all the images are real-life images unlike other existing datasets in this area. Our dataset includes 5 object categories (coveralls, face shield, gloves, mask, and goggles) and each image is annotated with a set of bounding boxes and positive labels. We present a detailed analysis of the dataset in comparison to other popular broad category datasets as well as datasets focusing on personal protective equipments, we also find that at present there exist no such publicly available datasets. Finally we also analyze performance and compare model complexities on baseline and state-of-the-art models for bounding box results. Our code, data, and trained models are available at https://git.io/cppe5-dataset .

The pandemic has put a spotlight on how big data and analytics technologies are being used in the public health sector. Contact tracing, where phone numbers and location data from mobile devices were combined with lab results in public health systems to issue alerts when an individual came in contact with a confirmed COVID patient. This information empowered people to preemptively self-isolate and/or head for rapid testing. Google and Apple, meanwhile, developed some groundbreaking application programming applications (APIs) for contact tracing that protected anonymity, while allowing their devices to receive updates from state disease surveillance systems and send out alerts. The use of big data during the pandemic is certainly a harbinger of things to come, and public health agencies must understand how such data is being used.

With Amazon Rekognition PPE detection, customers can analyze images from their on-premises cameras across multiple locations to automatically detect if persons in the images are wearing the required PPE. When customers analyze an image using Amazon Rekognition PPE detection, for each person detected in the image, they receive confidence scores with bounding boxes for each item of protective equipment detected (face cover, hand covers, and head cover) and Boolean responses (true or false) with confidence scores for whether each detected item of protective equipment covers the corresponding body part (nose, hands, and head). They can also supply a list of required protective equipment (such as face cover or face cover and head cover) and a minimum confidence threshold (such as 80%) to receive a consolidated per-image summary of Persons with Required PPE, Persons without Required PPE, and Persons Indeterminate. Using these PPE detection results, customers can trigger timely alarms or notifications that remind people to wear PPE before or during their presence in a hazardous area in order to help improve or maintain everyone's safety. They can also aggregate the PPE detection results and analyze them by time and place to identify how safety warnings or training practices can be improved and generate reports for use during regulatory audits.

The following image shows an example input image and its corresponding output from the DetectProtectiveEquipment as seen on the Amazon Rekognition PPE detection console. In this example, we supply face cover as the required PPE and 80% as the required minimum confidence threshold as part of summarizationattributes. We receive a summarization result that indicates that there are four persons in the image that are wearing face covers at a confidence score of over 80% [person identifiers 0, 1,2, 3]. It also provides the full fidelity API response in the per-person results. Note that this feature doesn't perform facial recognition or facial comparison and can't identify the detected persons.