Unplanned extubation (UE)--the unintended removal of an airway tube--remains a critical patient safety concern in intensive care units (ICUs), often leading to severe complications or death. Real-time UE detection has been limited, largely due to the ethical and privacy challenges of obtaining annotated ICU video data. We propose Augmented Unplanned Removal Alert (AURA), a vision-based risk detection system developed and validated entirely on a fully synthetic video dataset. By leveraging text-to-video diffusion, we generated diverse and clinically realistic ICU scenarios capturing a range of patient behaviors and care contexts. The system applies pose estimation to identify two high-risk movement patterns: collision, defined as hand entry into spatial zones near airway tubes, and agitation, quantified by the velocity of tracked anatomical keypoints. Expert assessments confirmed the realism of the synthetic data, and performance evaluations showed high accuracy for collision detection and moderate performance for agitation recognition. This work demonstrates a novel pathway for developing privacy-preserving, reproducible patient safety monitoring systems with potential for deployment in intensive care settings.

Agitation is one of the most common responsive behaviors in people living with dementia, particularly among those residing in community settings without continuous clinical supervision. Timely prediction of agitation can enable early intervention, reduce caregiver burden, and improve the quality of life for both patients and caregivers. This study aimed to develop and benchmark machine learning approaches for the early prediction of agitation in community-dwelling older adults with dementia using multimodal sensor data. A new set of agitation-related contextual features derived from activity data was introduced and employed for agitation prediction. A wide range of machine learning and deep learning models was evaluated across multiple problem formulations, including binary classification for single-timestamp tabular sensor data and multi-timestamp sequential sensor data, as well as anomaly detection for single-timestamp tabular sensor data. The study utilized the Technology Integrated Health Management (TIHM) dataset, the largest publicly available dataset for remote monitoring of people living with dementia, comprising 2,803 days of in-home activity, physiology, and sleep data. The most effective setting involved binary classification of sensor data using the current 6-hour timestamp to predict agitation at the subsequent timestamp. Incorporating additional information, such as time of day and agitation history, further improved model performance, with the highest AUC-ROC of 0.9720 and AUC-PR of 0.4320 achieved by the light gradient boosting machine. This work presents the first comprehensive benchmarking of state-of-the-art techniques for agitation prediction in community-based dementia care using privacy-preserving sensor data. The approach enables accurate, explainable, and efficient agitation prediction, supporting proactive dementia care and aging in place.

The influence of Large Language Models (LLMs) is rapidly growing, automating more jobs over time. Assessing the fairness of LLMs is crucial due to their expanding impact. Studies reveal the reflection of societal norms and biases in LLMs, which creates a risk of propagating societal stereotypes in downstream tasks. Many studies on bias in LLMs focus on gender bias in various NLP applications. However, there's a gap in research on bias in emotional attributes, despite the close societal link between emotion and gender. This gap is even larger for low-resource languages like Bangla. Historically, women are associated with emotions like empathy, fear, and guilt, while men are linked to anger, bravado, and authority. This pattern reflects societal norms in Bangla-speaking regions. We offer the first thorough investigation of gendered emotion attribution in Bangla for both closed and open source LLMs in this work. Our aim is to elucidate the intricate societal relationship between gender and emotion specifically within the context of Bangla. We have been successful in showing the existence of gender bias in the context of emotions in Bangla through analytical methods and also show how emotion attribution changes on the basis of gendered role selection in LLMs. All of our resources including code and data are made publicly available to support future research on Bangla NLP. Warning: This paper contains explicit stereotypical statements that many may find offensive.

Agitation is one of the most prevalent symptoms in people with dementia (PwD) that can place themselves and the caregiver's safety at risk. Developing objective agitation detection approaches is important to support health and safety of PwD living in a residential setting. In a previous study, we collected multimodal wearable sensor data from 17 participants for 600 days and developed machine learning models for detecting agitation in one-minute windows. However, there are significant limitations in the dataset, such as imbalance problem and potential imprecise labelsas the occurrence of agitation is much rarer in comparison to the normal behaviours. In this paper, we first implemented different undersampling methods to eliminate the imbalance problem, and came to the conclusion that only 20% of normal behaviour data were adequate to train a competitive agitation detection model. Then, we designed a weighted undersampling method to evaluate the manual labeling mechanism given the ambiguous time interval assumption. After that, the postprocessing method of cumulative class re-decision (CCR) was proposed based on the historical sequential information and continuity characteristic of agitation, improving the decision-making performance for the potential application of agitation detection system. The results showed that a combination of undersampling and CCR improved F1-score and other metrics to varying degrees with less training time and data.

The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen's kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.

Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological substrates could be associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning has shown promise in predicting treatment response in MDD, but one limitation has been the lack of clinical interpretability of machine learning models. We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a neural network model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Model validity and clinical utility were measured based on area under the curve (AUC) and expected improvement in sample remission rate with model-guided treatment, respectively. Post-hoc analyses yielded clusters (subgroups) based on patient prototypes learned during training. Prototypes were evaluated for interpretability by assessing differences in feature distributions and treatment-specific outcomes. A 3-prototype model achieved an AUC of 0.66 and an expected absolute improvement in population remission rate compared to the sample remission rate. We identified three treatment-relevant patient clusters which were clinically interpretable. It is possible to produce novel treatment-relevant patient profiles using machine learning models; doing so may improve precision medicine for depression. Note: This model is not currently the subject of any active clinical trials and is not intended for clinical use.

According to Markets and Markets, the global AI drug discovery market is projected to reach $ 1,434 million by 2024 from $ 259 million in 2019, at a CAGR of 40.8% during the forecast period 2019–2024. For example, BioXcel Therapeutics, Inc. (Nasdaq: BTAI) is a clinical-stage company utilising AI drug discovery approaches in neuroscience and immuno-oncology and has an emerging drug named BXCL501, that is an orally dissolving thin film formulation of dexmedetomidine, a selective alpha-2a receptor agonist for the treatment of agitation associated with neuropsychiatric disorders (Via Finance Yahoo). BioXcel Therapeutics has observed anti-agitation results in multiple clinical studies with BXCL501 including: SERENITY I for schizophrenia related agitation, SERENITY II for bipolar disorder related agitation and TRANQUILITY for dementia related agitation. Accordingly, BXCL501 has been granted Breakthrough Therapy designation for the acute treatment of agitation associated with dementia and Fast Track designation for the acute treatment of agitation associated with schizophrenia, bipolar disorders and dementia. Moreover, BioXcel recently received acceptance of its New Drug Application for BXCL501 for the acute treatment of agitation associated with schizophrenia and bipolar disorders.

The importance of artificial intelligence and machine learning (AI/ML) has not been lost on drug development companies. Recently, to help accelerate the discovery of therapies to treat COVID-19, several deals have been established to help deploy those tools. For example, Abcellera Biologics Inc., of Vancouver, British Columbia, and Eli Lilly and Co., of Indianapolis, agreed to co-develop antibody products for treating and preventing COVID-19. The collaboration will build on Abcellera's pandemic response platform, developed under the DARPA Pandemic Prevention Platform (P3) program, and Lilly's global capabilities for rapid development, manufacturing and distribution of therapeutic antibodies. Within one week of receiving a blood sample from one of the first U.S. patients who recovered from COVID-19, Abcellera screened more than 5 million immune cells looking for those that produced functional antibodies that helped the patient neutralize the virus and recover from the disease and identified more than 500 unique fully human antibody sequences.

Soul Machines has discussed services for the elderly with prospective clients but has not announced any partnerships on that subject to date, says chief business officer Greg Cross. Soul Machines envisions a future in which digital instructors educate students without access to quality human teachers, and in which famous deceased artists are digitally resurrected to discuss their works in museums. Robot companions for the infirm, then, are not too far a leap. Nor is the prospect of a future in which a family converses with the lively AI recreation of a person suffering from dementia, while a caregiver--robot or human--tends to their ailing body in another room. The potential for deception is already here. A few years ago, Brent Lawson, the president of 1 AM Dolls, a manufacturer of life-sized rubber sex dolls, was on the phone with a client who wanted a specific doll he'd seen on the company's website. The man was particularly concerned that the doll's hair was just so, and peppered Lawson with questions about the color and style, Lawson told Quartz.

SRI International, the Silicon Valley research lab where Apple's virtual assistant Siri was born, is working on a new generation of virtual assistants that respond to users' emotions. As artificial-intelligence systems such as those from Amazon, Google, and Facebook increasingly pervade our lives, there is an ever greater need for the machines to understand not only the words we speak, but what we mean as well--and emotional cues can be valuable here (see "AI's Language Problem"). "[Humans] change our behavior in reaction to how whoever we are talking to is feeling or what we think they're thinking," says William Mark, who leads SRI International's Information and Computing Sciences Division. "We want systems to be able to do the same thing." SRI is focused first on commercial partners for the technology, called SenSay Analytics.