Effective pulmonary rehabilitation requires walking programs that adapt to a patient’s daily progress and health status. However, using cloud-based Artificial Intelligence to personalize these goals raises significant privacy concerns regarding sensitive medical data. This paper introduces Alento-AI, an intelligent assistant that runs entirely on a patient’s mobile phone, ensuring total data privacy. By fine-tuning a Small Language Model (Gemma-3-1B) on a specialized dataset, we created an engine capable of following complex clinical rules without needing a constant internet connection. Our results show that the model’s ability to behave like a clinical assistant improved from a 29.8

Forest fires have far-reaching consequences, threatening human life, economic stability, and the environment. Understanding the dynamics of forest fires is crucial, especially in high-incidence regions. In this work, we apply deep networks to simulate the spatiotemporal progression of the area burnt in a forest fire. We tackle the region interpolation problem challenge by using a Conditional Variational Autoencoder (CVAE) model and generate in-between representations on the evolution of the burnt area. We also apply a CVAE model to forecast the progression of fire propagation, estimating the burnt area at distinct horizons and propagation stages. We evaluate our approach against other established techniques using real-world data. The results demonstrate that our method is competitive in geometric similarity metrics and exhibits superior temporal consistency for in-between representation generation. In the context of burnt area forecasting, our approach achieves scores of 90% for similarity and 99% for temporal consistency. These findings suggest that CVAE models may be a viable alternative for modeling the spatiotemporal evolution of 2D moving regions of forest fire evolution.

Introduction: About ¼ of the world9s population is infected with M. tuberculosis. The gold standard for diagnosis is cultural exam. Nucleic Acid Amplification Tests (NAAT) are recommended in the initial diagnosis, allowing the early detection of tuberculosis (TB). Its isolated positivity remains unclear, particularly in patients who do not report previous MTB infection. Aim: To evaluate clinical, imaging and sociodemographic characteristics of individuals with positive NAAT, but negative AFB and cultural exams. Methods: Retrospective analysis of bronchoscopies performed between 04/01/2007 and 12/31/2021. Inclusion criteria: positivity in any of the diagnostic methods. 2 groups were created (I: positive NAAT only; II: positivity in ≥1 of the other diagnostic methods). Results: Results of 3019 bronchoscopies. Group I (n=16): Predominance of males (n=9; 56.3%). Average age: 70.06 years. Previous respiratory pathology: 5 (31.3%). Constitutional symptoms: 6 (37.5%). Suspected infection: 3 (18.8%). Cavitation: 2 (12.5%). History of smoking: 3 (18.8%). Under antibacillary drugs: 1 (6.25%). Previous diagnosis of TB: 6 (37.5%). 3 (18.8%) developed the disease. Statistically significant relationship (p=0.036) between previous infection and development of TB. Mean time between positive NAAT and development of TB: 4.4 years. Group II: n=69. Statistically significant differences between groups: age (p=0.006), previous MTB infection (p=0.034) and cavitation (p=0.032). Conclusions: Patients from group I had higher age and history of MTB infection and developed the disease, on average, 4.4 years after NAAT result. More robust studies are needed to establish which factors influence NAAT positivity, especially in the absence of previous TB.

In recent years, the term Augmented Humanity (AH) has been increasingly used in the research community. AH is a term that refers to the use of advanced technologies to enhance human capabilities, whether physical, cognitive, or social. Technologies used to achieve AH range from wearable devices such as smart watches to cybernetic implants and advanced prostheses. The purpose of this article is to present a proposal for a taxonomy of AH. After describing the main research topics that have been worked on in this area, the reasons why such a taxonomy is needed are explained. Then, this article presents three main approaches to AH: the enhancement of physical, intellectual, and social capabilities. In addition, several challenges of providing a taxonomy of AH are introduced. Finally, it may be concluded that this proposed AH taxonomy will help to organize the field of research and establish a common knowledge base and terminology for future studies.

Background: Telemonitoring symptoms and physiological parameters may enable to reduce the burden of COPD on quality of life (QoL) by providing timely medical intervention at the earliest stage of deterioration, but evidence from previous studies is conflicting. Aim: This study aimed to evaluate the effect of telemonitoring on QoL of patients with COPD. Methods: Patients were followed for 12 months after being recruited. Impact of COPD on QoL was measured at baseline and at 12 months using St George's Respiratory Questionnaire (SGRQ), COPD Assessment Test (CAT) and Hospital Anxiety and Depression Scale (HADS). Statistical differences were assessed with paired-sample t-test. A p-value<0.05 was considered statistically significant. Results: Ten patients were included. Mean age was 72.1 years (±8.8). Ten percent of the patients had moderate COPD, 60% had severe COPD, and 30% had very severe COPD. Six patients (60%) received long-term oxygen therapy. HADS at baseline indicated no symptoms of depression or anxiety (mean scores 6.30±4.14 and 4.50±3.03, respectively). SGRQ total score at baseline indicated poor health related QoL (mean score 48.70±9.90). CAT mean score at baseline was 20.50±7.26. The difference in mean scores from baseline to 12-months in SGRQ was 13.20 (6.65;19.76)(p=0.01), and in CAT was 3.60 (0.09;7.11)(p=0.045), corresponding to a significant difference. No changes were observed in symptoms of anxiety and depression evaluated with HADS. Conclusion: In our study, telemonitoring of patients with COPD improved patient reported QoL, but further studies and long-term follow-up are needed to evaluate the impact of telemonitoring on QoL for patients with COPD.

Background: Anxiety in university students can lead to poor academic performance and even dropout. The Adult Manifest Anxiety Scale (AMAS-C) is a validated measure designed to assess the level and nature of anxiety in college students. Objective: The aim of this study is to provide internet-based alternatives to the AMAS-C in the automated identification and prediction of anxiety in young university students. Two anxiety prediction methods, one based on facial emotion recognition and the other on text emotion recognition, are described and validated using the AMAS-C Test Anxiety, Lie and Total Anxiety scales as ground truth data. Methods: The first method analyses facial expressions, identifying the six basic emotions (anger, disgust, fear, happiness, sadness, surprise) and the neutral expression, while the students complete a technical skills test. The second method examines emotions in posts classified as positive, negative and neutral in the students' profile on the social network Facebook. Both approaches aim to predict the presence of anxiety. Results: Both methods achieved a high level of precision in predicting anxiety and proved to be effective in identifying anxiety disorders in relation to the AMAS-C validation tool. Text analysis-based prediction showed a slight advantage in terms of precision (86.84 %) in predicting anxiety compared to face analysis-based prediction (84.21 %). Conclusions: The applications developed can help educators, psychologists or relevant institutions to identify at an early stage those students who are likely to fail academically at university due to an anxiety disorder.

The continuous representation of spatiotemporal data commonly relies on using abstract data types, such as moving regions , to represent entities whose shape and position continuously change over time. Creating this representation from discrete snapshots of real-world entities requires using interpolation methods to compute in-between data representations and estimate the position and shape of the object of interest at arbitrary temporal points. Existing region interpolation methods often fail to generate smooth and realistic representations of a region’s evolution. However, recent advancements in deep learning techniques have revealed the potential of deep models trained on discrete observations to capture spatiotemporal dependencies through implicit feature learning. In this work, we explore the capabilities of Conditional Variational Autoencoder (C-VAE) models to generate smooth and realistic representations of the spatiotemporal evolution of moving regions. We evaluate our proposed approach on a sparsely annotated dataset on the burnt area of a forest fire. We apply compression operations to sample from the dataset and use the C-VAE model and other commonly used interpolation algorithms to generate in-between region representations. To evaluate the performance of the methods, we compare their interpolation results with manually annotated data and regions generated by a U-Net model. We also assess the quality of generated data considering temporal consistency metrics. The proposed C-VAE-based approach demonstrates competitive results in geometric similarity metrics. It also exhibits superior temporal consistency, suggesting that C-VAE models may be a viable alternative to modeling the spatiotemporal evolution of 2D moving regions.

People with COPD present inactive lifestyles and physical activity (PA) promotion is a major recommendation in disease management. Technology-based interventions may be useful, especially if tailored to the target population to improve adherence. We assessed the usability of the OnTRACK platform to promote PA through individualised goal setting and feedback: mobile application (app) for patients and web app for health professionals (HP). Patients and HP were asked to complete 9 and 10 tasks, respectively, and rate how easy completing each task was, from 1 (I couldn't complete it) to 5 (I completed it easily). Suggestions were recorded. In the end, participants completed the System Usability Scale (SUS; 10 questions, score 0-100%, higher scores indicate better usability). 15 patients with COPD (68±6 years, 80% male; 80% used smartphone, 80% internet, 20% wearables) and 22 HP (40±10 years, 86% female; all used computer, smartphone and internet; 64% wearables) participated. The easiness of task completion was 3.9±0.3 for patients and 4.6±0.3 for HP. The SUS score was 66±22 for patients and 88±10 for HP. Patients with experience using PA apps (n=5, 33%; 86±17) scored significantly higher in the SUS than those without experience (n=10, 67%; 56±19). Participants' main suggestions were related to information labels (n=8, 22%), graphical aspects (n=6, 16%) and improvement of the feature "add new goal" (n=8, 22%). The need for guidance or tutorials to get the most of the apps was referred by 10 patients (67%) and 7 HP (32%). Overall, end-users found the OnTRACK platform easy to use. Improvements in some features and inclusion of guidance/tutorials on how to use them, especially for patients, are still needed.

Background:The increase in the number of patients with COVID-19 on a global scale made the early recognition of severe forms of the disease essential. Considering that IL-6 acts as a pro-inflammatory mediator, mediating acute phase responses, the objective of this study was to assess its value in the early severity stratification of SARS-CoV2 infection. Materials and Methods:It was a prospective study included IL-6 measurement in patients with SARS-CoV2 infection upon admission to the emergency department. Two groups were considered (Group I: patients without hospitalization criteria; Group II: patients with hospitalization criteria). Analyzed variables were serum levels of IL-6, C-reactive protein, ferritin, d-dimers, sociodemographics, ventilator support, ICU admission, mortality, dates of diagnosis, hospitalization, and discharge. For the statistical analyses, Mann-Whitney test, Pearson's chi-square test, area under the receiver operating characteristic curve, Youden index, and Spearman correlation were applied. Results:A total number of 117 patients were included. Mean age was significantly higher for group II (72,35±15,39 years; p<0,001). No statistically significant difference was seen between the groups regarding gender (p=0,111). The IL-6 values showed an excellent power of discrimination for the need for hospitalization (AUC=0,888; p<0,001) and the need for ICU admission (AUC=0,897; p=7.9 × 10-5). Also, its cut-off value of 12,4pg/mL for the need for hospitalization and 42,95 pg/mL for the need for ICU admission was determined. Positive correlation was seen between IL-6 value and length of stay [r(35)=0,380; p=0,020]. Three deaths were observed among patients with hospitalization criteria (8,1%). Conclusion:The value of IL-6 at admission seems to independently influence the probability of hospitalization (general ward or ICU) and its duration.

Introduction: Studies predict that by 2030 COPD will be the third leading cause of death. The prevalence of COPD increases in individuals over 40 years old and with a high smoking load. Early diagnosis of COPD is sometimes difficult, as the symptoms develop progressively and are often undervalued which leads the disease to progress to advanced stages. Objective/Methods: To evaluate the effectiveness of a spirometry network in primary care in COPD screening. Retrospective study on COPD screening through a spirometry network implemented in 11 primary care centers between 2019 and 2020. Variables evaluated:gender, age, smoking status, ventilatory syndrome, diagnosis, and stage of COPD. Results: Patients ≥35 years old with ≥1 criteria: smoker/ex-smoker and/or respiratory symptoms were selected. N=341 patients, 56% men. The mean age was 63.96, with 95.8% being over 40 years old.63.3% were smokers/ex-smokers and 36.7% had respiratory symptoms. Obstructive, restrictive, and mixed ventilatory syndrome were identified in 25.3%; 6.7% and 4.7% of patients, respectively. COPD was diagnosed in 19.9% of patients. COPD GOLD 1(64.7%) was the most prevalent, followed by COPD GOLD 2(25.0%) and COPD GOLD 3(10.3%). Conclusion: Conducting spirometry directed at patients with risk factors for COPD emerges as an innovative strategy for screening and early diagnosis. However, access to spirometry is essentially done by referring patients to hospital care, which implies long waiting times and patient relocation. An alternative would be to perform spirometry in primary care centers, implementing a spirometry network that would allow articulation between a hospital pulmonology department and primary care centers within the hospital9s area of influence.

Wildfires have significant impacts on the environment, society, and economy. Consequently, understanding its dynamics is crucial to evaluate such effects. Nonetheless, monitoring and measuring the burned area by traditional, non-automatic methods remains time-consuming and challenging. For several years, automatic semantic segmentation models have been used to describe natural phenomena, but deep learning models have recently achieved very competitive results. However, this new breed of models typically needs annotated datasets of significant dimensions. Nonetheless, datasets for real-time burnt area segmentation are often scarce. In this article, we create tools to support the benchmarking for testing and validating burned area segmentation models in a wildfire context. As such, we propose a new manually annotated dataset for segmentation of forest fire burned area based on a video captured by a UAV to train and evaluate semantic segmentation models. We suggest specific temporal consistency metrics to validate burned area polygons generated by the models in successive frames of non-annotated data. We also explore deep learning-based techniques and establish baselines, including IoU values superior to 95% on the test set.

Chronic Obstructive Pulmonary Disease (COPD) is one of the most prevalent diseases in the world, affecting respiratory performance of many people, limiting the airflow and is not fully reversible. It is a clinical syndrome characterized by chronic respiratory symptoms, structural pulmonary abnormalities or impairment of lung function. In order to help people with this disease, we propose an innovative personalized mHealth coaching platform that will address patient preferences and contextual factors – the OnTRACK platform. This platform is composed of a mobile application for patients, a web platform for healthcare professionals – and a conversational agent (or chatbot), named “Hígia”, which acts as an alternative interface between patients and the platform. This conversational agent includes several of the main functionalities already available in OnTRACK’s smartphone app, complementing and extending it. It allows consulting prescription information in a multitude of ways, getting and setting all personal data, inserting physical activity measurements, and obtaining historical data on physical activity and prescriptions, among others. The evaluation of the conversational agent yielded encouraging results, with users reporting being happier, more motivated, dedicated and confident when interacting with the systems using their voice, while allowing the development team to identify topics for improvement.

Augmented humanity (AH) is a term that has been mentioned in several research papers. However, these papers differ in their definitions of AH. The number of publications dealing with the topic of AH is represented by a growing number of publications that increase over time, being high impact factor scientific contributions. However, this terminology is used without being formally defined. The aim of this paper is to carry out a systematic mapping review of the different existing definitions of AH and its possible application areas. Publications from 2009 to 2020 were searched in Scopus, IEEE and ACM databases, using search terms “augmented human”, ”human augmentation” and “human 2.0”. Of the 16,914 initially obtained publications, a final number of 133 was finally selected. The mapping results show a growing focus on works based on AH, with computer vision being the index term with the highest number of published articles. Other index terms are wearable computing, augmented reality, human–robot interaction, smart devices and mixed reality. In the different domains where AH is present, there are works in computer science, engineering, robotics, automation and control systems and telecommunications. This review demonstrates that it is necessary to formalize the definition of AH and also the areas of work with greater openness to the use of such concept. This is why the following definition is proposed: “Augmented humanity is a human–computer integration technology that proposes to improve capacity and productivity by changing or increasing the normal ranges of human function through the restoration or extension of human physical, intellectual and social capabilities”.

In the original version of the book, the following belated corrections have been incorporated: The author name “Marcelo Brites” has been changed to “Marcelo Brites-Pereira” in the Frontmatter, Backmatter and in Chapter 49. The book has been updated with the changes.

Introduction: eHealth platforms can be used as a tool to promote physical activity (PA) in patients with COPD. When developing such platforms, a bottom-up approach is needed to ensure that patients’ and healthcare professionals’ (HCP) needs and expectations are addressed. Aim: To assess patients’ and HCP’ perspectives on the ideal eHealth platform (web application - app - for HCP + mobile app for patients) for PA promotion in patients with COPD. Methods: One focus group with 5 patients (68±8 yrs, FEV1 44±21pp) and 6 individual interviews with HCP (physicians and physiotherapist, 39±10 yrs) were conducted using a semi-structured interview guide. Interviews were recorded and transcripts were analysed using the Grounded Theory approach. Results: Participants considered an eHealth platform to promote patients9 PA valuable. Both groups suggested that PA should be individualised according to patients’ characteristics. The main features for a mobile app included: shared goal setting, PA progress graphs, motivational messages and goal badges, notifications, a bi-directional communication system to support patients and information on breathing exercises. Both groups highlighted the importance of measuring steps, PA duration, SpO2, and dyspnoea on exertion. For the web app, the HCP highlighted the importance of a notification system to signal PA changes or non-compliance (e.g., colour scheme), as well as tabs for PA goal setting and monitoring. HCP recommended this platform for patients with stable or mild disease and/or those attending pulmonary rehabilitation. Conclusion: Findings provide guidance to the design of future eHealth platforms for PA promotion in COPD.

A key factor for the adoption of an active lifestyle is self-determined motivation; however, it is often overlooked in COPD. Understanding the motives underlying patients’ decision to be (or not) physically active will provide insight into future interventions. This study assessed the motives for patients with COPD to engage in physical activity (PA) and their association with PA behaviour. A cross-sectional study was conducted in stable patients with COPD. Motivation was assessed with the Exercise Motivation Inventory-2 (EMI-2; score 0 [Not at all true for me]–5 [Very true for me]; 5 dimensions) and PA with accelerometry [ActiGraph-GT3X+, 7 days; moderate to vigorous PA (MVPA), steps/day]. Spearman’s correlations (ρ) were used to assess their relationship. 60 participants were enrolled (67.2±7.7 years; 76.7% men; FEV1 49.5±19.7pp). Patients’ motives to be physically active were mostly Health, Fitness and Psychological. Correlations with PA were weak and non-significant (p>0.05) (Table 1). Patients with COPD value Health, Fitness and Psychological motives to be physically active, although these are not related to patients’ PA behaviour. Findings highlight the complex nature of PA and the need to further explore factors influencing PA and motivation in this population.

TOPIC: Procedures TYPE: Medical Student/Resident Case Reports INTRODUCTION: Tracheobronquial foreign body aspiration (FBA) is uncommon in adults, representing < 25% of aspirations. It mostly happens in the sixth or seventh decade of life and is associated to failure of airway protective mechanism. Iatrogenic FBA in adults is commonly related to dentistry procedures that require local anesthesia and supine positions, although the incidence of aspiration in root canal treatment were 0.001 per 100 000. CASE PRESENTATION: A 71-years-old male, former smoker (50 pack years) with past medical history of Chronic Obstructive Pulmonary Disease (COPD) and Severe Obstructive Sleep Apnea (OSA) was presented to pulmonology consultation with persistent cough and breathlessness for the last four months, since dental procedure under local anesthesia. He had stable vital signs, no respiratory difficulty signs or adventitious breath sounds. Chest radiography showed a retrocardiac opacity on the right hemithorax, compatible with radiopaque foreign body. Chest Computed Tomography (CT) revealed a foreign body image in the distal portion of the intermediate bronchus, immediately prior to division into the right basal pyramid. Rigid bronchoscopy confirmed the presence of foreign body in the intermediate bronchus, without total obstruction, surrounded by granulation tissue, compatible with dental implant screwdriver. The dentistry instrument was removed and the patient initiated a short course of glucocorticoid (Prednisolone 1 mg/Kg) with successful improvement of chronic cough. DISCUSSION: Our case describes a patient with accidental aspiration of a dental implant screwdriver during dentistry procedure. The small instruments used for dentistry treatment, under saliva slippery environment, associated with local anesthesia and supine position, is favorable for instrument drop and consequent aspiration. Persistent cough is the most common symptom and the symptomatology can mimic chronic respiratory disease such as COPD, as presented in our patient. In adults, more than 50% of FBA are founded in right bronchial tree, favoring the intermedius bronchus and basal segments of right lower lobe. The majority of foreign bodies in adults can be extracted safely with flexible bronchoscopy, although rigid bronchoscopy was used in the first approach to avoid damages during extraction due to the aggressive metallic object. CONCLUSIONS: Even though FBA are more frequent in children, the elderly may have a more silent presentation due to more distal obstruction. High degree of suspicious, with early recognition and treatment, may minimize potentially severe complications of a retained foreign body. REFERENCE #1: Casalini, A.G et al. Foreign Body Aspiration in Adults and in Children. J CronchlIntervent Pulmonl 2013;20:313-321. REFERENCE #2: Hewlett J.C et al. Foreign body aspiration in adult airways: therapeutica approach. J Thorac Dis 2017;9(9):3398-3409. DISCLOSURES: no disclosure on file for Sara Braga; no disclosure on file for João Fernandes Costa; No relevant relationships by Filipa Jesus, source=Web Response no disclosure on file for Rebeca Martins Natal; no disclosure on file for Rita Matos Gomes; no disclosure on file for Fernando Pereira da Silva; No relevant relationships by Joana Ribeiro, source=Web Response

Fatigue is highly prevalent in COPD and may be associated with reduced physical activity (PA) and poor outcomes. This study explored the relationship between fatigue, objectively measured PA and health-related factors in people with COPD. Fatigue was assessed with the Checklist of Individual Strength (CIS20) and CIS20-Subjective Fatigue (CIS20-SF) and PA with Actigraph GT3X monitors (moderate-to-vigorous PA, MVPA; total PA; steps/day). Dyspnoea (modified Medical Research Council, mMRC), exercise tolerance (6-min walk distance, 6MWD), lung function (spirometry) and GOLD A-D were collected. Spearman (ρ) and Pearson (r) correlations and multiple regressions were performed. Variables entered the model if correlation≥0.2. 54 patients participated (68±7 years; 82% men) and 69% reported fatigue (CIS20-SF≥27). Fatigue was significantly correlated with MVPA, steps/day, mMRC, 6MWD, GOLD A-D and FEV1pp (Table 1). In regression models for CIS20 (p=.001; r2=.61) and CIS20-SF (p=.003; r2=.56), dyspnoea was the only significant variable. Table 1. Descriptives and correlations between fatigue, PA and health-related factors. aρ; br; cVariables entering the regression models; dMedian[Q1-Q3], mean±SD or n. People with higher scores of fatigue present lower PA levels, although the relationship is weak. Dyspnoea appears to have the largest influence on fatigue.