Integrating factors associated with complex wound healing into a mobile application: Findings from a cohort study.

Complex, chronic or hard-to-heal wounds are a prevalent health problem worldwide, with significant physical, psychological and social consequences. This study aims to identify factors associated with the healing process of these wounds and develop a mobile application for wound care that incorporates these factors. A prospective multicentre cohort study was conducted in nine health units in Portugal, involving data collection through a mobile application by nurses from April to October 2022. The study followed 46 patients with 57 wounds for up to 5 weeks, conducting six evaluations. Healing time was the main outcome measure, analysed using the Mann-Whitney test and three Cox regression models to calculate risk ratios. The study sample comprised various wound types, with pressure ulcers being the most common (61.4%), followed by venous leg ulcers (17.5%) and diabetic foot ulcers (8.8%). Factors that were found to impair the wound healing process included chronic kidney disease (U = 13.50; p = 0.046), obesity (U = 18.0; p = 0.021), non-adherence to treatment (U = 1.0; p = 0.029) and interference of the wound with daily routines (U = 11.0; p = 0.028). Risk factors for delayed healing over time were identified as bone involvement (RR 3.91; p < 0.001), presence of odour (RR 3.36; p = 0.007), presence of neuropathy (RR 2.49; p = 0.002), use of anti-inflammatory drugs (RR 2.45; p = 0.011), stalled wound (RR 2.26; p = 0.022), greater width (RR 2.03; p = 0.002), greater depth (RR 1.72; p = 0.036) and a high score on the healing scale (RR 1.21; p = 0.001). Integrating the identified risk factors for delayed healing into the assessment of patients and incorporating them into a mobile application can enhance decision-making in wound care.

Desensitization in children allergic to drugs: Indications, protocols, and limits.

Any drug can potentially induce a hypersensitivity reaction. If after the allergological work-up the drug hypersensitivity reaction is confirmed, in most cases, the simple avoidance of the culprit drug and a suggestion of an unrelated alternative is enough. However, there are circumstances where the choice to stop the treatment affects the survival, the safety and/or the quality of life of the patient and the global outcome of the disease in question. When this occurs, drug desensitization can be the answer and should not be viewed as an extravagance, nor the pediatric age should be considered a contraindication. Drug desensitization in children can be safely and successfully performed, having a positive impact on the survival and overall prognosis. In general, the indications for DDS are the same in adults as in children. However, in this age group there are specificities that this paper aimed to describe, reviewing the mechanisms behind drug hypersensitivity and rapid drug desensitization, types of protocols, indications, and contraindications, as well as several technical aspects that are specific to the pediatric age.

Determinants of the Use of Health and Fitness Mobile Apps by Patients With Asthma: Secondary Analysis of Observational Studies.

BACKGROUND: Health and fitness apps have potential benefits to improve self-management and disease control among patients with asthma. However, inconsistent use rates have been reported across studies, regions, and health systems. A better understanding of the characteristics of users and nonusers is critical to design solutions that are effectively integrated in patients' daily lives, and to ensure that these equitably reach out to different groups of patients, thus improving rather than entrenching health inequities. OBJECTIVE: This study aimed to evaluate the use of general health and fitness apps by patients with asthma and to identify determinants of usage. METHODS: A secondary analysis of the INSPIRERS observational studies was conducted using data from face-to-face visits. Patients with a diagnosis of asthma were included between November 2017 and August 2020. Individual-level data were collected, including age, gender, marital status, educational level, health status, presence of anxiety and depression, postcode, socioeconomic level, digital literacy, use of health services, and use of health and fitness apps. Multivariate logistic regression was used to model the probability of being a health and fitness app user. Statistical analysis was performed in R. RESULTS: A total of 526 patients attended a face-to-face visit in the 49 recruiting centers and 514 had complete data. Most participants were ≤40 years old (66.4%), had at least 10 years of education (57.4%), and were in the 3 higher quintiles of the socioeconomic deprivation index (70.1%). The majority reported an overall good health status (visual analogue scale [VAS] score>70 in 93.1%) and the prevalence of anxiety and depression was 34.3% and 11.9%, respectively. The proportion of participants who reported using health and fitness mobile apps was 41.1% (n=211). Multivariate models revealed that single individuals and those with more than 10 years of education are more likely to use health and fitness mobile apps (adjusted odds ratio [aOR] 2.22, 95%CI 1.05-4.75 and aOR 1.95, 95%CI 1.12-3.45, respectively). Higher digital literacy scores were also associated with higher odds of being a user of health and fitness apps, with participants in the second, third, and fourth quartiles reporting aORs of 6.74 (95%CI 2.90-17.40), 10.30 (95%CI 4.28-27.56), and 11.52 (95%CI 4.78-30.87), respectively. Participants with depression symptoms had lower odds of using health and fitness apps (aOR 0.32, 95%CI 0.12-0.83). CONCLUSIONS: A better understanding of the barriers and enhancers of app use among patients with lower education, lower digital literacy, or depressive symptoms is key to design tailored interventions to ensure a sustained and equitable use of these technologies. Future studies should also assess users' general health-seeking behavior and their interest and concerns specifically about digital tools. These factors may impact both initial engagement and sustained use.

Automatic Focus Assessment on Dermoscopic Images Acquired with Smartphones.

Over recent years, there has been an increase in popularity of the acquisition of dermoscopic skin lesion images using mobile devices, more specifically using the smartphone camera. The demand for self-care and telemedicine solutions requires suitable methods to guide and evaluate the acquired images' quality in order to improve the monitoring of skin lesions. In this work, a system for automated focus assessment of dermoscopic images was developed using a feature-based machine learning approach. The system was designed to guide the user throughout the acquisition process by means of a preview image validation approach that included artifact detection and focus validation, followed by the image quality assessment of the acquired picture. This paper also introduces two different datasets, dermoscopic skin lesions and artifacts, which were collected using different mobile devices to develop and test the system. The best model for automatic preview assessment attained an overall accuracy of 77.9% while focus assessment of the acquired picture reached a global accuracy of 86.2%. These findings were validated by implementing the proposed methodology within an android application, demonstrating promising results as well as the viability of the proposed solution in a real life scenario.

A Review of Computational Methods for Cervical Cells Segmentation and Abnormality Classification.

Cervical cancer is the one of the most common cancers in women worldwide, affecting around 570,000 new patients each year. Although there have been great improvements over the years, current screening procedures can still suffer from long and tedious workflows and ambiguities. The increasing interest in the development of computer-aided solutions for cervical cancer screening is to aid with these common practical difficulties, which are especially frequent in the low-income countries where most deaths caused by cervical cancer occur. In this review, an overview of the disease and its current screening procedures is firstly introduced. Furthermore, an in-depth analysis of the most relevant computational methods available on the literature for cervical cells analysis is presented. Particularly, this work focuses on topics related to automated quality assessment, segmentation and classification, including an extensive literature review and respective critical discussion. Since the major goal of this timely review is to support the development of new automated tools that can facilitate cervical screening procedures, this work also provides some considerations regarding the next generation of computer-aided diagnosis systems and future research directions.

Symptoms of anxiety and depression in patients with persistent asthma: a cross-sectional analysis of the INSPIRERS studies.

OBJECTIVES: Anxiety and depression are relevant comorbidities in asthma, but, in Portugal and Spain, data on this topic are scarce. We assessed, in patients with asthma, the frequency of anxiety and depression using the Hospital Anxiety and Depression Scale (HADS) and the European Quality of Life Five Dimension Questionnaire (EQ-5D); the level of agreement between these questionnaires, and the factors associated with these symptoms. METHODS: This is a secondary analysis of the INSPIRERS studies. A total of 614 adolescents and adults with persistent asthma (32.6±16.9 years, 64.7% female) were recruited from 30 primary care centres and 32 allergy, pulmonology and paediatric clinics. Demographic and clinical characteristics, HADS and EQ-5D were collected. A score ≥8 on Hospital Anxiety and Depression Scale-Anxiety/Hospital Anxiety and Depression Scale-Depression or a positive answer to EQ-5D item 5 indicated the presence of these symptoms. Agreement was determined by Cohen's kappa. Two multivariable logistic regressions were built. RESULTS: According to HADS, 36% of the participants had symptoms of anxiety and 12% of depression. According to EQ-5D, 36% of the participants had anxiety/depression. The agreement between questionnaires in identifying anxiety/depression was moderate (k=0.55, 95% CI 0.48 to 0.62). Late asthma diagnosis, comorbidities and female gender were predictors of anxiety/depression, while better asthma control, health-related quality of life and perception of health were associated with lower odds for anxiety/depression. CONCLUSION: At least 1/3 of the patients with persistent asthma experience symptoms of anxiety/depression, showing the relevance of screening these disorders in patients with asthma. EQ-5D and HADS questionnaires showed a moderate agreement in the identification of anxiety/depression symptoms. The identified associated factors need to be further investigated in long-term studies.

AlergiaPT: A Portuguese media campaign to inspire people with allergies to make a positive change in their life.

Allergic diseases comprise a significant cause of morbidity worldwide and a substantial burden on the health and medical systems of both developed and emerging economies. Although highly prevalent, relatively severe, and largely impactful on the quality of life of patients, allergic diseases are commonly trivialized. Increasing awareness of the relevance of allergic diseases as a major public health problem might lead to an improved acknowledgment by governments and health authorities. Based on the positive impact that media campaigns might have on health-related behaviors, as well as the large use of social media by different types of users, social media might be used as a powerful tool for spreading awareness and education even more effective than traditional face-to-face communication. Therefore, we aimed to develop a social media-based communication program, the AlergiaPT, reaching all stakeholders, to increase the awareness of allergic diseases tackling the causes, prevention, control, and economic impact. The AlergiaPT will provide user-generated and interactive content toward engagement, include both long-form and short-form video productions toward education, as well as stories and time-sensitive content toward empowerment. It will be targeted to all populations, engaging different stakeholders. Contents will address the 5 campaign goals: i) allergy health is promoted; ii) tolerance is actively reinforced, and avoidance reduced; iii) treatment control and guided self-management of patients of asthma, rhinitis, food allergy, and atopic eczema are strengthened; iv) recognition and treatment of severe allergy and anaphylaxis are improved, and v) indoor air quality is promoted. Engagement on the campaign will be promoted through stepwise educational takeaways meetings using different social media, and targeting all audience groups, by promoting the organization of resources for common goals and the involvement of social media to improve public awareness. The impact of AlergiaPT will be assessed through google analytics.

Incremental Learning for Dermatological Imaging Modality Classification.

With the increasing adoption of teledermatology, there is a need to improve the automatic organization of medical records, being dermatological image modality a key filter in this process. Although there has been considerable effort in the classification of medical imaging modalities, this has not been in the field of dermatology. Moreover, as various devices are used in teledermatological consultations, image acquisition conditions may differ. In this work, two models (VGG-16 and MobileNetV2) were used to classify dermatological images from the Portuguese National Health System according to their modality. Afterwards, four incremental learning strategies were applied to these models, namely naive, elastic weight consolidation, averaged gradient episodic memory, and experience replay, enabling their adaptation to new conditions while preserving previously acquired knowledge. The evaluation considered catastrophic forgetting, accuracy, and computational cost. The MobileNetV2 trained with the experience replay strategy, with 500 images in memory, achieved a global accuracy of 86.04% with only 0.0344 of forgetting, which is 6.98% less than the second-best strategy. Regarding efficiency, this strategy took 56 s per epoch longer than the baseline and required, on average, 4554 megabytes of RAM during training. Promising results were achieved, proving the effectiveness of the proposed approach.

Integrating Domain Knowledge into Deep Learning for Skin Lesion Risk Prioritization to Assist Teledermatology Referral.

Teledermatology has developed rapidly in recent years and is nowadays an essential tool for early diagnosis. In this work, we aim to improve existing Teledermatology processes for skin lesion diagnosis by developing a deep learning approach for risk prioritization with a dataset of retrospective data from referral requests of the Portuguese National Health System. Given the high complexity of this task, we propose a new prioritization pipeline guided and inspired by domain knowledge. We explored automatic lesion segmentation and tested different learning schemes, namely hierarchical classification and curriculum learning approaches, optionally including additional patient metadata. The final priority level prediction can then be obtained by combining predicted diagnosis and a baseline priority level accounting for explicit expert knowledge. In both the differential diagnosis and prioritization branches, lesion segmentation with 30% tolerance for contextual information was shown to improve classification when compared with a flat baseline model trained on original images; furthermore, the addition of patient information was not beneficial for most experiments. Curriculum learning delivered better results than a flat or hierarchical approach. The combination of diagnosis information and a knowledge map, created in collaboration with dermatologists, together with the priority achieved interesting results (best macro F1 of 43.93% for a validated test set), paving the way for new data-centric and knowledge-driven approaches.

Physician's experience on managing asthma in adolescents: results of the International AMADO (Asthma Management in ADOlescents) survey.

BACKGROUND: Worldwide prevalence of asthma seems to be increasing in adolescents, but limited data is available regarding the management of asthma in this age group. OBJECTIVE: Therefore, we conducted an international survey focused on physicians who manage asthma in order to understand how Asthma Management in ADOlescents (AMADO) is currently performed. METHODS: The AMADO survey is a web-based global survey of physician's attitudes towards the management of asthma in adolescents, circulated for 17 weeks. The survey had an anonymous and voluntary standard. The questionnaire consisted in 27 questions covering the training background of respondents, difficulties in diagnosis, and in management of asthma in adolescents. RESULTS: Two hundred forty-four responses were received from 46 countries, from all continents. Most (65%) of participants indicated allergy as being their main specialty. The majority of participants (62%) had more than 5 years of clinical practice, but 62% have no formal training in management of adolescents with asthma. Most of participants (96%) indicated having at least one case of asthma in adolescents per month. 60% of respondents mentioned that the asthmatic adolescents only had the consultation due to the family imposition. All respondents mentioned having difficulties in the management of asthma in adolescents due to patient poor adherence. Overall, 44% of participants have no specific health care resources for adolescents in their departments. Main suggestions from the participants were: optimization of time and personalized communication to these cohort, and standardization of multidisciplinary actions to improve adherence to asthma control treatment. CONCLUSION: Management of asthma in adolescents is still a challenge in clinical practice. The results from this survey helped us to identify the key issues to improve clinical outcomes in the future. This survey is the first step of the international AMADO initiative, which intends to optimize diagnosis and control of asthma and prevent avoidable deaths.

Profiling Persistent Asthma Phenotypes in Adolescents: A Longitudinal Diagnostic Evaluation from the INSPIRERS Studies.

We aimed to identify persistent asthma phenotypes among adolescents and to evaluate longitudinally asthma-related outcomes across phenotypes. Adolescents (13-17 years) from the prospective, observational, and multicenter INSPIRERS studies, conducted in Portugal and Spain, were included (n = 162). Latent class analysis was applied to demographic, environmental, and clinical variables, collected at a baseline medical visit. Longitudinal differences in clinical variables were assessed at a 4-month follow-up telephone contact (n = 128). Three classes/phenotypes of persistent asthma were identified. Adolescents in class 1 (n = 87) were highly symptomatic at baseline and presented the highest number of unscheduled healthcare visits per month and exacerbations per month, both at baseline and follow-up. Class 2 (n = 32) was characterized by female predominance, more frequent obesity, and uncontrolled upper/lower airways symptoms at baseline. At follow-up, there was a significant increase in the proportion of controlled lower airway symptoms (p < 0.001). Class 3 (n = 43) included mostly males with controlled lower airways symptoms; at follow-up, while keeping symptom control, there was a significant increase in exacerbations/month (p = 0.015). We have identified distinct phenotypes of persistent asthma in adolescents with different patterns in longitudinal asthma-related outcomes, supporting the importance of profiling asthma phenotypes in predicting disease outcomes that might inform targeted interventions and reduce future risk.

Monitoring Adherence to Asthma Inhalers Using the InspirerMundi App: Analysis of Real-World, Medium-Term Feasibility Studies.

Background: Poor medication adherence is a major challenge in asthma and objective assessment of inhaler adherence is needed. InspirerMundi app aims to monitor inhaler adherence while turning it into a positive experience through gamification and social support. Objective: We assessed the medium-term feasibility of the InspirerMundi app to monitor inhaler adherence in real-world patients with persistent asthma (treated with daily inhaled medication). In addition, we attempted to identify the characteristics of the patients related to higher app use. Methods: Two real-world multicenter observational studies, with one initial face-to-face visit and a 4-month telephone interview, were conducted in 29 secondary care centers from Portugal. During an initial face-to-face visit, patients were invited to use the app daily to register their asthma medication intakes. A scheduled intake was considered taken when patients took a photo of the medication (inhaler, blister, or others) using the image-based medication detection tool. Medication adherence was calculated as the number of doses taken as a percentage of the number scheduled. Interacting with the app ≥30 days was used as the cut-off for higher app use. Results: A total of 114 patients {median 20 [percentile 25 to percentile 75 (P25-P75) 16-36] years, 62% adults} were invited, 107 (94%) installed the app and 83 (73%) completed the 4-month interview. Patients interacted with the app for a median of 18 [3-45] days, translated on a median use rate of 15 [3-38]%. Median inhaler adherence assessed through the app was 34 [4-73]% when considering all scheduled inhalations for the study period. Inhaler adherence assessed was not significantly correlated with self-reported estimates. Median adherence for oral and other medication was 41 [6-83]% and 43 [3-73]%, respectively. Patients with higher app use were slightly older (p = 0.012), more frequently taking medication for other health conditions (p = 0.040), and more frequently prescribed long-acting muscarinic antagonists (LAMA, p = 0.024). After 4 months, Control of Allergic Rhinitis and Asthma Test (CARAT) scores improved (p < 0.001), but no differences between patients interacting with the app for 30 days or less were seen. Conclusions: The InspirerMundi app was feasible to monitor inhaler adherence in patients with persistent asthma. The persistent use of this mHealth technology varies widely. A better understanding of characteristics related to higher app use is still needed before effectiveness studies are undertaken.

Feasibility and Acceptability of an Asthma App to Monitor Medication Adherence: Mixed Methods Study.

BACKGROUND: Poor medication adherence is a major challenge in asthma, and objective assessment of inhaler adherence is needed. The InspirerMundi app aims to monitor adherence while providing a positive experience through gamification and social support. OBJECTIVE: This study aimed to evaluate the feasibility and acceptability of the InspirerMundi app to monitor medication adherence in adolescents and adults with persistent asthma (treated with daily inhaled medication). METHODS: A 1-month mixed method multicenter observational study was conducted in 26 secondary care centers from Portugal and Spain. During an initial face-to-face visit, physicians reported patients' asthma therapeutic plan in a structured questionnaire. During the visits, patients were invited to use the app daily to register their asthma medication intakes. A scheduled intake was considered taken when patients registered the intake (inhaler, blister, or other drug formulation) by using the image-based medication detection tool. At 1 month, patients were interviewed by phone, and app satisfaction was assessed on a 1 (low) to 5 (high) scale. Patients were also asked to point out the most and least preferred app features and make suggestions for future app improvements. RESULTS: A total of 107 patients (median 27 [P25-P75 14-40] years) were invited, 92.5% (99/107) installed the app, and 73.8% (79/107) completed the 1-month interview. Patients interacted with the app a median of 9 (P25-P75 1-24) days. At least one medication was registered in the app by 78% (77/99) of patients. A total of 53% (52/99) of participants registered all prescribed inhalers, and 34% (34/99) registered the complete asthma therapeutic plan. Median medication adherence was 75% (P25-P75 25%-90%) for inhalers and 82% (P25-P75 50%-94%) for other drug formulations. Patients were globally satisfied with the app, with 75% (59/79) scoring ≥4,; adherence monitoring, symptom monitoring, and gamification features being the most highly scored components; and the medication detection tool among the lowest scored. A total of 53% (42/79) of the patients stated that the app had motivated them to improve adherence to inhaled medication and 77% (61/79) would recommend the app to other patients. Patient feedback was reflected in 4 major themes: medication-related features (67/79, 85%), gamification and social network (33/79, 42%), symptom monitoring and physician communication (21/79, 27%), and other aspects (16/79, 20%). CONCLUSIONS: The InspirerMundi app was feasible and acceptable to monitor medication adherence in patients with asthma. Based on patient feedback and to increase the registering of medications, the therapeutic plan registration and medication detection tool were redesigned. Our results highlight the importance of patient participation to produce a patient-centered and engaging mHealth asthma app.

Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images.

Dermoscopic images allow the detailed examination of subsurface characteristics of the skin, which led to creating several substantial databases of diverse skin lesions. However, the dermoscope is not an easily accessible tool in some regions. A less expensive alternative could be acquiring medium resolution clinical macroscopic images of skin lesions. However, the limited volume of macroscopic images available, especially mobile-acquired, hinders developing a clinical mobile-based deep learning approach. In this work, we present a technique to efficiently utilize the sizable number of dermoscopic images to improve the segmentation capacity of macroscopic skin lesion images. A Cycle-Consistent Adversarial Network is used to translate the image between the two distinct domains created by the different image acquisition devices. A visual inspection was performed on several databases for qualitative evaluation of the results, based on the disappearance and appearance of intrinsic dermoscopic and macroscopic features. Moreover, the Fréchet Inception Distance was used as a quantitative metric. The quantitative segmentation results are demonstrated on the available macroscopic segmentation databases, SMARTSKINS and Dermofit Image Library, yielding test set thresholded Jaccard Index of 85.13% and 74.30%. These results establish a new state-of-the-art performance in the SMARTSKINS database.