Browsing by Author "Rocha, Sara"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Measuring adherence to inhaled control medication in patients with asthma: Comparison among an asthma app, patient self‐report and physician assessmentPublication . Cachim, Afonso; Pereira, Ana Margarida; Almeida, Rute; Amaral, Rita; Correia, Magna Alves; Marques, Pedro Vieira; Loureiro, Cláudia Chaves; Ribeiro, Carmelita; Cardia, Francisca; Gomes, Joana; Vidal, Carmen; Silva, Eurico; Rocha, Sara; Rocha, Diana; Marques, Maria Luís; Páscoa, Rosália; Morais, Daniela; Cruz, Ana Margarida; Santalha, Marta; Simões, José Augusto Rodrigues; Silva, Sofia da; Silva, Diana; Gerardo, Rita; Bom, Filipa Todo; Morete, Ana; Vieira, Inês; Vieira, Pedro; Monteiro, Rosário; Raimundo, Rosário; Monteiro, Luís; Neves, Ângela; Santos, Carlos; Penas, Ana Margarida; Regadas, Rita; Marques, José Varanda; Rosendo, Inês; Aguiar, Margarida Abreu; Fernandes, Sara; Cardoso, Carlos Seiça; Pimenta, F.; Meireles, Patrícia; Gonçalves, Mariana; Fonseca, Joao A; Jácome, CristinaBackground Previous studies have demonstrated the feasibility of using an asthma app to support medication management and adherence but failed to compare with other measures currently used in clinical practice. However, in a clinical setting, any additional adherence measurement must be evaluated in the context of both the patient and physician perspectives so that it can also help improve the process of shared decision making. Thus, we aimed to compare different measures of adherence to asthma control inhalers in clinical practice, namely through an app, patient self-report and physician assessment. Methods This study is a secondary analysis of three prospective multicentre observational studies with patients (≥13 years old) with persistent asthma recruited from 61 primary and secondary care centres in Portugal. Patients were invited to use the InspirerMundi app and register their inhaled medication. Adherence was measured by the app as the number of doses taken divided by the number of doses scheduled each day and two time points were considered for analysis: 1-week and 1-month. At baseline, patients and physicians independently assessed adherence to asthma control inhalers during the previous week using a Visual Analogue Scale (VAS 0–100). Results A total of 193 patients (72% female; median [P25–P75] age 28 [19–41] years old) were included in the analysis. Adherence measured by the app was lower (1 week: 31 [0–71]%; 1 month: 18 [0–48]%) than patient self-report (80 [60–95]) and physician assessment (82 [51–94]) (p < 0.001). A negligible non-significant correlation was found between the app and subjective measurements (ρ 0.118–0.156, p > 0.05). There was a moderate correlation between patient self-report and physician assessment (ρ = 0.596, p < 0.001). Conclusions Adherence measured by the app was lower than that reported by the patient or the physician. This was expected as objective measurements are commonly lower than subjective evaluations, which tend to overestimate adherence. Nevertheless, the low adherence measured by the app may also be influenced by the use of the app itself and this needs to be considered in future studies.
- Stacked Denoising Autoencoders and Transfer Learning for Immunogold Particles Detection and RecognitionPublication . Sousa, Ricardo; Santos, Jorge M.; Silva, Luís M.; Alexandre, Luís; Esteves, Tiago; Rocha, Sara; Monjardino, Paulo; Sá, Joaquim Marques de; Figueiredo, Francisco; Quelhas, PedroIn this paper we present a system for the detection of immunogold particles and a Transfer Learning (TL) framework for the recognition of these immunogold particles. Immunogold particles are part of a high-magnification method for the selective localization of biological molecules at the subcellular level only visible through Electron Microscopy. The number of immunogold particles in the cell walls allows the assessment of the differences in their compositions providing a tool to analise the quality of different plants. For its quantization one requires a laborious manual labeling (or annotation) of images containing hundreds of particles. The system that is proposed in this paper can leverage significantly the burden of this manual task. For particle detection we use a LoG filter coupled with a SDA. In order to improve the recognition, we also study the applicability of TL settings for immunogold recognition. TL reuses the learning model of a source problem on other datasets (target problems) containing particles of different sizes. The proposed system was developed to solve a particular problem on maize cells, namely to determine the composition of cell wall ingrowths in endosperm transfer cells. This novel dataset as well as the code for reproducing our experiments is made publicly available. We determined that the LoG detector alone attained more than 84\% of accuracy with the F-measure. Developing immunogold recognition with TL also provided superior performance when compared with the baseline models augmenting the accuracy rates by 10\%.