Multimodality Fusion Strategies in Eye Disease Diagnosis.

Multimodality fusion has gained significance in medical applications, particularly in diagnosing challenging diseases like eye diseases, notably diabetic eye diseases that pose risks of vision loss and blindness. Mono-modality eye disease diagnosis proves difficult, often missing crucial disease indicators. In response, researchers advocate multimodality-based approaches to enhance diagnostics. This study is a unique exploration, evaluating three multimodality fusion strategies-early, joint, and late-in conjunction with state-of-the-art convolutional neural network models for automated eye disease binary detection across three datasets: fundus fluorescein angiography, macula, and combination of digital retinal images for vessel extraction, structured analysis of the retina, and high-resolution fundus. Findings reveal the efficacy of each fusion strategy: type 0 early fusion with DenseNet121 achieves an impressive 99.45% average accuracy. InceptionResNetV2 emerges as the top-performing joint fusion architecture with an average accuracy of 99.58%. Late fusion ResNet50V2 achieves a perfect score of 100% across all metrics, surpassing both early and joint fusion. Comparative analysis demonstrates that late fusion ResNet50V2 matches the accuracy of state-of-the-art feature-level fusion model for multiview learning. In conclusion, this study substantiates late fusion as the optimal strategy for eye disease diagnosis compared to early and joint fusion, showcasing its superiority in leveraging multimodal information.

Functional size measurement of postnatal care apps: Morocco case study.

This study empirically evaluates the functionality coverage of 18 mobile applications (apps) for Postnatal care including a recently developed app in Morocco "Mamma&Baby". This evaluation is based on a comparison of the COSMIC _ISO 19,761 functional size of these apps with the score obtained in a previous evaluation based on functions extraction through a quality assessment questionnaire. This comparison allows to discuss the relationship between the functional size of the 18 apps, their users' ratings in the Play Store as well as the number of downloads. While for most of the assessed apps, there is only a small shift between the rankings of the two evaluations, for some apps, the shift is huge due to the number of features added and not covered by the score previously obtained. This study illustrates the use of COSMIC as an effective method for corrective or evolutionary updates since it takes into account all the functions and features of postnatal apps. For the "Mamma&Baby" app, efforts are required to boost the number of downloads, optimize its visibility, and attract the highest number of users.

Taking the pulse of a classroom with a gamified audience response system.

BACKGROUND AND OBJECTIVE: This paper presents an empirical study of a gamified mobile-based assessment approach that can be used to engage students and improve their educational performance. METHOD: A gamified audience response system called G-SIDRA was employed. Three gamification elements were used to motivate students in classroom activities: badges for achievements to increase engagement, points to indicate progression and performance in the subject and ranking for promoting competitiveness. A total of 90 medical students in a General and Descriptive Anatomy of the Locomotor System course were taught using G-SIDRA in the academic year 2019/2020. Smart bracelets were configured to collect heart rate measurements from 30 students with the aim of evaluating the impact of the gamification elements. The control group consisted of a sample of 110 students enrolled on the same course in the academic year 2016/2017 using non-gamified SIDRA. RESULTS: Statistically significant differences were found between multiple choice questions (MCQ) scores obtained by using SIDRA and G-SIDRA in the four experiments (U = 1.621,50, p < 0,01 for Exp1; U = 1.950,00, p < 0,01 for Exp2; U = 955,00, p < 0,01 for Exp3; U = 2.335,00, p < 0,01 for Exp4). In the students' final exam grades, statistically significant differences between students that used G-SIDRA as opposed to SIDRA (T(157) = 3.992; p = 0.044) were obtained. Concerning gamification elements, statistically significantly differences were found in comparing the pulse increases after and before the badge event in the four experiments (U = 2.484,00, p = 0,038 for Exp1; U = 2.109,50, p = 0,046 for Exp2; U = 1.790,50, p = 0,025 for Exp3; U = 1.557,0, p = 0,048 for Exp4). However, there are not statistically significant differences between the pulse increases after and before the ranking event in the four experiments. In a 5-point Likert-type scale, the students expressed satisfaction with G-SIDRA (M = 4.552) and thought the system helped to better understand both theoretical and practical concepts (M = 4.092). Their global assessment of the G-SIDRA platform was 4.471. CONCLUSIONS: Of the three gamification elements used in the study, only badge has an effect on heart rate. Better student responses and academic performance were achieved when using G-SIDRA. Nevertheless, more research is required to evaluate the impact of the gamification elements on the motivation, engagement and performance of students. Physiological measures are promising approaches for gamification elements evaluation.

Effects of Gamification on the Benefits of Student Response Systems in Learning of Human Anatomy: Three Experimental Studies.

This paper presents three experiments to assess the impact of gamifying an audience response system on the perceptions and educational performance of students. An audience response system called SIDRA (Immediate Audience Response System in Spanish) and two audience response systems with gamification features, R-G-SIDRA (gamified SIDRA with ranking) and RB-G-SIDRA (gamified SIDRA with ranking and badges), were used in a General and Descriptive Human Anatomy course. Students participated in an empirical study. In the academic year 2019-2020, a total of 90 students used RB-G-SIDRA, 90 students employed R-G-SIDRA in the academic year 2018-2019, and 92 students used SIDRA in the academic year 2017-2018. Statistically significant differences were found between final exam grades obtained by using RB-G-SIDRA and SIDRA, U = 39.211 adjusted p = 0.001 and RB-G-SIDRA and R-G-SIDRA U = 31.157 adjusted p = 0.015, thus finding strong evidence with respect to the benefit of the badges used in RB-G-SIDRA. Moreover, in the students' SIDRA systems scores, statistically significant differences were found between RB-G-SIDRA and SIDRA, U = -90.521 adjusted p < 0.001, and between R-G-SIDRA and SIDRA, U = -87.998 adjusted p < 0.001. Significant correlations between individual and team scores were also found in all of the tests in RB-G-SIDRA and G-SIDRA. The students expressed satisfaction, engagement, and motivation with SIDRA, R-G-SIDRA, and RB-G-SIDRA, thus obtaining a final average assessment of 4.28, 4.61, and 4.47 out of 5, respectively. Students perform better academically with gamified versus non-gamified audience response systems. Findings can be used to build a gamified adaptive learning system.

Mobile Technology for Improved Contraceptive Care in Morocco.

The fulfillment of unmet needs for contraception can help women reach their reproductive goals. Therefore, there is a growing concern worldwide about contraception and women's knowledge of making an advised choice about it. In this aspect, an outgrown number of apps are now available providing information concerning contraception whether it concerns natural contraception or modern contraception. However, vast amounts of these apps contain inaccurate sexual health facts and non-evidence-based information concerning contraception. On these bases, and in respect to: (1) the needs of women to effectively prevent unintended pregnancies while conducting a stress-free healthy lifestyle. (2) the World Health Organization (WHO) Medical Eligibility Criteria (MEC) for contraception's recommendations, and (3) the results/recommendations of a field study conducted in the reproductive health center 'Les Orangers' in Rabat to collect the app's requirements, we developed an evidence-based patient-centered contraceptive app referred to as 'MyContraception'. Thereafter, we conducted a set of functional tests to ensure that the MyContraception solution is performing as expected and is conform to the software functional requirements previously set before moving to non-functional requirements evaluation. Since customer's feedback is valuable to non-functional testing, we choose to evaluate potential users' feedback. Moreover, giving that mobile app testing is a complex process involving different skill sets, we elaborated a rigorous experimental design to conduct an empirical evaluation of the MyContraception solution, which will exhaustively assess the overall quality of this solution and examine its effects on improving the quality of patient-centered contraception care.

Reviewing Machine Learning and Image Processing Based Decision-Making Systems for Breast Cancer Imaging.

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods.

Missing data techniques in classification for cardiovascular dysautonomias diagnosis.

Missing data (MD) is a common and inevitable problem facing data mining (DM)-based decision systems in e-health since many medical historical datasets contain a huge number of missing values. Therefore, a pre-processing stage is usually required to deal with missing values before building any DM-based decision system. The purpose of this paper is to evaluate the impact of MD techniques on classification systems in cardiovascular dysautonomias diagnosis. We analyzed and compared the accuracy rates of four classification techniques: random forest (RF), support vector machines (SVM), C4.5 decision tree, and Naive Bayes (NB), using two MD techniques: deletion or imputation with k-nearest neighbors (KNN). A total of 216 experiments were therefore carried out using three missingness mechanisms (MCAR: missing completely at random, MAR: missing at random and NMAR: not missing at random), two MD techniques (deletion and KNN imputation), nine MD percentages from 10 to 90% over a dataset collected from the autonomic nervous system (ANS) unit of the University Hospital Avicenne in Morocco. The results obtained suggest that using KNN imputation rather than deletion enhances the accuracy rates of the four classifiers. Moreover, the MD percentages have a negative impact on the performance of classification techniques regardless of the MD mechanisms and MD techniques used. In fact, the accuracy rates of the four classifiers decrease as the MD percentage increases. Graphical abstract.

A mapping study of ensemble classification methods in lung cancer decision support systems.

Achieving a high level of classification accuracy in medical datasets is a capital need for researchers to provide effective decision systems to assist doctors in work. In many domains of artificial intelligence, ensemble classification methods are able to improve the performance of single classifiers. This paper reports the state of the art of ensemble classification methods in lung cancer detection. We have performed a systematic mapping study to identify the most interesting papers concerning this topic. A total of 65 papers published between 2000 and 2018 were selected after an automatic search in four digital libraries and a careful selection process. As a result, it was observed that diagnosis was the task most commonly studied; homogeneous ensembles and decision trees were the most frequently adopted for constructing ensembles; and the majority voting rule was the predominant combination rule. Few studies considered the parameter tuning of the techniques used. These findings open several perspectives for researchers to enhance lung cancer research by addressing the identified gaps, such as investigating different classification methods, proposing other heterogeneous ensemble methods, and using new combination rules. Graphical abstract Main features of the mapping study performed in ensemble classification methods applied on lung cancer decision support systems.

Mobile health applications for postnatal care: Review and analysis of functionalities and technical features.

BACKGROUND: Providing a continuum of care from antenatal, childbirth and postnatal period results in reduced maternal and neonatal morbidity and mortality. Timely, high quality postnatal care is crucial for maximizing maternal and newborn health. In this vein, the use of postnatal mobile applications constitutes a promising strategy. METHODS: A Systematic Literature Review (SLR) protocol was adopted to perform the selection, data extraction and functional evaluation of the available postnatal apps on iOS and Android platforms. The analysis of the functionalities and technical features of the apps selected was performed according to a 37-items assessment questionnaire developed on the basis of the scientific literature of postnatal care and a preliminary analysis of available postnatal apps RESULTS: A total of 48 postnatal apps were retrieved from the app repositories of the iOS and Android platforms. The results of the functional content analysis show that the postnatal apps selected relatively achieved low scores owing to the complexity and the ramification of the postnatal care. CONCLUSIONS: The present study helps in identifying areas related to the postnatal care that require further endeavors to be properly addressed. It also provides directions for developers to leverage the advancement and innovation on mobile technology to build complete and well-suited postnatal apps.

Applying trans-theoretical model for blood donation among Spanish adults: a cross-sectional study.

BACKGROUND: Relying solely on altruistic appeals may fail to fulfil the increasing demand for blood supplies. Current research has largely been attempted to determine and understand motives that serve as blood donation drivers. The Trans-Theoretical Model of behaviour change (TTM) can be used to conceptualise the process of intentional blood donation behaviour. METHODS: A cross sectional survey of Spanish adults was conducted. The final sample consisted of 504 individuals who were administered a self-report questionnaire including the measures of demographic characteristics, Stages of Change, Processes of Change, Self-efficacy and Decisional Balance. Data were analysed by frequency analysis, MANOVA/ANOVA and correlation analysis. RESULTS: Findings indicated that most of the behavioural and cognitive processes of change, self-efficacy and physical cons differentiated participants across the stages of change of blood donation. In contrast, eligibility cons and pros were less influential in stage transitions. Furthermore, significant correlations were observed between TTM constructs except for the physical cons and the processes of change. CONCLUSIONS: The present study extensively supports and replicates the applicability of the TTM to blood donation behaviour change and offers important implications for the development of effective stage-matched interventions to increase blood donation.

Sizing Prenatal mPHRs using COSMIC Measurement Method.

This paper presents an empirical evaluation of the COSMIC Function Points method (e.g., ISO 19761) through measuring the functional size of 33 prenatal mobile Personal Health Records (mPHRs) apps. This evaluation compares the functional size of each mobile app measured using the COSMIC method to the score of the app obtained in a previous evaluation that relied on functions extraction using a quality assessment questionnaire. It includes as well an investigation of the relationships between the functional sizes of these apps, their ratings in the apps stores, as well as the number of installs. As results, it was noticed that there is a considerable shift between the rankings of the functional sizes and the functionality scores obtained in the opinion-based questionnaire, for most of the apps assessed. Moreover, the study of the relationship between the functional sizes and the ratings, as well as the number of installs indicated that these variables are not linked, since they are impacted by external factors. The findings support the use of the COSMIC method for these apps in regard to measuring the functional size for further updates or improvements, which can also help developers to have an overview about the existing apps on the market and compare between them. Moreover, COSMIC is more effective since it covers all the features and functionalities of prenatal mPHRs.

Reviewing ensemble classification methods in breast cancer.

CONTEXT: Ensemble methods consist of combining more than one single technique to solve the same task. This approach was designed to overcome the weaknesses of single techniques and consolidate their strengths. Ensemble methods are now widely used to carry out prediction tasks (e.g. classification and regression) in several fields, including that of bioinformatics. Researchers have particularly begun to employ ensemble techniques to improve research into breast cancer, as this is the most frequent type of cancer and accounts for most of the deaths among women. OBJECTIVE AND METHOD: The goal of this study is to analyse the state of the art in ensemble classification methods when applied to breast cancer as regards 9 aspects: publication venues, medical tasks tackled, empirical and research types adopted, types of ensembles proposed, single techniques used to construct the ensembles, validation framework adopted to evaluate the proposed ensembles, tools used to build the ensembles, and optimization methods used for the single techniques. This paper was undertaken as a systematic mapping study. RESULTS: A total of 193 papers that were published from the year 2000 onwards, were selected from four online databases: IEEE Xplore, ACM digital library, Scopus and PubMed. This study found that of the six medical tasks that exist, the diagnosis medical task was that most frequently researched, and that the experiment-based empirical type and evaluation-based research type were the most dominant approaches adopted in the selected studies. The homogeneous type was that most widely used to perform the classification task. With regard to single techniques, this mapping study found that decision trees, support vector machines and artificial neural networks were those most frequently adopted to build ensemble classifiers. In the case of the evaluation framework, the Wisconsin Breast Cancer dataset was the most frequently used by researchers to perform their experiments, while the most noticeable validation method was k-fold cross-validation. Several tools are available to perform experiments related to ensemble classification methods, such as Weka and R Software. Few researchers took into account the optimisation of the single technique of which their proposed ensemble was composed, while the grid search method was that most frequently adopted to tune the parameter settings of a single classifier. CONCLUSION: This paper reports an in-depth study of the application of ensemble methods as regards breast cancer. Our results show that there are several gaps and issues and we, therefore, provide researchers in the field of breast cancer research with recommendations. Moreover, after analysing the papers found in this systematic mapping study, we discovered that the majority report positive results concerning the accuracy of ensemble classifiers when compared to the single classifiers. In order to aggregate the evidence reported in literature, it will, therefore, be necessary to perform a systematic literature review and meta-analysis in which an in-depth analysis could be conducted so as to confirm the superiority of ensemble classifiers over the classical techniques.

Software Development Effort Estimation Using Regression Fuzzy Models.

Software effort estimation plays a critical role in project management. Erroneous results may lead to overestimating or underestimating effort, which can have catastrophic consequences on project resources. Machine-learning techniques are increasingly popular in the field. Fuzzy logic models, in particular, are widely used to deal with imprecise and inaccurate data. The main goal of this research was to design and compare three different fuzzy logic models for predicting software estimation effort: Mamdani, Sugeno with constant output, and Sugeno with linear output. To assist in the design of the fuzzy logic models, we conducted regression analysis, an approach we call "regression fuzzy logic." State-of-the-art and unbiased performance evaluation criteria such as standardized accuracy, effect size, and mean balanced relative error were used to evaluate the models, as well as statistical tests. Models were trained and tested using industrial projects from the International Software Benchmarking Standards Group (ISBSG) dataset. Results showed that data heteroscedasticity affected model performance. Fuzzy logic models were found to be very sensitive to outliers. We concluded that when regression analysis was used to design the model, the Sugeno fuzzy inference system with linear output outperformed the other models.

Improving Accessibility for People with Disabilities: A Case Study on Inclusive Beach Tourism.

Disability is an important area in biomedical engineering. But research on disability should not only focus on the healthcare aspects, but also on the integration of people with disabilities in the cultural and social contexts, such as the existence of architectural elements that prevent the use of common public services. The present research aims to improve accessibility and enjoyment of people with physical and motor disabilities to the tourist resources of the area of interest. We present a case study focused on the beaches of the Region of Murcia, Spain. Both the architectural and technological aspects of accessibility are analyzed. From the architectural point of view, the method includes the definition of the parameters of accessibility, and the features required for the equipment according to the local and national regulations. From the technological point of view, the tools and requirements necessary to develop the system are presented.

Using ensemble classification methods in lung cancer disease.

This paper presents an overview of the use of ensemble classification methods in the lung cancer disease. An analysis is carried out according to seven aspects: publication trends, channels and venues; medical tasks tackled; ensemble types proposed; single techniques used to construct the ensemble methods; rules used to draw the output of the ensemble; datasets used to build and evaluate the ensemble methods; and tools used. The application of ensemble methods in lung cancer disease started in 2003. The diagnosis task was the most tackled one by researchers. Furthermore, the homogeneous ensembles were the most frequent in the literature, and decision tree techniques were the most adopted ones for constructing ensembles. Several datasets related to the lung cancer disease were used to build and assess the ensemble methods. The most used tool was Weka. To conclude, some recommendations for future research are: tackle the medical tasks not investigated in the literature by means of ensemble methods; investigate other classification methods; propose other heterogeneous ensemble methods; and use other combination rules.

Homogeneous and heterogeneous ensemble classification methods in diabetes disease: a review.

This paper explores the use of ensemble classification methods in the context of the diabetes disease. An analysis was carried out that formulates and answers seven research questions: publication trends, channels and venues; medical tasks undertaken; ensemble types proposed; single techniques used to construct the ensemble methods; rules used to draw the output of the ensemble; datasets used to build and evaluate the ensemble methods; and tools used. A total of 107 papers were chosen after a study selection process. Ensemble methods were applied to diabetes in 2003 for the first time. All medical tasks related to the diabetes disease were investigated, and the diagnosis task was the most frequently addressed activity by means of ensemble methods. The homogeneous ensembles were the most common in the literature. Moreover, decision trees and support vector machines were the most used techniques to build homogeneous and heterogeneous ensembles, respectively. The most frequently found combiner was the majority voting rule. Our findings suggest that ensemble classification methods yield better accuracy than single classifiers. This statement, however, requires an aggregation of the evidence reported in the literature by means of a systematic literature review.

Systematic mapping study of data mining-based empirical studies in cardiology.

Data mining provides the methodology and technology to transform huge amount of data into useful information for decision making. It is a powerful process to extract knowledge and discover new patterns embedded in large data sets. Data mining has been increasingly used in medicine, particularly in cardiology. In fact, data mining applications can greatly benefits all parts involved in cardiology such as patients, cardiologists and nurses. This article aims to perform a systematic mapping study so as to analyze and synthesize empirical studies on the application of data mining techniques in cardiology. A total of 142 articles published between 2000 and 2015 were therefore selected, studied and analyzed according to the four following criteria: year and channel of publication, research type, medical task and empirical type. The results of this mapping study are discussed and a list of recommendations for researchers and cardiologists is provided.

Evaluating the Privacy Policies of Mobile Personal Health Records for Pregnancy Monitoring.

A mobile personal health record (mPHR) for pregnancy monitoring allows the pregnant woman to track and manage her personal health data. However, owing to the privacy and security issues that may threaten the exchange of this sensitive data, a privacy policy should be established. The aim of this study is to evaluate the privacy policies of 19 mPHRs for pregnancy monitoring (12 for iOS and 7 for Android) using a template covering the characteristics of privacy, security, and standards and regulations. The findings of this study show that none of the privacy policies evaluated entirely comply with the characteristics studied. The developers of mPHRs for pregnancy monitoring are, therefore, requested to improve and pay more attention to the structure and the content of the privacy policies of their apps.

Reusable Software Usability Specifications for mHealth Applications.

One of the key factors for the adoption of mobile technologies, and in particular of mobile health applications, is usability. A usable application will be easier to use and understand by users, and will improve user's interaction with it. This paper proposes a software requirements catalog for usable mobile health applications, which can be used for the development of new applications, or the evaluation of existing ones. The catalog is based on the main identified sources in literature on usability and mobile health applications. Our catalog was organized according to the ISO/IEC/IEEE 29148:2011 standard and follows the SIREN methodology to create reusable catalogs. The applicability of the catalog was verified by the creation of an audit method, which was used to perform the evaluation of a real app, S Health, application created by Samsung Electronics Co. The usability requirements catalog, along with the audit method, identified several usability flaws on the evaluated app, which scored 83%. Some flaws were detected in the app related to the navigation pattern. Some more issues related to the startup experience, empty screens or writing style were also found. The way a user navigates through an application improves or deteriorates user's experience with the application. We proposed a reusable usability catalog and an audit method. This proposal was used to evaluate a mobile health application. An audit report was created with the usability issues identified on the evaluated application.

E-health internationalization requirements for audit purposes.

BACKGROUND AND OBJECTIVE: In the 21st century, e-health is proving to be one of the strongest drivers for the global transformation of the health care industry. Health information is currently truly ubiquitous and widespread, but in order to guarantee that everyone can appropriately access and understand this information, regardless of their origin, it is essential to bridge the international gap. The diversity of health information seekers languages and cultures signifies that e-health applications must be adapted to satisfy their needs. METHODS: In order to achieve this objective, current and future e-health programs should take into account the internationalization aspects. This paper presents an internationalization requirements specification in the form of a reusable requirements catalog, obtained from the principal related standards, and describes the key methodological elements needed to perform an e-health software audit by using the internationalization knowledge previously gathered. RESULTS: S Health, a relevant, well-known Android application that has more than 150 million users in over 130 countries, was selected as a target for the e-health internationalization audit method and requirements specification presented above. This application example helped us to put into practice the proposal and show that the procedure is realistic and effective. CONCLUSIONS: The approach presented in this study is subject to continuous improvement through the incorporation of new knowledge originating from additional information sources, such as other standards or stakeholders. The application example is useful for early evaluation and serves to assess the applicability of the internationalization catalog and audit methodology, and to improve them. It would be advisable to develop of an automated tool with which to carry out the audit method.