RESUMEN
BACKGROUND: Dengue fever is a re-emerging viral disease commonly occurring in tropical and subtropical areas. The clinical features and abnormal laboratory test results of dengue infection are similar to those of other febrile illnesses; hence, its accurate and timely diagnosis for providing appropriate treatment is difficult. Delayed diagnosis may be associated with inappropriate treatment and higher risk of death. Early and correct diagnosis can help improve case management and optimise the use of resources such as hospital staff, beds, and intensive care equipment. The goal of this study was to develop a predictive model to characterise dengue severity based on early clinical and laboratory indicators using data mining and statistical tools. METHODS: We retrieved data from a study of febrile illness in children at Angkor Hospital for Children, Cambodia. Of 1225 febrile episodes recorded, 198 patients were confirmed to have dengue. A classification and regression tree (CART) was used to construct a predictive decision tree for severe dengue, while logistic regression analysis was used to independently quantify the significance of each parameter in the decision tree. RESULTS: A decision tree algorithm using haematocrit, Glasgow Coma Score, urine protein, creatinine, and platelet count predicted severe dengue with a sensitivity, specificity, and accuracy of 60.5%, 65% and 64.1%, respectively. CONCLUSIONS: The decision tree we describe, using five simple clinical and laboratory indicators, can be used to predict severe cases of dengue among paediatric patients on admission. This algorithm is potentially useful for guiding a patient-monitoring plan and outpatient management of fever in resource-poor settings.
Asunto(s)
Toma de Decisiones Clínicas/métodos , Árboles de Decisión , Dengue/diagnóstico , Índice de Severidad de la Enfermedad , Adolescente , Niño , Preescolar , Femenino , Humanos , Lactante , Recién Nacido , Modelos Logísticos , Masculino , Valor Predictivo de las Pruebas , Estudios Retrospectivos , Sensibilidad y Especificidad , Dengue Grave/diagnósticoRESUMEN
BACKGROUND: The risk of disease is a key factor that travelers have identified when planning to travel abroad, as many people are concerned about getting sick. Mobile devices can be an effective means for travelers to access information regarding disease prevalence in their planned destinations, potentially reducing the risk of exposure. METHODS: We developed a mobile app, ThaiEpidemics, using cross-platform technology to provide information about disease prevalence and status for travelers to Thailand. We aimed to assess the app's usability in terms of engagement, search logs, and effectiveness among target users. The app was developed using the principle of mobile application development life cycle, for both iOS and Android. As its data source, the app used weekly data from national disease-surveillance reports. We conduced our study among visitors to the Travel Clinic in the Hospital for Tropical Diseases, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand. The participants were informed that the app would collect usage and search logs related to their queries. After the second log-in, the app prompted participants to complete an e-survey regarding their opinions and preferences related to their awareness of disease prevalence and status. RESULTS: We based our prototype of ThaiEpidemics on a conceptualized framework for visualizing the distribution of 14 major diseases of concern to tourists in Southeast Asia. The app provided users with functions and features to search for and visualize disease prevalence and status in Thailand. The participants could access information for their current location and elsewhere in the country. In all, 83 people installed the app, and 52 responded to the e-survey. Regardless of age, education, and continent of origin, almost all e-survey respondents believed the app had raised their awareness of disease prevalence and status when travelling. Most participants searched for information for all 14 diseases; some searched for information specifically about dengue and malaria. CONCLUSIONS: ThaiEpidemics is evidently potentially useful for travelers. Should the app be adopted for use by travelers to Thailand, it could have an impact on wider knowledge distribution, which might result in decreased exposure, increased prophylaxis, and therefore a potential decreased burden on the healthcare system. For app developers who are developing/implementing this kind of app, it is important to address standardization of the data source and users' concerns about the confidentiality and safety of their mobile devices.
RESUMEN
BACKGROUND: Breastfeeding is proven to have lasting health benefits for both mothers and infants; however, 6-month exclusive breastfeeding rate remains below 20% in Thailand. Although the number of research literature and commercial apps for breastfeeding women is significantly growing, they are country-specific and restricted to English-speaking users. There exists a major knowledge gap on how mobile health apps could support breastfeeding in Thailand. To address these gaps, MoomMae has been developed with the intention to support Thai women in breastfeeding outside of their homes and in keeping their feeding records. OBJECTIVE: The aim of this study was to evaluate the usability and usefulness of MoomMae, a mobile phone app designed to support breastfeeding women. METHODS: Our study was reviewed and approved by Thailand's National Science and Technology Development Agency (NSTDA) ethics committee. A total of 21 breastfeeding women with at least one Android phone or tablet were recruited via convenience and snowball sampling. The study process for each participant was as follows: the participant was requested to attend a preuse interview and given the app to use for 4 weeks. Following this period, a postuse interview was conducted to examine the usability and usefulness of the app. Both sessions were held individually and audiorecorded for qualitative analysis. RESULTS: The mean scores of usability and usefulness from the postuse survey were 4.33 (SD 0.87; range 1-5) and 4.60 (SD 0.74; range 2-5). Our qualitative analysis revealed a total of 137 feedbacks: 71 related to usability and 66 associated with usefulness. A further sentimental analysis showed that comments on usability were generally negative (59 negative, 11 positive, and 1 neutral), and comments on usefulness were relatively positive (56 positive, 9 negative, and 1 neutral). We discovered 26 unique design issues and proposed recommendations for future improvement. CONCLUSIONS: Our usability and usefulness assessment of MoomMae demonstrated that MoomMae has a great potential to be a useful self-management tool for breastfeeding mothers in Thailand. The qualitative analysis suggested that the app is supportive of breastfeeding on demand, but the flow and inputs of the app should be redesigned to be more intuitive. For future implementations, the most desirable feature is a pump-reminding notification system.