Thiago Martini da Costa

Results of a randomized controlled trial to assess the effects of a mobile SMS-based intervention on treatment adherence in HIV/AIDS-infected Brazilian women and impressions and satisfaction with respect to incoming messages

OBJECTIVE To assess whether a warning system based on mobile SMS messages increases the adherence of HIV-infected Brazilian women to antiretroviral drug-based treatment regimens and their impressions and satisfaction with respect to incoming messages. DESIGN A randomized controlled trial was conducted from May 2009 to April 2010 with HIV-infected Brazilian women. All participants (n=21) had a monthly multidisciplinary attendance; each participant was followed over a 4-month period, when adherence measures were obtained. Participants in the intervention group (n=8) received SMS messages 30 min before their last scheduled time for a dose of medicine during the day. The messages were sent every Saturday and Sunday and on alternate days during the working week. Participants in the control group (n=13) did not receive messages. MEASUREMENTS Self-reported adherence, pill counting, microelectronic monitors (MEMS) and an interview about the impressions and satisfaction with respect to incoming messages. RESULTS The HIV Alert System (HIVAS) was developed over 7 months during 2008 and 2009. After the study period, self-reported adherence indicated that 11 participants (84.62%) remained compliant in the control group (adherence exceeding 95%), whereas all 8 participants in the intervention group (100.00%) remained compliant. In contrast, the counting pills method indicated that the number of compliant participants was 5 (38.46%) for the control group and 4 (50.00%) for the intervention group. Microelectronic monitoring indicated that 6 participants in the control group (46.15%) were adherent during the entire 4-month period compared to 6 participants in the intervention group (75.00%). According to the feedback of the 8 participants who completed the research in the intervention group, along with the feedback of 3 patients who received SMS for less than 4 months, that is, did not complete the study, 9 (81.81%) believed that the SMS messages aided them in treatment adherence, and 10 (90.90%) responded that they would like to continue receiving SMS messages. CONCLUSION SMS messaging can help Brazilian women living with HIV/AIDS to adhere to antiretroviral therapy for a period of at least 4 months. In general, the results are encouraging because the SMS messages stimulated more participants in the intervention group to be adherent to their treatment, and the patients were satisfied with the messages received, which were seen as reminders, incentives and signs of affection by the health clinic for a marginalized population.

Use of Medical Subject Headings (MeSH) in Portuguese for categorizing web-based healthcare content

INTRODUCTION Internet users are increasingly using the worldwide web to search for information relating to their health. This situation makes it necessary to create specialized tools capable of supporting users in their searches. OBJECTIVE To apply and compare strategies that were developed to investigate the use of the Portuguese version of Medical Subject Headings (MeSH) for constructing an automated classifier for Brazilian Portuguese-language web-based content within or outside of the field of healthcare, focusing on the lay public. METHODS 3658 Brazilian web pages were used to train the classifier and 606 Brazilian web pages were used to validate it. The strategies proposed were constructed using content-based vector methods for text classification, such that Naive Bayes was used for the task of classifying vector patterns with characteristics obtained through the proposed strategies. RESULTS A strategy named InDeCS was developed specifically to adapt MeSH for the problem that was put forward. This approach achieved better accuracy for this pattern classification task (0.94 sensitivity, specificity and area under the ROC curve). CONCLUSIONS Because of the significant results achieved by InDeCS, this tool has been successfully applied to the Brazilian healthcare search portal known as Busca Saúde. Furthermore, it could be shown that MeSH presents important results when used for the task of classifying web-based content focusing on the lay public. It was also possible to show from this study that MeSH was able to map out mutable non-deterministic characteristics of the web.