Short Text Messages Research Articles

Impact of an SMS intervention to support type 2 diabetes self-management: DiabeText clinical trial.

Complications arising from uncontrolled Type 2 Diabetes Mellitus (T2DM) pose a significant burden on individuals' well-being and healthcare resources. Digital interventions may play a key role in mitigating such complications by supporting patients to adequately self-manage their condition. To assess the impact of DiabeText, a new theory-based, patient-centered, mobile health intervention integrated with electronic health records to send tailored short text messages to support T2DM self-management. Pragmatic, Phase III, 12-month, two-arm randomized clinical trial with T2DM primary care patients in Spain. 742 participants with suboptimal glycemic control (HbA1c>7.5) were randomly allocated to a control (usual care) or intervention (DiabeText) group. The DiabeText group received, in addition to usual care, 165 messages focused on healthy lifestyle and medication adherence. glycated hemoglobin (HbA1c). medication possession ratio, quality of life (EQ-5D-5L), diabetes self-efficacy (DSES); and self-reported adherence to medication, Mediterranean diet (MEDAS-14), and physical activity (IPAQ). Over the 12-month period, we observed no significant differences in HbA1c between the intervention and the control groups (Beta=-0.025 (-0.198 to 0.147; p=0.772)). In comparison with the control group, the DiabeText group showed significant (p<0.05) improvements in self-reported medication adherence (OR=1.4; 95%CI: 1.0 to 1.9), DSES (Cohen's d=0.35), and EQ5D-5L (Cohen's d=0.18) scores; but not in the rest of secondary outcomes. DiabeText successfully improved quality of life, diabetes self-management, and self-reported medication adherence in primary care patients with T2DM. Further research is needed to enhance its effects on physiological outcomes.

Who is Mobilized to Vote by Short Text Messages? Evidence from a Nationwide Field Experiment with Young Voters

AbstractUsing a large randomized controlled trial and rich individual-level data on eligible voters and their household members, we evaluate how get-out-the-vote (GOTV) appeals affect inequalities in voting, transmit from treated to untreated individuals within households, and how the transmission of voting decisions through family networks influences inequalities in voting. We find that receiving a text message reminder before the Finnish county elections in 2022 mobilized mainly low-propensity voters. As a result, the GOTV intervention reduced existing social inequalities in voting within the target group of young voters. We remarkably find that over 100% of the direct treatment effect spilled over to untreated household members. These spillovers reduced inequality in political participation among the older voters who were not part of the target group. Overall, our results exemplify how randomized controlled trials with a limited focus on the analysis of individuals in the treatment and control groups alone may lead to misestimating the compositional effects of get-out-the-vote interventions.

Impact of mobile health technologies on human papillomavirus vaccination uptake among mothers of unvaccinated girls aged 9-14 years in Lagos, Nigeria (mHealth-HPVac): Study protocol of a randomised controlled trial.

Despite the availability of effective vaccines, human papillomavirus (HPV) vaccine uptake remains low in most resource-limited settings including Nigeria. Mobile health technology (mHealth) may empower patients to control their health, reduce inequalities, and improve the uptake of HPV vaccination. The "mHealth-HPVac" study will assess the effects of mHealth using short text messages on the uptake of HPV vaccination among mothers of unvaccinated girls aged 9-14 years and also determine the factors influencing the uptake of HPV vaccination among these mothers. This protocol highlights a randomised controlled trial involving women aged 25-65 years who will be enrolled on attendance for routine care at the General Outpatient clinics of Lagos University Teaching Hospital, Lagos, Nigeria between July and December 2024. At baseline, n=224 women will be randomised to either a short text message or usual care (control) arm. The primary outcome is vaccination of the participant's school-age girl(s) at any time during the 6 months of follow-up. The associations between any two groups of continuous variables will be tested using the independent sample t-test (normal distribution) or the Mann-Whitney U test (skewed data) and that of two groups of categorical variables with Chi-square (X2) or Fisher's exact test where appropriate. Using the multivariable binary logistic regression model, we will examine the effects of all relevant sociodemographic and clinical variables on HPV vaccination uptake among mothers of unvaccinated but vaccine-eligible school-age girls. Statistical significance will be defined as A P<0.05. The mHealth-Cervix study will evaluate the impact of mobile technologies on HPV vaccination uptake among mothers of unvaccinated but vaccine-eligible school-age girls in Lagos, Nigeria as a way of contributing to the reduction in the wide disparities in cervical cancer incidence through primary prevention facilitated using health promotion to improve HPV vaccination uptake. PACTR202406727470443 (6th June 2024).

On the use of SMS messages in teaching foreign language communication, with a focus on German as a Foreign Language

Acquiring proficiency in conveying information through short text messages is clearly connected with the changes that have taken places in the world around us. It should, therefore, find its reflection in the teaching of foreign languages, especially in language studies. It is worth noting that SMS messages, as a means of communication, can be an interesting and useful topic for students who can no longer (or perhaps do not want to) function without a smartphone. The considerations presented here are rooted in educational practice and provide a description of a project aimed at developing proficiency in understanding and creating text messages in practical German language classes. Features included writing with correct spelling, the style of SMS messages, the choice of linguistic elements and the use of abbreviations, both in German and English. The paper also includes examples of exercises and discusses the impact of SMS messages on the progress and quality of German language classes. The project presented aims to demonstrate the relevance of introducing such texts and their didactic value in foreign language teaching. It offers sample solutions that can be employed in the process of developing writing skills in a foreign language and suggests how SMS messages can be used as a communication tool in foreign language classes to broaden and reinforce vocabulary related to mobile phones.

Impact of mobile health technologies on human papillomavirus vaccination uptake among mothers of unvaccinated girls aged 9–14 years in Lagos, Nigeria (mHealth-HPVac): study protocol of a randomised controlled trial

BackgroundDespite the availability of effective vaccines, human papillomavirus (HPV) vaccine uptake remains low in most resource-limited settings including Nigeria. Mobile health technology (mHealth) has the potential to empower patients to manage their health, reduce health disparities, and enhance the uptake of HPV vaccination.AimThe “mHealth-HPVac” study will assess the effects of mHealth using short text messages on the uptake of HPV vaccination among mothers of unvaccinated girls aged 9–14 years and also determine the factors influencing the uptake of HPV vaccination among these mothers.MethodsThis protocol highlights a randomised controlled trial involving women aged 25–65 years who will be enrolled on attendance for routine care at the General Outpatient clinics of Lagos University Teaching Hospital, Lagos, Nigeria between July and December 2024. At baseline, n = 123 women will be randomised to either a short text message or usual care (control) arm. The primary outcome is vaccination of the participant’s school-age girl(s) at any time during the 6 months of follow-up. The associations between any two groups of continuous variables will be assessed using the independent sample t-test for normally distributed data, or the Mann-Whitney U test for skewed data. For two groups of categorical variables, the Chi-square (X2) test or Fisher’s exact test will be used, as appropriate. Using the multivariable binary logistic regression model, we will examine the effects of all relevant sociodemographic and clinical variables on HPV vaccination uptake among mothers of unvaccinated but vaccine-eligible school-age girls. Statistical significance will be reported as P < 0.05.DiscussionThe mHealth-Cervix study will evaluate the impact of mobile technologies on HPV vaccination uptake among mothers of unvaccinated but vaccine-eligible school-age girls in Lagos, Nigeria as a way of contributing to the reduction in the wide disparities in cervical cancer incidence through primary prevention facilitated using health promotion to improve HPV vaccination uptake.RegistrationPACTR202406727470443 (6th June 2024).

Conducting a diabetes mellitus prevention trial in women with GDM in Pakistan: a feasibility study

BackgroundWomen with gestational diabetes mellitus (GDM) are at a greater risk of developing type 2 diabetes mellitus (T2DM) than women without GDM. Despite this elevated risk, few trials on the prevention of T2DM among South Asian women with GDM have been reported. Therefore, this study aimed to assess the feasibility of conducting a diabetes prevention program on women with a history of GDM to inform the development of a contextually relevant definitive trial.MethodsUsing a randomized controlled trial, women with GDM (n = 180) who delivered at the study hospitals (one public and one private teaching hospital, Karachi) with fasting blood glucose levels < 120 mg/dl at 6 weeks postpartum were randomized to the intervention (n = 88) or control arms (n = 92). Women in the intervention group received individualized home-based educational sessions from trained community health workers at 0, 1, 3, 6, and 9 months. In addition, they received short text messages, prerecorded messages, and printed educational material (calendars and pamphlets) for reinforcement. The intervention was centered on equipping women with knowledge, skills, and confidence to eat a healthy diet rich in fruits, vegetables, and low-fat dairy products and perform regular physical activity based on walking and household chores to reduce weight (up to 5% of their initial body weight). Women in the control arm received standard care. The feasibility outcomes of the study included screening, recruitment, and retention rates and in-depth interviews at 6 months post-intervention to explore women’s experiences with the intervention. Descriptive analysis and thematic analysis were performed.ResultsOf the 324 women screened during the antenatal care visits and after delivery, 255 (78.7%) were contactable 6 weeks postpartum, and 180 (70.6%) were eligible and randomized to intervention (n = 88) and control (n = 92) groups. Loss to follow-up in the intervention and control arms was 22.7% (n = 20/88) and 18.5% (n = 17/92), respectively. Women expressed satisfaction with home-based counseling and follow-up visits, text message reminders, and printed material in the form of a calendar through our qualitative interviews.ConclusionsHome-based lifestyle modification intervention augmented with text messages and printed material is feasible. However, to evaluate the intervention’s effectiveness, a larger trial is warranted to assess its long-term impact on diabetes prevention.Trial registrationISRCTN, ISRCTN11387113. Registered 5 December 2017—retrospectively registered.

Survey Paper on Implementation of Abusive Language Detection in Chatting Application

Communication has become stronger due to exponential increase in the usage of social media in the last few years. People use them for communicating with friends, finding new friends, updating any important activities of their life, etc. Due to their growing popularity and deep reach, these mediums are infiltrated with huge Volume of spam messages. Spam message randomly sent to multiple addressees by all sorts of groups, but mostly lazy advertisers and criminals who wish to lead you to phishing sites. In this we are using various machine learning techniques for detecting spam in the short text messages and also Google vision API for detecting spam images. Key Words: Spam Filtration, Google Vision API, OWASP, Naive baise classifier, Dictionary Based Algorithm

A randomised controlled trial to evaluate the effectiveness of a culture and disease-specific, patient-centric multi-component tobacco cessation intervention package for the patients attending non-communicable disease clinics in Punjab, India

Background Developing an infrastructure to support tobacco cessation through existing systems and resources is crucial for ensuring the greatest possible access to cessation services. The present study aims to evaluate the effectiveness of a newly developed multi-component cessation among tobacco users in Non- Communicable Disease (NCD) clinics, functioning under the National Programme for Prevention & Control of Cancer, Diabetes, Cardiovascular Diseases, & Stroke (NPCDCS) of the Government of India. Methods The intervention package consisting of culture- and disease-specific four face-to-face counselling sessions, pamphlets, and short text messages (bilingual) with follow-ups at 3rd, 6th, and 9th months with an endline assessment at 12th months was delivered to the intervention arm of the two-arm- parallel group randomised controlled trial at two selected NCD clinics. Self-reported seven-day abstinence, frequency of use, expenditure in seven days at each follow-up, FTND score, stage of change and plasma cotinine values were assessed at baseline, follow-ups, and endline (using Liquid Chromatography –Mass Spectrometry), as applicable. Results The intervention arm reported a significantly more reduction in self-reported frequency of tobacco use at 6 months (mean: 13.6, 95% CI (7.8–19.4)), 9 months (mean: 20.3, 95% CI (12.2–28.4)) and 12 months (mean: 18.7, 95% CI (8.7–28.7)). The plasma cotinine concentration at endline in the intervention arm was statistically significantly lower than the baseline concentration. Conclusion Strengthening existing health systems is crucial for offering cessation support in the resource-restraint setting of LMICs to assist in quitting sustainably.

Survey Paper on Implementation of Abusive Language Detection in Chatting Application

Communication has become stronger due to exponential increase in the usage of social media in the last few years. People use them for communicating with friends, finding new friends, updating any important activities of their life, etc. Due to their growing popularity and deep reach, these mediums are infiltrated with huge volume of spam messages. Spam message randomly sent to multiple addressees by all sorts of groups, but mostly lazy advertisers and criminals who wish to lead you to phishing sites. In this we are using various machine learning techniques for detecting spam in the short text messages and also Google vision API for detecting spam images. Key Words: Spam Filtration, Google Vision API, OWASP, Naive baise classifier, Dictionary Based Algorithm

A state-of-the-art universal machine learning framework for decoding suspect coded messages

This proposed framework aims to mitigate global terrorist threats, suspicious activities, and legal violations by introducing an innovative system that monitors encrypted short-text messages across instant messaging programs. In the current landscape, criminals, terrorists, and clandestine entities extensively employ encrypted messages for illicit endeavours on a global scale. Despite the escalating use of encrypted messages on social media platforms, a comprehensive solution for combating online crime is notably absent.The outlined framework addresses this gap by employing a cryptographic system that integrates semantic web ontology, a Predefined Dataset, and machine learning technology for encryption, decryption, and cryptanalysis. A key feature is the framework's ability to predict potential crimes by analyzing blogs for suspicious terminology conveyed through coded information. The identified information is then promptly communicated to law enforcement agencies, thereby alleviating the burden on numerous security entities and offering an efficient strategy against global crime.What sets this proposed framework apart is its unique utilization of encrypted text, a dimension that has remained unexplored in previous studies. The cohesive integration of its components expedites the process of anticipating crime types and significantly reduces the incidence of encrypted crimes on a global scale.

The effectiveness of short mobile phone text message reminders compared to usual care on medication adherence in patients with hypertension: a systematic review protocol

BackgroundPoor adherence to long-term medication increases the risk of morbidity and mortality and decreases the quality of life of patients with hypertension. One strategy to improve treatment adherence is to use a short text message reminder. Although evidence indicates that such programs increase medication adherence, the extent of their effectiveness and translation into clinical practice needs to be better documented. Our systematic review will collect and analyze the available evidence for clinical practice implementation. This systematic review aimed to evaluate the effectiveness of short mobile phone text message reminders versus usual/standard care for medication adherence in patients with hypertension.MethodsThis review will include and summarize evidence from randomized controlled trials. Adults (age > 18 years) with hypertension. The comparator group received either the usual care or standard care. It encompasses standard medical care for patients not participating in a structured and supervised intervention program such as a telemedicine program.We will include studies that assess the effectiveness of short mobile phone text message reminders in improving medication adherence in patients with hypertension compared to usual care. We will search the following databases: PubMed, EMBASE, CINAHL, SCOPUS, Web of Science, Cochrane Library Central Register of Controlled Trials, and Cochrane Library. We will include studies published in English. Furthermore, we will consider studies published from the inception of the database until April 20, 2024. At least two reviewers will independently conduct study selection, data extraction, and quality assessment. A third reviewer will determine and resolve discrepancies. We will conduct a quality assessment using the ROBIS 2 critical appraisal checklist. At least two independent reviewers will crosscheck the data synthesis.DiscussionWe expect this review to provide current evidence for future studies and clinical practice concerning the impact of mobile phone text message reminders on medication adherence issues. We will publish our results in a peer-reviewed journal for publication.Systematic review registrationPROSPERO CRD42023391236.

Supporting people with type 2 diabetes in effective use of their medicine through mobile health technology integrated with clinical care (SuMMiT-D pilot): results of a feasibility randomised trial

BackgroundThe purpose of this 6-month intervention pilot feasibility randomised trial was to test sending brief messages using mobile phones to promote self-management through taking medication as prescribed to people with type 2 diabetes. This was to inform the design and conduct of a future large-scale United Kingdom-based clinical trial and establish the feasibility of recruitment, the technology used, follow-up, and data collection.MethodsA multicentre individually randomised, controlled parallel group trial in primary care, recruiting adults (≥ 35 years) with type 2 diabetes in England. Consenting participants were randomly allocated to receive short message system text messages up to four times a week, or usual care, for a period of 6 months; messages contained behavioural change techniques targeting medication use. The primary outcome was the rate of recruitment to randomisation of participants to the trial with a planned rate of 22 participants randomised per month. The study also aimed to establish the feasibility of follow-up at 6 months, with an aim of retaining more than 80% of participants. Data, including patient-reported measures, were collected at baseline and the end of the 6-month follow-up period, and a notes review was completed at 24 months.ResultsThe trial took place between 26 November 2018 and 30 September 2019. In total 209 participants were randomly allocated to intervention (n = 103) or usual care (n = 106). The maximum rate of monthly recruitment to the trial was 60–80 participants per month. In total, 12,734 messages were sent to participants. Of these messages, 47 were identified as having failed to be sent by the service provider. Participants sent 2,864 messages to the automated messaging system. Baseline data from medical records were available for > 90% of participants with the exception of cholesterol (78.9%). At 6 months, a further HbA1c measurement was reported for 67% of participants. In total medical record data were available at 6 months for 207 (99.0%) of participants and completed self-report data were available for 177 (84.7%) of participants.ConclusionThe feasibility of a large-scale randomised evaluation of brief message intervention for people with type 2 diabetes appears to be high using this efficient design. Failure rate of sending messages is low, rapid recruitment was achieved among people with type 2 diabetes, clinical data is available on participants from routine medical records and self-report of economic measures was acceptable.Trial registrationISCTRN ISRCTN13404264. Registered on 10 October 2018.

Teaching by texting to promote positive health behaviours in pregnancy: a protocol for a randomised controlled trial of SmartMom

IntroductionPrenatal education is associated with positive health behaviours, including optimal weight gain, attendance at prenatal care, acceptance of routine screening tests, smoking cessation, decreased alcohol consumption and breast feeding. Adoption...

Interventions of eHealth technologies integrated with non-physician health workers for improving management of hypertension: Systematic review and meta-analysis

Hypertension is a major public health problem, accounting for 7.5 million deaths and 57 million disability-adjusted life years annually worldwide. The majority of hypertension-related deaths occur in low- and middle-income countries (LMICs). Despite the escalating prevalence of hypertension in many LMICs, only one-third of those affected are aware of their hypertension status. The rapid proliferation of eHealth technologies presents an opportunity to improve the detection and management of hypertension. Many LMICs face a critical shortage of physicians, and their services often come at a considerable cost to the health system. Non-physician health workers could be a cost-effective alternative to improve the detection and management of hypertension, particularly in LMICs. In this systematic review, we aim to synthesize and evaluate the effectiveness of interventions that integrated eHealth technologies with non-physician health workers to reduce blood pressure. A diverse range of eHealth technologies, such as mobile-based applications, telemonitoring, short text messaging and electronic decision support systems, are being used by non-physician health workers for the management of hypertension. We found that eHealth technologies integrated with non-physician health workers reduced overall mean systolic blood pressure by -4.09 mmHg (95%CI: -5.87 to -2.32) compared to usual care. Similarly, such an integrated approach also reduced diastolic blood pressure by -1.25 mmHg (-2.31 to -0.81) in the intervention group than usual care. Therefore, leveraging the use of cost-effective eHealth technologies to support task-sharing with non-physicians presents an effective strategy for enhancing blood pressure management, applicable to both high- and low-income countries.

Multifaceted Strategy Based on Automated Text Messaging After a Recent Heart Failure Admission

Readmissions after an index heart failure (HF) hospitalization are a major contemporary health care problem. To evaluate the feasibility and efficacy of an intensive telemonitoring strategy in the vulnerable period after an HF hospitalization. This randomized clinical trial was conducted in 30 HF clinics in Brazil. Patients with left ventricular ejection fraction less than 40% and access to mobile phones were enrolled up to 30 days after an HF admission. Data were collected from July 2019 to July 2022. Participants were randomly assigned to a telemonitoring strategy or standard care. The telemonitoring group received 4 daily short message service text messages to optimize self-care, active engagement, and early intervention. Red flags based on feedback messages triggered automatic diuretic adjustment and/or a telephone call from the health care team. The primary end point was change in N-terminal pro-brain natriuretic peptide (NT-proBNP) from baseline to 180 days. A hierarchical win-ratio analysis incorporating blindly adjudicated clinical events (cardiovascular deaths and HF hospitalization) and variation in NT-proBNP was also performed. Of 699 included patients, 460 (65.8%) were male, and the mean (SD) age was 61.2 (14.5) years. A total of 352 patients were randomly assigned to the telemonitoring strategy and 347 to standard care. Satisfaction with the telemonitoring strategy was excellent (net promoting score at 180 days, 78.5). HF self-care increased significantly in the telemonitoring group compared with the standard care group (score difference at 30 days, -2.21; 95% CI, -3.67 to -0.74; P = .001; score difference at 180 days, -2.08; 95% CI, -3.59 to -0.57; P = .004). Variation of NT-proBNP was similar in the telemonitoring group compared with the standard care group (telemonitoring: baseline, 2593 pg/mL; 95% CI, 2314-2923; 180 days, 1313 pg/mL; 95% CI, 1117-1543; standard care: baseline, 2396 pg/mL; 95% CI, 2122-2721; 180 days, 1319 pg/mL; 95% CI, 1114-1564; ratio of change, 0.92; 95% CI, 0.77-1.11; P = .39). Hierarchical analysis of the composite outcome demonstrated a similar number of wins in both groups (telemonitoring, 49 883 of 122 144 comparisons [40.8%]; standard care, 48 034 of 122 144 comparisons [39.3%]; win ratio, 1.04; 95% CI, 0.86-1.26). An intensive telemonitoring strategy applied in the vulnerable period after an HF admission was feasible, well-accepted, and increased scores of HF self-care but did not translate to reductions in NT-proBNP levels nor improvement in a composite hierarchical clinical outcome. ClinicalTrials.gov Identifier: NCT04062461.

Linguistic peculiarities of fake publications about the COVID-19 pandemic (on the example of Russian and English-language new media)

The aim of the study is to identify the linguistic features of fake publications about the COVID-19 pandemic on the example of Russian and English-language new media in order for a modern person to be able to recognize such types of news among the published information content. The scientific novelty of the study lies in the identification and study of similarities and differences in the use of the language of fake news about COVID-19 in Russian and English languages. The work included a linguistic assessment of the ability of authors of fake publications in Russian and English-language new media to operate a variety of stylistic techniques in order to expand the emotional range of published media materials, thereby contributing to a stronger emotional impact on the audience of readers (viewers, listeners). As a result of the study, it was found that Russian and English-language fake news about the pandemic have a number of linguistic patterns, knowing which one can predict the truth or falsity of news content of this type in the information space and, accordingly, prevent its dissemination. In particular, such principles include the use of imperative constructions, stylistic means of expression in news texts (e.g., metaphors); the presence of a trigger in informational headlines, as well as the generation of short text messages accompanying memes that can influence the affective actions of media audiences in their interaction with Russian and English-language media resources. Further prospects for the study of fake news texts about COVID-19 and epidemics in general are identified to explore the phenomenon of disinformation and post-truth and their impact on media reality.

The state of knowledge regarding delivering behavior change techniques via short text messages is already quite advanced: A response to "Can behavior change techniques be delivered via short text messages?"

Doğru et al. recent study reported developing text messages that attempted to capture each of 93 behavior change techniques (BCTs) in a standardized taxonomy. They found that a panel of experts identified the majority of the messages developed as having good fidelity to the intended BCTs. While this work has clear merit, we do not believe it accurately reflects the large body of existing research in this area. A process of producing text messages to address BCTs that yielded high fidelity has previously been reported. Furthermore, this work showed that messages developed for one behavior can be modified to address another behavior with similarly good fidelity. Importantly, these messages have been shown to successfully change target constructs in an experimental study and are being used in a randomized trial that has recently completed recruitment of over 1000 people with Type 2 diabetes.

Meta-Analyses and Narrative Review of Home-Based Interventions to Improve Literacy and Mathematics Outcomes for Children Between the Ages of 3 and 5 Years Old

The purpose of these meta-analyses was to examine the effectiveness of home-based interventions aimed at improving literacy and mathematics outcomes for preschool-age children (mean age = 4.29 years; range = 3.07–5.32 years) and to develop an understanding of what home-based interventions work in different contexts. A total of 32 studies met the inclusion criteria for these meta-analyses; 30 studies included sufficient data for inclusion in the meta-analyses, and two studies did not contain sufficient quantitative data and instead were summarized in a narrative review. The average weighted effect size for interventions with literacy (d = 0.10; CI = [−0.17, 0.38]; n = 27) and mathematical outcomes (d = 0.18; CI = [−1.62, 1.99]; n = 8) were minimal. Hence, these meta-analyses showed that home-based interventions had minimal effect on literacy and mathematical outcomes for preschoolers. There were more home-based interventions with literacy (N = 28) than mathematical outcomes (N = 10). The heterogeneity showed no variability, indicating that all intervention impacted on children’s outcomes to similar effect. Overall, many interventions were relatively light touch (i.e., time spent engaging in parent training), and the engagement requirement of the parent in some studies was minimal (e.g., reading a short text message). More in-depth research into the components of interventions (e.g., focus, training approaches) and evaluation of interventions before they are implemented is essential for ensuring that early interventions will be effective and lead to the development of the intended skills.

Abstract 15333: The Addressing Hypertension Care in Africa (ADHINCRA) Study: A Multi-Level Nurse-Led, Mobile-Health Enhanced Intervention to Improve Hypertension Control in Ghana

Background: Ghana, is experiencing silent epidemics of hypertension (HTN) and cardiovascular disease (CVD). There is a dire need to implement multilevel strategies to improve HTN control in Ghana. The Addressing Hypertension Care in Africa (ADHINCRA) Study sought to test the feasibility of a multilevel, nurse-led, mobile-health enhanced intervention to improve HTN control in Ghana. Methods: Using a cluster-randomized controlled pilot trial design, we enrolled 4 hospitals in Kumasi, Ghana and recruited 240 patients with uncontrolled HTN, defined as systolic blood pressure (BP) ≥140 mm Hg. Two hospitals were randomized to the intervention and 2 to the enhanced usual care (UC) arm. Patients in the intervention arm received nurse-led task-shifting, a mobile health application and home BP monitoring. The intervention was administered for six months, after which it was withdrawn and patients were followed for 6 more months. The enhanced UC arm received usual care, plus short text messages on health. The primary outcome was change in BP control status at 6 and 12 months. We used general linear models to examine the probability of BP control, accounting for clustering within hospitals. Results: The mean age was 53 ± 9.7 years, 51% were women. After 6 months, BP control improved in the intervention arm (57.0%, 95% CI 56.8% to 57.1%) versus 18.1%, 95% CI 16.9% to 19.3%, for the UC arm), with a between-group difference of 38.9% (95% CI 37.7% to 40.1%; p&lt;0.001). After 12 months, BP control improved in the intervention arm (80.5%, 95% CI 65.5% to 95.4%) versus 24.2%, 95% CI 10% to 38.5%, for the UC arm), with a between-group difference of 56.2% (95% CI 35.6% to 76.8%; p&lt;0.001). ( Figure) Conclusion: A multi-level intervention nurse-led, mobile-health enhanced intervention was associated with greater BP control than enhanced UC among patients with HTN in Ghana. A larger scale study is warranted to support future scale-up of the ADHINCRA Study.

A Hybrid Model with New Word Weighting for Fast Filtering Spam Short Texts.

Short message services (SMS), microblogging tools, instant message apps, and commercial websites produce numerous short text messages every day. These short text messages are usually guaranteed to reach mass audience with low cost. Spammers take advantage of short texts by sending bulk malicious or unwanted messages. Short texts are difficult to classify because of their shortness, sparsity, rapidness, and informal writing. The effectiveness of the hidden Markov model (HMM) for short text classification has been illustrated in our previous study. However, the HMM has limited capability to handle new words, which are mostly generated by informal writing. In this paper, a hybrid model is proposed to address the informal writing issue by weighting new words for fast short text filtering with high accuracy. The hybrid model consists of an artificial neural network (ANN) and an HMM, which are used for new word weighting and spam filtering, respectively. The weight of a new word is calculated based on the weights of its neighbor, along with the spam and ham (i.e., not spam) probabilities of short text message predicted by the ANN. Performance evaluations on benchmark datasets, including the SMS message data maintained by University of California, Irvine; the movie reviews, and the customer reviews are conducted. The hybrid model operates at a significantly higher speed than deep learning models. The experiment results show that the proposed hybrid model outperforms other prominent machine learning algorithms, achieving a good balance between filtering throughput and accuracy.