Explore the vast range of titles available.

Increased mobile phone penetration allows the interviewing of respondents using interactive voice response surveys in low- and middle-income countries. However, there has been little investigation of the best type of incentive to obtain data from a representative sample in these countries. We assessed the effect of different airtime incentives options on cooperation and response rates of an interactive voice response survey in Bangladesh and Uganda. The open-label randomized controlled trial had three arms: (1) no incentive (control), (2) promised airtime incentive of 50 Bangladeshi Taka (US $0.60; 1 BDT is approximately equivalent to US $0.012) or 5000 Ugandan Shilling (US $1.35; 1 UGX is approximately equivalent to US $0.00028), and (3) lottery incentive (500 BDT and 100,000 UGX), in which the odds of winning were 1:20. Fully automated random-digit dialing was used to sample eligible participants aged ≥18 years. The risk ratios (RRs) with 95% confidence intervals for primary outcomes of response and cooperation rates were obtained using log-binomial regression. Between June 14 and July 14, 2017, a total of 546,746 phone calls were made in Bangladesh, with 1165 complete interviews being conducted. Between March 26 and April 22, 2017, a total of 178,572 phone calls were made in Uganda, with 1248 complete interviews being conducted. Cooperation rates were significantly higher for the promised incentive (Bangladesh: 39.3%; RR 1.38, 95% CI 1.24-1.55, P<.001; Uganda: 59.9%; RR 1.47, 95% CI 1.33-1.62, P<.001) and the lottery incentive arms (Bangladesh: 36.6%; RR 1.28, 95% CI 1.15-1.45, P<.001; Uganda: 54.6%; RR 1.34, 95% CI 1.21-1.48, P<.001) than those for the control arm (Bangladesh: 28.4%; Uganda: 40.9%). Similarly, response rates were significantly higher for the promised incentive (Bangladesh: 26.5%%; RR 1.26, 95% CI 1.14-1.39, P<.001; Uganda: 41.2%; RR 1.27, 95% CI 1.16-1.39, P<.001) and lottery incentive arms (Bangladesh: 24.5%%; RR 1.17, 95% CI 1.06-1.29, P=.002; Uganda: 37.9%%; RR 1.17, 95% CI 1.06-1.29, P=.001) than those for the control arm (Bangladesh: 21.0%; Uganda: 32.4%). Promised or lottery airtime incentives improved survey participation and facilitated a large sample within a short period in 2 countries. ClinicalTrials.gov NCT03773146; http://clinicaltrials.gov/ct2/show/NCT03773146.

In this work, we demonstrate the current advancements assimilated in the earlier developed continuous Kannada automatic speech recognition (ASR) spoken query system (SQS) under uncontrolled environment. The SQS comprises interactive voice response system and ASR models which are developed using Kaldi. A variety of background noises were added to the continuous Kannada speech data while training the ASR system, as it was gathered under a corrupted environment. In the earlier SQS, the background and other types of noises have reduced the accuracy of speech recognition. This can be overcome by developing a robust noise reduction algorithm for degraded speech enhancement. In the enhanced SQS, a background noise reduction module is introduced before the speech feature extraction step. The proposed noise cancellation algorithm is represented by the degraded spectrum of speech in a complex plane which is an amalgamation of clean speech spectrum and noise model vectors. The conducted investigational results reveal that the proposed noise suppression algorithm outperforms the traditional spectral subtraction algorithms and magnitude squared spectrum (MSS) estimators. The outputs of the proposed approach show that there is no audibility of musical noise and other types of noises in enhanced NOIZEUS speech corpora and continuous Kannada speech data. Therefore, the noise suppression algorithm is applied to the degraded continuous Kannada speech data for its enhancement. Using noise suppression algorithm and time delay neural network ASR modelling technique in SQS, there is an improvement of 1.87% in terms of word error rate in comparison with the earlier developed deep neural network - hidden Markov model (DNN-HMM)-based SQS. The online testing of enhanced continuous Kannada SQS is done by the 500 speakers/users of the Karnataka state under a corrupted environment. The source code of algorithms and ASR models used in this work is made publicly available https://sites.google.com/view/thimmarajayadavag/downloads.

In this paper, a spoken query system is demonstrated which can be used to access the latest agricultural commodity prices and weather information in Kannada language using mobile phone. The spoken query system consists of Automatic Speech Recognition (ASR) models, Interactive Voice Response System (IVRS) call flow, Agricultural Marketing Network (AGMARKNET) and India Meteorological Department (IMD) databases. The ASR models are developed by using the Kaldi speech recognition toolkit. The task specific speech data is collected from the different dialect regions of Karnataka (a state in India speaks Kannada language) to develop ASR models. The web crawler is used to get the commodity price and weather information from AGMARKNET and IMD websites. The postgresql database management system is used to manage the crawled data. The 80 and 20% of validated speech data is used for system training and testing respectively. The accuracy and Word Error Rate (WER) of ASR models are highlighted and end to end spoken query system is developed for Kannada language.

In summer 2015, we conducted an exploratory study of how people in the U.S. use and respond to robot-like systems in order to achieve their needs through mediated customer service interfaces. To understand this process, we carried out three focus groups sessions along with 50 in-depth interviews. Strikingly we found that people perceive (correctly or not) that interactive voice response customer service technology is set up to deter them from pursuing further contact. And yet, for the most part, people were unwilling to simply give up on the goals that motivated their initial contact. Consequently, they had to innovate ways to communicate with the automated systems that essentially serve as gatekeepers to their desired ends. These results have implications for communication theory and system design, especially since these systems will be increasingly presented to consumers as social media affordances evolve.

Female sex workers (FSWs) were recruited for a 4-month placebo vaginal gel trial in Nellore, India. Two experiments explored if prior knowledge of biomarkers for unprotected sex and insertion of gel applicators would yield more accurate self-reports. A third experiment compared self-reports of gel use and adherence levels between FSWs randomly assigned to interactive voice response survey (IVRS) and those assigned to paper diaries. Prior knowledge of biomarkers did not improve accuracy of self-reported condom or gel use, nor did it affect actual adherence. Of those who tested positive for the presence of semenogelin in the vagina, 76 % reported no unprotected sex in the previous 48 h. Overall, women reported using gel on 90 % of days whereas the biomarker indicated gel use on fewer than 50 % of days. Compliance to IVRS was low, despite familiarity with mobile phone technology. Additional explorations with other populations are needed.

Medication nonadherence leads to suboptimal treatment outcomes, making it a major priority in health care. eHealth provides an opportunity to offer medication adherence interventions with minimal effort from health care providers whose time and resources are limited. The aim of this systematic review is twofold: (1) to evaluate effectiveness of recently developed and tested interactive eHealth (including mHealth) interventions on medication adherence in adult patients using long-term medication and (2) to describe strategies among effective interventions. MEDLINE, EMBASE, Cochrane Library, PsycINFO, and Web of Science were systematically searched from January 2014 to July 2019 as well as reference lists and citations of included articles. Eligible studies fulfilled the following inclusion criteria: (1) randomized controlled trial with a usual care control group; (2) a total sample size of at least 50 adult patients using long-term medication; (3) applying an interactive eHealth intervention aimed at the patient or patient's caregiver; and (4) medication adherence as primary outcome. Methodologic quality was assessed using the Cochrane risk of bias tool. Selection and quality assessment of studies were performed by 2 researchers (BP and BvdB or JV) independently. A best evidence synthesis was performed according to the Cochrane Back Review Group. Of the 9047 records screened, 22 randomized clinical trials were included reporting on 29 interventions. Most (21/29, 72%) interventions specified using a (mobile) phone for calling, SMS text messaging, or mobile apps. A majority of all interactive interventions (17/29) had a statistically significant effect on medication adherence (P<.05). Of these interventions, 9 had at least a small effect size (Cohen d ≥ 0.2) and 3 showed strong odds for becoming adherent in the intervention group (odds ratio > 2.0). Our best evidence synthesis provided strong evidence for a positive effect of interventions using SMS text messages or interactive voice response, mobile app, and calls as mode of providing adherence tele-feedback. Intervention strategies \"to teach medication management skills,\" \"to improve health care quality by coordinating medication adherence care between professionals,\" and \"to facilitate communication or decision making between patients and health care providers\" also showed strong evidence for a positive effect. Overall, this review supports the hypothesis that interactive eHealth interventions can be effective in improving medication adherence. Intervention strategies that improve patients' treatment involvement and their medication management skills are most promising and should be considered for implementation in practice.

This paper analyses the performance of different types of Deep Neural Networks to jointly estimate age and identify gender from speech, to be applied in Interactive Voice Response systems available in call centres. Deep Neural Networks are used, because they have recently demonstrated discriminative and representation capabilities in a wide range of applications, including speech processing problems based on feature extraction and selection. Networks with different sizes are analysed to obtain information on how performance depends on the network architecture and the number of free parameters. The speech corpus used for the experiments is Mozilla’s Common Voice dataset, an open and crowdsourced speech corpus. The results are really good for gender classification, independently of the type of neural network, but improve with the network size. Regarding the classification by age groups, the combination of convolutional neural networks and temporal neural networks seems to be the best option among the analysed, and again, the larger the size of the network, the better the results. The results are promising for use in IVR systems, with the best systems achieving a gender identification error of less than 2% and a classification error by age group of less than 20%.

Effective broad-reach interventions to reduce childhood obesity are needed, but there is currently little consensus on the most effective approach. Parental involvement in interventions appears to be important. The use of eHealth modalities in interventions also seems to be promising. To our knowledge, there have been no previous reviews that have specifically investigated the effectiveness of parent-focused eHealth obesity interventions, a gap that this systematic review and meta-analysis intends to address. The objective of this study was to review the evidence for body mass index (BMI)/BMI z-score improvements in eHealth overweight and obesity randomized controlled trials for children and adolescents, where parents or carers were an agent of change. A systematic review and meta-analysis was conducted, which conforms to the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. Seven databases were searched for the period January 1995 to April 2015. Primary outcome measures were BMI and/or BMI z-score at baseline and post-intervention. Secondary outcomes included diet, physical activity, and screen time. Interventions were included if they targeted parents of children and adolescents aged 0-18 years of age and used an eHealth medium such as the Internet, interactive voice response (IVR), email, social media, telemedicine, or e-learning. Eight studies were included, involving 1487 parent and child or adolescent dyads. A total of 3 studies were obesity prevention trials, and 5 were obesity treatment trials. None of the studies found a statistically significant difference in BMI or BMI z-score between the intervention and control groups at post-intervention, and a meta-analysis demonstrated no significant difference in the effects of parent-focused eHealth obesity interventions compared with a control on BMI/BMI z-score (Standardized Mean Difference -0.15, 95% CI -0.45 to 0.16, Z=0.94, P=.35). Four of seven studies that reported on dietary outcomes demonstrated significant improvements in at least 1 dietary measurement, and 1 of 6 studies that reported on physical activity outcomes demonstrated significant improvements compared with the control. The quality of the interventions was generally not high; therefore, these results should be interpreted with caution. It is recommended that larger, longer duration, high-quality parent-focused eHealth studies are conducted, which transform successful components from face-to-face interventions into an eHealth format and target younger age groups in particular. PROSPERO International Prospective Register of Systematic Reviews: CRD42015019837; http://www.crd.york.ac.uk/PROSPERO/display_record.asp?ID=CRD42015019837 (Archived by WebCite at http://www.webcitation.org/6ivBHvBhq).

Growing interest on the effects of home telemonitoring on patients with chronic heart failure (HF) has led to a rise in the number of systematic reviews addressing the same or very similar research questions with a concomitant increase in discordant findings. Differences in the scope, methods of analysis, and methodological quality of systematic reviews can cause great confusion and make it difficult for policy makers and clinicians to access and interpret the available evidence and for researchers to know where knowledge gaps in the extant literature exist. This overview aims to collect, appraise, and synthesize existing evidence from multiple systematic reviews on the effectiveness of home telemonitoring interventions for patients with chronic heart failure (HF) to inform policy makers, practitioners, and researchers. A comprehensive literature search was performed on MEDLINE, EMBASE, CINAHL, and the Cochrane Library to identify all relevant, peer-reviewed systematic reviews published between January 1996 and December 2013. Reviews were searched and screened using explicit keywords and inclusion criteria. Standardized forms were used to extract data and the methodological quality of included reviews was appraised using the AMSTAR (assessing methodological quality of systematic reviews) instrument. Summary of findings tables were constructed for all primary outcomes of interest, and quality of evidence was graded by outcome using the GRADE (Grades of Recommendation, Assessment, Development, and Evaluation) system. Post-hoc analysis and subgroup meta-analyses were conducted to gain further insights into the various types of home telemonitoring technologies included in the systematic reviews and the impact of these technologies on clinical outcomes. A total of 15 reviews published between 2003 and 2013 were selected for meta-level synthesis. Evidence from high-quality reviews with meta-analysis indicated that taken collectively, home telemonitoring interventions reduce the relative risk of all-cause mortality (0.60 to 0.85) and heart failure-related hospitalizations (0.64 to 0.86) compared with usual care. Absolute risk reductions ranged from 1.4%-6.5% and 3.7%-8.2%, respectively. Improvements in HF-related hospitalizations appeared to be more pronounced in patients with stable HF: hazard ratio (HR) 0.70 (95% credible interval [Crl] 0.34-1.5]). Risk reductions in mortality and all-cause hospitalizations appeared to be greater in patients who had been recently discharged (≤28 days) from an acute care setting after a recent HF exacerbation: HR 0.62 (95% CrI 0.42-0.89) and HR 0.67 (95% CrI 0.42-0.97), respectively. However, quality of evidence for these outcomes ranged from moderate to low suggesting that further research is very likely to have an important impact on our confidence in the observed estimates of effect and may change these estimates. The post-hoc analysis identified five main types of non-invasive telemonitoring technologies included in the systematic reviews: (1) video-consultation, with or without transmission of vital signs, (2) mobile telemonitoring, (3) automated device-based telemonitoring, (4) interactive voice response, and (5) Web-based telemonitoring. Of these, only automated device-based telemonitoring and mobile telemonitoring were effective in reducing the risk of all-cause mortality and HF-related hospitalizations. More research data are required for interactive voice response systems, video-consultation, and Web-based telemonitoring to provide robust conclusions about their effectiveness. Future research should focus on understanding the process by which home telemonitoring works in terms of improving outcomes, identify optimal strategies and the duration of follow-up for which it confers benefits, and further investigate whether there is differential effectiveness between chronic HF patient groups and types of home telemonitoring technologies.

National and subnational level surveys are important for monitoring disease burden, prioritizing resource allocation, and evaluating public health policies. As mobile phone access and ownership become more common globally, mobile phone surveys (MPSs) offer an opportunity to supplement traditional public health household surveys. The objective of this study was to systematically review the current landscape of MPSs to collect population-level estimates in low- and middle-income countries (LMICs). Primary and gray literature from 7 online databases were systematically searched for studies that deployed MPSs to collect population-level estimates. Titles and abstracts were screened on primary inclusion and exclusion criteria by two research assistants. Articles that met primary screening requirements were read in full and screened for secondary eligibility criteria. Articles included in review were grouped into the following three categories by their survey modality: (1) interactive voice response (IVR), (2) short message service (SMS), and (3) human operator or computer-assisted telephone interviews (CATI). Data were abstracted by two research assistants. The conduct and reporting of the review conformed to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. A total of 6625 articles were identified through the literature review. Overall, 11 articles were identified that contained 19 MPS (CATI, IVR, or SMS) surveys to collect population-level estimates across a range of topics. MPSs were used in Latin America (n=8), the Middle East (n=1), South Asia (n=2), and sub-Saharan Africa (n=8). Nine articles presented results for 10 CATI surveys (10/19, 53%). Two articles discussed the findings of 6 IVR surveys (6/19, 32%). Three SMS surveys were identified from 2 articles (3/19, 16%). Approximately 63% (12/19) of MPS were delivered to mobile phone numbers collected from previously administered household surveys. The majority of MPS (11/19, 58%) were panel surveys where a cohort of participants, who often were provided a mobile phone upon a face-to-face enrollment, were surveyed multiple times. Very few reports of population-level MPS were identified. Of the MPS that were identified, the majority of surveys were conducted using CATI. Due to the limited number of identified IVR and SMS surveys, the relative advantages and disadvantages among the three survey modalities cannot be adequately assessed. The majority of MPS were sent to mobile phone numbers that were collected from a previously administered household survey. There is limited evidence on whether a random digit dialing (RDD) approach or a simple random sample of mobile network provided list of numbers can produce a population representative survey.