Using mobile meditation app data to predict future app engagement: an observational study.

The similarity between a pair of time series, i.e., sequences of indexed values in time order, is often estimated by the dynamic time warping (DTW) distance, instead of any in the well-studied family of measures including the longest common subsequence (LCS) length and the edit distance. Although it may seem as if the DTW and the LCS(-like) measures are essentially different, we reveal that the DTW distance can be represented by the longest increasing subsequence (LIS) length of a sequence of integers, which is the LCS length between the integer sequence and itself sorted. For a given pair of time series of n integers between zero and c, we propose an integer sequence that represents any substring-substring DTW distance as its band-substring LIS length. The length of the produced integer sequence is O(c⁴ n²) or O(c² n²) depending on the variant of the DTW distance used, both of which can be translated to O(n²) for constant cost functions. To demonstrate that techniques developed under the LCS(-like) measures are directly applicable to analysis of time series via our reduction of DTW to LIS, we present time-efficient algorithms for DTW-related problems utilizing the semi-local sequence comparison technique developed for LCS-related problems.

There are more than 318,000 mobile health apps available worldwide and more than 200 new apps become available each day. Although most are general wellness apps, the number of those related to patient care and management of health conditions continues to increase and has reached 40 percent of all health apps on the market. In fact, there is at least one high-quality app (i.e., apps with such attributes as good patient ratings, frequent updates, and promising clinical evidence) available to support patients’ needs at each stage of the care continuum, from prevention to treatment. More than 570 studies on mobile apps have been published, providing a robust amount of clinical evidence on their quality and effectiveness.1 One survey identified that 75 percent of U.S. health consumers believe technology, including apps, is important for managing their health. Mobile health apps are being embraced by patients for a multitude of uses, including virtual care and tracking, recording, and sharing health data, such as blood pressure and heart rate.2 Top uses for virtual care have included after-hours and follow-up appointments and concern-specific discussions. The use of virtual care continues to increase; 25 percent of surveyed consumers indicated they used these services in 2018, which is up from 21 percent in 2017. The majority of 2018 respondents who used these services (74 percent) said they were satisfied with the virtual care they received; in fact, approximately 50 percent of all respondents reported they would prefer a faster virtual care appointment than a delayed in-person visit.2 Moreover, 79 percent of U.S. consumers reported in another survey that they are more likely to choose a health care provider who has methods in place to connect virtually instead of one who does not.3 Ninety percent of patients surveyed indicated they are willing to share their health data obtained from mobile apps and wearable devices with their health care team.2 For health care professionals, mobile apps are beneficial for a range of uses, including to access medical references for point-of-care decisions; assist with hospital information systems, such as the electronic health record; communicate with other clinicians; perform training; and remotely monitor patients. In one survey, approximately 30 to 50 percent of U.S. clinicians reported using apps to actively engage in patient care, including to collect patient information at the bedside and monitor medical device information.3 Approximately 66 percent of the 100 biggest U.S. hospitals provide mobile apps for patients; 40 percent of these developed the apps in house.4 Health apps have been proven to reduce use of acute care services for diabetes, asthma, and cardiac and pulmonary rehabilitation; the use of apps in just these categories has the potential to save $7 billion in health care costs annually in the United States.1 Mobile apps can augment care for both patients and health care providers at all stages of care. Surveys of U.S. health care consumers and professionals point to an increasing adoption of this technology, highlighting the importance of identifying ways to incorporate these tools into patients’ health maintenance and care. This month’s lead feature discusses the use of mobile apps to aid patients in their postoperative recovery, including for medication compliance, pain management, and follow-up care.

Dynamic time warping(DTW) distance is the most effective similarity measurement methods in time-series data mining area. Because of the high computational complexity of DTW, it is not suitable for huge amounts of data. Thus, some DTW distance lower bound methods are proposed, which can improve the efficiency of DTW distance calculation. In this paper, we summarized the existing lower bound of DTW method and then proposed a closely related field with the application and exacted Lower Bounding distance measure with Segmentation(eLBS). Experiment results show that this method meet the need of non-omission.

Children with communication disorders experience difficulty in one or more areas of articulation and speech, language, fluency, voice and social communication, and they work with speech-language pathologists (SLPs) to improve their communication. With the rise of adoption and use for mobile applications among special education and healthcare service providers, SLPs also have implemented, and for some, contributed to the design of, mobile applications (apps) during clinical practice. However, how these mobile apps are designed and implemented for clinicians to facilitate their clients' communication and learning experiences during therapy remains underinvestigated. This qualitative research study investigates how mobile apps were designed for clinicians to target assessment and intervention goals. Additionally, it focused on how clinicians adopted these apps while integrating therapy techniques to facilitate their clients' learning. Informed by the Research, Practice, and Design for iPad Apps (iRPD) framework and the Consolidated Framework for Implementation Research (CFIR), semi-structured interviews were conducted with 37 licensed pediatric SLPs, including 23 SLPs who have used apps and 14 SLPs who have contributed to the design of their own mobile apps. Two rounds of qualitative coding via template analysis and thematic analysis were then used to analyse client and clinician characteristics, clinical practice, therapy tools, app characteristics, influential factors and app design and use recommendations. Results showed SLPs utilise different genres of assistive, educational and recreational game apps to support children's communication development when working with children who have diverse disorders and therapy needs across different age groups. SLPs who have designed their own apps emphasised the importance of following evidence-based practice, well-researched teaching methods and learning theories. Additionally, multiple financial, sociocultural, political and ethical factors contributed to the design, adoption and implementation of mobile apps during services. By understanding the clinician's app use practices situated in various therapy activities and techniques, we specified a list of design recommendations for app designers who are interested in creating mobile apps for supporting children's speech and language development. By bringing insights from both clinical practitioners as well as those with additional technical design backgrounds, this study contributes to the understanding of clinical practice needs and strategies and will lead to the most optimal app design and adoption practice to support the well-being of children with communication disorders. What is already known on the subject Speech language pathologist (SLPs) implement mobile apps for clients with diverse therapy needs, and their app adoption and use are influenced by multifaceted factors. Although prior studies have reported SLPs' mobile app use, additional information is still needed. For example, the research literature does not include how specific technology is used during therapy practice, or specific details about challenges and needs in implementing and utilising the technology. Additional research also needs to include influential factors (e.g., financial, sociocultural, political, ethical) that are considered when selecting, implementing, assessing and designing an app. The lack of research in these areas directly affects the understanding of clinical mobile technology practices and further hinders clinicians' abilities to advocate for better clinical and design decisions towards identifying and implementing effective mobile apps that facilitate children's communication. What this study adds to existing knowledge This qualitative study is the first known empirical research that interviewed pediatric speech-language pathologists who have used and designed mobile apps for children who receive speech-language therapy across different clinical settings. By investigating experiences from clinician stakeholders to illustrate a holistic overview of app design and development to deployment, this study reported finding on (1) how clinicians use mobile apps to help children to participate in different therapy activities, and (2) a list of recommended design and development guidelines that informs the design and use of mobile apps that best support and motivate children to engage in therapy. What are the potential or actual clinical implications of this work? This study disseminates clinician-reported practices of app design and use with pediatric clients across different speech-language disorders, and identifies gaps and needs for clinicians and researchers who are interested in understanding the role of mobile technology in relationship to human communication and interaction. Additionally, the paper demonstrates that SLPs have instrumental roles rather than passive users in influencing the design and implementation of different genres of mobile apps through evidence-based clinical practice, and call for partnerships across clinicians, special educators and technologists to support children's communication development.

The similarity between a pair of time series, i.e., sequences of indexed values in time order, is often estimated by the dynamic time warping (DTW) distance, instead of any in the well-studied family of measures including the longest common subsequence (LCS) length and the edit distance. Although it may seem as if the DTW and the LCS(-like) measures are essentially different, we reveal that the DTW distance can be represented by the longest increasing subsequence (LIS) length of a sequence of integers, which is the LCS length between the integer sequence and itself sorted. For a given pair of time series of length n such that the dissimilarity between any elements is an integer between zero and c, we propose an integer sequence that represents any substring-substring DTW distance as its band-substring LIS length. The length of the produced integer sequence is O(c n^2), which can be translated to O(n^2) for constant dissimilarity functions. To demonstrate that techniques developed under the LCS(-like) measures are directly applicable to analysis of time series via our reduction of DTW to LIS, we present time-efficient algorithms for DTW-related problems utilizing the semi-local sequence comparison technique developed for LCS-related problems.

When a single-phase grounding fault occurs in a resonant grounding system, the determination of the fault location remains a significant challenge due to the small fault current and the instability of the grounding arc. In order to solve the problem of low protection sensitivity when a high-resistance grounding fault occurs in a resonant grounding system, this paper proposes a fault location method based on the combination of dynamic time warping (DTW) distance and fuzzy C-means (FCM) clustering. By analyzing the characteristics of the zero-sequence current upstream and downstream of the fault point when a single-phase grounding fault occurs in the resonant grounding system, it is concluded that the waveform similarity on both sides of the fault point is low. DTW distance can be used to measure the similarity of two time series, and has the characteristics of good fault tolerance and synchronization error tolerance. According to the rule that the DTW value of faulty section is much larger than that of nonfaulty sections, FCM clustering is used to classify the DTW value of each section. The membership degree matrix and cluster centers are obtained. In the membership degree matrix, the section corresponding to the data in a class of their own is the faulty section, and all other data correspond to the nonfaulty section; otherwise, it is a fault occurring at the end of the line. The simulation results of MATLAB/Simulink and the field data test show that the method can accurately locate the faulty section.

Synchronized spontaneous low frequency fluctuations of the so called BOLD signal, as measured by functional Magnetic Resonance Imaging (fMRI), are known to represent the functional connections of different brain areas. Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient and the usage of the DTW algorithm has further advantages: beside the DTW distance, the algorithm generates the warping path, i.e. the time-delay function between the compared two time-series. In this paper, we propose to use the relative length of the warping path as classification feature and demonstrate that the warping path itself carries important information when classifying patients according to cannabis addiction. We discuss biomedical relevance of our findings as well.

BackgroundThere is a need for tools to decrease cancer patients’ and survivors’ long-term symptom burden. Complementary strategies, such as meditation, can accompany pharmacologic therapy to improve symptoms. Although support programs with targeted content have wider reach, higher adherence, and greater impact, there are no consumer-based meditation apps designed specifically for cancer.ObjectiveThis study aimed to gather information to advise the development of a cancer-specific meditation app in a small convenience sample of cancer patients and survivors who currently use the Calm app.MethodsAdult cancer patients and survivors who are Calm users (N=82) were recruited through the Daily Calm Facebook page. Participants completed a Web-based survey related to Calm app use and satisfaction, interest in and ideas for a cancer-specific Calm app, and demographic characteristics. Open-ended responses were inductively coded.ResultsParticipants were aged between 18 and 72 years (mean 48.60 years, SD 15.20), mostly female (77/82, 94%), white (65/79, 82%), and non-Hispanic (70/75, 93%), and reported using Calm at least 5 times per week (49/82, 60%). Although rates of satisfaction with current Calm components were high (between 65/82, 79% and 51/81, 63%), only 49% (40/82) of participants used guided meditations that they felt specifically helped with their cancer-related symptoms and survivorship, and 40% (33/82) would prefer more cancer-related content, with guided meditations for cancer-specific anxieties (eg, fear of recurrence; n=15) and coping with strong emotions (n=12) being the most common suggestions. A majority of participants (51/82, 62%) reported that they would be interested in becoming a member of a Calm cancer community (eg, in-app discussion boards: 41/46, 89%; and social media communities: 35/42, 83%). Almost half of the participants (37/82, 45%) reported that they would benefit from features that tracked symptoms in concurrence with app usage, but respondents were divided on whether this information should be shared with health care providers through the app (49/82, 60% would share).ConclusionsResponses suggest ways in which the current Calm app could be adapted to better fit cancer patients’ and survivors’ needs and preferences, including adding cancer-specific content, increasing the amount of content focusing on coping with strong emotions, developing communities for Calm users who are cancer patients and survivors, and including features that track cancer-related symptoms. Given differences in opinions about which features were desirable or would be useful, there is a clear need for future cancer-specific apps to be customizable (eg, ability to turn different features on or off). Although future research should address these topics in larger, more diverse samples, these data will serve as a starting point for the development of cancer-specific meditation apps and provide a framework for evaluating their effects.

Effectiveness of technology-based interventions to improve physical activity (PA) in people with COPD is controversial. Mixed results may be due to participants' characteristics influencing their use of and engagement with mobile health apps. This study compared demographic, clinical, physical and PA characteristics of patients with COPD using and not using mobile apps in daily life. Patients with COPD who used smartphones were asked about their sociodemographic and clinic characteristics, PA habits and use of mobile apps (general and PA-related). Participants performed a six-minute walk test (6MWT), gait speed test and wore an accelerometer for 7 days. Data were compared between participants using (App Users) and not using (Non-App Users) mobile apps. A sub-analysis was conducted comparing characteristics of PA–App Users and Non-Users. 59 participants were enrolled (73% Male; 66.3 ± 8.3 yrs; FEV1 48.7 ± 18.4% predicted): 59% were App Users and 25% were PA-App Users. Significant differences between App Users and Non-App Users were found for age (64.2 ± 8.9 vs. 69.2 ± 6.3yrs), 6MWT (462.9 ± 91.7 vs. 414.9 ± 82.3 m), Gait Speed (Median 1.5 [Q1–Q3: 1.4–1.8] vs. 2.0 [1.0–1.5]m/s), Time in Vigorous PA (0.6 [0.2–2.8] vs. 0.14 [0.1–0.7]min) and Self-Reported PA (4.0 [1.0–4.0] vs. 1.0 [0.0–4.0] Points). Differences between PA–App Users and Non-Users were found in time in sedentary behavior (764.1 [641.8–819.8] vs. 672.2 [581.2–749.4] min) and self-reported PA (4.0 [2.0–6.0] vs. 2.0 [0.0–4.0] points). People with COPD using mobile apps were younger and had higher physical capacity than their peers not using mobile apps. PA-App Users spent more time in sedentary behaviors than Non-Users although self-reporting more time in PA.

BackgroundThe use of smartphone apps to monitor and deliver health care guidance and interventions has received considerable attention recently, particularly with regard to behavioral disorders, stress relief, negative emotional state, and poor mood in general. Unfortunately, there is little research investigating the long-term and repeated effects of apps meant to impact mood and emotional state.ObjectiveWe aimed to investigate the effects of both immediate point-of-intervention and long-term use (ie, at least 10 engagements) of a guided meditation and mindfulness smartphone app on users’ emotional states. Data were collected from users of a mobile phone app developed by the company Stop, Breathe & Think (SBT) for achieving emotional wellness. To explore the long-term effects, we assessed changes in the users’ basal emotional state before they completed an activity (eg, a guided meditation). We also assessed the immediate effects of the app on users’ emotional states from preactivity to postactivity.MethodsThe SBT app collects information on the emotional state of the user before and after engagement in one or several mediation and mindfulness activities. These activities are recommended and provided by the app based on user input. We considered data on over 120,000 users of the app who collectively engaged in over 5.5 million sessions with the app during an approximate 2-year period. We focused our analysis on users who had at least 10 engagements with the app over an average of 6 months. We explored the changes in the emotional well-being of individuals with different emotional states at the time of their initial engagement with the app using mixed-effects models. In the process, we compared 2 different methods of classifying emotional states: (1) an expert-defined a priori mood classification and (2) an empirically driven cluster-based classification.ResultsWe found that among long-term users of the app, there was an association between the length of use and a positive change in basal emotional state (4% positive mood increase on a 2-point scale every 10 sessions). We also found that individuals who were anxious or depressed tended to have a favorable long-term emotional transition (eg, from a sad emotional state to a happier emotional state) after using the app for an extended period (the odds ratio for achieving a positive emotional state was 3.2 and 6.2 for anxious and depressed individuals, respectively, compared with users with fewer sessions).ConclusionsOur analyses provide evidence for an association between both immediate and long-term use of an app providing guided meditations and improvements in the emotional state.

Meditation apps are increasingly popular, yet there is limited understanding of how much users actually engage with them. While meditation apps show promise for supporting mental health, engagement in real-world settings appears to be notably low. The patterns of app use and the factors that influence usage remain relatively unclear. This study aims to examine the extent of meditation app use and the factors associated with user engagement. We conducted a cross-sectional survey of 536 recent meditation app users across 5 English-speaking countries. Engagement data were collected via self-report and app-verified screenshots. Assessed factors included user characteristics (age, education, income, sex, country, personality, self-efficacy, readiness and expectations for change, self-compassion, and quality of life), mental health (distress, well-being, life satisfaction, anxiety, depression, support, and stress), and app-related elements (therapeutic alliance, appeal, functionality, aesthetics, information, quality, and perceived impact). The 4 outcome variables representing engagement were app-verified minutes, self-reported minutes, app-verified minutes per year (adjusted for app download date), and self-reported minutes per year (adjusted for app download date). Associations between app use and variables of interest were examined using correlations. Factors with significant associations were then included in multivariable regression models to identify those most strongly associated with engagement. Age (ρ=0.13-0.15, PPFDR, where FDR is false discovery rate), expectations for sleep (ρ=0.12-0.33, PFDR<.05), and expectations for thriving (ρ=0.12-0.18, PFDR<.05) were associated with all outcome measures except adjusted objective minutes. Readiness to change was associated with all outcome measures (ρ=0.24-0.33, PFDR<.05). Among app factors, appeal (ρ=0.18-0.23, PFDR<.05) and perceived impact (ρ=0.23-0.32, PFDR<.05) were associated with all outcome measures except adjusted self-report minutes, while perceived quality (r=0.28-0.51, PFDR<.05) was associated with all outcome measures. Robust linear regressions showed that greater readiness to change (β=0.005-0.026, P=.006-.02), higher education level (β=0.029-0.540, P<.001), and higher openness (β=0.004-0.010, P=.008-.03) were associated with increased engagement. Additionally, greater expectations for sleep (β=0.004-0.009, P=.02-.04), greater expectation match (β=0.023, P=.03), and higher perceived app quality (β=0.008-0.042, P=.001-.01) were uniquely associated with increased engagement. Most individuals who download meditation apps engage minimally. Our findings suggest that users who are more educated, open to new experiences, and hold strong beliefs in the effectiveness of meditation apps are more likely to use them regularly. Longitudinal studies are needed to examine patterns of use and strengthen causal inferences.

Rice is a food commodity that is a basic need for Indonesian people. Since the end of 2022, average rice prices in Indonesia have been increasing, breaking the record for the highest price from August to October 2023. The price of rice in each province in Indonesia is different. This can happen because rice center provinces will distribute their rice production to other regions to meet rice needs. The grouping of provinces in Indonesia based on rice prices over time is an interesting thing to research. The analysis method used to group similar objects into groups for time series data is called clustering time series. The distance that can be used to measure the closeness of two-time series is the Dynamic Time Warping (DTW) distance. The clustering analysis used is the single, complete, average, Ward, and median linkage method. The results of the analysis show that time series clustering in provinces in Indonesia based on rice prices is best using median linkage hierarchical clustering. The median linkage method has a cophenetic correlation coefficient value of 0.899064, meaning that clustering using the DTW distance with the median difference is very good. The resulting clusters contained 3 clusters which had different characteristics between the clusters. There are 2 clusters that can be of concern to the government, because there are clusters that have rice prices that have always been high in the last period and there are provincial clusters that have rice prices that are very diverse or can be said to be unstable.

In this paper, we propose an efficient approach that computes the dynamic time warping (DTW) distance in time-series similarity search. The DTW distance is known to offer the high accuracy in similarity search, but it has difficulty in supporting the large database due to its high computational complexity. Recently, FastDTW and FTW have been proposed for efficient computation of DTW distances, but they have still performance limitations. In this paper, we propose a hybrid approach, called HybridFTW, which combines the advantages of both FastDTW and FTW. First, HybridFTW takes the advantage of FastDTW that provides fast computation through the limitation of allowable ranges. We call these allowable ranges dynamic (warping) bands, which reduce the computation spaces on the fly, and we reanalyze previous FastDTW and FTW in the viewpoint of static and dynamic bands. Second, HybridFTW also takes the advantage of FTW that exploits the early abandon effect by using the segment-based tight lower bound. To maximize the synergy of combining two methods, we obtain the dynamic band of FastDTW during the process of computing the lower bound in FTW. Using HybridFTW, we next propose range search and k-NN search algorithms and prove their correctness through formal theorems. Experimental results on real and synthetic data sets show that HybridFTW improves the search performance by up to 38 times over FastDTW and by up to 12 times over FTW.

One of the most famous algorithms for time series data clustering is k -means clustering with Euclidean distance as a similarity measure. However, many recent works have shown that Dynamic Time Warping (DTW) distance measure is more suitable for most time series data mining tasks due to its much improved alignment based on shape. Unfortunately, k -means clustering with DTW distance is still not practical since the current averaging functions fail to preserve characteristics of time series data within the cluster. Recently, Shape-based Template Matching Framework (STMF) has been proposed to discover a cluster representative of time series data. However, STMF is very computationally expensive. In this paper, we propose a Shape-based Clustering for Time Series (SCTS) using a novel averaging method called Ranking Shape-based Template Matching Framework (RSTMF), which can average a group of time series effectively but take as much as 400 times less computational time than that of STMF. In addition, our method outperforms other well-known clustering techniques in terms of accuracy and criterion based on known ground truth.

One of the advantages of the kernel methods is that they can deal with various kinds of objects, not necessarily vectorial data with a fixed number of attributes. In this paper, we develop kernels for time series data using dynamic time warping (DTW) distances. Since DTW distances are pseudo distances that do not satisfy the triangle inequality, a kernel matrix based on them is not positive semidefinite, in general. We use semidefinite programming (SDP) to guarantee the positive definiteness of a kernel matrix. We present neighborhood preserving embedding (NPE), an SDP formulation to obtain a kernel matrix that best preserves the local geometry of time series data. We also present an out-of-sample extension (OSE) for NPE. We use two applications, time series classification and time series embedding for similarity search, to validate our approach.