In the past few decades, analysis of heart sound signals (i.e. the phonocardiogram or PCG), especially for automated heart sound segmentation and classification, has been widely studied and has been reported to have the potential value to detect pathology accurately in clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of high-quality, rigorously validated, and standardized open databases of heart sound recordings. This paper describes a public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016. The archive comprises nine different heart sound databases sourced from multiple research groups around the world. It includes 2435 heart sound recordings in total collected from 1297 healthy subjects and patients with a variety of conditions, including heart valve disease and coronary artery disease. The recordings were collected from a variety of clinical or nonclinical (such as in-home visits) environments and equipment. The length of recording varied from several seconds to several minutes. This article reports detailed information about the subjects/patients including demographics (number, age, gender), recordings (number, location, state and time length), associated synchronously recorded signals, sampling frequency and sensor type used. We also provide a brief summary of the commonly used heart sound segmentation and classification methods, including open source code provided concurrently for the Challenge. A description of the PhysioNet/CinC Challenge 2016, including the main aims, the training and test sets, the hand corrected annotations for different heart sound states, the scoring mechanism, and associated open source code are provided. In addition, several potential benefits from the public heart sound database are discussed.
H igh blood pressure is a major risk factor for global disease burden.1 Even modest reductions in blood pressure are important and would reduce the risk of associated morbidity and premature mortality. [2][3][4] In settings where health care and medicines are freely available, a substantial burden of cardiovascular disease may be attributable to suboptimal adherence to blood pressure-lowering treatments. 5 Missed appointments for collection of medicine and challenges with taking lifelong treatment are some of the major reasons for suboptimal Background-We assessed the effect of automated treatment adherence support delivered via mobile phone short message system (SMS) text messages on blood pressure. Methods and Results-In this pragmatic, single-blind, 3-arm, randomized trial (SMS-Text Adherence Support [StAR]) undertaken in South Africa, patients treated for high blood pressure were randomly allocated in a 1:1:1 ratio to information only, interactive SMS text messaging, or usual care. The primary outcome was change in systolic blood pressure at 12 months from baseline measured with a validated oscillometric device. All trial staff were masked to treatment allocation. Analyses were intention to treat. Between June 26, 2012, and November 23, 2012, 1372 participants were randomized to receive information-only SMS text messages (n=457), interactive SMS text messages (n=458), or usual care (n=457). Primary outcome data were available for 1256 participants (92%). At 12 months, the mean adjusted change in systolic blood pressure compared with usual care was −2.2 mm Hg (95% confidence interval, −4.4 to −0.04) with informationonly SMS and −1.6 mm Hg (95% confidence interval, −3.7 to 0.6) with interactive SMS. Odds ratios for the proportion of participants with a blood pressure <140/90 mm Hg were 1.42 (95% confidence interval, 1.03-1.95) for information-only messaging and 1.41 (95% confidence interval, 1.02-1.95) for interactive messaging compared with usual care. Conclusions-In this randomized trial of an automated adherence support program delivered by SMS text message in a general outpatient population of adults with high blood pressure, we found a small reduction in systolic blood pressure control compared with usual care at 12 months. There was no evidence that an interactive intervention increased this effect. Clinical Trial Registration-URL: http://www.clinicaltrials.gov.
The identification of the exact positions of the first and second heart sounds within a phonocardiogram (PCG), or heart sound segmentation, is an essential step in the automatic analysis of heart sound recordings, allowing for the classification of pathological events. While threshold-based segmentation methods have shown modest success, probabilistic models, such as hidden Markov models, have recently been shown to surpass the capabilities of previous methods. Segmentation performance is further improved when a priori information about the expected duration of the states is incorporated into the model, such as in a hidden semi-Markov model (HSMM). This paper addresses the problem of the accurate segmentation of the first and second heart sound within noisy real-world PCG recordings using an HSMM, extended with the use of logistic regression for emission probability estimation. In addition, we implement a modified Viterbi algorithm for decoding the most likely sequence of states, and evaluated this method on a large dataset of 10,172 s of PCG recorded from 112 patients (including 12,181 first and 11,627 second heart sounds). The proposed method achieved an average F1 score of 95.63 ± 0.85%, while the current state of the art achieved 86.28 ± 1.55% when evaluated on unseen test recordings. The greater discrimination between states afforded using logistic regression as opposed to the previous Gaussian distribution-based emission probability estimation as well as the use of an extended Viterbi algorithm allows this method to significantly outperform the current state-of-the-art method based on a two-sided paired t-test.
In the past few decades heart sound signals (i.e., phonocardiograms or PCGs) have been widely studied. Automated heart sound segmentation and classification techniques have the potential to screen for pathologies in a variety of clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of a large and open database of heart sound recordings. The PhysioNet/Computing in Cardiology (CinC) Challenge 2016 addresses this issue by assembling the largest public heart sound database, aggregated from eight sources obtained by seven independent research groups around the world. The database includes 4,430 recordings taken from 1,072 subjects, totalling 233,512 heart sounds collected from both healthy subjects and patients with a variety of conditions such as heart valve disease and coronary artery disease. These recordings were collected using heterogeneous equipment in both clinical and nonclinical (such as in-home visits). The length of recording varied from several seconds to several minutes. Additional data provided include subject demographics (age and gender), recording information (number per patient, body location, and length of recording), synchronously recorded signals (such as ECG), sampling frequency and sensor type used. Participants were asked to classify recordings as normal, abnormal, or not possible to evaluate (noisy/uncertain). The overall score for an entry was based on a weighted sensitivity and specificity score with respect to manual expert annotations. A brief description of a baseline classification method is provided, including a description of open source code, which has been provided in association with the Challenge. The open source code provided a score of 0.71 (Se=0.65 Sp=0.76). During the official phase of the competition, a total of 48 teams submitted 348 open source entries, with a highest score of 0.86 (Se=0.94 Sp=0.78).
BackgroundInterventions to support people with hypertension in attending clinics and taking their medication have potential to improve outcomes, but delivery on a wide scale and at low cost is challenging. Some trials evaluating clinical interventions using short message service (SMS) text-messaging systems have shown important outcomes, although evidence is limited. We have developed a novel SMS system integrated with clinical care for use by people with hypertension in a low-resource setting. We aim to test the efficacy of the system in improving blood pressure control and treatment adherence compared to usual care.Methods/designThe SMS Text-message Adherence suppoRt trial (StAR) is a pragmatic individually randomised three-arm parallel group trial in adults treated for hypertension at a single primary care centre in Cape Town, South Africa. The intervention is a structured programme of clinic appointment, medication pick-up reminders, medication adherence support and hypertension-related education delivered remotely using an automated system with either informational or interactive SMS text-messages. Usual care is supplemented by infrequent non-hypertension related SMS text-messages. Participants are 1:1:1 individually randomised, to usual care or to one of the two active interventions using minimisation to dynamically adjust for gender, age, baseline systolic blood pressure, years with hypertension, and previous clinic attendance. The primary outcome is the change in mean systolic blood pressure at 12-month follow-up from baseline measured with research staff blinded to trial allocation. Secondary outcomes include the proportion of patients with 80% or more of days medication available, proportion of participants achieving a systolic blood pressure less than 140 mmHg and a diastolic blood pressure less than 90 mmHg, hospital admissions, health status, retention in clinical care, satisfaction with treatment and care, and patient related quality of life. Anonymised demographic data are collected on non-participants.DiscussionThe StAR trial uses a novel, low cost system based on widely available mobile phone technology to deliver the SMS-based intervention, manage communication with patients, and measure clinically relevant outcomes. The results will inform implementation and wider use of mobile phone based interventions for health care delivery in a low-resource setting.Trial registrationNCT02019823
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.