Fig 3 - uploaded by Tuan Le
Content may be subject to copyright.
Different use cases that the system should identify when it is time for a patient to take his or her medication. The capabilities of existing systems are shown in green, while blue includes features unique to our system.
Similar publications
Introdução: Este artigo mostra os papéis e responsabilidades do arquivista no contexto da curadoria digital, verificando como o profissional a partir do uso de teorias, das tecnologias, instrumentos, processos e políticas, pode atuar e delinear ações e procedimentos estratégicos para os processos de curadoria e preservação digital.Objetivo: Investi...
Citations
... Sleep activity has been studied further using sensor data obtained from electroencephalograms and electromyogram devices to develop neural network models [38]. To detect medication taking, numerous approaches and technologies have been introduced, including experimental devices worn on wrists [15,[39][40][41], sensors worn around the neck to detect swallowing [42][43][44], and vision modules embedded in smart environments such as Microsoft's EasyLiving project. [45,46] , The EasyLiving project showcased the early investigations into context-aware computing using an array of video-capture devices instead of more traditional physical sensors. ...
Background:
Medication adherence is a global public health challenge, as only approximately 50% of people adhere to their medication regimens. Medication reminders have shown promising results in terms of promoting medication adherence. However, practical mechanisms to determine whether a medication has been taken or not, once people are reminded, remain elusive. Emerging smartwatch technology may more objectively, unobtrusively, and automatically detect medication taking than currently available methods.
Objective:
This study aimed to examine the feasibility of detecting natural medication-taking gestures using smartwatches.
Methods:
A convenience sample (N=28) was recruited using the snowball sampling method. During data collection, each participant recorded at least 5 protocol-guided (scripted) medication-taking events and at least 10 natural instances of medication-taking events per day for 5 days. Using a smartwatch, the accelerometer data were recorded for each session at a sampling rate of 25 Hz. The raw recordings were scrutinized by a team member to validate the accuracy of the self-reports. The validated data were used to train an artificial neural network (ANN) to detect a medication-taking event. The training and testing data included previously recorded accelerometer data from smoking, eating, and jogging activities in addition to the medication-taking data recorded in this study. The accuracy of the model to identify medication taking was evaluated by comparing the ANN's output with the actual output.
Results:
Most (n=20, 71%) of the 28 study participants were college students and aged 20 to 56 years. Most individuals were Asian (n=12, 43%) or White (n=12, 43%), single (n=24, 86%), and right-hand dominant (n=23, 82%). In total, 2800 medication-taking gestures (n=1400, 50% natural plus n=1400, 50% scripted gestures) were used to train the network. During the testing session, 560 natural medication-taking events that were not previously presented to the ANN were used to assess the network. The accuracy, precision, and recall were calculated to confirm the performance of the network. The trained ANN exhibited an average true-positive and true-negative performance of 96.5% and 94.5%, respectively. The network exhibited <5% error in the incorrect classification of medication-taking gestures.
Conclusions:
Smartwatch technology may provide an accurate, nonintrusive means of monitoring complex human behaviors such as natural medication-taking gestures. Future research is warranted to evaluate the efficacy of using modern sensing devices and machine learning algorithms to monitor medication-taking behavior and improve medication adherence.
... The devices could also be suitable for people who travel a lot to improve the day-time adaptation period after, e.g., jet lag. Smart necklaces [150][151][152][153][154] C, LT, N, S, M L-M Luxury jewelry with activity tracking, health monitoring, posture correction, or safety functionality. This group of devices did not find much attention due to the actual need for miniaturization and keeping the appearance high. ...
Technology is continually undergoing a constituent development caused by the appearance of billions new interconnected “things” and their entrenchment in our daily lives. One of the underlying versatile technologies, namely wearables, is able to capture rich contextual information produced by such devices and use it to deliver a legitimately personalized experience. The main aim of this paper is to shed light on the history of wearable devices and provide a state-of-the-art review on the wearable market. Moreover, the paper provides an extensive and diverse classification of wearables, based on various factors, a discussion on wireless communication technologies, architectures, data processing aspects, and market status, as well as a variety of other actual information on wearable technology. Finally, the survey highlights the critical challenges and existing/future solutions.
... Approaches include sensing of pill bottle movement, removal of its cap, and pouring of the pill into one hand. [15][16][17] Myriad technologies and sensors have been evaluated including collar switch activation and mass analysis pre/post event. However, a limitation lies in that they only imply intent to take medications. ...
... This technology is able to decipher if a user has swallowed saliva, food, or a pill through an inbuilt piezoelectric sensor. 16,20 Other approaches have deployed invasive technologies, the most widely publicized being ingestible sensors. With this approach, RFID tags are embedded into the gelatin capsule of the medication which emits a signal when liberated by gastric fluids. ...
Introduction
Heart failure remains a substantive contributor to patient morbidity and mortality rates worldwide and represents a significant burden on the healthcare ecosystem. Faced with persistent physical symptoms and debilitating social consequences, patients follow complex treatment regimens and often have difficulty adhering to them.
Purpose
In this manuscript, we review factors which contribute to low adherence rates and advance potential single- and multi-factor-based interventions. It is hoped that these observations can lead to improvements in managed care of this vulnerable population of patients.
Methods
A narrative review of the primary literature was performed on contributing factors with primary focus on the period 2015–2020 using available databases and search engines. Adherence pain points identified were mapped against a series of potential solutions which are presented.
Results
Enhancement of treatment adherence relies on two approaches viz. single-factor and multi-factor solutions. Single factors identified include electronic reminders, enhanced health education, financial incentives, gamification strategies, community drivers, persona-based modeling, and burden relief of poly pharmacy. Multi-factor solutions combine two or more of the seven approaches offering the potential for flexible interventions tailored to the individual.
Discussion and Conclusion
Heart failure patients with poor adherence have increased mortality, hospitalization needs, and healthcare costs. This review highlights current single-factor and multi-factor adherence methods. Against a backdrop of diversity of approaches, multi-factor solutions cast the widest net for positively influencing adherent behaviors. A key enabler lies in the development and leveraging of patient personas in the synthesis of successful intervention methods. Deployable solutions can also be envisioned in clinical trials where adherence tracking represents an essential component.
... Wearable sensors detect motions related to cap twisting, hand-to-mouth, pouring the pill into the hand, and pill swallowing. Neck-worn sensors [10,11], and wrist-worn sensors (in the form of smartwatches) [12][13][14] have been used to track medication adherence. ...
Good medication adherence is directly proportional to good health recovery and general improvement of a patient’s health condition. Although many good medication adherence monitoring methods/techniques exist, the level of medication adherence for some chronic diseases by patients in rural settings is still suboptimal. Hence, the need for healthcare organisations to devise viable governance frameworks that will facilitate effective medication adherence monitoring and improved adherence by patients. This paper presents the conceptual overview of a governance framework for medication adherence monitoring and improvement that enables the collaboration of multiple stakeholders and data analytics (MUCODAF) in support of the patient in the treatment journey. The framework allows relevant stakeholders such as Healthcare workers (HCW), family members, and close friends to collaborate in support of a patient through the engagement of critical human factors such as empathy, motivation, encouragement, flexibility, and negotiation. The use cases of the framework, its technical composition, and the implementation plan are discussed in this paper. A concrete example of the application of the governance framework for medication adherence monitoring and improvement for a Tuberculosis patient in the African Country of Lesotho is presented to highlight the plausibility of the framework.
... On similar lines, Kalantarian et al. [9] developed a system based on a smart wrist watch which detects the hand gestures for opening the bottle and consuming the pill. Recently, in addition to the detection of opening the bottle via force sensors, they included the feature of detecting accurate pill ingestion through movement beneath the skin below the lower part of the neck [11]. This feature was integrated with a smart necklace by using a piezoelectric sensor. ...
... The achieved precision and recall for capsule were 87.09% and 90%, respectively. It is worth mentioning that another step that is used in this system is a commercial smart pill [109]. Major challenges associated with this approach pertain to user comfort and social acceptance [110] as the necklace needs to be worn by the patient and must be fastened and placed in contact with the skin during dose swallowing. ...
Medication non-adherence is a prevalent, complex problem. Failure to follow medication schedules may lead to major health complications, including death. Proper medication adherence is thus required in order to gain the greatest possible drug benefit during a patient’s treatment. Interventions have been proven to improve medication adherence if deviations are detected. This review focuses on recent advances in the field of technology-based medication adherence approaches and pays particular attention to their technical monitoring aspects. The taxonomy space of this review spans multiple techniques including sensor systems, proximity sensing, vision systems, and combinations of these. As each technique has unique advantages and limitations, this work describes their trade-offs in accuracy, energy consumption, acceptability and user’s comfort, and user authentication.
... In [21], a collaborative sensing system that uses piezoelectric and pressure sensors was proposed. The piezoelectric sensor is embedded into a necklace of a pendant-style that is powered by a battery. ...
... For example, in order to detect if the bottle is picked while the cap is on, we can use ball-tube sensors such as that used in [7] for detecting the movement of the bottle and upon this, the accelerometer can be activated. Another approach may use pressure sensor attached to the bottom of the bottle for the same goal [21]. Hardware optimization. ...
... Hence, few of these approaches have already been used for diet and food intake activities monitoring as well [10]. [11] 2006 Smart pill box NA Lid opening [13] 2004 RFID NA Pill bottle removal [14] 2009 RFID NA Pill removal [15] 2010 RFID NA Pill bottle removal [16] 2012 RFID (NFC) NA Pill removal [19] 2015 Body sensors (smart necklace) Smart pill box Pill bottle pick up, pill swallowing [23] [24] 2015, 2016 Wearable sensors (smart watch) NA Pill box opening, medication removal, pill pouring into either hands, and water bottle handling [25] 2016 Wearable sensors (smart watch) NA Hand to mouth movement [26] 2014 Wearable sensors (smart watch) NA Hand movement gesture classification [27] 2014 Body sensors (inertial sensor) NA Cap twisting and hand to mouth movement [28] 2015 Wearable sensors (smart watch) NA Opening pill box, drinking water, putting pill in mouth, and putting glass back [29] 2017 Body sensors (inertial sensor) NA Hands movement [31] 2015 Visual NA Pill bottle weight change detection [33] 2014 RFID Body sensors Proximity sensing and hand movement gesture [34] 2013 RFID Video Pill bottle removal [35] 2011 Visual Ubiquitous sensors Pill removal detection and patient's behavior monitoring detects the lids opening of a 7-day reminder pillbox using plungers that were embedded in each compartment, where the plunger would release a switch inside the device that triggers the MCU about lid opening. Data were wirelessly transferred via a Bluetooth connection to a nearby computer. ...
... In [19], the authors proposed a collaborative sensing system that uses piezoelectric and pressure sensors. In that system, piezoelectric sensor is embedded into a pendant-style necklace that is battery powered. ...
... Typically it is formulated as identifying whether a sequence of data, gathered from environment, can be interpreted as a footprint of medication intake activity carried out by a person. Existing solutions include: camera-based system [12][13][14][15][16], wireless sensor networks [17], [18], RFID based systems [19], [20], wearable devices (with either inertial sensors [21], or accelerometer [22] or a piezoelectric sensor [23]), and multitechnology frameworks, such as [24]- [25]. However, these formulations still suffer from either high user burden (e.g. ...
... Swallowing and respiration were assessed through a wireless throat-belt in [4]. Necklace shaped piezoelectric sensors have been suggested for physiological information monitoring of a wide range of applications, such as monitoring a person's eating habits [5], nutrition intake [6], and medication ingestion [7]. Mechanical strain sensors showed high sensitivity of small-scale movements of the throat in [8]. ...
This paper presents a wearable signal acquisition system, which can measure physiological signs, i.e., electrocardiogram (ECG) and photoplethysmogram (PPG). The system is comprised of two parts: (1) an ECG sensor implemented in the master board which will be mounted on the chest and, (2) a combined PPG and motion sensor implemented in the slave board which will be worn around the neck area. The single-lead ECG, the single-channel PPG, and the 3-channel accelerometer signals are all sampled at 200Hz, and transmitted to an Android app through Bluetooth® low energy (BLE) in real time. The system is powered by a 3.7V lithium polymer battery, with an average current consumption of 10mA. In addition to giving an overview of the system design and implementation decisions, we summarize the finding of a PPG test region study based on our system, which indicates that the highest PPG stability is in the mid-throat region over the thyroid gland, and the PPG in the lower throat region is an excellent choice for respiration rate extraction with an average error less than 5%. With the assistance of the motion sensor, an obvious swallow motion can also be easily identified.
