skip to main content

Title: An Activity Recognition System for Taking Medicine Using In-The-Wild Data to Promote Medication Adherence
Nearly half of people prescribed medication to treat chronic or short-term conditions do not take their medicine as prescribed. This leads to worse treatment outcomes, higher hospital admission rates, increased healthcare costs, and increased morbidity and mortality rates. While some instances of medication non-adherence are a result of problems with the treatment plan or barriers caused by the health care provider, many are instances caused by patient-related factors such as forgetting, running out of medication, and not understanding the required dosages. This presents a clear need for patient-centered systems that can reliably increase medication adherence. To that end, in this work we describe an activity recognition system capable of recognizing when individuals take medication in an unconstrained, real-world environment. Our methodology uses a modified version of the Bagging ensemble method to suit unbalanced data and a classifier trained on the prediction probabilities of the Bagging classifier to identify when individuals took medication during a full-day study. Using this methodology we are able to recognize when individuals took medication with an F-measure of 0.77. Our system is a first step towards developing personal health interfaces that are capable of providing personalized medication adherence interventions.
; ;
Award ID(s):
Publication Date:
Journal Name:
IUI '21: 26th International Conference on Intelligent User Interfaces
Page Range or eLocation-ID:
575 to 584
Sponsoring Org:
National Science Foundation
More Like this
  1. In this work, we study the optimal design of two-armed clinical trials to maximize the accuracy of parameter estimation in a statistical model, where the interaction between patient covariates and treatment are explicitly incorporated to enable precision medication decisions. Such a modeling extension leads to significant complexities for the produced optimization problems because they include optimization over design and covariates concurrently. We take a min-max optimization model and minimize (over design) the maximum (over population) variance of the estimated interaction effect between treatment and patient covariates. This results in a min-max bilevel mixed integer nonlinear programming problem, which is notably challenging to solve. To address this challenge, we introduce a surrogate optimization model by approximating the objective function, for which we propose two solution approaches. The first approach provides an exact solution based on reformulation and decomposition techniques. In the second approach, we provide a lower bound for the inner optimization problem and solve the outer optimization problem over the lower bound. We test our proposed algorithms with synthetic and real-world data sets and compare them with standard (re)randomization methods. Our numerical analysis suggests that the proposed approaches provide higher-quality solutions in terms of the variance of estimators and probabilitymore »of correct selection. We also show the value of covariate information in precision medicine clinical trials by comparing our proposed approaches to an alternative optimal design approach that does not consider the interaction terms between covariates and treatment. Summary of Contribution: Precision medicine is the future of healthcare where treatment is prescribed based on each patient information. Designing precision medicine clinical trials, which are the cornerstone of precision medicine, is extremely challenging because sample size is limited and patient information may be multidimensional. This work proposes a novel approach to optimally estimate the treatment effect for each patient type in a two-armed clinical trial by reducing the largest variance of personalized treatment effect. We use several statistical and optimization techniques to produce efficient solution methodologies. Results have the potential to save countless lives by transforming the design and implementation of future clinical trials to ensure the right treatments for the right patients. Doing so will reduce patient risks and reduce costs in the healthcare system.« less
  2. Background Digital health is poised to transform health care and redefine personalized health. As Internet and mobile phone usage increases, as technology develops new ways to collect data, and as clinical guidelines change, all areas of medicine face new challenges and opportunities. Inflammatory bowel disease (IBD) is one of many chronic diseases that may benefit from these advances in digital health. This review intends to lay a foundation for clinicians and technologists to understand future directions and opportunities together. Objective This review covers mobile health apps that have been used in IBD, how they have fit into a clinical care framework, and the challenges that clinicians and technologists face in approaching future opportunities. Methods We searched PubMed, Scopus, and to identify mobile apps that have been studied and were published in the literature from January 1, 2010, to April 19, 2019. The search terms were (“mobile health” OR “eHealth” OR “digital health” OR “smart phone” OR “mobile app” OR “mobile applications” OR “mHealth” OR “smartphones”) AND (“IBD” OR “Inflammatory bowel disease” OR “Crohn's Disease” (CD) OR “Ulcerative Colitis” (UC) OR “UC” OR “CD”), followed by further analysis of citations from the results. We searched the Apple iTunes app storemore »to identify a limited selection of commercial apps to include for discussion. Results A total of 68 articles met the inclusion criteria. A total of 11 digital health apps were identified in the literature and 4 commercial apps were selected to be described in this review. While most apps have some educational component, the majority of apps focus on eliciting patient-reported outcomes related to disease activity, and a few are for treatment management. Significant benefits have been seen in trials relating to education, quality of life, quality of care, treatment adherence, and medication management. No studies have reported a negative impact on any of the above. There are mixed results in terms of effects on office visits and follow-up. Conclusions While studies have shown that digital health can fit into, complement, and improve the standard clinical care of patients with IBD, there is a need for further validation and improvement, from both a clinical and patient perspective. Exploring new research methods, like microrandomized trials, may allow for more implementation of technology and rapid advancement of knowledge. New technologies that can objectively and seamlessly capture remote data, as well as complement the clinical shift from symptom-based to inflammation-based care, will help the clinical and health technology communities to understand the full potential of digital health in the care of IBD and other chronic illnesses.« less
  3. Abstract Stigma toward people living with HIV/AIDS (PLWHA) has impeded the response to the disease across the world. Widespread stigma leads to poor adherence of preventative measures while also causing PLWHA to avoid testing and care, delaying important treatment. Stigma is clearly a hugely complex construct. However, it can be broken down into components which include internalized stigma (how people with the trait feel about themselves) and enacted stigma (how a community reacts to an individual with the trait). Levels of HIV/AIDS-related stigma are particularly high in sub-Saharan Africa, which contributed to a surge in cases in Kenya during the late twentieth century. Since the early twenty-first century, the United Nations and governments around the world have worked to eliminate stigma from society and resulting public health education campaigns have improved the perception of PLWHA over time, but HIV/AIDS remains a significant problem, particularly in Kenya. We take a data-driven approach to create a time-dependent stigma function that captures both the level of internalized and enacted stigma in the population. We embed this within a compartmental model for HIV dynamics. Since 2000, the population in Kenya has been growing almost exponentially and so we rescale our model system to createmore »a coupled system for HIV prevalence and fraction of individuals that are infected that seek treatment. This allows us to estimate model parameters from published data. We use the model to explore a range of scenarios in which either internalized or enacted stigma levels vary from those predicted by the data. This analysis allows us to understand the potential impact of different public health interventions on key HIV metrics such as prevalence and disease-related death and to see how close Kenya will get to achieving UN goals for these HIV and stigma metrics by 2030.« less
  4. Theory—understanding mental processes that drive decisions—is important to help patients and providers make decisions that reflect medical advances and personal values. Building on a 2008 review, we summarize current tenets of fuzzy-trace theory (FTT) in light of new evidence that provides insight regarding mental representations of options and how such representations connect to values and evoke emotions. We discuss implications for communicating risks, preventing risky behaviors, discouraging misinformation, and choosing appropriate treatments. Findings suggest that simple, fuzzy but meaningful gist representations of information often determine decisions. Within minutes of conversing with their doctor, reading a health-related web post, or processing other health information, patients rely on gist memories of that information rather than verbatim details. This fuzzy-processing preference explains puzzles and paradoxes in how patients (and sometimes providers) think about probabilities (e.g., “50-50” chance), outcomes of treatment (e.g., with antibiotics), experiences of pain, end-of-life decisions, memories for medication instructions, symptoms of concussion, and transmission of viruses (e.g., in AIDS and COVID-19). As examples, participation in clinical trials or seeking treatments with low probabilities of success (e.g., with antibiotics or at the end of life) may indicate a defensibly different categorical gist perspective on risk as opposed to simply misunderstanding probabilitiesmore »or failing to make prescribed tradeoffs. Thus, FTT explains why people avoid precise tradeoffs despite computing them. Facilitating gist representations of information offers an alternative approach that goes beyond providing uninterpreted “neutral” facts versus persuading or shifting the balance between fast versus slow thinking (or emotion vs. cognition). In contrast to either taking mental shortcuts or deliberating about details, gist processing facilitates application of advanced knowledge and deeply held values to choices. Highlights Fuzzy-trace theory (FTT) supports practical approaches to improving health and medicine. FTT differs in important respects from other theories of decision making, which has implications for how to help patients, providers, and health communicators. Gist mental representations emphasize categorical distinctions, reflect understanding in context, and help cue values relevant to health and patient care. Understanding the science behind theory is crucial for evidence-based medicine.« less
  5. Obeid, Iyad ; Selesnick, Ivan ; Picone, Joseph (Ed.)
    The Neural Engineering Data Consortium has recently developed a new subset of its popular open source EEG corpus – TUH EEG (TUEG) [1]. The TUEG Corpus is the world’s largest open source corpus of EEG data and currently has over 3,300 subscribers. There are several valuable subsets of this data, including the TUH Seizure Detection Corpus (TUSZ) [2], which was featured in the Neureka 2020 Epilepsy Challenge [3]. In this poster, we present a new subset of the TUEG Corpus – the TU Artifact Corpus. This corpus contains 310 EEG files in which every artifact has been annotated. This data can be used to evaluate artifact reduction technology. Since TUEG is comprised of actual clinical data, the set of artifacts appearing in the data is rich and challenging. EEG artifacts are defined as waveforms that are not of cerebral origin and may be affected by numerous external and or physiological factors. These extraneous signals are often mistaken for seizures due to their morphological similarity in amplitude and frequency [4]. Artifacts often lead to raised false alarm rates in machine learning systems, which poses a major challenge for machine learning research. Most state-of-the-art systems use some form of artifact reduction technologymore »to suppress these events. The corpus was annotated using a five-way classification that was developed to meet the needs of our constituents. Brief descriptions of each form of the artifact are provided in Ochal et al. [4]. The five basic tags are: • Chewing (CHEW): An artifact resulting from the tensing and relaxing of the jaw muscles. Chewing is a subset of the muscle artifact class. Chewing has the same characteristic high frequency sharp waves with 0.5 sec baseline periods between bursts. This artifact is generally diffuse throughout the different regions of the brain. However, it might have a higher level of activity in one hemisphere. Classification of a muscle artifact as chewing often depends on whether the accompanying patient report mentions any chewing, since other muscle artifacts can appear superficially similar to chewing artifact. • Electrode (ELEC): An electrode artifact encompasses various electrode related artifacts. Electrode pop is an artifact characterized by channels using the same electrode “spiking” with an electrographic phase reversal. Electrostatic is an artifact caused by movement or interference of electrodes and or the presence of dissimilar metals. A lead artifact is caused by the movement of electrodes from the patient’s head and or poor connection of electrodes. This results in disorganized and high amplitude slow waves. • Eye Movement (EYEM): A spike-like waveform created during patient eye movement. This artifact is usually found on all of the frontal polar electrodes with occasional echoing on the frontal electrodes. • Muscle (MUSC): A common artifact with high frequency, sharp waves corresponding to patient movement. These waveforms tend to have a frequency above 30 Hz with no specific pattern, often occurring because of agitation in the patient. • Shiver (SHIV): A specific and sustained sharp wave artifact that occurs when a patient shivers, usually seen on all or most channels. Shivering is a relatively rare subset of the muscle artifact class. Since these artifacts can overlap in time, a concatenated label format was implemented as a compromise between the limitations of our annotation tool and the complexity needed in an annotation data structure used to represent these overlapping events. We distribute an XML format that easily handles overlapping events. Our annotation tool [5], like most annotation tools of this type, is limited to displaying and manipulating a flat or linear annotation. Therefore, we encode overlapping events as a series of concatenated names using symbols such as: • EYEM+CHEW: eye movement and chewing • EYEM+SHIV: eye movement and shivering • CHEW+SHIV: chewing and shivering An example of an overlapping annotation is shown below in Figure 1. This release is an update of TUAR v1.0.0, which was a partially annotated database. In v1.0.0, a similar five way system was used as well as an additional “null” tag. The “null” tag covers anything that was not annotated, including instances of artifact. Only a limited number of artifacts were annotated in v1.0.0. In this updated version, every instance of an artifact is annotated; ultimately, this provides the user with confidence that any part of the record that is not annotated with one of the five classes does not contain an artifact. No new files, patients, or sessions were added in v2.0.0. However, the data was reannotated with these standards. The total number of files remains the same, but the number of artifact events increases significantly. Complete statistics will be provided on the corpus once annotation is complete and the data is released. This is expected to occur in early July – just after the IEEE SPMB submission deadline. The TUAR Corpus is an open-source database that is currently available for use by any registered member of our consortium. To register and receive access, please follow the instructions provided at this web page: The data is located here:« less